Abstract: An online concierge system facilitates a concierge service for ordering, procurement, and delivery of food items from physical retailers. The order fulfillment is based in part on automatically inferring one or more quality metrics, such as remaining shelf-life, associated with perishable food items. A picker shopping on behalf of a customer may capture images of available food items for the order using a picker client device. The images are processed through a machine learning model to infer the one or more quality metrics, and a price is then determined based in part on a dynamic pricing model. The online concierge system communicates with a customer client device to meet quality characteristics and pricing preferences set by the customer. The online concierge system may further facilitate a checkout process for the items obtained by the picker and may facilitate delivery of the items by the picker to the customer.

Abstract: An online concierge system detects acquired items included among an inventory of a customer and identifies one or more candidate available items from the acquired items based on a predicted perishability of each item and a predicted amount of each item that was used. The system retrieves recipes, matches the item(s) likely to be available to a set of recipes based on their ingredients, and identifies any remaining items for each matched recipe not likely to be available. The system retrieves a set of attributes associated with the customer and the set of recipes and computes a suggestion score for each recipe based on the attributes. The system ranks the recipes based on their scores, identifies one or more recipes for suggesting to the customer based on the ranking, and sends the recipe(s) and any remaining items for each recipe to a client device associated with the customer.

Abstract: An online concierge system receives a request to purchase a gift for a user of the system and retrieves a profile associated with the user. Based on the profile and attributes of items included among inventories of one or more retailer locations, the system identifies a set of candidate items for which the user is likely to have an affinity. The system accesses a machine learning model trained to predict a giftability score for an item and applies the model to attributes of each candidate item to predict its giftability score. Based on its giftability score and the profile, the system computes a composite score for each candidate item indicating an appropriateness of gifting the candidate item to the user. The system ranks the set of candidate items based on the composite scores and selects one or more suggested items for gifting to the user based on the ranking.

Abstract: A computer-implemented method for suggesting keywords as a search term of a content item includes receiving, from a content provider, information about the content item in a database of content items. The method further includes generating a set of seed keywords related to the content item, and expanding the set of seed keywords to a plurality of candidate keywords. The plurality of candidate keywords are then scored based, at least in part, on an engagement metric measuring a user engagement with the content item in response to being presented with results from a search query comprising the candidate keyword. A candidate keyword is then selected from the plurality of candidate keywords based on the scoring, and stored relationally to the content item to define an audience for a recommendation about the content item, providing a suggestion to the content provider.

Abstract: A method, apparatus and system for understanding visual content includes determining at least one region proposal for an image, attending at least one symbol of the proposed image region, attending a portion of the proposed image region using information regarding the attended symbol, extracting appearance features of the attended portion of the proposed image region, fusing the appearance features of the attended image region and features of the attended symbol, projecting the fused features into a semantic embedding space having been trained using fused attended appearance features and attended symbol features of images having known descriptive messages, computing a similarity measure between the projected, fused features and fused attended appearance features and attended symbol features embedded in the semantic embedding space having at least one associated descriptive message and predicting a descriptive message for an image associated with the projected, fused features.

Abstract: A method, apparatus and system for understanding visual content includes determining at least one region proposal for an image, attending at least one symbol of the proposed image region, attending a portion of the proposed image region using information regarding the attended symbol, extracting appearance features of the attended portion of the proposed image region, fusing the appearance features of the attended image region and features of the attended symbol, projecting the fused features into a semantic embedding space having been trained using fused attended appearance features and attended symbol features of images having known descriptive messages, computing a similarity measure between the projected, fused features and fused attended appearance features and attended symbol features embedded in the semantic embedding space having at least one associated descriptive message and predicting a descriptive message for an image associated with the projected, fused features.