Systems and methods are disclosed herein for automatic subscription-based ordering of product components. During display of media content, the system receives a voice input and determines that the voice input indicates interest in a product. The system identifies the components required to create the product and identifies a subscription to an automated shopping service. Upon identifying the subscription, the system determines whether required components are available via the automated shopping service. Further, the system excludes components that were previously purchased via the automated shopping service, and the system automatically places an order through the automated shopping service for the remaining components.

A POS terminal for fulfilling orders includes a state processor and an order processor. The state processor queues state changes in durable order queues that correspond to orders in a restaurant. The order processor, coupled to the state processor, generates the state changes and accesses and transmits the state changes in each of the durable order queues to a synchronization server, from oldest to youngest, when operably connected to a network, where the order processor includes current order state fields corresponding to all of the orders, and where the order processor utilizes domain specific rules disposed therein to resolve conflicts in the orders occurring from state change updates received from the synchronization server which result from other state changes to the one or more orders generated by one or more other POS terminals, where one or more of the orders are received from a third-party terminal that is not on-premise with the POS terminal.

A fish purchasing system 1 receives as an input image data on a cross section of a tail of a fish under determination, and infers and outputs quality of the fish under determination, based on a relation analyzed through first machine learning. Moreover, the system 1 receives as inputs, the quality data on the fish under determination and weight data on the fish under determination, and infers and outputs a price of the fish under determination, based on a relation analyzed through second machine learning. When quality data, weight data, and price data on a fish desired for purchase are acquired, the system 1 compares the acquired data with quality data, weight data, and price data on fish stored in a database section 29, outputs fish that meet the desired conditions for purchase, and performs processing of ordering a fish selected based on a user input.

Systems and methods for obtaining product information via a conversational user interface. The communication channel receives communication from a user, the intent and entities of which are deduced by the NLP. These are communicated by the fulfillment API to the knowledge engine which retrieves information that fulfills the intent. The information is communicated to the fulfillment API, which converts the intent into a response, which in turn is forwarded by the NLP to the communication channel, and back to the user.

Presenting digital ads on user devices through banner overlays. In one embodiment, a method may include displaying a page on a screen of a user device. The method may also include overlaying a banner having at least one ad above at least a portion of the page so that the banner covers an underlying portion of the page. The method may further include determining whether the banner is in a passive or active state. When the banner is in a passive state, user input on the banner may pass through the banner to the underlying portion of the page. When the banner is in an active state, user input on the banner is received by the banner. A user may be able to provide input determining whether the banner is in an active or passive state.

The invention provides methods and apparatus for detecting when an online session is compromised. A plurality of device fingerprints may be collected from a user computer that is associated with a designated Session ID. A server may include pages that are delivered to a user for viewing in a browser at which time device fingerprints and Session ID information are collected. By collecting device fingerprints and session information at several locations among the pages delivered by the server throughout an online session, and not only one time or at log-in, a comparison between the fingerprints in association with a Session ID can identify the likelihood of session tampering and man-in-the middle attacks.

An online system maintains various items and maintains values for different attributes of the items, as well as an item embedding for each item. When the online system receives a query for retrieving one or more items, the online system generates an embedding for the query. Based on measures of similarity between the embedding for the query and item embeddings, the online system selects a set of items. The online system identifies a specific attribute of items and generates a whitelist of values for the specific attribute based on measures of similarity between item embeddings for items in the selected set and the embedding for the query. The online system removes items having values for the selected attribute outside of the whitelist of values from the selected set of items to identify items more likely to be relevant to the query.

An online system leverages stored interactions with items made by users after the online system received queries to determine display of items satisfying the query. For example, the online system trains a model to predict a likelihood of a user performing an interaction with an item displayed after a query was received. As different items receive different amounts of interaction from users, limited historical interaction with certain items may limit accuracy of the model. The online system generates embeddings for previously received queries and uses measures of similarity between embeddings for queries to generate clusters of queries. Previous interactions with queries in a cluster are combined, with the combined data being used for determining display of items in response to a query.

An online concierge system displays a search interface to users. When displaying suggestions for a query, or displaying results, the online concierge system retrieves candidate suggestions and ranks the candidate suggestions. The online concierge system also obtains an embedding for each candidate suggestion. The online concierge system determines measures of similarity between embeddings for different pairs of candidate suggestion. If a candidate suggestion in a pair has at least a threshold measure of similarity to the other candidate suggestion in the pair, the online concierge system removes one of the candidate suggestions from the pair when displaying candidate suggestions. The online concierge system may remove a candidate suggestion having a lower position in the ranking in a pair of candidate suggestions.

A commodity data processing apparatus includes a communication interface connected to a network, and a processor that executes a program that includes an acquiring module that acquires order information relating to an ordered commodity, a specifying module that identifies a purchaser who comes to a store, and a notifying module that notifies the identified purchaser through the communication interface that the ordered commodity is in stock at the store if the ordered commodity is in stock at the store.