Systems and techniques for presenting and rating items in an online marketplace

0001(Cross-reference of related applications) This application claims priority over US Provisional Patent Application No. 62 / 156,584, Invention Name "Presentation and Recommendation of Products in an Online Marketplace", filing date May 4, 2015, Agent Control No. CTL-001PR. The contents of the US provisional patent application are incorporated herein by reference to the maximum extent permitted by applicable law.

0002(Copyright statement) This disclosure includes materials subject to copyright protection, including drawings. Copyright owner has no disputed replication by patent document or patent disclosure any person, such as described in patent file or records Patent and Trademark Office, the otherwise, all have kana that copyright Also reserve.

0003(Field of invention) The present disclosure generally relates to systems and techniques for ranking and rating items. Some embodiments specifically relate to the ranking of items in e-commerce, and more specifically, at least in part, an online marketplace for goods and services based on the ranking of goods and services. Regarding the generation of user-specific catalogs in. Some embodiments relate specifically to the valuation of an item in an e-commerce, and more specifically to the generation of a predicted valuation of an item in an online marketplace.

0004(background) Widespread availability of computer devices capable of communicating with each other through communication networks (eg, the Internet) facilitates online shopping and e-commerce ("e-commerce"). For example, consumers can shop for items (eg, products and / or services) in online marketplaces. Purchased products can be shipped directly to consumers. For many consumers, online shopping can be more convenient and efficient than visiting a physical store directly.

0005The availability of networked computer devices also facilitates consumer rating sharing and item reviews. For example, many online marketplaces allow users to submit ratings and reviews for an item, which others can view when deciding whether to purchase the item.

<p num="0006"> (Outline of the invention) Shopping in online marketplaces can be more convenient than visiting physical stores, but many online marketplaces offer an inefficient online shopping experience, thereby providing consumer time as well as online marketplaces. It makes the use of computer system resources that implement and provide access inefficient. Such inefficiencies can be significant, especially when consumers are shopping for certain types of items but have not yet decided which items to buy. We recognize that the efficiency of a user's online shopping experience can be improved by presenting a defined type of items to the user in a particular order based on the item's "purchasability score". I understand. Thus, the item most likely to be purchased (or interested in) by the user is the user before (or instead) presenting other items that the user is less likely to purchase. Can be presented to. As a result, the user can complete the shopping experience more quickly and successfully, thereby saving the user's time and the resources of the computer system that implements and provides access to the online marketplace.</p><p num="0007"> According to one aspect of the disclosure, a step of receiving data from a user's device indicating the selection of a type of item, and for each of multiple items of that type, at least in part, (1) during a period of time. The number of individual item impressions provided to multiple users, (2) the quantity of individual items purchased by multiple users, and (3) the quantity of individual items added to multiple users' shopping carts. Based on the steps to determine the affordability score for an individual item and, at least in part, the items contained within multiple items based on the purchaseability score of the individual item contained within multiple items. The step of determining the ranking of items and the step of generating item feed data indicating the order of a set of items containing a plurality of items, and the order of the items contained in the set of items is at least partially plural. A step that is determined based on the ranking of items contained within an item, and a step that provides item feed data to the user's device, where the user's device corresponds to the item contained within the set of items. A computer-implemented method is provided that is configured to display the panel's scrollable feed, and that the item panel in the scrollable feed is ordered according to the order of the corresponding items in the item feed data, including steps.</p><p num="0008"> In some embodiments, the affordability score for an individual item is further, at least in part, based on the purchase price of the item. In some embodiments, the affordability score for an individual item is further, at least in part, based on the quantity of the individual item added to the wishlist of multiple users.</p><p num="0009"> In some embodiments, the affordability score for an individual item is, at least in part, based on the following formula:<chemistry num="1"><img id="000003" he="11" wi="123" file="JP2018519613A_D0001.tif" img-format="tif" img-content="drawing" /></chemistry>During the ceremony, W₁, W₂, And W₃Are the first, second, and third weights, respectively, "impressions" is the number of impressions of individual items provided to multiple users during that time period, and "quant_purchases" is The quantity of items purchased by multiple users, "quant_cart" is the quantity of items added to the shopping carts of multiple users, and "quant_wish_list" is the quantity of items added to the wishlist of multiple users. The "price" is the purchase price of the item.</p><p num="0010"> In some embodiments, the method further selects users for inclusion within multiple users, at least in part, based on one or more similarities between the user and the plurality of users. Including steps. In some embodiments, the plurality of items is the first plurality of items, and the method further comprises, at least in part, (1) one or more similarities between the user and the plurality of users. The set of items further includes a step to determine the ranking of a second multiple item based on gender and (2) data indicating whether the user has purchased an individual item contained within the multiple items. Includes a second set of items. In some embodiments, the order of the set of items is further determined, at least in part, based on the ranking of the second plurality of items.</p><p num="0011"> In some embodiments, the order between the first plurality of items in the set of items matches the order among the first plurality of items in the ranking of the first plurality of items, and within the set of items. The order between the second items matches the order between the second items in the ranking of the second items, and the items contained within the first item and the second item The order in the set of items with the items contained in the plurality of items is determined probabilistically.</p><p num="0012"> In some embodiments, the method further comprises determining the order of a set of items, (a) probabilistically selecting between a first plurality of items and a second plurality of items. And the first probability of selecting the first multiple items is P₁And the second probability of selecting the second multiple items is 1-P₁From the steps and (b) selected items, the highest ranked item that has not yet been assigned a rank in the order of the set of items is identified, and the identified item is placed in the order of the set of items. The step to assign to the next rank and until a specified number of items are assigned a rank in the order of the set of items, or all items in the first and second items are ranked in the order of the set of items. Includes a step that repeats steps (a) and (b) until assigned.</p><p num="0013"> In some embodiments, the method further modifies the first and second probabilities in response to the passage of a specified time period and / or in response to a request to reorder a set of items. Includes steps to do. In some embodiments, the method further steps to change the ranking of items contained within a plurality of items by performing weighted random shuffling of the purchaseability score of the items contained within the plurality of items. Including.</p><p num="0014"> According to another aspect of the disclosure, the step of receiving data indicating the selection of a type of item from the user's device, and for each of multiple items of that type, at least in part, (1) for a period of time. The number of impressions of individual items provided to multiple users, (2) the quantity of individual items purchased by multiple users, and (3) the number of individual items added to multiple users' shopping carts. Included within multiple items based on the steps to determine the affordability score for an individual item based on quantity and, at least in part, the purchaseability score for an individual item contained within multiple items. A step of determining the ranking of items and a step of generating item feed data indicating the order of a set of items containing a plurality of items, and the order of the items contained in the set of items is at least partially plural. A step that is determined based on the ranking of items contained within an item, and a step that provides item feed data to the user's device, where the user's device corresponds to an item contained within the set of items. The item panel is configured to display a scrollable feed, and the item panel in the scrollable feed is programmed to perform actions, including steps, ordered according to the order of the corresponding items in the item feed data. A system is provided that includes one or more computers.</p><p num="0015"> In some embodiments, the affordability score for an individual item is further, at least in part, based on the purchase price of the item. In some embodiments, the affordability score for an individual item is further, at least in part, based on the quantity of the individual item added to the wishlist of multiple users.</p><p num="0016"> In some embodiments, the affordability score for an individual item is, at least in part, based on the following formula:<chemistry num="2"><img id="000004" he="10" wi="122" file="JP2018519613A_D0001.tif" img-format="tif" img-content="drawing" /></chemistry>During the ceremony, W₁, W₂, And W₃Are the first, second, and third weights, respectively, "impressions" is the number of impressions of individual items provided to multiple users during that time period, and "quant_purchases" is The quantity of items purchased by multiple users, "quant_cart" is the quantity of items added to the shopping carts of multiple users, and "quant_wish_list" is the quantity of items added to the wishlist of multiple users. The "price" is the purchase price of the item.</p><p num="0017"> In some embodiments, the behavior further selects the user with respect to inclusion within the plurality of users, at least in part, based on one or more similarities between the user and the plurality of users. including. In some embodiments, the plurality of items is the first plurality of items, and the behavior is further, at least in part, (1) one or more similarities between the user and the plurality of users. And (2) a second set of items further includes a step of determining the ranking of the second multiple items based on data indicating whether the user has purchased individual items contained within the multiple items. Contains 2 multiple items. In some embodiments, the order of the set of items is further determined, at least in part, based on the ranking of the second plurality of items.</p><p num="0018"> In some embodiments, the order between the first plurality of items in the set of items matches the order among the first plurality of items in the ranking of the first plurality of items, and within the set of items. The order between the second items matches the order between the second items in the ranking of the second items, and the items contained within the first item and the second item The order in the set of items with the items contained in the plurality of items is determined probabilistically.</p><p num="0019"> In some embodiments, the action further comprises the step of determining the order of the set of items, (a) in the step of probabilistically selecting between the first plurality of items and the second plurality of items. So, the first probability of selecting the first multiple items is P₁And the second probability of selecting the second multiple items is 1-P₁From the steps and (b) selected items, the highest ranked item that has not yet been assigned a rank in the order of the set of items is identified, and the identified item is placed in the order of the set of items. The step to assign to the next rank and until a specified number of items are assigned a rank in the order of the set of items, or all items in the first and second items are ranked in the order of the set of items. Includes a step that repeats steps (a) and (b) until assigned.</p><p num="0020"> In some embodiments, the action further modifies the first and second probabilities in response to the passage of a defined time period and / or in response to a request to reorder the set of items. Including steps. In some embodiments, the action further comprises changing the ranking of the items contained within the item by performing a weighted random shuffling of the purchaseability score of the items contained within the item. ..</p><p num="0021"> According to another aspect of the disclosure, when a computer storage medium is provided and the computer storage medium is executed by a data processor, the data indicating to the data processor the selection of a type of item from the user's device. And, at least in part, for each of multiple items of that type, (1) the number of impressions of individual items provided to multiple users over a period of time, and (2) by multiple users. Steps to determine the availability score for an individual item, and at least in part, based on the quantity of individual items purchased and (3) the quantity of individual items added to multiple users' shopping carts. , An item feed that shows the steps to determine the ranking of items contained within multiple items and the order of sets of items containing multiple items, based on the purchaseability score of individual items contained within multiple items. The steps that generate data, the order of the items contained within a set of items, is determined, at least in part, based on the ranking of the items contained within multiple items. A step provided to the user's device, the user's device is configured to display a scrollable feed of the item panel corresponding to the items contained within the set of items, and the item panel in the scrollable feed is It has instructions that are ordered according to the order of the corresponding items in the item feed data, include steps, perform an action, and are stored on it.</p><p num="0022"> User-provided evaluation of an item in an online marketplace can help consumers to judge the opinions of other consumers of an item before purchasing the item, but user-provided evaluation can be misleading. Consumers who make purchase decisions based on misleading evaluation data may make suboptimal purchase decisions that are at their own disadvantage. For example, the number of user-provided ratings for some items (eg, recently sold items) can be very small, and the distribution of ratings for such items is for consumers familiar with the item. It may not represent the actual distribution of opinions. Therefore, there is a need for evaluation systems and techniques that more accurately represent the actual distribution of consumer opinions familiar with an item, even when the number of user-provided evaluations for that item is small. We recognize and understand that the accuracy of the distribution of ratings for items with a small number of user-provided ratings can be improved by supplementing the user-supplied ratings with one or more predicted ratings. ing. For many items, the actual distribution of item ratings can be accurately predicted (eg, based on item type, price, manufacturer, etc.). As the number of user-provided ratings for an item increases, the expected number of ratings can be reduced until only user-provided ratings for that item are displayed.</p><p num="0023"> According to another aspect of the disclosure, a step of obtaining one or more user-provided ratings for an item, one or more of which is a user-provided rating provided by a user of the computer system. Based on the step of determining whether the number of user-provided evaluations for the item exceeds the number of evaluation thresholds for the item and the determination that the number of user-provided evaluations for the item does not exceed the number of evaluation thresholds. The step of obtaining multiple predicted ratings for an item and providing a set of ratings for the item to the user's device, where a set of ratings for an item is one or more user-provided ratings and multiple predictions. A method is provided that includes steps, including evaluations that are performed.</p><p num="0024"> In some embodiments, the expected distribution of valuations for the item substantially matches the expected distribution of valuations for the item. In some embodiments, the method further, at least in part, is a predicted distribution of valuations for an item based on item categorization, item manufacturer, item seller, and / or item price. Includes a step to determine. In some embodiments, the method further comprises determining, at least in part, the expected distribution of valuations for an item based on the actual distribution of valuations for one or more other items. .. In some embodiments, the item and one or more other items are in the same item category (or set), manufactured by the same manufacturer, sold by the same seller, and / Or have prices within the same price range.</p><p num="0025"> In some embodiments, one or more user-provided ratings are one or more first user-provided ratings, and the method further comprises one or more second user-provided ratings for the item. A combination of the step of obtaining an offer rating, the step of determining whether the combined number of first and second user-provided ratings for an item exceeds the threshold number of ratings for an item, and the user-provided rating for an item. A step of providing a set of ratings for an item to a user's device based on the determination that the number given exceeds the threshold of ratings, the first set of ratings for an item being one or more. Includes a step consisting of a user-provided evaluation of and one or more second user-provided evaluations.</p><p num="0026"> According to another aspect of the disclosure, a step of obtaining one or more user-provided ratings for an item, one or more of which is a user-provided rating provided by a user of the computer system. Based on the step of determining whether the number of user-provided evaluations for the item exceeds the evaluation threshold number for the item and the determination that the number of user-provided evaluations for the item does not exceed the evaluation threshold number. The step of obtaining multiple predicted ratings for an item and providing a set of ratings for the item to the user's device, where a set of ratings for an item is one or more user-provided ratings and multiple predictions. A system is provided that includes one or more computers that are programmed to perform an operation, including evaluations that are performed, including steps, and so on.</p><p num="0027"> In some embodiments, the expected distribution of valuations for the item substantially matches the expected distribution of valuations for the item. In some embodiments, the behavior further, at least in part, provides a predicted distribution of valuations for the item, based on item categorization, item manufacturer, item seller, and / or item price. Includes a determination step. In some embodiments, the action further comprises determining, at least in part, the expected distribution of valuations for an item based on the actual distribution of valuations for one or more other items. In some embodiments, the item and one or more other items are in the same item category (or set), manufactured by the same manufacturer, sold by the same seller, and / Or have prices within the same price range.</p><p num="0028"> In some embodiments, one or more user-provided ratings are one or more first user-provided ratings, and the behavior is further one or more user-provided ratings for the item. A combination of a step to get a rating, a step to determine if the combined number of first and second user-provided ratings for an item exceeds the threshold number of ratings for an item, and a user-provided rating for an item. A step of providing the user's device with a set of ratings for an item based on the determination that the number of items exceeds the threshold of the rating, the first set of ratings for an item being one or more. Includes a step consisting of a user-provided evaluation and one or more second user-provided evaluations.</p><p num="0029"> According to another aspect of the disclosure, when a computer storage medium is provided and the computer storage medium is run by a data processor, the data processor gets one or more user-provided ratings for an item. One or more user-provided ratings are whether the number of steps and user-provided ratings for the item, provided by the user of the computer system, exceeds the threshold number of ratings for the item. Based on the decision step and the determination that the number of user-provided ratings for the item does not exceed the rating threshold, obtain multiple predicted ratings for the item and provide a set of ratings for the item to the user's device. A set of ratings for an item to perform an action, including one or more user-provided ratings, including multiple predicted ratings, and stored on it. Have an order.</p><p num="0030"> In some embodiments, the expected distribution of valuations for the item substantially matches the expected distribution of valuations for the item. In some embodiments, the behavior further, at least in part, provides a predicted distribution of valuations for the item, based on item categorization, item manufacturer, item seller, and / or item price. Includes a determination step. In some embodiments, the action further comprises determining, at least in part, the expected distribution of valuations for an item based on the actual distribution of valuations for one or more other items. In some embodiments, the item and one or more other items are in the same item category (or set), manufactured by the same manufacturer, sold by the same seller, and / Or have prices within the same price range.</p><p num="0031"> In some embodiments, one or more user-provided ratings are one or more first user-provided ratings, and the behavior is further one or more user-provided ratings for the item. A combination of a step to get a rating, a step to determine if the combined number of first and second user-provided ratings for an item exceeds the threshold number of ratings for an item, and a user-provided rating for an item. A step of providing the user's device with a set of ratings for an item based on the determination that the number of items exceeds the threshold of the rating, the first set of ratings for an item being one or more. Includes a step consisting of a user-provided evaluation and one or more second user-provided evaluations.</p><p num="0032"> Other aspects and advantages of some embodiments of the invention will be apparent from the following drawings and embodiments for carrying out the invention, which illustrate the principles of the invention only as examples.</p><p num="0033"> An overview of the invention described above, including a description of the motivations and / or advantages of some embodiments, is intended to assist the reader in understanding the present disclosure, and any of the claims. The range is not limited in any way.</p>

0034The advantages of some embodiments may be understood by reference to the following description, which is considered in conjunction with the accompanying drawings. In drawings, similar reference characters generally refer to the same part throughout different figures. Also, the drawings are not necessarily to scale, but instead are generally focused on exemplifying the principles of some embodiments of the invention.

0035<figref num="1">FIG. 1 shows a computer system according to some embodiments.</figref><figref num="2">FIG. 2 shows a user interface for accessing an online marketplace, according to some embodiments.</figref><figref num="3A">Figures 3A, 3B, and 3C show first, second, and third user interfaces, respectively, to encourage the user to put an item in a virtual shopping cart, according to some embodiments.</figref><figref num="3B">Figures 3A, 3B, and 3C show first, second, and third user interfaces, respectively, to encourage the user to put an item in a virtual shopping cart, according to some embodiments.</figref><figref num="3C">Figures 3A, 3B, and 3C show first, second, and third user interfaces, respectively, to encourage the user to put an item in a virtual shopping cart, according to some embodiments.</figref><figref num="4A">Figures 4A and 4B show first and second user interfaces, respectively, to encourage the user to initiate the checkout process in the online marketplace, according to some embodiments.</figref><figref num="4B">Figures 4A and 4B show first and second user interfaces, respectively, to encourage the user to initiate the checkout process in the online marketplace, according to some embodiments.</figref><figref num="5">FIG. 5 shows a user interface for viewing an item feed, according to some embodiments.</figref><figref num="6A">6A, 6B, and 6C show first, second, and third user interfaces, respectively, to encourage the user to save an item in a virtual wishlist, according to some embodiments.</figref><figref num="6B">6A, 6B, and 6C show first, second, and third user interfaces, respectively, to encourage the user to save an item in a virtual wishlist, according to some embodiments.</figref><figref num="6C">6A, 6B, and 6C show first, second, and third user interfaces, respectively, to encourage the user to save an item in a virtual wishlist, according to some embodiments.</figref><figref num="7A">Figures 7A, 7B, 7C, and 7D show the first, second, third, and fourth user interfaces for submitting item ratings, respectively, according to some embodiments.</figref><figref num="7B">Figures 7A, 7B, 7C, and 7D show the first, second, third, and fourth user interfaces for submitting item ratings, respectively, according to some embodiments.</figref><figref num="7C">Figures 7A, 7B, 7C, and 7D show the first, second, third, and fourth user interfaces for submitting item ratings, respectively, according to some embodiments.</figref><figref num="7D">Figures 7A, 7B, 7C, and 7D show the first, second, third, and fourth user interfaces for submitting item ratings, respectively, according to some embodiments.</figref><figref num="8A">8A, 8B, and 8C show the first, second, and third user interfaces for registering in the online marketplace, respectively, according to some embodiments.</figref><figref num="8B">8A, 8B, and 8C show the first, second, and third user interfaces for registering in the online marketplace, respectively, according to some embodiments.</figref><figref num="8C">8A, 8B, and 8C show the first, second, and third user interfaces for registering in the online marketplace, respectively, according to some embodiments.</figref>

0036FIG. 1 illustrates an exemplary computer system 100 suitable for implementing and providing access to an online marketplace. Server system 122 provides functionality for implementing an online marketplace. The server system 122 includes, for example, software components and databases that can be deployed in one or more data centers 121 in one or more geographic locations. The software components of the server system 122 include a front-end server 112, a catalog generator 114, and an evaluation module 116. The server system 122 can also include one or more software components for inventory management and load balancing. Software components can include sub-components that can run on the same or different individual data processing equipment. The database of the server system 122 includes a user data database 132, a transaction data database 134, and a product data database 136. The database can reside in one or more physical storage systems. Software components and databases will be further described below.

0037The front-end server 112 provides catalog content to users of the online marketplace, facilitates transactions by the user, and manages user access to the online marketplace. Catalog generator 114 generates catalog content (or "feed") for users of online marketplaces. Evaluation module 116 generates evaluation data for items (eg, products and / or services) in the online marketplace. The front-end server 112, catalog generator 114, and evaluation module 116 will be further described below.

0038Users of the online marketplace (eg, user 151) use client devices (eg, client device 150) and are implemented by server system 122 through one or more data communication networks 113, such as the Internet. Access the online marketplace. The client device is a data processing device (eg, a smartphone, tablet computer, smartwatch, personal computer, game console, or in-vehicle media system). Other embodiments of the client device are also possible. The user can access the online marketplace from the user interface 154 of the client application 152 launched on the client device 150. The client application 152 can be, for example, a web browser or a dedicated software application (eg, a "mobile application"). The user interface 154 is graphical, allowing users to interact with, for example, one or more catalogs in the online store, make purchases, create wishlists, and / or log on to the online store. It is a user interface. User interface 154 will be further described below.

0039As an example, when a user uses the client application 152 and accesses the online marketplace, the client application 152 reads the user-specific catalog content from the front-end server 112 and presents the catalog content in the user interface 154. The catalog content can be created by the catalog generator 114 and provided to the front-end server 112. Creating catalog content will be further described below.

0040When the user selects an item (eg, product or service) to purchase from one or more catalogs presented within user interface 154, the client application 152 displays the selected product and within user interface 154. / Or present a "shopping cart" or list containing the service. Meanwhile, the client application 152 can send a request to the front-end server 112 to make or update a copy of the user's shopping cart stored in the transaction data database 134.

0041When a user makes a purchase (eg, begins to settle for an item in the user's shopping cart presented by client device 152), client device 152 sends a request to the front-end server 112 to complete the purchase. To do. The front-end server 112 completes the purchase and stores transaction records for the purchase in the transaction data database 134.

0042The user also selects one or more products or services in the catalog presented by the client application 152 and adds the item to the "wish list" that the user can return to later for future viewing or purchase. be able to. In response to the user's selection, the client application 152 presents within the user interface 152 a wish list containing the selected product and / or service, along with any previously added products and services. The client application 152 sends a request to the front-end server 112 to make or update a copy of the user's wish list stored in the transaction data database 134.

0043Hybrid user interface FIG. 2 illustrates an exemplary user interface 201 for client application 152 for accessing an online marketplace implemented by server system 122. User interface 201 presents a product catalog (or "feed") for the online marketplace. In some implementations, the user interface 201 comprises a category panel 210, an aggregate panel 220, and an item panel (eg, a product panel) 230. The category panel 210 presents one or more selectable icons for individual item categories in the online marketplace. Illustrative categories include fashion, watches, shoes, pants, shirts, jeans, sunglasses, jackets, polo shirts, belts, trousers, accessories, hoodies, suits, rings, purses and bags, services, and accessories. Other categories are also possible. The category panel 210 can be scrolled horizontally (to the left or right) to display the available icons (categories). The user can select the category icon and have the client application 152 present another user interface that displays a list of individual products in the corresponding category (product feed).

0044The set panel 220 presents a set of one or more items (an "item set", eg, a product set or a service set). A product set is a list of similar products. Each selectable frame (eg, 221) displays a sample product image of the corresponding set. The set panel 220 can be scrolled horizontally to display the available sets. The user can select a set frame and have the client application 152 present another user interface that displays a list of individual products in the set (product feed).

0045Product panel 230 presents a list or feed of individual products. Each selectable frame (eg, 231) displays a sample image of the corresponding product. The product panel 230 can be scrolled vertically (up or down) to display the available products. The product panel 230 can be extended upward and overlaid on the assembly panel 220 and the category panel 210. The user can select a product frame and have the client application 152 present another user interface (detailed product page) that displays further information on the corresponding product.

0046The set and product feeds described above are created for a particular user (ie, user-specific) by the catalog generator 114 of server system 122. The client application 152 can record the browsing history of the user and send the browsing history to the front-end server 112, which in turn can store the browsing history in the user data database 132. The catalog generator 114 accesses the user's browsing history, creates catalog content containing the layout of the user interface 201 for the user based on the user's browsing history, and delivers the catalog content to the client device 152 (eg, front end). Can be provided (via server 112). For example, if a user browses products or sets related to a particular category more often, the particular category may be placed before other categories in the category panel 210. Sets related to a particular category can also be placed before other sets in the set panel 220. Products related to a particular category can also be placed in front of products related to other categories within the product panel 230. In various implementations, the order of assembly or product placement within assembly panel 220 and product panel 230 can be rearranged (shuffled) so that the user can discover "new" products. For example, for the first 10 products listed in Product Panel 230, Catalog Generator 114 is from the four products from the most frequently viewed category by the user and the next most frequently viewed category by the user. Two products, two products from the next most frequently viewed category by the user, and two products from one or more other categories (eg, randomly selected categories). You can create a layout that includes. Browsing history can be collected over a relatively short travel time window (eg, the last two weeks). In this way, the product The content of the seed can reflect the user's more recent activity in the online marketplace. Creating a product feed will be explained further later.

0047Additional offer to cart The product feed created by the catalog generator 114 and presented by the client application 152 to encourage the user to make a purchase through the online marketplace implemented by the server system 122 contains various incentives or offers to the user. Can be done.

0048Figure 3A-3C illustrates a user interface that encourages the user to put the viewed product in the shopping cart. In some embodiments, the user interface illustrated in FIGS. 3A-3C may be presented to the user as part of a method for encouraging the user to put the viewed product in the shopping cart. In FIG. 3A, the user can select a particular item (eg, product) 302 within the item feed (eg, product feed) 301. In response to the user's choice, client application 152 presents an item detail page (eg, product detail page) 310, as illustrated in FIG. 3B. Product detail page 310 contains offer 312 to the user. Offer 312 encourages users to place a particular product in their shopping cart and get ("withdraw") a discount to the list price ($ 14) of that particular product. The actual discount is not known to the user until the user puts a particular product in the shopping cart. Offer 312 also includes a timer ("03:58") that indicates the time left before the offer ends, prompting the user to immediately add a particular product to the shopping cart. After the user selects the "buy" icon 314, the client application 152 presents a shopping cart page 320 containing an overlay frame 322, as illustrated in FIG. 3C. The overlay frame 322 indicates a discounted price ($ 13). The overlay frame 322 also includes a timer ("00:59:58") that indicates the time left before the offer ends, identified by the user completing the checkout of a particular product from the shopping cart. Encourage you to buy your product.

0049In the product feed 301, a subset of products can be selected (eg, by the catalog generator 114) and offer an offer to encourage the user to put the product in the shopping cart. More specifically, a subset of products can be randomly selected. The discount amount for each offer can also be randomly determined. In this way, each user may see different products offering different discounts that encourage each user to put the product in the shopping cart. In addition, if the provision of a particular product to a particular user ends, the offer for the same particular product may be unavailable to that user for a specified time period (eg, one week). it can.

0050Settlement offer Figures 4A and 4B illustrate a user interface that encourages users to start paying for products in their shopping cart. In some embodiments, the user interface illustrated in FIGS. 4A and 4B may be presented to the user as part of a method for encouraging the user to start paying for the products in the shopping cart. FIG. 4A illustrates exemplary product detail page 401. In response to the user's selection of the "buy" icon 402 in the product detail page 401, the client application 152 presents the shopping cart page 420 as illustrated in FIG. 4B. The shopping cart page prompts the user to settle the product (from the shopping cart) within the specified time period, as indicated by the timer ("10:34"), offer 422 ("5 on next order"). % Is returned as a gift card ") is included. The user can complete the purchase by selecting the "payment" icon 425 in the shopping cart page 420. Offers can be automatically offered to users. For example, after receiving a message from the client application 152 indicating the start of the purchase by the user, the front-end server 152 can complete the purchase and bring the purchase information into the transaction data database 134. The front-end server 152 can also store a record of credits (5% of $ 12.00 = $ 0.60) that can be used later by the user in the transaction data database 134.

0051Offers to encourage users to settle products in their shopping cart shall be offered to users who have not settled (have not made a purchase) over a specified time period (eg, the last two weeks). Can be done. Offers can be randomly offered to such users, so users cannot predict when the offer will be available. If an offer is presented to a particular user and ends before that particular user makes a purchase, the offer may be unavailable to that particular user for a specified time period (eg, 3 days). ..

0052Hourly trading FIG. 5 illustrates an exemplary item feed page (eg, product feed page) 501 with a time-limited offer. In Figure 5, one or more products 502 from the product feed on product feed page 501 have a time-limited offer ("Hourly Transactions"). Each discounted product 502 has a timer (eg, "58:32") that indicates the time remaining until the end of the offer. The discounted product 502 is placed at the top of the product feed and can stay at the top of the product feed after refreshing the product feed page 501 (until the timer expires).

0053The discounted product 502 can be randomly selected from the product feed (eg, by the catalog generator 114). Once a particular product has been selected for this offer, that particular product may be made unavailable with respect to the selection for this offer over a specified time period (eg, 5 days).

0054Save to confirm price Figure 6A-6C illustrates a user interface that encourages users to save their products in their wishlist. In some embodiments, the user interface illustrated in FIGS. 6A-6C may be presented to the user as part of a method for encouraging the user to save the product in a wish list. FIG. 6A illustrates an item feed page (eg, product feed page) 601. Product feed page 601 shows a discount (-38%) for product 602, but not the price for product 602. Instead, the message "Save and confirm today's price!" Prompts the user to save the product 602 to their wishlist. The detail item page (eg, detail product) even after the user has selected product 602 in product feed page 601 without selecting the "Save" icon 605 (to save product 602 to the wishlist). Note that page) 611 still does not show the price for product 602, as illustrated in Figure 6B. Instead, detail product page 611 indicates the message "Save and confirm today's price!" Prompting the user to save product 602 to their wishlist. In the embodiment of FIG. 6B, the detailed product page 611 also includes a timer 615 ("04:32") that indicates the time remaining for the offer and prompts the user to add the product 612 to the shopping cart.

0055If the user selects the save icon 605 in the product feed page 601 illustrated in FIG. 6A, or the save icon 614 in the detailed product page 611 illustrated in FIG. 6B, the client application 152 sees FIG. 6C. Update details product page 611 with a discounted price of 621 ($ 31) as illustrated in. In the embodiment of FIG. 6C, the updated detailed product page 611 also includes a timer 615 that prompts the user to put the product 612 in the shopping cart within the remaining time.

0056In various implementations, one product is shown at once in the view of the product feed page with a "Save and Check Price" offer. Referring to Figure 6A, about 4-6 products are shown in the viewport of product feed page 601 at a time, so for example, one of the 4-6 products in product feed page 601 "save and save". Can be shown with the "Check Price" offer. Within the group of four products, the product with the maximum discount (eg, the maximum difference between the manufacturer's suggested retail price and the actual retail price) is selected to hide its retail price and is "preserved and priced". Can be shown with the "Confirm" offer.

0057User-submitted evaluation photos and inferred evaluations FIG. 7A-7D illustrates a user interface through which a user can submit or view a rating of an item (eg, product) purchased by the user through an online marketplace implemented by server system 122. In some embodiments, the user interface illustrated in FIGS. 7A-7D may be presented to the user as part of a method for submitting or viewing item ratings. FIG. 7A illustrates an exemplary item order history page (eg, product order history page) 701 presented by client application 152. In response to the user selection of the "Edit Rating" icon 705, the client application 152 presents a rating page 711, as illustrated in FIG. 7B. On rating page 711, the user has the option (715) to upload a photo of the actual product received by the user. For example, the user can upload a photo of the product through rating page 711 (eg, from client device 150). After receiving an indication about the photo from the user, the client application 152 sends the photo and information about the user and purchase (eg, a particular size of the product purchased by the user, an identifier for the purchase record stored in the transaction data database 134). Etc.) is transmitted to the front-end server 112. The front-end server 112 can populate the product data database 136 with the photo provided by the user. In addition, the photo can be scrutinized by a computer or person (eg, in terms of image quality). Catalog generator 114 can generate a product detail page for this particular product and include user-supplied photos within the product detail page along with other images of the particular product.

0058In Figure 7C, when another user browses the detailed product page 750 for this particular product, the user slides left or right on image 751 of the product and other images containing user-supplied photos of the particular product. Can be seen. The user can also select the "Show All" icon 752 to see other images of a particular product. FIG. 7D illustrates a detailed product page 750, including user-supplied photos for a particular product. The detailed product page 750 can also include information 761 related to the user-supplied photo, such as the user who supplied the photo, the size of the product for this photo, and so on.

0059The user can also provide ratings on scores such as 1 star, 2 star, 3 star, 4 star, and 5 star. A five-star rating can be the best rating, while a one-star rating can be the worst rating. For example, a user can submit a rating (score) for a particular item (eg, product) through the user interface (eg, 701) of client application 152. Client application 152 transmits the user's rating to the front-end server 112, which in turn stores the rating (for a particular product) in the product data database 136. When the catalog generator 114 creates a detailed product page for a particular product, the rating module 116 accesses the product data database 136 for rating data about the particular product and tells the catalog generator 114 to be included within the detailed product page. Provides comprehensive rating data (eg, 1 5 star, 4 3 star, 1 2 star, 1 1 star).

0060When the number of ratings (scores) submitted by users for a particular product is small (eg, less than 10), the overall rating data for the particular data is at one end of the rating scale (eg, most are one). Can skew towards (star score). To prevent skew, the evaluation module can apply a predefined distribution to the overall evaluation data when the number of evaluations submitted is small. As more evaluation scores are submitted, the overall evaluation data is automatically adjusted to ultimately reflect the actual overall evaluation data submitted by the user. For example, the predefined distribution can be 20% 5 stars, 20% 4 stars, 10% 3 stars, 20% 2 stars, 30% 1 star. The evaluation module can calculate the initial overall evaluation data assuming a certain number of users (eg, 100) who have purchased a particular product but may not have submitted a rating for that particular product. it can. Therefore, the overall rating data can be 5 stars for 20 people, 4 stars for 20 people, 3 stars for 10 people, 2 stars for 20 people, and 1 star for 30 people. When there is an additional score submitted by the user, the evaluation module adds the submitted score (count) to the initial overall evaluation data for the overall evaluation data.

0061In some embodiments, system 100 may implement method M1 to reduce or prevent evaluation skew for items. In the first step of method M1, the server system 122 may obtain one or more user-provided ratings for the item. The user may enter a rating in the user interface 154 of the client application 152 running on the client device 150. User interface 154 provides ratings for one or more of the user interfaces or items illustrated in Figure 7A-7D (eg, star-based ratings on a 1-5 star scale). It may include any other user interface suitable for this purpose. The client device 150 may send a user-provided evaluation to the server system 122.

0062In the second step of method M1, the server system 122 may determine whether the number of user-provided ratings for the item exceeds the threshold number of ratings for the item. The number of evaluation thresholds can be 5, 10, 20, 50, or any other suitable number of evaluations.

0063In the third step of method M1, based on the determination that the number of user-provided evaluations for the item does not exceed the number of evaluation thresholds, the server system 122 determines the expected evaluation for the item (eg, as described above). It acquires the "initial overall evaluation data") and provides a set of evaluations for the item (eg, the "overall evaluation data" described above) to the user's client device 150. Client application 152 on client device 150 may display a set of ratings for an item within user interface 154. The set of ratings provided to the user may include any user-provided rating for the item and the expected rating for the item.

0064In some embodiments, the probability distribution of the predicted valuation for the item substantially matches the predicted distribution of the valuation for the item. As used herein, the mean, median, variance, and standard deviation of the first distribution are within ± 20% of the mean, median, variance, and standard deviation of the second distribution, respectively. In some cases, the two probability distributions are "substantially matched". In some embodiments, the expected distribution of valuations for an item can be determined based on the item's category, manufacturer, seller, and / or price. For example, the predicted distribution of valuations for an item can be obtained by combining (eg, averaging) the actual distribution of valuations for other items in the same category that have about the same price as the item of interest.

0065In the fourth step of Method M1, the server system 122 may obtain one or more additional user-provided ratings for the item, and the total number of user-provided ratings for the item exceeds the rating threshold. Can be determined. Based on this determination, the server system 122 may provide a set of ratings for the item to the user's client device 150. The set of ratings provided may include user-provided ratings for the item, but not the expected ratings for the item. In other words, if the number of user-provided ratings for an item exceeds a threshold, the server system 122 may stop using the predicted ratings for the item.

0066Sign-up flow Figure 8A-8C illustrates a user interface for registering (eg, "signing up") with the online marketplace implemented by server system 122 using client application 152. In some embodiments, the user interface illustrated in FIGS. 8A-8C may be presented to the user as part of a method for registering with an online marketplace. FIG. 8A illustrates an exemplary introductory page ("Splash Page") presented by Client Application 152. The user can select "Create Account" to register in the online marketplace. In response to the user's choice, client application 152 presents the sign-up form page illustrated in FIG. 8B. Users can provide their name, email address, and password to create an account on the online marketplace. In addition, users can provide their age, gender, and location to the online marketplace. Client application 152 presents the aggregate page illustrated in Figure 8C. The user can select a specific set from the set page. The client application 152 transmits the user information provided by the user to the front-end server 112. The front-end server 112 stores user information in the user data database 132.

0067In some implementations, the particular category selected by the user during sign-up is initially the first (and only) record in the user's browsing history. In response to a request from the client application 152 for catalog content and layout, for example, after selecting a particular category on the aggregate page of FIG. 8C, the user enters the user interface 201 described with reference to FIG. The catalog generator 114 can create a layout for user interface 201 such that a particular set is placed in front of other sets in the set panel 220. Categories related to a particular set can also be placed before other categories in the category panel 210.

0068User similarity and product feed Catalog generator 114 can create item feeds (eg, product feeds) based on the popularity of products and / or services. For example, a product with higher sales (higher popularity) can be ranked higher in the product feed than another product with lower sales (lower popularity). Higher-ranked products can appear before lower-ranked products in a given feed. Products can be ranked by "purchasability score" (described below), which can be the possibility that a particular user will purchase a given product. As another example, a product with a large number of instances in a user's wish list (more popular) has a small number of instances in the user's wish list (less popular). ) Can be ranked higher in the product feed than another product.

0069In various implementations, the product purchaseability score can be, for example, the purchase quantity for the product divided by the weighted sum of the individual sums of the different user actions. User actions include a user browsing a product (for example, a product detail product page), a user putting a product in a wishlist, a user putting a product in a shopping cart, and / or a user putting a product in a shopping cart. It can be a purchase. Other types of user actions are also possible.

0070As another embodiment, the product availability score is a weighted sum of the number of instances of a particular user action with respect to the product and can be normalized to the number of impressions of the product. The number of impressions can be the number of products viewed by the user within the product feed page during the specified time period (eg, the last 3 days). In other implementations, the number of impressions can be the number of product detail product pages viewed by the user during a specified time period. In some embodiments, an item "impression" thereby presents information about the item (eg, an advertisement about the item, an image of the item, a detailed item page about the item, etc.) through the user interface of the client device 150. Includes any suitable event or action (eg, displayed). For the purpose of determining the purchaseability score for an item, the number of impressions for the item may be limited to the impressions generated during the specified time period.

0071For example, the purchaseability score of a product can be:<chemistry num="3"><img id="000005" he="11" wi="129" file="JP2018519613A_D0001.tif" img-format="tif" img-content="drawing" /></chemistry>In the formula, "purchases" can refer to the number of users who purchased the product or the total quantity of products purchased by a specified group of users (eg, all users), and "added to shopping carts" It can refer to the number of users who have added products to their shopping cart or the total quantity of products added to their shopping cart for a specified group of users, and the "saved to wish list" is the number of users who have added products to their wish list. It can refer to a number or the total quantity of products added to a specified group of users' wishlists.

0072In addition, or as an alternative, product feeds for a particular user can be created based on the similarity of a particular user to another group of users. In addition to user segments (eg age, gender, location), similarities between users can also be determined by user actions. For example, similar users may have similar purchase quantities during a defined time period (eg, the last week). Similar users may have similar items placed within their individual wishlists. Catalog Generator 114 creates product feeds for specific users by copying or aggregating product feeds for one or more groups of users with age, gender, location, or user actions similar to specific users. can do. As another embodiment, the weights in the affordability score described above can be adjusted based on the corresponding weights in the buyability score formula for similar users.

0073In certain implementations, A is a sparse matrix, so when user i is involved in product j, A_{i, j}= 1 and otherwise A_{i, j}Assume that = 0. When a product impression is presented (eg, displayed) to a user through a client device 150 (eg, within a specified time period), and the user adds the product to the user's shopping cart, the user adds the product. User i may be involved in product j if added to the user's wish list and / or if the user purchases the product. The similarity score between users u and v can be:<chemistry num="4"><img id="000006" he="20" wi="47" file="JP2018519613A_D0001.tif" img-format="tif" img-content="drawing" /></chemistry>

0074For a given user u, the catalog generator 114 can find the top similar users (eg, the top 10,000 similar users) by individual similarity score. Catalog generator 114 can calculate the similarity weighting involvement score for a given product with respect to the top similar users as follows.<chemistry num="5"><img id="000007" he="10" wi="15" file="JP2018519613A_D0001.tif" img-format="tif" img-content="drawing" /></chemistry>

0075In the above equation, if the top similar user k purchases a given product, SW_{u, k}= S_{u, k}And otherwise SW_{u, k}= 0. The catalog generator 114 can determine a set of top-ranked products (eg, 1,000) according to the above equation and recommend the set of top-ranked products to user u.

0076The catalog generator 114, for a particular user, has a first set of items (eg, products) based on affordability and items (eg, products) based on the similarity score as described above. A second set of can be generated. Catalog generator 114 can generate a product feed for a particular user by interleaving a first and second set of products. For example, when a product feed is first displayed to a particular user, products from the first set will be fed until the first set is used up and all products from the second set are displayed next. You can have the opportunity to see 70% in a given arrangement of. When a product feed is displayed a second time to a particular user (eg, due to a refresh by a particular user), the products from the first set will show 50% in a given placement of the product feed. Can have the opportunity to feed. The percentage can be reduced to 30% the third time the product feed is displayed to a specific user and up to 10% the fourth time the product feed is displayed to a specific user. Subsequently, the products from the first set can be randomly placed between the products from the second set in the product feed.

0077When a user requests or refreshes an item feed (eg, a product feed), the catalog generator 114 or client application 152 can rearrange (shuffle) the order of the products in the product feed. In this way, the user can see the new one every time the user loads or refreshes the product feed. In various implementations, the order of the products in the product feed can be rearranged, for example, by the following weighted random shuffling or ordering.<chemistry num="6"><img id="000008" he="11" wi="33" file="JP2018519613A_D0001.tif" img-format="tif" img-content="drawing" /></chemistry>

0078In some embodiments, system 100 may implement method M2 for determining the order of items in an item feed. In the first step of method M2, the server system 122 may receive data indicating the selection of certain types of items (eg, items of a category and / or items of a set). The selection data may be received, for example, from the user's client device 150. For example, the user may select a category through the category panel 210 of the user interface shown in FIG. 2 or via any other suitable user interface. As another embodiment, the user may select a set via the set panel 220 of the user interface shown in FIG. 2 or via any other suitable user interface. The client device 150 may then send data indicating the selected item type to the server system 122.

0079In the second step of method M2, the server system 122 may determine the purchaseability score for a specified set of items (eg, for a specified set of items in a category or set). The server system 122, at least in part, has (1) the number of impressions of an item provided to a specified group of users (eg, all users) during a specified time period, and (2) a specified group. The purchaseability score of an item can be determined based on the quantity of items purchased by the user in (3) and (3) the quantity of items added to the shopping cart of the users in the specified group. In some embodiments, the availability score determination for an item on the server system is also based on the purchase price of the item and / or the total quantity of the item added to the user's wishlist for a defined group. In some embodiments, the server system 122 determines the affordability score for an item, at least in part, based on the following equation:<chemistry num="7"><img id="000009" he="12" wi="124" file="JP2018519613A_D0001.tif" img-format="tif" img-content="drawing" /></chemistry>During the ceremony, W₁, W₂, And W₃Are the first, second, and third weights, respectively, and "impressions" are the number of impressions (or their) of individual items provided to a specified group of users during a specified time period. The number of users whose impressions of the item were presented during the time period), and "quant_purchases" is the quantity of the item purchased by the users of the specified group (or the number of users in the group who purchased the item). Yes, "quant_cart" is the quantity of items added to the shopping cart of users in the specified group (or the number of users in the group who added at least one of the items to the shopping cart). "Quant_wish_list" is the quantity of items added to the wishlist of users in a given group (or the number of users who have added at least one of the items to that wishlist), and "price" is the item's The purchase price (for example, the average purchase price of an item). A defined group of users may be selected by the server system 122, at least in part, based on the similarity between the user's group and the user for which the purchaseability score has been calculated.

0080In the third step of Method M2, the server system 122 determines, at least in part, the ranking of a set of items of a defined type based on the purchaseability score of individual items contained within multiple items. Can be done. The ranking can be, for example, a total ranking or a partial ranking.

0081In the fourth step of method M2, the server system 122 may determine the ranking of the second set of items. A second set of items may include items contained within the item feed of a group of users similar to the user to whom the item is ranked. In some embodiments, the server system ranks a second set of items for a user, at least in part, based on the similarity between the user to whom the item feed provided the item and the group of users. .. In some embodiments, the similarity between a user and a group of users can be determined using the formula provided above. In some embodiments, the similarity between users may include similarities in demographics (eg, the "user segment" described above). In some embodiments, similarities between users are in shopping activities (eg, browsing an item, adding an item to a shopping cart and / or wishlist, purchasing an item, etc.). Can include similarities.

0082In some embodiments, the second set of items can consist entirely of items that are not contained within the first set of items. In some embodiments, the second set of items and the first set of items may partially overlap (eg, one or more items may be contained within both sets of items. ). In an embodiment where the set of items overlaps, any item contained in both sets can be removed from one of the sets to avoid duplication of items in the item feed.

0083In the fifth step of Method M2, the server system 122 uses the first set of items (and optionally the second set of items) to populate the item feed for the type of item selected by the user. obtain. If the item feed contains only items from the first set of items, the order of the items in the item feed may match the ranking of the items in the first set of items. If the item feed contains items from the first and second sets of items, the order of the items in the item feed may depend on the ranking of the first and second sets of items.

0084Server system 122 may use any suitable technique to merge a first and second set of items into an ordered item feed. In some embodiments, the first and second sets of items are contained within the second set of items without disturbing the relative ranking between the items contained within the first set of items. Can be merged into an ordered item feed without disturbing the relative ranking between items. Therefore, the partial order in the item feed for items contained within the first set of items can match the ranking of the same item within the first set and is contained within the second set of items. The partial order of the items in the item feed can match the ranking of the same item in the second set. In some embodiments, the server system 122 can probabilistically determine the relative order in the item feed between items from the first set and items from the second set.

0085In some embodiments, the server system 122 (a) stochastically selects between a first set of items and a second set of items, selecting the first set of items. The first probability to do is P₁And the second probability of choosing a second set of items is 1-P₁Steps and (b) identify the highest ranked item that has not yet been assigned a rank in the order of the item feed from the set of selected items, and (c) item feed the identified item. Steps to assign to the next rank in the order of, and (d) until a specified number of items are assigned a rank in the order of the item feed, or all items in the first and second sets of items are in the item feed. The order of the items in the item feed is determined by repeating steps (a)-(c) until a rank is assigned in the order of. As explained above, the server system modifies the first and second probabilities in response to the passage of a specified time period and / or in response to a request to reorder a set of items. Can be done. As further described above, the server system 122 may change the ranking of items within the first set of items by performing weighted random shuffling of the affordability scores of those items.

0086In the sixth step of method M2, the server system 122 may provide the item feed data to the user's client device 150. The client device 150 may be configured to display a scrollable feed in the item panel (eg, frame) corresponding to the item identified in the item feed data. The item panel in the scrollable feed can be ordered according to the order of the corresponding items in the item feed data.

0087new product For new products added to the online marketplace implemented by the server system 122, the catalog generator 114 can insert the new product into an existing product feed for the user to "look for". Catalog generator 114 first assigns user segments to new products based on contextual information from the new product description. For example, Catalog Generator 114 may assign a new product to a female user segment if the product description contains the phrase "handbag" or another phrase that is generally associated with items that are generally more of interest to women than men. Catalog Generator 114 can assign a new product to the male user segment if the product description contains the phrase "Oxford dress shoes" or another phrase that is generally associated with items that are generally more of interest to men than women. Catalog Generator 114 recommends a new product if the product description contains another phrase that is generally associated with an item of interest to a person under the age of 41 rather than a "video game" or a person generally 41 or older. Can be assigned to age segments under the age of. Catalog generator 114 then inserts the new product into one or more product feeds associated with the assigned user segment. As users browse new products and perform various user actions (eg, browsing, putting in wishlists, putting in shopping carts, buying), Catalog Generator 114 describes earlier. New products can be placed in different product feeds based on such user actions.

0088For a given item (eg, product), the catalog generator 114 can maintain an engagement score (eg, the ratio of the number of user actions to the number of impressions about the product). When the number of impressions of a new product exceeds a defined threshold (eg 10,000), the Catalog Generator 114 sets the engagement score of the new product to the engagement score of other existing products in the user segment (eg male user segment). Compare with. The engagement score of the new product is comparable to or higher than the engagement score of other existing products in the user segment (for example, the engagement score of the new product is equal to or higher than the central engagement score of other products. If so, the new product can be kept for the user's color. Otherwise, the new product can be considered uninteresting to the user and the catalog generator 114 can stop showing the new product in the product feed. New products (eg, high quality new products) can be ultimately included in product feed recommendations based on similarity or affordability scores as described above.

0089Typical implementation The subjects and behaviors described herein, but not limited to, methods M1 and M2 and behaviors performed by client device 150, server system 122, front-end server 112, catalog generator 114, and / or evaluation module 116. Implementations include, including, the structures disclosed herein and their structural equivalents, in digital electronic circuits, or in computer software, firmware, or hardware, or one or more of them. It can be implemented in combination. Implementations of the subject matter described herein are one or more computer programs, ie, computers encoded on a computer storage medium for execution by a data processor or to control its operation. It can be implemented as a module with one or more program instructions. Alternatively, or in addition, a program instruction is an artificially generated propagating signal, eg, generated to encode information for transmission to a suitable receiver device for execution by a data processor. Can be encoded on machine-generated electrical, optical, or electromagnetic signals. The computer storage medium can be, or include, a computer-readable storage device, a computer-readable storage board, a random or serial access memory array or device, or a combination of one or more of them. Further, although the computer storage medium is not a propagating signal, the computer storage medium can be the source or destination of computer program instructions encoded within the artificially generated propagating signal. Computer storage media can also be, or be contained within, one or more separate physical components or media (eg, multiple CDs, discs, or other storage devices).

0090The actions described herein are implemented as actions performed by a data processor on data stored on one or more computer-readable storage devices or received from other sources. Can be done.

0091The term "data processor" is an embodiment of all types of devices, devices, and machines for processing data, including programmable processors, computers, systems on chips, or multiples or combinations of those described above. Including. The device may include dedicated logic circuits, such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits). In addition to the hardware, the device also creates code that creates an execution environment for the computer program, such as processor firmware, protocol stacks, database management systems, operating systems, cross-platform runtime environments, virtual machines, or theirs. It can contain codes that make up one or more combinations. The device and execution environment can implement a variety of different computing model infrastructures such as web services, distributed computing, and grid computing infrastructures.

0092Computer programs (also known as programs, software, software applications, scripts, or code) can be written in any form of programming language, including languages that are compiled or interpreted, declarative or procedural languages. , It can be deployed in any form, included as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. Computer programs are not required, but can accommodate files in the file system. A program is another program in a single file dedicated to the program, or in multiple collaborative files (eg, a file that stores one or more modules, subprograms, or parts of code). Or it can be stored in some of the files that hold the data (eg, one or more programs stored in the markup language resource). Computer programs are deployed to run on multiple computers, located on one computer, or located in one location, or distributed across multiple locations and interconnected by communication networks. be able to.

0093The processes and logical flows described herein are one or more programmable processors that run on one or more computer programs that run on input data and perform actions by producing output. Can be carried out by. The process and logic flow can also be implemented by dedicated logic circuits, such as FPGAs (Field Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits), and the equipment is also implemented as such. be able to.

0094Suitable processors for the execution of computer programs include, by way of example, both general purpose and dedicated microprocessors and any one or more processors of any type of digital computer. In general, the processor will receive instructions and data from read-only memory and / or random access memory. An integral part of a computer is a processor for performing actions according to instructions and one or more memory devices for storing instructions and data. In general, computers also include, or receive data from, or transmit data to one or more high-capacity storage devices for storing data, such as magnetic, magneto-optical disks, or optical discs. Will be operably combined to do or both. However, the computer need not have such a device. In addition, the computer may be another device, such as a mobile phone, personal digital assistant (PDA), mobile audio or video player, game console, Global Positioning System (GPS) receiver, or portable storage, to name a few. It can be built into a device (eg, a universal serial bus (USB) flash drive). Suitable devices for storing computer program instructions and data include, by way of example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, magnetic disks such as internal hard disks or removable disks, magneto-optical disks. , And all forms of non-volatile memory, media, and memory devices, including CD-ROMs and DVD-ROMs. Processors and memory can be complemented or incorporated into dedicated logic circuits.

0095To provide user interaction, the implementation of the subject matter described herein is a display device for displaying information to the user, such as a CRT (Brown Tube) or LCD (Liquid Display) monitor, and the like. It can be implemented on a computer with a keyboard and pointing device, such as a mouse or trackball, from which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user, eg, the feedback provided to the user is any form of sensory feedback, eg, visual feedback, auditory. It can be feedback, or tactile feedback, and the input from the user can be received in any form, including acoustic, audio, or tactile input. In addition, the computer sends a resource to the device used by the user and then receives the resource, for example, in response to a request received from a web browser, to bring a web page to the web on the user's client device. You can interact with the user by sending it to the browser.

0096Implementations of the subject matter described herein include back-end components (eg, as data servers), or include middleware components, such as application servers, or front-end components, eg, through which the user is described herein. Any combination of such backend, middleware, or frontend components, including, or more than one, a client computer with a graphical user interface or web browser that can interact with the implementation of the subject matter described in. Can be implemented within a computing system, including. The components of the system can be interconnected by digital data communication, eg, any form or medium of communication network. Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), internetworks (eg, the Internet), and peer-to-peer networks (eg, ad hoc peer-to-peer networks).

0097A computing system can include a client and a server. Clients and servers are generally remote from each other and typically interact through communication networks. The client-server relationship arises from computer programs that start on separate computers and have a client-server relationship with each other. In some implementations, the server transmits data (eg, an HTML page) to a client device (eg, for the purpose of displaying the data to the user interacting with the client device and then receiving user input). The data generated on the client device (eg, as a result of user interaction) can be received from the client device on the server.

0098A system of one or more computers may have a particular action or action by having the Software, Firmware, Hardware, or a combination thereof installed on the System that causes the System to perform actions during operation. Can be configured to carry out. One or more computer programs, when executed by a data processing device, can be configured to perform a particular action or action by including instructions that cause the device to perform an action.

0099Although the present specification contains many specific implementation details, these should not be construed as limitations to the scope of any invention or claim, but rather features specific to a particular implementation of a particular invention. Should be interpreted as an explanation for. Certain features described herein in the context of separate implementations can also be implemented in combination in a single implementation. Conversely, the various features described in the context of a single implementation can also be implemented separately in multiple implementations or in any suitable secondary combination. In addition, one or more features from the claimed combination, described above as acting in a characteristic combination and may be initially claimed as such, in some cases. , Can be removed from the combination, and the claimed combination may also cover a secondary combination or a variant of the secondary combination.

0100Similarly, the actions are depicted in the drawings in a particular order, but this is performed in the particular order in which such actions are shown, or in a continuous order, or in order to achieve the desired result. It should not be understood as requiring that all illustrated actions be performed. In some situations, multitasking and parallelism can be advantageous. Moreover, the separation of the various system components in the implementations described above should not be understood as requiring such separation in all implementations, and the program components and systems described are generally single. Please understand that they can be integrated together or packaged into multiple software products.

0101Although some aspects of at least one embodiment of the invention have been described in this way, it should be appreciated that various modifications, modifications and improvements will be readily recalled to those skilled in the art. Such modifications, modifications, and improvements are intended to be part of this disclosure and are intended to be within the spirit and scope of the invention. Therefore, the above description and drawings are merely examples.

0102The various aspects of the present disclosure can be used alone, in combination, or in various sequences not specifically described above, and the invention is therefore described in the above description in its application. It is not limited to the details and arrangement of components that are used or illustrated in the drawings. For example, the aspects described in one embodiment can be combined with the aspects described in another embodiment in a suitable manner.

0103Terminology The terms and terminology used herein are for explanatory purposes only and should not be considered limiting.

0104The term "about", the phrase "approximately equal to", and other similar terms as used herein and in the claims (eg, "X has a value of about Y" or "X to Y". "Approximately equal") should be understood to mean that one value (X) is within the pre-determined range of another value (Y). The pre-determined range can be less than ± 20%, ± 10%, ± 5%, ± 3%, ± 1%, ± 0.1%, or ± 0.1%, unless otherwise indicated.

0105The indefinite articles "a" and "an" as used herein and in the claims should be understood to mean "at least one" unless explicitly stated otherwise. The terms "and / or" as used herein and in the claims are elements that are so combined, that is, they exist in some cases associative and in other cases as detachive. It should be understood to mean "one or both" of the elements present in. Multiple elements listed using "and / or" should be construed in the same manner, i.e. as "one or more" of such combined elements. Other elements than those specifically identified by the "and / or" clause may optionally exist, whether or not they are related to those specifically identified. Thus, as a non-limiting example, when used in combination with a non-limiting language such as "with", the reference to "A and / or B" is, in one embodiment, only A (optionally other than B). In another embodiment, it refers to only B (optionally, including elements other than A), and in another embodiment, it refers to both A and B (optionally, other elements). Including) etc.

0106As used herein and in the claims, "or" should be understood to have the same meaning as "and / or" as defined above. For example, when separating items in a list, "or" or "and / or" is considered to be inclusive, i.e. at least one (but more than one) of several elements or the list. It shall be construed as inclusion of (including) and optionally additional unlisted items. When used in "only one of" or "exactly one of" or in the claims, there are only a few terms that clearly indicate otherwise, such as "consisting of". Will refer to the inclusion of exactly one element in or its list. In general, the term "or" as used is "any", "one of ~", "only one of ~", or "exactly one of ~", etc. Preceded by the term of exclusivity, it shall be construed only to indicate an exclusive alternative (ie, "but not both, but one or the other"). As used in the claims, "consisting essentially of" shall have its usual meaning as used in the field of patent law.

0107As used herein and in the claims, the phrase "at least one" for a list of one or more elements is selected from one or more of the elements in the list of elements. It should be understood to mean at least one element, but it does not necessarily include at least one of all the elements specifically listed in the list of elements, but in the list of elements. It does not exclude any combination of elements. The definition also optionally includes elements other than the specifically identified elements in the list of elements pointed to by the phrase "at least one", whether or not they relate to those specifically identified elements. Allows you to do. Therefore, as a non-limiting example, "at least one of A and B" (or also "at least one of A or B" or also "at least one of A and / or B" ") Refers to at least one A (and optionally, including elements other than B), optionally including more than one A, in which no B is present in one embodiment, and in another embodiment. Any A does not exist, optionally refers to at least one B containing more than one B (and optionally includes elements other than A), and in another embodiment optionally more than one A Can refer to at least one A containing, and optionally at least one B containing more than one B (and optionally including other elements), and the like.

0108The use of "contains", "contains", "has", "contains", "with", and variants thereof are listed below and additional items. Means to include.

0109The use of ordinal terms such as "first", "second", "third" in a claim to qualify a claim element is, by itself, an arbitrary precedence over another of one claim element. It does not imply a order, priority, or order, or temporal order in which the act of the method is performed. Ordinal terms are simply used as a marker to distinguish one claim element with a name from another element with the same name (without the use of the ordinal term) and to distinguish the claim elements. ..

0110Equal The present invention can be embodied in other concrete forms without departing from its spirit or essential properties. The aforementioned embodiments should therefore be considered exemplary in all respects, not limited to the inventions described herein. The scope of the present invention is therefore indicated by the appended claims, rather than the aforementioned description, and all modifications that fall within the meaning and scope of the claims are therefore incorporated therein. Intended for.