A user preference hierarchy is determined from user response to images that are tagged. Tagged images may be generated by processing them with machine learning models trained to determine values for images. Product records including images and other data are analyzed to generate attribute vectors that are encoded to generate product vectors. Products are clustered according to their product vectors. Images of products within a cluster are clustered according to composition and groups of images are selected from image clusters for soliciting feedback regarding user preference for products of a cluster. Feedback is used to train a user preference model to estimate affinity for a product having a given product vector. A user may provide feedback regarding a price point and products are weighted according to a distribution having a highest value at the price point. The distribution may be asymmetrical according to direction of movement of the price point.

A method includes receiving a first request from a user device. The first request includes a partial search query sent from the user device while a user is typing a search query. The method includes generating one or more suggested search queries based on the partial search query and selecting a query advertisement record based on the partial search query. The query advertisement record includes an advertised search query and a bid price associated with the advertised search query. The method further includes sending a first response to the user device that includes the advertised search query and the one or more suggested search queries. The method further includes receiving a second request that includes the advertised search query, generating search results based on the advertised search query included in the second request, and sending the search results to the user device.

A search engine provides diverse search results in response to a search query using a trained diversity ranker. The diverse results may be generated by determining ranking positions of at least some search results based on delta feature values that are dependent on higher-ranked results. Delta feature values indicate a degree or magnitude of difference between a particular result and other results with respect to a particular feature, such as price, category, or shipping type. In providing the ranked results for presentation to a user at a computing device, a diversity feature indicator for at least some results may be generated. The diversity feature is a feature that distinguishes a given result from other results. As such, the diversity feature indicator represents that diversity feature for the particular result being different from other results and distinguishes the diversity feature from other features in the particular result.

In some embodiments, apparatuses and methods are provided herein useful to automatically recommending an item. In some embodiments, there is provided a system for automatically recommending an item to a customer comprising a plurality of items available for purchase; a portable electronic device configured to obtain identifying data corresponding to a first item collected by a user; and a control circuit configured to receive data associated with the first item; determine a location in the retail store of the first item; identify one or more items previously purchased by the user that are located within a threshold proximity to the location; determine a most frequently bought item of the identified one or more items; and cause a portable electronic device to display a suggestion for the user to collect the most frequently bought item and add the most frequently bought item to an electronic shopping list of items to purchase.

Disclosed herein are systems, methods, and computer-readable storage devices for a new browser including multiple application programming interfaces. A method includes receiving, from a site, at a browser and via a first application programming interface that defines a first protocol for communicating data between the browser and the site, a first payment request associated with a potential purchase by a user, in response to the first payment request and based on an identification of a payment service, communicating, from the browser and via a second application programming interface that defines a second protocol for communicating data between the browser and the payment service, a second payment request to the payment service, receiving, at the browser, from the payment service, via the second application programming interface, authorized payment information and communicating, from the browser, to the site and via the first application programming interface, the authorized payment information.

Ordering and delivery of food ingredients and food service items is opaque and inefficient. A computer system for recommending substitute food products to food service providers is disclosed. The system contains a database of information about food products that is continuously updated. The database is updated by food service providers and vendors submitting information about food products and the system tags the items entered and sorts them into the database. The system then provides recommendations to food service providers of substitute food products by comparing a food service provider's order history with a query entered with items in the database. A method for increasing efficiency in delivery of food products by streamlining the ordering and delivery process is also disclosed. The streamlined system includes options for price as a function of delivery route and a central container location for food delivery to multiple food service providers within one geographic location.

Embodiments of the present disclosure a method for determining product relevancy including extracting metadata from an image file of a digital image collection, the metadata being indicative of at least one feature of the image file. The method includes creating an input profile corresponding to the metadata extracted from the image files of the digital image collection. The method includes comparing the input profile to a product profile, the product profile having one or more rules corresponding to a consumer product, wherein the rules are indicative of the requirements of the product. The method includes determining a match score, the match score indicative of a relevancy of the product profile to the input profile such that a high relevancy correlates to a consumer product that is suited to the input profile and a low relevancy correlates to the consumer product that is not suited to the input profile.

An information processing method includes: generating a first functional component for a first functional module of a first application, the first functional component comprising first information of the first functional module; generating a second functional component for a second functional module of a second application, the second functional component comprising second information of the second functional module; obtaining an instruction for matching the first functional component with the second functional component; and outputting a matching result corresponding to the instruction.

A computer-implemented method of operating a user-searchable database system of curated, themed digital content data, which method includes operating a Connects function to process and store heterogeneous digital content comprising topic data as curated topic data and identified connections between each topic and other topics, and operating a user interface to enable users to search the curated topics and present a search results page in a way that invites further investigation of topics searched, including a list or compilation of topics matching terms defining the search. The method also includes displaying topic elements corresponding to the list or compilation of matching topics in prioritized order based on each topic's relatedness to the search.

Methods and systems to build containers of uncategorized items are described. In some example embodiments, the methods and systems collect information from titles of items available for purchase within a network-based publication system, generate a title for a container of uncategorized items available for purchase within the network-based publication system that is based on the collected information, and associate two or more uncategorized items available for purchase within the network-based publication system to the container based on a comparison of titles of the two or more uncategorized items and the generated title for the container of uncategorized items.