Agent device

[Technical Field to which the Invention Affiliates] The present invention relates to an agent device that appears in a vehicle and assists a driver in route guidance, operation of various devices, and the like, and easily provides a plurality of information in an agent device. Regarding.

PROBLEM TO BE SOLVED: Conventionally, in a vehicle, a situation such as a position and a state of the vehicle, and information such as a warning and a route guidance corresponding to these situations are displayed on a display as a human facial expression or an action. The technology for transmitting information to drivers and the like is known (Japanese Patent Laid-Open No. 9-102098). This conventional technique has an advantage that it is easy to grasp at a glance because the information is visually expressed.

[0003] However, in the above-mentioned prior art, when the number of information to be transmitted changes over time or when a plurality of pieces of information change over time, they change over time. There are problems such as difficulty in recognizing changes in the target, and there is a demand for a technology that makes it easier to grasp information.

[0004] An object of the present invention is to provide an agent device that easily grasps and easily provides a plurality of pieces of information in a vehicle or the like.

[Means for Solving the Problems] In the invention described in claim 1, an agent appearance means for causing an anthropomorphic agent to appear in a vehicle, a situation determination means for determining the situation of the vehicle, and this situation. The agent action determining means for determining the action of the agent from the situation determined by the judging means, the agent controlling means for causing the agent appearing by the agent appearing means to perform the action determined by the agent action determining means, and the agent controlling means. From the situation determined by the situation determination means, the necessity determination means for determining the necessity of the appearance of the anthropomorphic subagent under the appearance of the agent, and the subagent based on the determination of the necessity determination means. With the sub-agent appearance means for recognizing the appearance of the agent separately from the agent, the sub-agent action determination means for determining the action of the sub-agent from the situation determined by the situation determination means, and the sub-agent action determination means. The agent device is provided with a sub-agent control means for causing the sub-agent appearing by the sub-agent appearance means to perform the determined action to achieve the above-mentioned object. In the invention described in claim 2, in the agent device according to claim 1, the sub-agent achieves the above object by providing an agent device that explains an act of the agent. In the invention described in claim 3, in the agent device according to claim 1, the sub-agent achieves the above object by providing an agent device that short-circuits a part of a series of actions of the agent. In the invention according to claim 4, in the agent device according to any one of claims 1 to 3, the situation determination means includes a direction acquisition means for acquiring the driver's direction, and the necessity The determination means achieves the above object by providing an agent device for determining whether or not the appearance of a sub-agent is necessary, with the driver's orientation as the situation of the vehicle. In the invention described in claim 5. In the agent device according to claim 4, the orientation acquisition means acquires the driver's proficiency level with respect to the agent as the driver's orientation, and the necessity determination means uses the proficiency level as the situation of the vehicle. The above object is achieved by providing an agent device for determining the necessity of a sub-agent. The invention according to claim 6 comprises a learning means for learning by memorizing a predetermined situation by the situation determination means in the agent device according to any one of claims 1 to 5. The necessity-determining means achieves the object by providing an agent device for determining the necessity of the sub-agent, using the learning result of the learning means as the situation of the vehicle. The invention according to claim 7 comprises a learning means for learning by memorizing a predetermined situation by the situation determination means in the agent device according to any one of claims 1 to 6. At least one of the agent action determining means and the subagent action determining means achieves the object by providing an agent device for determining an agent or a subagent's action using the learning result as the situation of the vehicle. .. In the invention according to claim 8, the agent device according to any one of claims 1 to 7 includes an image display means, and the agent appearance means is an agent for the image display means. The sub-agent appearance means provides the image display means with an agent device including an agent display means for displaying an image of the sub-agent so as to visually distinguish the sub-agent from the agent. By doing so, the above object is achieved. In the invention described in claim 9, the agent device according to any one of claims 1 to 8 includes a voice output device, and the agent appearance means is an agent for the voice output device. The sub-agent appearance means includes the agent voice output means for outputting the voice of the above.

[Embodiments of the Invention] Hereinafter, preferred embodiments of the agent device of the present invention will be described in detail with reference to FIGS. 1 to 13. (1) Outline of the First Embodiment In the agent device of the present embodiment, an anthropomorphic agent is made to appear in a vehicle by an image (planar image, three-dimensional image such as holography, etc.). Then, the condition of the vehicle including the vehicle itself, the driver, the passenger, the oncoming vehicle, etc. (including the response and reaction of the driver) is judged, and the agent determines the driver and the condition of the vehicle based on the vehicle condition at each time point. Respond to the vehicle with various variations (action = action and voice). As a result, the driver can interact (communicate) with his / her own agent in the vehicle, and can make the environment in the vehicle comfortable. Here, the anthropomorphic agent in the present embodiment has the same identity as a specific human being, creature, cartoon character, etc., and the creature having the same identity maintains the identity / continuity. It outputs the tendency (action, response by voice). In addition, identity and continuity can be expressed as a personality with a unique personality, and can be regarded as a kind of pseudo-living body in an electronic device. The agent that appears in the vehicle is a pseudo-personalized (virtual personalized) subject that judges in the same way as a human being. Occasionally, there is a judgment error within the range not related to the running of the vehicle, and an unnecessary (dumb) response may be made due to this judgment error. In the embodiment, the main agent who determines the situation of the vehicle itself and the vehicle including the driver and performs various actions such as route guidance and operation of the device on behalf of the driver and assists the driver further includes the situation of the vehicle and It learns the driver's response and performs various actions based on the judgment including the learning result. Therefore, even in the same vehicle situation, the content of the agent's communication differs depending on the past learning content and the like. Occasionally, there is a judgment error within the range not related to the running of the vehicle, and an unnecessary (dumb) response may be made due to this judgment error. And based on the driver's response, the judgment Judge whether or not it is a problem and learn. Further, in the present embodiment, when the main agent appears, a help agent is made to appear as a sub agent according to the driver's proficiency level with respect to the agent. The help agent provides the driver with an explanation of the main agent's actions, such as how to respond to the main agent's proposal and how to teach the expected result by the response. These two agents will appear in the car with different looks and voices. In this way, by making it possible for two agents to appear according to the situation, it is possible to realize an agent action that is more detailed than one agent and is in line with the vehicle situation such as the driver's proficiency level. By differentiating the appearance and voice of the two agents with different appearance times and functions, the driver can easily identify these two agents and provide accurate information with a clear awareness of the functions of each agent. It is possible to grasp and respond to each agent.

(2) Detailed FIG. 1 of the embodiment is a block diagram showing a configuration of an agent device according to the present embodiment. In the present embodiment, the overall processing unit 1 that controls the entire communication function is provided. This overall processing unit 1 is a navigation processing unit 10 that searches for a route to a set destination and guides it by voice or image display, learns the vehicle situation and past responses by the driver, and appropriately talks and controls. Agent processing unit 11, navigation processing unit 10 and I / F unit 12 for agent processing unit 11, image processing unit 13 that processes image output and input images such as agent images and map images, agent voice, route guidance voice, etc. It has a voice control unit 14 that controls the voice output and input voice of the vehicle, and a status information processing unit 15 that processes detection data of various situations related to the vehicle and the driver.

[0008] The navigation processing unit 10 and the agent processing unit 11 include a CPU (central processing unit) that controls data processing and the operation of each unit, and a ROM connected to this CPU by a bus line such as a data bus or a control bus. Equipped with RAM, timer, etc. Both processing units 10 and 11 are connected to a network so that they can acquire each other's processing data. ROM is a read-only memory in which various data and programs for control by the CPU are stored in advance, and RAM is a random access memory used by the CPU as a working memory.

[0009] In the navigation processing unit 10 and the agent processing unit 11 of the present embodiment, the CPU reads various programs stored in the ROM and executes various processes. The CPU reads a computer program from an external recording medium set in the recording medium drive device 23 and stores (installs) it in another storage device such as an agent storage device 29, a navigation data storage device 30, or a hard disk (not shown). Then, a necessary program or the like may be read (loaded) from this storage device into RAM and executed. Further, a necessary program or the like may be directly read into the RAM from the recording medium driving device 23 and executed.

The current position detection device 21 and the navigation data storage device 30 are connected to the navigation processing unit 10, the agent data storage device 29 is connected to the agent processing unit 11, and the input device 22 is connected to the I / F unit 12. The storage medium drive device 23 and the communication control device 24 are connected, the display device 27 and the image pickup device 28 are connected to the image processing unit 13, and the voice output device 25 and the microphone 26 are connected to the voice control unit 14. A status sensor unit 40 is connected to the information processing unit 15.

[0011] The current position detection device 21 is for detecting the absolute position (depending on latitude and longitude) of the vehicle, and GPS (Global Positioning) that measures the position of the vehicle using an artificial satellite. System) A receiving device 211, a directional sensor 212, a steering angle sensor 213, a distance sensor 214, a beacon receiving device 215 that receives position information from a beacon arranged on the road, and the like are used. The GPS receiver 211 and the beacon receiver 215 can measure the position independently, but in places where reception by the GPS receiver 211 or the beacon receiver 215 is not possible, both the orientation sensor 212 and the distance sensor 214 are used. The current position is detected by speculative navigation. The orientation sensor 212 includes, for example, a geomagnetic sensor that detects geomagnetism and obtains the orientation of the vehicle, a gyro such as a gas rate gyro or an optical fiber gyro that detects the rotational angular velocity of the vehicle and integrates the angular velocity to obtain the orientation of the vehicle, left and right. Wheel sensors, etc. are used in which the wheel sensors of the above are arranged and the displacement amount of the orientation is calculated by detecting the turning of the vehicle by the output pulse difference (difference in the moving distance). The steering angle sensor 213 detects the steering angle α by using an optical rotation sensor attached to the rotating portion of the steering, a rotation resistance volume, or the like. As the distance sensor 214, various methods are used, for example, one that detects and counts the number of rotations of a wheel, or detects an acceleration and integrates it twice.

[0012] The input device 22 is a predetermined driving environment (transmission) of a vehicle that wants to send a request for information such as congestion information to the current location (departure point), destination (arrival point), and information providing station at the start of traveling in the navigation process. Condition), type (model) of mobile phone 6 and so on. The input device 22 is also one means for the driver to respond to an agent inquiry or the like according to the present embodiment. As the input device 22, various devices such as a touch panel (functioning as a switch), a keyboard, a mouse, a light pen, a joystick, a remote controller using infrared rays, and a voice recognition device can be used. Further, a remote controller using infrared rays or the like and a receiving unit for receiving various signals transmitted from the remote controller may be provided. On the remote controller, various keys such as a menu specification key (button) and a numeric keypad are arranged in addition to a joystick for moving the cursor displayed on the screen.

[0013] The recording medium driving device 23 is a driving device used for reading a computer program for the navigation processing unit 10 and the agent processing unit 11 to perform various processes from an external recording medium. The computer program recorded on the recording medium includes various programs, data, and the like. Here, the recording medium means a recording medium on which a computer program is recorded, and specifically, a magnetic recording medium such as a floppy disk, a hard disk, or a magnetic tape, a semiconductor recording medium such as a memory chip or an IC card, or a CD-. Recording media such as ROM, MO, PD (phase change rewritable optical disc) that can read information optically, paper cards and paper tapes, and paper (and paper) such as printed matter for reading programs using a character recognition device. A recording medium using a medium having a corresponding function) and a recording medium on which a computer program is recorded by various other methods are included.

In addition to reading computer programs from these various recording media, the recording medium driving device 23 reads the computer program from these various recording media, and when the recording medium is a writable recording medium such as a floppy disk or an IC card, the navigation processing unit 10 It is possible to write the RAM of the agent processing unit 11 and the data of the storage devices 29 and 30 to the recording medium. For example, the IC card stores the learning contents (learning item data, response data, proficiency level data, etc.) related to the functions of the main agent and the help agent, and even when driving another vehicle, the stored IC card can be stored. It allows you to communicate with agents who have been trained to your liking (depending on past response situations). This makes it possible for an agent unique to the driver to appear in the vehicle instead of an agent for each vehicle.

[0015] The communication control device 24 is connected to a mobile phone made of various wireless communication devices. The communication control unit 24 is used for communication with an information providing station that provides data on traffic information such as road congestion and traffic regulation, and karaoke data used for communication karaoke in a car, in addition to telephone line calls. It is possible to communicate with the information providing station that provides the information. It is also possible to send and receive learning data and the like related to the functions of each agent via the communication control device 24.

[0016] The voice output device 25 is composed of a plurality of speakers arranged in the vehicle, and is in accordance with the voice controlled by the voice control unit 14, for example, the guidance voice when performing route guidance by voice, or the action of the agent. Voice and sound are output. The audio output device 25 may also be used as an audio speaker. The voice control device 14 can control the tone color, accent, and the like of the voice output from the voice output device 25 in response to the input of the tuning instruction of the driver. The microphone 26 is used as a voice input means for inputting / outputting the voice to be recognized by the voice control unit 14, for example, the input voice of the destination in the navigation process, the driver's conversation (response, etc.) with the agent, and the like. Function. The microphone 26 may also be used as a microphone for performing karaoke such as online karaoke, and a dedicated directional microphone is used to accurately collect the driver's voice. May be good. A hands-free unit may be formed by the voice output device 25 and the microphone 26 so that a telephone communication can be made without going through a mobile phone.

On the display device 27, a road map for route guidance and various image information processed by the navigation processing unit 10 are displayed, and various actions (videos) of the main agent and the help agent by the agent processing unit 11 are displayed. It is supposed to be done. Further, the images inside and outside the vehicle captured by the image pickup apparatus 28 are also displayed after being processed by the image processing unit 13. As the display device 27, various display devices such as a liquid crystal display device and a CRT are used. The display device 5 may have a function as the input device 2, such as a touch panel.

[0018] The image pickup device 28 is composed of a camera provided with a CCD (charge coupling element) for taking an image, and in addition to an in-vehicle camera for taking an image of the driver, the front side, the rear side, the right side side, and the left side side of the vehicle. Each outside-vehicle camera that captures images is arranged. The image captured by each camera of the image pickup apparatus 28 is supplied to the image processing unit 13, processing such as image recognition is performed, and each recognition result is used by the agent processing unit 11 to determine the program number. There is.

[0019] The agent data storage device 29 is a storage device that stores various data (including programs) necessary for realizing the functions of the main agent and the functions of the help agent according to the present embodiment. For the agent data storage device 29, for example, various recording media such as a floppy disk, a hard disk, a CD-ROM, an optical disk, a magnetic tape, an IC card, and an optical card, and a driving device thereof are used. In this case, for example, learning item data 292, response data 294, and proficiency level data 295 are composed of an easy-to-carry IC card or floppy disk, and other data is composed of a hard disk. And a drive device, and those drive devices may be used as the drive device.

[0020] The agent data storage device 29 is used to display images of the appearance and behavior of the agent program 290, the program selection table 291, the learning item data 292, the response data 293, and the agents and help agents illustrated in FIGS. 4 and 13. Image data 294, help agent program 295, help agent program correspondence table 296, proficiency level data 297, and other data are stored. The learning item data 292, the response data 293, and the proficiency level data 297 are data that store the results learned by the agent according to the driver's driving operation and response. Therefore, the learning item data 292, the response data 293, and the proficiency level data 297 are stored / updated (learned) for each driver. The appearance stored in the image data 294 does not have to be a human (male, female) appearance, for example, the appearance of the animal itself such as a chick, a dog, a cat, a frog, a mouse, or a human design ( It may be the appearance of an animal (illustrated), or it may be a robot-like appearance, the appearance of a specific character, or the like. In addition, the age of the agent does not have to be constant, and as a learning function of the agent, the appearance of the child is initially set, and then the appearance changes as it grows over time (changes to the appearance of an adult and then to the elderly). It may change to the appearance of). Images of the appearances of these various main agents and help agents are stored in the image data 294, and the appearances of the main agent and the help agent can be individually selected from the input device 22 and the like according to the driver's preference. Can be done. The appearances of the selected main agent and help agent are stored corresponding to the driver and read out at startup. In addition, the appearance of the main agent and the help agent can be changed as appropriate from the input device 22 and the like.

[0021] In the agent program 290, an agent processing program for realizing the function of the main agent and detailed actions when the agent and the driver communicate with each other are displayed as an image on the display device 27 and the actions are supported. The communication programs for outputting the conversation from the voice output device 25 are stored in the order of the program numbers. The agent program 290 stores a plurality of types of voice data for the voice of each program number, and the driver selects the voice from the input device 22 and the like together with the selection of the appearance of the main agent. Can be done. The voices of the main agents include male voices, female voices, children's voices, mechanical voices, animal voices, voices of specific voice actors and actors, voices of specific characters, etc. The driver selects from the above. The voice and the selection of the appearance can be changed in a timely manner.

[0022] The program selection table 291 is a table for selecting a communication program stored in the agent program 290. FIG. 2 shows the program selection table 291 and FIG. 3 shows the contents of the agent's actions (actions and vocalizations) corresponding to each program number selected in the program selection table 291. The program numbers shown in FIGS. 2 and 3 match the numbers of each communication program stored in the agent program 290.

[0023] FIG. 4 shows several screens of the main agent's smart bowing behavior displayed on the display device 27 by the program numbers 00001 to 00002 of FIGS. 2 and 3. As shown in Fig. 4, the main agent E is expressed as a clever bow by bowing while tightening his mouth and putting his hand on his knee. The words (vocalization) spoken by the main agent E along with this action can be changed depending on the vehicle situation, learning situation, and the like.

[0024] When the cooling water temperature of the engine is low, the action "sleepy ..." is selected according to the condition of the engine. Sleepy expressions include a lowered eyelid expression, yawning or stretching, then taking certain actions (bowing, etc.), rubbing the eyes first, or slowing movements and vocalizations. Can be represented by. These sleepy expressions are not always the same, but the expressions are changed as appropriate by learning the number of actions and the like. For example, rub your eyes once every three times (behavior A), yawn once every ten times (behavior B), and otherwise make your eyelids look down (behavior C). These changes are realized by combining the additional programs of Action B and Action C with the basic program of Action A. Then, as for which action to combine, the number of times the program of the basic action A is executed is counted as a learning item, and the additional programs are combined according to the number of times. In addition, when expressing the action "energically", it is expressed by increasing the intonation of the voice or making the main agent E appear on the screen while running.

Each item displayed in FIG. 2 represents a selection condition for selecting each program number, and is an item (time) determined from various situations of the vehicle and the driver detected by the state sensor 40. , Startup location, cooling water temperature, etc.) and items determined from the learning content stored in the learning item data 292 and response data 293 (today's IG ON count, elapsed time since the previous end, total startup count, etc.) There is. In the program selection table 291, the program that satisfies all of these items is always uniquely determined. In the table, the "" mark indicates an item that must be satisfied in order for the program number to be selected, and the "-" mark indicates an item that is not considered in the selection of the program.

[0026] In FIGS. 2 and 3, actions and selection conditions related to communication (greeting) when the ignition is turned on are described, but a program that regulates various other actions (actions and vocalizations) is selected. The program number and selection conditions for this are also specified in various ways. For example, a program is also stipulated in which the main agent takes actions such as putting on a "sticky rice cake" or stepping on a "tatara" on the condition that a sudden brake is applied, and makes a surprise voice. The choice of each action by the main agent should be changed by learning about sudden braking, for example, "tatara" is applied from the first sudden braking to the third time, and "tatara" is applied from the fourth to the tenth time. From the 10th time onward, try to take the action of "stepping on one foot just one step forward" so that the main agent gradually gets used to sudden braking. Then, if there is a week interval from the last sudden braking, move back one step.

[0027] The learning item data 292 and the response data 293 in FIG. 1 are both data stored and updated by the learning of the agent, and their contents are conceptually shown in FIGS. 5 and 6, respectively. As shown in FIG. 5, the learning item data 292 includes the total number of start-ups for determining the selection conditions of the program selection table 291 (Fig. 2), the previous end date and time, the number of times the ignition is turned on today, and the remaining amount at the time of refueling the previous 5 times. Etc. are stored, and the number of rests / date and time, default value, and other data for deciding whether or not to start the program selected by the selection condition (whether or not to take a rest) are stored.

[0028] In the total number of activations, the total number of times the ignition has been activated is stored, and is counted up each time the ignition is turned ON. In the previous end date and time, the date and time is stored each time the ignition is turned off. Today's ignition ON count stores the number of ignition ON counts for that day and the end time of the day. It counts up every time the ignition is turned on, but when the day ends, the data is initialized to "0". 24:00 is stored as the default value for the end time of the day. This time can be changed according to the life pattern of the user (driver). If the time is changed, the changed time is stored.

[0029] The remaining amount of fuel detected immediately before refueling the fuel (gasoline) is stored in the remaining amount of refueling of the previous five times, and each data is shifted to the left side each time a new refueling is performed (oldest). (The leftmost data is deleted) The remaining amount just before refueling this time is stored on the far right. In this data, when the detection value G1 of the fuel detection sensor 415, which will be described later, becomes equal to or less than the average value G2 (G1 G2) of the remaining amount of refueling for all five times, Agent E appears on the display device 27 and refuels. The prompting action is displayed on the display device 27, and a voice such as "I'm hungry! I want gasoline!" Is output from the voice output device 25.

[0030] In the number of days off / date and time, even if the corresponding communication program is selected, the number of times of rest without execution is stored for each program number. This number of days off / date and time is stored for the agent action in which the rest item is set as a learning item, for example, the action of the agent proposing to stop the air conditioner (program number 00123) described later. If the driver's response to the agent's suggestion or conversation is rejected (rejected) or ignored (or not responded), "rest" is selectively set according to the communication program.

[0031] The default value stores initial setting values for each item such as time, number of times, temperature, vehicle speed, date and time, and is a value changed in the learning items such as the end time of the day described above. Is used to return to the initial value. Other data stored in the learning item data 292 include, for example, birthdays of drivers and their associates (this is a user input item), holidays and their so-called Christmas Eve (December 24th), Event dates such as Valentine's Day (February 14th) and White Day (March 14th) are stored. There is also a special menu communication program for each event day, for example, on Christmas Eve, an agent disguised as Santa Claus will appear.

[0032] In the response data 293 of FIG. 6, the history of the user's response to the action of the agent is stored for each communication program number whose learning item is the user response. The user response data 293 stores the latest response date and time and response contents for a predetermined number of times (program number 00123 is for two times) as shown in the communication program numbers 00123 and 00125 in FIG. 6 (A), and the user response data 293 is as shown in the program number 00124. Only the latest response content is stored once (so it is updated every time there is a response), only the latest response content is stored for a predetermined time, and the latest date and time and response content are stored once. Some are stored, while others store only the latest date and time for one time or a predetermined time. The symbols A, B, and C displayed in FIG. 6 (A) represent the response contents, and as shown in FIG. 6 (B), when the symbol A is ignored or the symbol B is rejected, Represents the case where the symbol C is accepted. The driver's response content is determined from the result of voice recognition for the driver's voice input from the microphone 26 and the input result by the input device. In this embodiment, the driver's response is classified into three patterns of ignoring, rejecting, and accepting, but even if "strongly rejected", "angry", and "pleased" are newly added. Good. In this case, the learning item data 292 (for example, the number of rests) and the response data 293 are additionally changed according to the newly added response.

[0033] The help agent program 295 realizes a help agent function that explains the agent's actions such as how to respond to the agent and how to teach the expected result of the response to the driver when the communication program of the main agent is executed. Help agent processing program for this purpose, help communication for displaying the detailed actions when the help agent gives explanations to the driver on the display device 27 and outputting the conversation corresponding to the actions from the voice output device 25. Programs are stored in order of program number.

[0034] In this help agent program 295, a plurality of types of voice data are stored for the voice of each program number, and the driver can easily distinguish the voice of the main agent from the voice of the main agent from the input device 22 or the like. It is designed to be selected from the voices of. For example, when the voice of the main agent is a female voice, the voice of the help agent is a male voice, etc., and the voice of the main agent and the voice of the help agent can be easily distinguished as candidates. Is selected from. The voice and appearance of this help agent can be changed as appropriate. Further, the appearance and voice of the main agent and the appearance and voice of the help agent are each appearance and voice that can be well distinguished from each other between the main agent and the help agent unless otherwise selected by the driver. Audio is automatically selected and set.

[0035] The help agent program correspondence table 296 shows a response program (a program in which a response from a driver or the like is scheduled) among communication programs stored in the agent program 290, and a help agent executed for this response program. It is a table which shows the correspondence of a program and the proficiency threshold for executing the help agent program. Figure 7 shows the help agent program support table 296, and Figure 8 shows the help agent actions (actions and vocalizations) corresponding to each program number selected in the help agent program support table 296. Is. The program numbers shown in FIGS. 7 and 8 match the numbers of each communication program stored in the help agent program 295.

[0036] For example, when an agent program of program number 00123 (a program that proposes to stop the air conditioner) is started, if the driver's proficiency level with respect to this agent program is 50 or less, the help agent program of program number 50010 is started. Then, a help agent pointing to the agent is displayed on the display device 27, and a voice saying "Lisa will stop the air conditioner and open the front window halfway" is output from the audio output device 25. Even if the agent program with the same program number 00123 is started, the help agent does not appear if the driver's proficiency level is greater than 50. In the present embodiment, among the agent communication programs, the communication program by the help agent is determined correspondingly for each response communication program for requesting a response, such as the destination setting program of the route guidance system.

[0037] The proficiency level data 297 stores data for obtaining the proficiency level referred to when selecting and starting the help agent program for each agent program, and the proficiency level obtained based on these data. ing. The proficiency level data 297 is stored in the order of the program number for each driver for the response program in the agent program, and is stored and updated by learning.

[0038] FIG. 9 is a diagram conceptually showing the contents of the proficiency level data. As shown in FIG. 9, the proficiency level data 297 includes the activation flag of each agent program, the previous 5 response times, the average response time, the shortest response time, the number of response cancellations, and the proficiency obtained from each of these values. The degree is stored for each program number of the agent program. The start flag is set to flag 0 when each agent program is started, flag 1 is set, the proficiency level is calculated, and the proficiency level is learned as proficiency level data. The previous 5 response times are the times until the driver's response to each of the previous 5 response times to the launched agent program. The average response time is the average value of the response times of the previous 5 times, and the shortest response time is the minimum value of the response times of the previous 5 times. The number of times the response is canceled is the number of times the response is canceled while the program is running.

[0039] The proficiency level is, for example, 30 when the total number of startups is 0 (initial value), and when the agent program is started according to a predetermined formula, the average response time is less than the reference time. , If the shortest operation time is less than the reference time, the predetermined value specified for each item is added and becomes higher, and if the average response time is larger than the reference time, the shortest operation time is larger than the reference time. In the case, and when there is a cancel operation, it is calculated so that it will be lowered by subtracting the predetermined value specified for each item.

FIG. 10 shows the contents of a data file stored in the navigation data storage device 30 (FIG. 1). As shown in FIG. 10, the navigation data storage device 30 has communication area data file 301, drawing map data file 302, intersection data file 303, node data file 304, and road data as various data files used for route guidance and the like. File 305, search data file 306, and photo data file 307 are stored. As the navigation data storage device 30, for example, various recording media such as a floppy disk, a hard disk, a CD-ROM, an optical disk, a magnetic tape, an IC card, and an optical card, and a driving device thereof are used. The navigation data storage device 30 may be composed of a plurality of different types of recording media and a driving device. For example, the search data file 46 is composed of a readable and writable recording medium (for example, a flash memory), and other files are composed of a CD-ROM, and those driving devices are used as the driving device.

[0041] In the communication area data file 301, the area where the mobile phone connected to or not connected to the communication control device 24 and used in the vehicle can communicate from the inside of the vehicle is displayed on the display device 5, and the area where the communication can be performed is displayed on the display device 5. Communication area data to be used when searching for a route is stored for each type of mobile phone. Each communication area data for each type of mobile phone is numbered and managed for easy search, and the communicable area can be represented by the inside surrounded by the closed curve, so the closed curve is represented by a short line segment. It is divided into two parts and specified by the position data of the bending point. The communication area data may be divided into quadrangular areas of various sizes and converted into data by coordinate data of two diagonal points. It is desirable that the contents stored in the communication area data file 301 can be updated as the area where the mobile phone can be used expands or contracts. Therefore, by using the mobile phone and the communication control device 24, the contents are stored. It is configured so that the contents of the communication area data file 301 can be updated with the latest data by communicating with the information providing station. The communication area data file 301 may be composed of a floppy disk, an IC card, or the like, and may be rewritten with the latest data. The drawn map data file 302 stores the drawn map data drawn on the display device 27. This drawn map data stores a layered map, for example, map data for each layer from the top layer to Japan, the Kanto region, Tokyo, and Kanda. A map code is attached to the map data of each layer.

[0042] The intersection data file 303 contains an intersection number that identifies each intersection, an intersection name, intersection coordinates (latitude and longitude), a road number at which the intersection is a start point or an end point, and the presence or absence of a signal. It is stored as intersection data. The node data file 304 stores node data consisting of information such as latitude and longitude that specify the coordinates of each point on each road. That is, this node data is data about one point on the road, and when the one connecting the nodes is called an arc, it is expressed by connecting each of a plurality of node rows with an arc. The road data file 305 contains a road number that identifies each road, an intersection number that is a start point or an end point, a road number that has the same start point or end point, road thickness, prohibition information such as no entry, and photo data described later. The photo number etc. are stored. The road network data consisting of the intersection data, the node data, and the road data stored in the intersection data file 303, the node data file 304, and the road data file 305 is used for the route search.

[0043] The search data file 306 stores intersection row data, node row data, and the like that constitute the route generated by the route search. The intersection sequence data includes information such as an intersection name, an intersection number, a photo number showing a characteristic landscape of the intersection, a corner, and a distance. In addition, the node column data consists of information such as east longitude and north latitude indicating the position of the node. In the photographic data file 307, photographs of each intersection and characteristic landscapes that can be seen while going straight are stored in the form of digital, analog, or negative film corresponding to the photograph numbers.

[0044] FIG. 11 shows various sensors constituting the status sensor unit 40. As shown in FIG. 11, the status sensor unit 40 includes an ignition sensor 401, a vehicle speed sensor 402, an accelerator sensor 403, a brake sensor 404, a side brake detection sensor 405, a shift position detection sensor 406, a winker detection sensor 407, and a wiper detection sensor 408. Light detection sensor 409, seat belt detection sensor 410, door open / close detection sensor 411, passenger detection sensor 412, indoor temperature detection sensor 413, outdoor temperature detection sensor 414, fuel detection sensor 415, water temperature detection sensor 416, ABS detection sensor 417, Air conditioner sensor 418, weight sensor 419, front inter-vehicle distance sensor 420, rear inter-vehicle distance sensor 421, body temperature sensor 422, heart rate sensor 423, sweating sensor 424, brain wave sensor 425, eye tracer 426, infrared sensor 427, and other sensors (tires) Air pressure drop detection sensor, belt loosening detection sensor, window open / close state sensor, crush sensor, indoor humidity sensor, outdoor humidity sensor, oil temperature detection sensor, oil pressure detection sensor, etc.) It is equipped with various sensors that detect the conditions inside the vehicle. These various sensors are arranged at predetermined positions according to their respective sensing purposes. When each of these sensors does not exist as an independent sensor, it includes a case of indirectly sensing from another sensor detection signal. For example, a tire pressure drop detection sensor indirectly detects a drop in air pressure due to fluctuations in the signal of the wheel speed sensor.

[0045] The ignition sensor 401 detects ON and OFF of the ignition. As the vehicle speed sensor 402, a conventionally known vehicle speed sensor such as one that detects the rotation angular velocity or the rotation speed of the speedometer cable to calculate the vehicle speed can be used without particular limitation. The accelerator sensor 403 detects the amount of depression of the accelerator pedal. The brake sensor 404 detects the amount of depression of the brake, and detects whether or not the brake is suddenly applied from the depression force, the depression speed, and the like. The side brake detection sensor 405 detects whether or not the side brake is applied. The shift position detection sensor 406 detects the shift lever position. The blinker detection sensor 407 detects the blinking direction of the blinker. The wiper detection sensor 408 detects the driving state (speed, etc.) of the wiper. The light detection sensor 409 detects the lighting state of each lamp such as a head lamp, a tail lamp, a fog lamp, and a room lamp. The seatbelt detection sensor 410 detects whether or not the driver and passengers (auxiliary seat, rear seat) are wearing seatbelts. If it is not worn, an agent will appear as appropriate (to the extent that it is not disliked) and give warnings, cautions, comments, etc. (change the degree by learning).

[0046] The door open / close detection sensor 411 detects the open / closed state of the door, and in the case of a so-called half-door, the agent notifies that fact. The door open / close detection sensor 411 can detect the open / close of each door according to the vehicle type, such as the driver's seat door, the passenger seat door, the rear driver's seat side door, and the rear passenger seat side door. The passenger detection sensor 412 is a sensor that detects whether or not a passenger is in the passenger seat or the rear seat, and detects it from the image inside the vehicle captured by the image pickup device 28, or is placed in the auxiliary seat or the like. Detect with a pressure sensor or a weight scale. The indoor temperature detection sensor 413 detects the indoor air temperature, and the outdoor temperature detection sensor 414 detects the outside air temperature. The fuel detection sensor 415 detects the remaining amount of fuel such as gasoline and light oil. The detection values for the past five times immediately before refueling are stored in the learning item data 292, and when the average value is reached, the agent notifies that it is time to refuel.

The water temperature detection sensor 416 detects the temperature of the cooling water. Immediately after the ignition is turned on, if this detection temperature is low, the agent often acts sleepy. On the other hand, if the water temperature is too high, the agent will notify you with a "sloppy" behavior before overheating. The ABS detection sensor 417 detects whether or not ABS has been activated to prevent the tires from locking due to sudden braking and to ensure maneuverability and vehicle stability. The air conditioner sensor 418 detects the operating state of the air conditioner. For example, ON / OFF of the air conditioner, set temperature, air volume, etc. are detected. The weight sensor 419 is a sensor that detects the weight of the driver. The driver is identified from this weight or from the weight and the image of the image pickup device 28, and the agent learned in relation to the driver is made to appear. That is, by using the learning item data 292 and the response data 293 learned by the agent for the specified driver, an agent dedicated to that driver is made to appear. The driver may be identified by obtaining an ID code, fingerprint, voiceprint, or the like. The front inter-vehicle distance sensor 420 detects the distance to other vehicles and obstacles in front of the vehicle, and the rear inter-vehicle distance sensor 421 detects the distance to other vehicles and obstacles behind.

[0048] The body temperature sensor 422, the heart rate sensor 423, and the sweating sensor 424 are sensors that detect the driver's body temperature, heart rate, and sweating state, respectively. Detect from. Alternatively, the body temperature sensor 422 may detect the temperature distribution of each part of the driver by thermography using an infrared detection element. The brain wave sensor 425 is a sensor that detects the driver's brain wave, and detects, for example, an α wave or a β wave to check the driver's arousal state and the like. The eye tracer 426 detects the movement of the user's line of sight, and determines whether the user is searching for an object outside the vehicle, searching for an object inside the vehicle, or being awake during normal driving. The infrared sensor 427 detects the movement of the user's hand or face.

Next, the operation of the present embodiment configured as described above will be described. FIG. 12 is a flowchart showing the main operation of the agent processing according to the present embodiment. When the ignition sensor 401 detects that the ignition has been turned on, the agent processing unit 11 first performs the initial setting (step 11). Initial settings include clearing RAM, setting the work area for each process to RAM, loading the program selection table 291 (Fig. 2) and help agent program support table (Fig. 7) into RAM, setting the flag to 0, etc. Is processed. In the agent process of the present embodiment, the start of the process is set to ON, but the process may be started when, for example, the door open / close detection sensor 411 detects the opening / closing of any of the doors.

Next, the agent processing unit 11 uses the detection value supplied from each sensor of the status sensor unit 40 to the status information processing unit 15, the processing result of the image captured by the image pickup device 28, and the current position detection device 21. Data such as the current position of the detected vehicle is acquired and stored in a predetermined area of RAM, and the current situation such as identification of the driver and the state of the vehicle is grasped from the stored data (step 12). For example, when the temperature of the cooling water detected by the water temperature detection sensor 416 is t1, the agent processing unit 11 stores this temperature t1 in the RAM, and if t1 is equal to or less than a predetermined threshold value t2, the current vehicle is present. It is understood that the cooling water temperature (see Fig. 2) is low as the state of. The current situation is that there are other requests from the driver who have voice-recognized based on the input from the microphone 26, such as "Call XX" or "Display restaurants around here". And requests such as "play a CD" are also grasped as the current situation. In this case, the words "CD", "kake", etc. included in the recognized voice become the selection conditions (horizontal axis items) of the program selection table 291 (Fig. 2).

Further, the agent processing unit 11 checks the learning item data 292 and the response data 293 of the agent data storage device 29 to grasp the state (learning data) that the agent has learned so far (step 13). ..

[0052] Whether or not there is a communication program (number) that can be activated in the current situation by the program selection table 291 shown in FIG. 2 from the grasped current situation and the checked learning data. If there is no corresponding program (step 14; N), go back to step 12 and grasp the new state. On the other hand, if there is a communication program that can be started (step 14; Y), determine the program number. Then, the driver's response history to the determined program number is confirmed from the response data 293, and it is confirmed whether or not the start of the communication program of the program number should be absent (step 15).

[0053] If the communication program is in a resting state (step 15; Y), the process proceeds to step 44.

When the communication program is not in the resting state (step 15; N), the agent processing unit 11 activates the communication program corresponding to the determined program number, and the actions (behaviors and actions) of each agent shown in FIG. The image according to the audio) is displayed on the display device 27, and the audio is output from the audio output device 25. Further, the agent processing unit 11 checks the proficiency level data 297 of the agent data storage device 29, and grasps the proficiency level of the driver with respect to the activated communication program (step 17). Also, set the activation flag of proficiency level data 297 to flag 1. Then, referring to the help agent program correspondence table 296, it is determined whether or not there is a help agent program (number) to be started from the proficiency level of the driver and the program number of the started communication program (step 18). .. Without the help agent program (step 18; N), the driver's response to the agent's actions by the activated communication program from the voice recognition result based on the input from the microphone 26 and the input result from the input device 22 as it is. And the time from the output of the agent's action to the acquisition of the driver's response are acquired (step 41).

If there is a help agent program (step 18; Y), start the help agent program with the corresponding program number and display an image according to the help agent's actions (action and voice) shown in FIG. It is displayed on the display device 27 together with the agent, and the audio is output from the audio output device 25 (step 19). As a result, a help agent appears when the driver's proficiency level with respect to the agent program is low, and the help agent deepens the understanding of the agent's functions and enables smooth communication such as response to the agent. .. Then, from the voice recognition result based on the input from the microphone 26 and the input result to the input device 22, the driver's response to the agent's action by the activated communication program and the driver's response after the agent's action is output. To get the time and time to get (step 41).

Next, the agent processing unit 11 determines whether or not the communication program started in step 16 is a controlled program (step 42). Here, whether or not the program is controlled is specified for each program. For example, "Should I turn on the radio?" Or "I will guide you to the cafeteria" when you detect a belly ringing sound at noon. A communication program, etc., when an agent proposes an action that can be processed (power ON, restaurant guidance, etc.), such as "Should I?", Is defined as a controlled program.

If it is not a controlled target program (step 42; N), the process proceeds to step 23, and if it is a controlled target program (step 42; Y), control is performed according to the driver's response acquired in step 20. (Step 43). For example, if a response that accepts a proposal such as "turn on", "OK", or "yes" is recognized in response to the proposal communication for turning on the power of the radio, the agent processing unit 11 controls according to the response. As a result, the agent is made to reply (act and voice) and the radio is turned on.

[0058] Then, the agent processing unit 11 accumulates data related to the communication program this time (step 44). As for the accumulation of data, for example, when the communication program is not started (step 15; Y), the number of days off / date and time column of the corresponding program number of the learning item data 292 is counted up. However, if the number of rests stored in the number of rests / date and time column of the learning item data 292 is Ka times and the number of rests determined from the history of the response data 293 up to the previous time for the program number is Kb times, Ka = If it is Kb-1, it means that I took a specified number of times off this time. Therefore, the data (stored at the corresponding position) in the program number column of the learning item data 292 and the response data 293 is cleared.

As for the accumulation of data in other cases (in the case of step 42; after step 43 in the case of N), if there is a learning item in the current situation grasped in step 12, the value of the learning item data 292 is updated. If the program number of the agent program is the program number for which the response contents should be stored as a history, the response contents acquired in step 41 are stored in the response data 293 (Fig. 6). As for the history of this response, if the data for a predetermined number of times specified for each program number has already been stored, the oldest data is discarded and new data is stored. Further, in other cases (in the case of step 42; N, after step 43), the proficiency level data 297 (FIG. 9) in which the activation flag is 1 is rewritten. At this time, based on the response time acquired in step 41, the oldest response time is discarded and new data is stored in the previous 5 response times, and the average response time and the shortest response time are stored from the previous 5 response times. Is calculated. In addition, the number of response cancellations is stored as 0 if there is no response cancellation. Then, the proficiency level is obtained by a predetermined formula, this proficiency level is stored, and the activation flag is set to 0.

[0060] When each of the above program determination, communication, and learning processes is completed, the agent processing unit 11 confirms whether or not the flag 1 is set in the flag area initially set in the RAM in step 11 (step 45). .. If the flag is not set (step 45; N), it is determined whether or not the ignition sensor 401 has detected ignition OFF (step 46), and if it is not detected (step 46; N), step 12 Go back to and grasp the new state. On the other hand, when the ignition OFF is detected (step 46; Y), the flag 1 is set in the flag area of the RAM (step 47), and then the process returns to step 12 to perform post-processing. That is, the agent is made to perform a farewell act (behavior and voice) according to the current situation and learning data, control such as turning off the lights that have been forgotten to turn off, and learning for the post-processing (step 44), and then a flag. Is 1 (step 45; Y), so the agent process ends.

[0061] Next, a specific example of the action by the agent processing described above will be described. FIG. 13 conceptually shows the specific contents of agent processing while the vehicle is running. As shown in FIG. 13 (A), the agent processing unit 11 currently has the state detected by the air conditioner sensor 418 "ON" and the room temperature detected by the indoor temperature detection sensor 413 and the outdoor temperature detection sensor 414. Obtain T1 and outdoor temperature T2. Also, by checking the response data 293 of each program number, the previous two driver responses to program number 0123 are C (acceptance), so the default values (T3 = 2 degrees, T4 =) are the values of the threshold values T3 and T4. 24 degrees) is read from the learning item data 292. From these thresholds T3 and T4, the final situation is the relationship between room temperature and outdoor temperature, (T1-T2) T3 is "Yes", the relationship between outdoor temperature T2 and threshold T4 T2 T4 is "Yes", etc. It is grasped in (Fig. 13 (A)).

From the above processing, the agent processing unit 11 finally selects the communication program of program number 00123 from the program selection table 291 (step 14), and confirms that it is not a holiday target (step 15; N). Then, start the communication program with the relevant number (step 16).

[0063] Further, the agent processing unit 11 checks the proficiency level data 297 of the agent data storage device 29 to acquire the proficiency level of the driver for the started communication program (step 17), and the help agent program correspondence table 296. From, get the existence of the help agent program to be started (step 18). As shown in Fig. 13 (A), since the driver's proficiency level is 25, the program number to be started for the started communication program from the communication program No. 00123 column of the help agent program correspondence table 296 shown in Fig. 7. Get that there is a 50010 and launch the appropriate help agent program (step 19).

[0064] Then, by invoking the communication program of program number 00123 and the help agent program of program number 50010, as shown in FIG. 13 (B), a plurality of images of the agent and the help agent are displayed (or moving images) on the display device 27. Is displayed, and the voice output device 25 outputs a voice such as "It's cool outside. Would you like to let in the outside air?", Followed by the help agent "Lisa is an air conditioner." It will stop and open the front window by half. "

Subsequently, the agent processing unit 11 acquires the driver's response (step 41). And since program number 00123 is a controlled program (step 42; Y), if it is accepted, the power of the air conditioner is turned off as control according to the response, and the windows on the driver's seat side and the passenger's seat side are only halved. Control the opening (step 43).

[0066] After the control according to the response, the agent processing unit 11 sets A if the driver's response is ignored, B if the driver's response is ignored, and C if the driver's response is accepted, as shown in FIG. 13 (C). , It is stored in the response data 293 corresponding to the program number 0123 together with the response date and time. In this case, the response data of the previous two times is deleted, and the previous response and the current response become the stored contents of the response data 293. If the stored response content is ignored A, the next thresholds T3 and T4 will be lowered by 1 degree (T3-1 = 1 degree, T4-1 = 23 degrees) and will be rested once. If the stored response content is rejection B, the next thresholds T3 and T4 will be lowered by 1 degree (T3-1 = 1 degree, T4-1 = 23 degrees) and will be rested 5 times. As the threshold value for one rest, the temperatures T3 = T3-1 and T4 = T4-1 after lowering are used. If the stored response content is reception C, the same values as the previously used thresholds T3 and T4 are used.

[0067] Further, the agent processing unit 11 discards the oldest response time data stored in the previous five response times of the proficiency level data 297 corresponding to the program number 00123, and discards the oldest response time data of this time (display device). Stores the time taken from when the agent is displayed on 27 to when the driver's response is obtained). Furthermore, the average response time, the shortest response time, and the proficiency level are calculated from the data of the previous five response times, and are stored in the corresponding locations.

Subsequently, the current situation acquired by the agent processing unit 11 is the same as described above, and when the driver's proficiency level increases (when the proficiency level exceeds the proficiency level threshold value, proficiency level = 57 here. The agent processing for) will be explained. In this case as well, the agent processing unit 11 finally selects the communication program of program number 00123 from the program selection table 291 (step 14), confirms that it is not a holiday target (step 15; N), and then Launch the communication program with that number (step 16).

[0069] Then, the agent processing unit 11 checks the proficiency level data 297 of the agent data storage device 29, acquires the proficiency level of the driver for the activated communication program (step 17), and obtains the proficiency level of the driver for the activated communication program (step 17), and the help agent program correspondence table 296 From, get the existence of the help agent program to be started (step 18). Since the driver's proficiency level is 57, it means that there is no program to be started for the started communication program from the help agent program correspondence table 296 shown in FIG.

[0070] Therefore, only the communication program of program number 00123 is started, the image of only the agent is displayed (or a moving image is displayed) on the display device 27, and the voice output device 25 is used according to the learning attitude at that time. The agent's voice such as "It looks like it's cooler outside. Let's get in the outside air!" Is output. After that, the driver's response is acquired (step 41) as in the above case, control is performed according to the response (step 43), and the response data 293 and the proficiency level data 297 are rewritten.

[0071] As described above, in the present embodiment, when the agent program is started, if the driver's proficiency level is low, a help agent explaining the actions of the agent appears, and the driver's agent is notified. Facilitates communication such as response. When the driver's proficiency level is high, the help agent does not appear and enables efficient communication with the agent. According to the present embodiment, agents having different functions and appearance status and help agents are individually displayed and output by voice, so that the agents can be easily identified and information can be grasped without being confusing to the driver. ..

Next, a second embodiment of the agent device of the present invention will be described. (3) Outline of the Second Embodiment In the agent device of the first embodiment, a help agent appears as a sub-agent according to the proficiency level of the driver, but in the agent device of the present embodiment, the driver is oriented. Various sub-agents are appearing accordingly. Examples of this sub-agent include a shortcut agent that appears when the driver's proficiency level is high. This shortcut agent enables the driver to partially short-circuit the actions of the agent and proceed with the procedure when the driver is proficient in the operation performed by the agent in a certain procedure. The same components as those in the first embodiment described above are designated by the same reference numerals, and the description thereof will be omitted.

(4) Detailed view 14 of the second embodiment is a block diagram showing a configuration of an agent device of the present embodiment. As shown in FIG. 14, in the agent device of the present embodiment, the help agent program and the help agent program correspondence table are not stored in the agent data storage device 29, and instead of these, the oriented agent program 395 , Oriented agent program correspondence table 396, oriented data 397, and most selected program data 398 are stored. Further, the image data 294 stores data for displaying an image of the appearance and behavior of the main agent E and the shortcut agent S illustrated in FIG. 23.

[0074] The directional agent program 395 displays an image on the display device 27 of a directional agent processing program that realizes a directional agent function that appears in addition to the main agent according to the driver's orientation, and detailed actions of the directional agent. Communication programs for outputting the conversation corresponding to the action from the voice output device 25 are stored in the order of the program numbers. The directional agent processing program includes a shortcut agent processing program for realizing a shortcut agent function that short-circuits the actions of the main agent according to the driver's proficiency level.

[0075] In this directional agent program 395, a plurality of types of voice data are stored for the voice of each program number, and the driver inputs from among a plurality of voices that can be easily distinguished from the voice of the main agent. It is designed to be selected by the device 22 and the like. For example, when the appearance of both the main agent and the directional agent is female, the voice of the directional agent is higher than the voice of the main agent, and the voices that can be easily distinguished are listed as candidates, and are selected from these. To. The voice and appearance of this directional agent can be changed as appropriate. Further, the appearance and voice of the main agent and the appearance and voice of the directional agent are such that the appearance and voice of the agent and the directional agent can be well distinguished from each other unless otherwise selected by the driver. It is automatically selected and set.

[0076] The directional agent program correspondence table 396 is a table for selecting a communication program stored in the directional agent program 395. The directional agent program correspondence table 396 shows the program number of the directional agent program corresponding to this agent program, the directional threshold for starting this directional agent program, and other conditions corresponding to the program number of the agent program. Each item is stored. The agent program number and the shortcut agent program number shown in FIGS. 15 and 16 match the numbers of the respective communication programs stored in the agent program 295 and the directed agent program 395, respectively.

FIG. 15 shows a shortcut agent program correspondence table that is a part of the orientation agent program correspondence table 396, and FIG. 16 shows a shortcut agent corresponding to each program number selected in the shortcut agent program correspondence table. It represents the contents of the actions (actions and vocalizations) of.

[0078] In the shortcut agent program correspondence table shown in FIG. 15, the proficiency threshold, the most selected program number, and the shortcut agent (oriented agent) program number are stored corresponding to the agent program. The proficiency threshold represents a threshold of proficiency for each agent program as user-oriented, and when the proficiency level of the driver becomes equal to or higher than this proficiency threshold, the shortcut agent program is started. The most selected program number is detected from the most selected program data 398, and the shortcut agent program corresponding to each agent program is determined by the most selected program number.

[0079] For example, when an agent program (program number 00550) for selecting a method for setting a destination is started in the route guidance system, the driver's proficiency level with respect to this agent program is 70 or more. If the program number of the most selected program is 000080 (a program that displays the genre selection screen and waits for a response), the shortcut agent program with program number 80010 is started.

[0080] Note that, in the directional agent program correspondence table 396, not only the shortcut agent program correspondence table but also the correspondence table between the agent program and the directional agent program other than the shortcut agent program corresponding to this agent program is stored. .. Similar to the shortcut agent program correspondence table, the correspondence table also stores the program numbers of the agent program and the corresponding directional agent program, the directional threshold for starting this directional agent program, and other conditions.

[0081] The directional data 397 stores a directional value representing the driver's directional value and data of each item from which the directional value is acquired. In FIG. 17, each item of the data stored in the orientation data 397 is the system status which is an item related to the agent system and other related systems, the time status such as whether it corresponds to the current time or the anniversary, the gender, and the like. It is a table that is roughly classified into driver status such as age and hobbies, vehicle status, and external status such as weather. The data of each item is acquired by the driver's own input, collectively by the agent or as a response to the question as needed, or acquired from the driver's vehicle operation or external equipment. ..

[0082] The orientation value of each driver is obtained from one or more of the data of each of these items. The orientation value includes the same proficiency level as that of the first embodiment, and the orientation data 397 includes the same proficiency level data 297 as that of the first embodiment. The response time of the proficiency level data 297 includes the response time when responding to the shortcut agent that appears at the same time.

FIG. 18 is a diagram conceptually showing the contents of the most selected program data 398. This most selected program data 398 is used when proficiency is used as a directed value. The most selected program data 398 stores data for selecting the short-circuited agent program to which the shortcut agent short-circuits. The shortcut agent of the present embodiment enables an agent (hereinafter referred to as an item selection agent) that performs an item selection action having a multi-layered hierarchical structure to perform an item selection action in the nth layer and the n + 1th layer in the nth layer. It is a short circuit.

As shown in FIG. 18, the most selected program data 398 is selected and started by the response about the item selection agent for each program number of each item selection agent when the shortcut agent is not started. The program number of the agent program (selected agent program) in the next lower hierarchy is stored for the previous 5 times. In addition, the program number of the agent program (most selected agent program) selected and started most among the previous five selected agent programs is stored. This most selected program data 398 is stored and updated by learning, and is referred to when the shortcut agent program is started.

Next, the operation of the present embodiment configured as described above will be described. FIG. 19 is a flowchart showing the main operation of the agent processing according to the present embodiment. In the present embodiment as well, as in the first embodiment, when the ignition sensor 401 detects that the ignition has been turned on, the agent processing unit 11 initially performs the same as in the first embodiment described above. Setting (step 11), grasping the current situation (step 12), checking learning item data and response data (step 13), detecting the presence or absence of a communication program (step 14), and whether or not the communication program should be absent Confirm (step 15). Then, if the communication program should be in a state where it should be absent (step 15; Y), the process proceeds to step 44 as it is, and if it is not in a state where it should be absent (step 15; N), the communication program is started (step 16). ).

[0086] Following the activation of the communication program (step 16), the agent processing unit 11 of the present embodiment reads the directional value of each item of the driver from the directional data 397, and sets the directional threshold value in the directional agent program correspondence table 396. Compare (step 27). Then, when the driver's orientation value is equal to or greater than the orientation threshold value (step 27; Y), the orientation agent processing according to the driver's orientation is performed based on the orientation agent program correspondence table 396 (step 28).

[0087] Examples of the comparison of the directional thresholds (step 27) and the directional agent processing (step 28) are as follows. For example, the number of days Y until the family's birthday is obtained from the data of "today's date" and "family date of birth" in the orientation data 397, and the value of (annual days of the year -Y) is used as the orientation value. When it is acquired and one week before the family's birthday (direction threshold) (step 27; Y), a direction agent with a birthday cake is displayed and "One week until XX's birthday. Birth. Is the day present ready? Is output (step 28). In addition, there is a process of notifying the driver of the fortune of the day at the time of traffic jam based on the directional value acquired from the data of the driver's date of birth and the traffic jam situation. In addition, based on the data of the driver's favorite professional baseball team and the directional value of the game of the professional baseball team at the start of the radio broadcast, the broadcast will be started and the opponent will be notified, and the radio power will be turned on. Performs the process of inquiring whether or not to enter. In this case, the data scheduled to be broadcast on the radio (broadcast start time and the opponent team) is input by the driver from the input device 22 or acquired from the communication control device 24. The process of acquiring the direction value based on the vehicle position data and the data of the sights and historic sites that the driver is interested in and guiding the sights and historic sites in the vicinity of the vehicle, the data of the driver's driving history and the vehicle position A process of acquiring a directional value based on the vehicle and giving advice to a driver with a short driving history, such as "Be careful because the road is narrow around here." In addition, as the directional agent processing, as will be described in detail later, there is also a shortcut agent processing that acquires the proficiency level for the car navigation system as a directional value and short-circuits the hierarchical menu for selecting the destination etc. when the proficiency level is high. included.

[0088] After the directional agent processing as described above, the response from the driver to the activated communication program is acquired (step 41). When the driver's directional value is smaller than the directional threshold (step 27; N), the response is acquired as it is without starting the directional agent program (step 41).

After that, as in the first embodiment described above, the process from the determination of whether the agent program is the controlled program (step 42) to the end is performed.

[0090] For the agent program that was short-circuited by the shortcut agent and was not started when the data was accumulated, the number of rests / date and time of the learning item data 292 of the agent program is not counted up, and the response data 293 is also rewritten. It is not performed, and the response time of the previous 5 times of the proficiency level data 297 and the agent program selected after the previous 5 times of the most selected program data 398 shall not be rewritten.

[0091] Next, a case where the directed agent is a shortcut agent will be described as a specific example of the action by the agent processing described above.

[0092] FIG. 20 is an explanatory diagram showing a hierarchical structure of menu settings when a menu is set by input from a driver when performing car navigation, and FIG. 21 is a shortcut agent in the hierarchical structure of FIG. 20. It is explanatory drawing which showed the act of. As shown in FIG. 20, in this car navigation system, for example, when a destination is searched and set from a restaurant map or a list near the current location, it is usually a mode in which the destination is set first. Select the destination setting mode (1st level), select the destination selection from the genre Select the genre selection mode (2nd level), select the restaurant from the genre list (3rd level), Display a map or list of restaurants near your current location, and specify the restaurant that will be your destination. After that, the navigation processing unit 10 provides route guidance to the restaurant.

Then, in the present embodiment, as shown in FIG. 21, after selecting the destination setting mode (first layer) by the shortcut agent, the restaurant is directly selected and the restaurant map near the current location is selected. Alternatively, a list (third level) can be displayed, and then the destination restaurant can be specified.

[0094] First, a case where the driver's proficiency level with respect to the agent program is high (here, proficiency level = 75) will be described. In the present embodiment, when the car navigation system is activated by voice input from the microphone or the like, the agent processing unit 11 first selects a mode (first) of setting the destination and the setting related to the system. Perform processing for 1 layer). At this time, the agent program with program number 00540 is started (step 16). By this program, the main agent appears on the display device 27 on foot, and the voice output device 25 outputs a voice saying "Would you like to give directions immediately or set up the system?" .. Then, since there is no shortcut agent program corresponding to this agent program (step 27; N), it waits for a response as it is.

[0095] Then, when the destination setting mode is selected, such as acquiring a voice input of "direction guidance" from the microphone (step 41), this agent program is not a controlled program (step 42; N). , The agent processing unit 11 starts the agent program (program for selecting the method of setting the destination) of program number 00550 after processing such as data accumulation (step 44) (step 16). This will move to the second level of the route guidance menu, the main agent of the display device 27 will change to the up-shot display, and from the audio output device 25, "Please select the destination setting method. Do you want to search by genre?" Do you want to enter the phone number or look for the place name? " The agent then waits for input of the destination setting method.

[0096] Further, the agent processing unit 11 reads the directional value of each item of the driver from the directional data 397 and compares it with the directional threshold value of the directional agent program correspondence table 396 (step 27). Of the directed values, the proficiency level is proficiency level = 75. Then, referring to the shortcut agent program correspondence table 296 (Fig. 15), since the proficiency level is larger than the proficiency level threshold value of the activated agent program No. 550 (step 27; Y), the agent processing unit 11 is oriented. Shortcut agent processing as agent processing is performed (step 28).

[0097] FIG. 22 is a flowchart showing a process of shortcut agent processing as directional agent processing (step 28). As shown in FIG. 22, the shortcut agent processing in management, agent processing unit 11 displays the program number 00580 (genre selection screen of most selective agent program to the program number 00550 No. agent program from most selection program data 398 And get the program number of the program that prompts you to select a genre (step 281). In the most selected program data 398, the most selected agent program for the agent program with program number 00550 is 00540, which means that this driver started the program with 00550 in the previous five operations. In the 2nd layer, select by genre from 3 types of selection by genre, input of phone number, and input of place name, and as a result, the program of program number 00540 (program that displays the genre selection screen and prompts you to select the genre) is started. This is the most common case.

[0098] Then, the agent processing unit 11 acquires the program number 80010 of the shortcut agent program corresponding to the program number 00550 of the started agent program and the program number 00480 of the most selected agent program in the shortcut agent program correspondence table 396. (Step 282). Next, the agent processing unit 11 starts the shortcut agent program of this program number 80010 (step 283). By this shortcut agent program, as shown in FIG. 22, a long shot of the shortcut agent S is displayed on the display device 27 along with the up shot of the main agent E, and the above-mentioned agent is displayed from the audio output device 25. Following the voice of E, the voice of the shortcut agent S saying "You can enter the genre immediately." Is played. Subsequently, the shortcut agent waits for a response to the input of the genre.

[0099] When an input specifying a genre is directly obtained from the driver in response to the shortcut agent S, for example, "restaurant", the shortcut agent recognizes this response. Then, based on this information, the agent processing unit 11 terminates the agent program of program number 00550 without obtaining a response, and the agent program of program number 00600 (the agent after recognizing the response to the "restaurant"). Program) is started, and after that, agent actions are performed in order from this agent program, the vehicle position is detected, the restaurant map near the vehicle's current position is displayed on the display device 27, and the driver uses this map to become the destination. Obtain the designation of a restaurant. Therefore, by responding to the shortcut agent, the driver can skip the operation in the second layer (selection of the destination setting method) and move to the third layer.

[0100] On the other hand, when a response to the main agent such as "genre selection" is acquired from the driver, the process shifts to the third layer according to the acquired response after the response is recognized by the agent program. For example, when a response to "genre selection" is obtained, the agent processing unit 11 displays a genre-specific list on the display device 27 as the third layer, and the agent voice saying "Please select a genre." Is output. Then, when the input of "restaurant" is acquired, the agent program of program number 00600 is activated to detect the current position of the vehicle and display the restaurant map near the current position. By responding to the main agent, for example, with a "telephone number" or "place name", the driver can select a destination selection method other than the genre selection different from the shortcut destination by the shortcut.

[0101] When the driver's proficiency level with respect to the agent program is smaller than the proficiency level threshold value 70 (step 27; N), the agent processing unit 11 does not start the shortcut agent program, and in the second layer, FIG. 23. As shown in, the main agent E is displayed and the voice is output only to acquire the destination setting method, and then the process shifts to the lower hierarchy such as genre selection and restaurant map display.

[0102] Then, after displaying the restaurant map on the display device 27, the process returns to the main agent processing, and the driver specifies the destination restaurant as a response from the displayed map (step 41). After that, the control target program (step 42; Y) is controlled according to the response (route guidance) (step 43), and the data including the most selected program data 398 is accumulated (step 44). Perform the same processing as in the embodiment.

[0103] As described above, in the present embodiment, when the agent program is started, a shortcut agent appears when the driver's proficiency level is high, and the agent's actions can be short-circuited, so that the driver's action can be short-circuited. It makes communication such as response efficient and enables operation in a short time. When the driver's proficiency level is low, the shortcut agent does not appear, and by maintaining a sense of unity in operation, it becomes easier for the driver to grasp the hierarchical structure of the menu as a systematic system. There is. According to the present embodiment, the shortcut agent appears together with the main agent, so that even if the driver who has become proficient once forgets to operate because he / she has not used it for a long period of time, the main agent You can easily operate according to the menu hierarchy according to the guidance of, or select a menu (menu other than the shortcut destination) that you do not use on a daily basis.

[0104] According to the present embodiment, since the agents having different functions and appearance states and the shortcut agents are individually displayed and output by voice, it is not confusing to the driver and it is possible to easily identify and grasp the information of these agents. it can. According to the present embodiment, the program selected and started in the past is stored in the most selected program data 398 as a usage history, and frequently used items (most selected programs) are acquired, and the shortcut destination by the shortcut agent is based on this. Is determined, so an efficient shortcut function tailored to the driver is realized.

[0105] The present invention is not limited to the above-described embodiment, and can be appropriately modified as long as it does not deviate from the gist of the present invention. In each of the above embodiments, the sub-agent has an association with the main agent being started, such as a help agent and a shortcut agent, but the present invention is not limited to this, and the main agent and the sub-agent are not limited to this. It can also be unrelated to each other. For example, one of the agent and the sub-agent may provide route guidance, and the other may notify the state of the vehicle. For example, while one is giving directions, the other appears as "I'm hungry. I want gasoline." Then, even if the agent who arrives at the destination and guides the route ends, the agent who notifies the state of the vehicle can be displayed as it is and become a crying face unless refueling is performed.

[0106] In each of the above-described embodiments, the appearance of sub-agents such as help agents and shortcut agents is determined for each program, but is not limited to this, and for each system such as car navigation and air conditioning, and for each system. Alternatively, it may be determined for each driver, and if it is determined to be necessary, it may appear during the system activation or the driver's operation. Multiple sub-agents may appear at one time, and both help agents and shortcut agents can appear according to their proficiency level. The sub-agent may also perform an act of acquiring a response or the like from the driver, and the action of the sub-agent may be determined by learning from this response or the like.

[0107] In the first embodiment, the appearance / non-appearance of help is determined according to the proficiency level, but the action of the help agent (including non-appearance / non-appearance) is determined from the orientation other than the proficiency level. May be good. For example, for the main agent who informs the driver of the progress of the professional baseball game based on the professional baseball broadcast on the radio, the rules and terms can be explained to those who are not familiar with baseball. In the second embodiment, the shortcut agent short-circuits the agent action by enabling the item selection action in the n + 1 layer in the nth layer, but the shortcut agent is changed from the nth layer to the nth layer. It is also possible to short-circuit the agent action to enable operations in the hierarchy of n + 2 or higher. In the second embodiment described above, the shortcut agent only short-circuits the main agent, and the main agent performs the subsequent agent actions again. However, after the response to the shortcut agent is obtained, the shortcut agent is performed again. , The shortcut agent may act as an agent without returning to the main agent.

[Effect of the Invention] As described above, according to the agent device according to the present invention, agents and sub-agents having different functions and appearance states are made to appear individually, so that they are not confusing to the driver. The agent can be clearly identified and the information can be easily grasped.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram showing a configuration of an agent device according to a first embodiment of the present invention.

FIG. 2 is an explanatory diagram conceptually showing the contents of the program selection table according to the embodiment of FIG.

FIG. 3 is an explanatory diagram showing actions (behavior and voice) of an agent corresponding to each program number in the embodiment of FIG.

FIG. 4 is an explanatory diagram showing several screens of an agent's smart bowing behavior displayed on a display device when program numbers 00001 to 00002 are activated in the embodiment of FIG.

FIG. 5 is an explanatory diagram conceptually showing the contents of the learning item data in the embodiment of FIG.

FIG. 6 is an explanatory diagram conceptually showing the contents of the response data according to the embodiment of FIG.

FIG. 7 is an explanatory diagram conceptually showing the contents of a help agent program correspondence table stored in the navigation data storage device according to the embodiment of FIG.

FIG. 8 is an explanatory diagram showing a help agent action (behavior and voice) corresponding to each program number in the embodiment of FIG.

FIG. 9 is an explanatory diagram conceptually showing the contents of the proficiency level data in the embodiment of FIG.

FIG. 10 is an explanatory diagram conceptually showing the contents of a data file stored in the navigation data storage device according to the embodiment of FIG.

FIG. 11 is an explanatory diagram showing various sensors constituting the situation sensor unit according to the embodiment of FIG.

FIG. 12 is a flowchart showing a main operation of agent processing according to the embodiment of FIG.

FIG. 13 conceptually represents the specific content of agent processing while the vehicle is traveling in the embodiment of FIG.

FIG. 14 is a block diagram showing a configuration of an agent device according to a second embodiment of the present invention.

FIG. 15 is an explanatory diagram conceptually showing the contents of the directional agent program correspondence table according to the embodiment of FIG.

FIG. 16 is an explanatory diagram showing actions (behavior and voice) of a shortcut agent corresponding to each program number in the embodiment of FIG.

FIG. 17 is a table showing each item of data stored in the oriented data in the embodiment of FIG.

FIG. 18 is an explanatory diagram conceptually showing the contents of the most selected program data in the embodiment of FIG.

FIG. 19 is a flowchart showing a main operation of agent processing according to the embodiment of FIG.

20 is an explanatory diagram showing a hierarchical structure of menu setting when a menu is set by input from a driver when performing car navigation in the embodiment of FIG. 14. FIG.

FIG. 21 is an explanatory diagram showing the actions of the shortcut agent in the hierarchical structure of FIG. 20.

FIG. 22 is a flowchart showing the operation of the directional agent processing according to the embodiment of FIG.

FIG. 23 is an explanatory diagram showing a screen display and an audio output when a shortcut agent appears in the embodiment of FIG.

FIG. 24 is an explanatory diagram showing a screen display and an audio output when the shortcut agent does not appear in the embodiment of FIG.

[Explanation of codes] 1 Overall processing unit 10 Navigation processing unit 11 Agent processing unit 12 I / F unit 13 Image processing unit 14 Voice control unit 15 Status information processing unit 21 Current position detection device 22 Input device 23 Storage medium drive device 24 Communication Control device 25 Voice output device 26 Microphone 27 Display device 28 Imaging device 29 Agent data storage device 30 Navigation data storage device 40 Status sensor unit