Abstract: The present disclosure provides a system and method for providing a frictionless shopping experience. The method includes detecting that an item was removed from a first area and detecting, by a camera, a light signal emitted from a cart. The method also includes identifying the cart based on the light signal and determining, based on the identified cart, a shopper linked to the cart. The method further includes determining, based at least in part on a location of the camera in the space, that the shopper removed the item from the first area and assigning the item to the shopper.

Abstract: The innovation disclosed, in one aspect thereof, comprises systems and methods of a browser extension for product quality. Online shopping by a user can be monitored on a browser by a browser extension or integrated application with the browser. A potential purchase of a product is detected by the integrated application. The product is identified via analysis of a web page and cross reference to known products. The integrated application retrieves warranty claims data from an accessible warranty database. The warranty claims data is analyzed to determine a recommendation of the product. The integrated application presents the recommendation via the browser as an alert to the user.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for providing augmented reality-based makeup. The program and method provide for receiving, by a messaging application running on a device of a user, a request to present augmented reality content in association with an image captured by a device camera, the image depicting a face of the user; accessing an augmented reality content item configured to generate a plurality of completed looks with respect to applying makeup to the face; presenting the augmented reality content item, including the plurality of completed looks, in association with the face depicted in the image; receiving user input selecting a completed look of the plurality of completed looks; and displaying, in response to receiving the user input, an interface with a set of makeup products associated with the selected completed look.

Abstract: An online concierge system generates recipe embeddings for recipes including multiple items and user embeddings for users, with the recipe embeddings and user embeddings in a common latent space. To generate the user embeddings and the recipe embeddings, a model includes separate layers for a user model outputting user embeddings and for a recipe model outputting recipe embeddings. When training the model, a weight matrix generates a predicted dietary preference type for a user embedding and for a recipe embedding and adjusts the user model or the recipe model based on differences between the predicted dietary preference type and a dietary preference type applied to the user embedding and to the recipe embedding. Additionally cross-modal layers generate a predicted user embedding from a recipe embedding and generate a predicted recipe embedding from a user embedding that are used to further refine the user model and the recipe model.

Abstract: An online concierge system selects content for presentation to a user by using a product scoring engine. The product scoring engine generates a user embedding for user data and a query embedding for query data. The product scoring engine generates an anchor embedding based on the user embedding and the query embedding, where the anchor embedding is an embedding in a product embedding space. The product scoring engine compares the anchor embedding to a set of product embeddings to score a set of products for presentation to a user.

Abstract: A method including determining, in real-time, a diversity preference score for a user based at least in part on an anchor item chosen by the user via a user interface executed on a user device of the user. The method also can include determining, in real-time, a comparison result between the diversity preference score and a diversity preference threshold. The method further can include generating, in real-time, a personalized recommendation pool based on (a) the comparison result, (b) a complementary recommendation pool generated based at least in part on the anchor item, and (c) a diversity objective function. In many embodiments, when the comparison result indicates that the diversity preference score is greater than the diversity preference threshold, the diversity objective function can be associated with cross-domain diversity.

Abstract: The present disclosure relates to improving recommendations for small shops on an ecommerce platform while maintaining accuracy for larger shops. The improvement is achieved by retraining a machine-learning recommendation model to reduce sample selection bias using a meta-learning process. The retraining process comprises identifying a sample subset of shops on the ecommerce platform, where the sample batch includes shops in both a small size category and shops in a large size category. The machine-learning model is then used to make shop-specific user-item interaction predictions for each shop in the sample batch. A shop-specific loss is calculated for each shop based on the model's predicted user-item interactions for the shop-specific training dataset and the actual user-item interactions in the shop-specific training dataset. A global loss is calculated based on each of the shop-specific losses, and the baseline model is updated to minimize the global loss.

Abstract: This disclosure is directed to, in part, mobile carts and/or associated computing devices that are configured to determine their respective location, determine an item in a facility that is associated with an item location that is nearest the location of the cart, determine one or more items that have been designated as similar to the nearest item, and output recommendation data corresponding to the similar items. In some instances, items may be ranked according to similarity based on a comparison of text data associated with the items, based on a comparison of location data associated with the items in other facilities, or the like.

Abstract: Systems and methods for integrated retail and ecommerce shopping platforms. A shopping system for selling products including: a shopping facility including a primary product storage area; at least one showroom; at least one delivery location; a transport system for moving products between locations within the primary product storage area, the at least one showroom and the at least one delivery location; an inventory control system; a network server in operational communication with the inventory control system and the transport system, the network server adapted to transmit interactive shopping interface pages over a network; and a customer client device associated with one of the customers adapted to receive and display the interactive shopping interface pages, for selectively displaying product information about the products sold by the shopping system, and receiving customer input regarding the selecting and deselecting of one or more of the products for possible purchase by the customer.

Abstract: Techniques for identifying similar companies based on profile data sets of the companies are provided. In one embodiment, a method comprises using a processing device to obtain a benchmark profile data set for a benchmark company and obtain a plurality of profile data sets, each of the plurality of profile data sets corresponding to a candidate company. The processing device may utilize a machine learning algorithm to determine the distance between each of the plurality of profile data sets and the benchmark profile data set and build profile graphs indicating the distance. The processing device may determine one or more of the plurality of profile data sets that are most similar to the benchmark profile data set based on the determined distance and identify the one or more candidate companies corresponding to the one or more profile data sets as companies most similar to the benchmark company.

Abstract: An example method includes receiving merchandise information, and in response, initiating a virtual try-on application running on the computing device to simulate physical application of a real-world product corresponding to the merchandise information onto a portion of a user depicted in visual media. Another example method includes in response to receiving the merchandise information, retrieving an interactive graphical representation of information related to the merchandise information, providing for display an AR graphic overlaid onto a live view within a GUI of the computing device, for a topic of a selected item of the AR graphic, accessing via an AI engine data sources to identify retail information that is both (i) related to the merchandise information and (ii) determined to be related to information in a user profile, and dynamically modifying content and animation of the AR graphic to customize the AR graphic for the user.

Abstract: An approach for product localization is described that includes detecting one or more movement activities of a user in an indoor environment, and determining a respective position for each of the one or more movement activities using a sensor associated with the user. The approach further includes identifying one or more stoppage locations from the detected one or more movement activities, and receiving a list of one or more purchased items purchased by the user in the indoor environment. Finally, the approach further includes correlating at least one of the more purchased items with at least one of the one or more stoppage locations, and predicting the location of the one or more purchased items based on the correlating.

Abstract: This application relates to apparatus and methods for providing recommended items based on a search request. In some examples, a computing device determines a plurality of items for recommendation based on an item type in the search request from a user. The computing device then determines a model variant from a plurality of variants for each item based on a requested variant in the search request. The computing device generates item recommendations by modifying an item title for each of the plurality of items to indicate the corresponding model variant. The computing device then presents the item recommendations for the user's perusal.

Abstract: An information processing apparatus includes a communication interface, a storage, and a controller. The controller is configured to: acquire consumable item information including remaining amount information about a remaining amount of a consumable item; output screen information about an input screen to which condition information about an order condition for ordering a new consumable item for replacement is inputted; receive the condition information inputted to the input screen displayed on the basis of the screen information; determine whether or not the order condition represented by the received condition information is met in response to acquisition of the consumable item information; and output order information including information about an order of the new consumable item to a server in response to determination that the order condition represented by the received condition information is met.

Abstract: A system can include a database and a computing device. The computing device is configured to receive an item recommendation request corresponding to an asset from an analyst device and select a set of item identifiers of a plurality of item identifiers. An associated published timeframe of the selected item identifiers is related to a present timeframe. The computing device is further configured to determine a composite similarity value for each item identifier of the set of item identifiers comparing a similarity of the asset to each item identifier of the set of item identifiers. The computing device is also configured to generate an item recommendation list including each item identifier of the set of item identifiers with a corresponding composite similarity value above a threshold value and transmit the item recommendation list to the analyst device for display.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform generating one or more item relational graphs for one or more items based on historical user purchases; transforming, using spectral filtering, the one or more item relational graphs into one or more frequency signals to remove noise from the one or more frequency signals; constructing, using a machine learning model, one or more item pair label classifications for one or more item pairs of the one or more items; generating a respective similarity score for each of the one or more item pairs; outputting a top k results for the one or more item pairs ranked by the respective similarity scores; and re-ranking, using a re-ranking algorithm, the top k results of the one or more item pairs based on a user preference for display on a user interface of an electronic device of a user. Other embodiments are disclosed.

Abstract: A system, platform, device and method are herein provided for an apparatus, system, and method to facilitate personalized online shopping. In some embodiments, a method is provided for personalized shopping that includes the steps of: running a personalized shopping assistant application on a mobile user computing device to access product matching data from one or more product data sources; running the personalized shopping assistant application on the mobile user computing device to acquire anatomical data about one or more application users, based on anatomical data capture from one or more image capture sources; running the personalized shopping assistant application generate a personalized user shopping avatar based on the anatomical data capture of at least a selected part of the user anatomy; and running the personalized shopping assistant application to match one or more products from the one or more product data sources to one or more personalized user shopping avatars.

Abstract: A commodity recommendation method includes: receiving at least one image of a first commodity sent by a shopping cart, and the first commodity being a commodity placed in the shopping cart; inputting the at least one image into a commodity recognition model for commodity recognition to obtain commodity recognition information; inputting the commodity recognition information into a commodity recommendation model for purchase demand prediction to obtain at least one target recommended commodity; and sending information of the at least one target recommended commodity to the shopping cart.

Abstract: A processor-based system stores a plurality of card templates and a plurality of envelope templates in a database. The system receives a user selection of a selected card template from among the plurality of card templates. The system receives a user selection of a selected envelope template from among the plurality of envelope templates, wherein the selected envelope template includes an address block and non-text ornamentation. The system further receives a user-provided recipient name and a corresponding user-provided recipient address for inclusion in the address block of the selected envelope template. The system determines a potential overlap between the non-text ornamentation and the address block including the user-provided recipient name and the corresponding user-provided recipient address. In response to determining the potential overlap, the system causes an error message alerting of the potential overlap to be displayed on a graphical user interface (GUI) of a user computing device.

Abstract: The subject technology receives image data including a representation of a face of a user. The subject technology analyzes the image data to determine a set of characteristics of the representation of the face. The subject technology, based at least in part on the determined set of characteristics, selects a particular product and a set of media content associated with the particular product. The subject technology causes display, at a client device, at least one recommendation corresponding to the set of media content associated with the particular product.