Abstract: A language model is utilized to generate a recommendation for a user of an online system to update a current order. The user is grouped into a cluster of users based on how likely is that the user will not use a credit before expiration. A prompt for input into the language model includes information about the cluster, content of a cart, and information about the credit. Based on the prompt, the language model generates a risk score for the user representing a likelihood of the user not using the credit. The online system identifies, based on the risk score and the content of cart, a quantity of an item for recommendation to the user. A user client device displays a user interface with a suggestion for the user to include the quantity of the item in the cart and use the credit for purchasing the suggested quantity of item.

Abstract: According to a present invention embodiment, a system for processing an order in a computerized environment identifies an item selected by a user in the computerized environment. The system determines that a provider of the item is unable to provide the item to a delivery location based on one or more conditions. A bidding session is conducted for a plurality of service providers to select one or more service providers with services enabling the item to be provided to the delivery location. A transaction for the item is performed to deliver the item to the delivery location via the provider of the item and the one or more service providers. Embodiments of the present invention further include a method and computer program product for processing an order in a computerized environment in substantially the same manner described above.

Abstract: Embodiments of a supply chain management system (SCMS) are disclosed that enable the generation of synthetic supply chain activity data for developing machine learning models, such as models for predicting vendor lead times (VLTs) of purchase orders fulfilled by a supply chain network. In embodiments, the generation process is performed over successive time periods to simulate dynamically changing variables of the supply chain network, including inventory levels, product demand, and stock manager decisions. The generation process may also be used to generate synthetic data to simulate elements within the supply chain network, such as simulated warehouses, vendors, or products. The disclosed SCMS is able to generate highly realistic training data that simulates the operations within the supply chain network, which can be used to improve the performance of machine learning models.

Abstract: An electronic device is provided. The electronic device includes a communication circuit for communicating with a server, a display, at least one processor connected, and a memory, wherein the memory stores instructions causing, when executed, the at least one processor to collect an intermediate operation value corresponding to an item to which a user responds among first items introduced to the user through the display, store the collected intermediate operation value, receive item information about second items and intermediate operation values, input, as an input value, the intermediate operation values received from the server, input first user information indicating a profile of the user and the user response item vector, obtain scores assigned to each of the second items from a result value output from the recommendation model, and provide the item information to the user through the display on the basis of the scores.

Abstract: A power trading system includes: a matching-related data acquiring unit that acquires demand bid information and supply bid information, the demand bid information and the supply bid information each being given a priority level; an appearance rate prediction unit that obtains a predicted appearance rate of the demand bid information and that of the supply bid information; an agreement rate prediction unit that obtains a predicted agreement rate of the demand bid information and that of the supply bid information; and a matching unit that matches the demand bid information to the supply bid information while switching a priority level, based on the predicted appearance rate and the predicted agreement rate.

Abstract: An embodiment uses a computer-implemented approach to identify and automate workstreams from common actions in online applications. A browser extension collects and processes user event metadata, which is used to train machine learning models for workflow automation. The extension reads relevant fields from web services and delivers prompts with high-level actions (HLAs) based on user or organizational details. These HLAs are appended to prompts and sent to a large language model (LLM) via an API call. The LLM responds with a solution and a sequence of actions, which the browser extension executes automatically. Users retain control to pause, accelerate, or modify these actions. This method ensures secure, end-to-end workflow automation across various computing devices, enabling efficient and autonomous resolution of tasks while maintaining user oversight. The browser extension processes metadata, not enterprise data, ensuring security and privacy.

Abstract: Dynamic recommendations based on customer profiles is described. A computing system may receive, in association with a visit of a customer to a merchant location of a merchant, an identifier (ID) of the customer. The computing system may access, based at least in part on the ID, a customer profile of the customer. The computing system may access item availability data indicating whether items are in stock at the merchant location. The computing system may generate, based at least in part on the customer profile and the item availability data, a recommendation(s) associated with an item(s) that is in stock at the merchant location. The computing system may receive an indication that the customer is at the merchant location, and in response to the receiving of the indication, the computing system may determine a server, and cause an electronic device of the server to output the recommendation(s).

Abstract: It is determined that a device associated with a subscriber is accessing an online system of a service provider. Data usage information associated with the subscriber as accessed. Based on the data usage information, an offering from a plurality of offerings is selected, the offering including a service offering or a product offering. Information that identifies the offering is caused to be sent to the device for display.

Abstract: The present invention provides a system for determining a commodity or service suitable for a user. The system is configured to perform: acquisition of data and/or information regarding the user (step S701); calculation of a score that multi-dimensionally represents a feature of the user on the basis of the acquired data and/or information regarding the user (step S702); and determination of a commodity or service suitable for the user, by using the score (step S703).

Abstract: Various embodiments are directed to apparatuses, methods, computer-readable media, computer program products, and systems related to detecting a process trigger that identifies a target entity; identifying, entity data associated with the target entity; generating, using a machine learning based prediction model, a predictive asset output based at least in part on the entity data, wherein the predictive asset output comprises at least one predicted asset; generating, using a dynamic contextualization model, a multifactor contextualized asset representation for the at least one predicted asset based at least in part on the at least one predicted asset and the entity data; and transmitting the multifactor contextualized asset representation to one or more computing devices via one or more communication channels.

Abstract: An online system automatically generates a personalized collection of items around a theme. The online system generates a prompt for input into a language model, the prompt including information about a plurality of items and a text describing the theme around which the collection of items will be built. The online system requests the language model to generate, based on the prompt, a list of products eligible for building the collection of items. The online system accesses a computer model trained to identify a set of items personalized for a user of the online system. The computer model identifies, based on the list of eligible products and information about the user, the set of items for populating the collection of items. The online system causes a device of the user to display a user interface with the collection of items for inclusion into a cart of the user.

Abstract: According to one embodiment, a store system apparatus includes a communication interface connectable to a terminal of a customer of a store, a storage unit storing registration results of a plurality of customers, and a processor. The processor is configured to acquire position information of the terminal of the customer via the communication interface and output recommended commodity information via the communication interface to the terminal according to an area of the store corresponding to the acquired position information. The recommended commodity information indicates a recommended commodity that is in the area of the store. The processor also outputs registration summary information based on the stored registration results of the plurality of customers via the communication interface to the terminal.

Abstract: Artificial intelligence-based systems and methods are described for providing personalized skin product recommendations. Natural language data of a user is received using a conversation engine, such as a generative pretrained transformer AI model. The natural language data is input into a synthetic image generation model for generating a digital twin image depicting skin condition(s). A product recommendation model inputs the digital twin image and/or phenotype and/or demographic classifications of the user, and outputs a skin care product recommendation for the user. An image simulation model inputs the product recommendation, the digital twin image and phenotype and/or demographic classifications of the user to output a simulated image of the user having one or more graphical enhancements. The simulated image may be displayed to the user on display screen along with natural language data describing the simulated image as depicted skin as predicted to appear following treatment with the skin care product.

Abstract: Methods and systems for recommending prospective buyers to sellers and/or automatically pairing prospective buyers and sellers.

Abstract: The techniques herein are directed generally to a hospitality connection platform that connects travel consumers with resorts, hotels, vacation rentals, and destinations in a collaborative manner to create a dream booking and travel experience. In one embodiment, a device of a hospitality connection service maintains a traveler profile for a user that comprises travel preferences and travel history data for that user. The device predicts, based on the traveler profile, trip parameters for a recommended trip for the user and an associated likelihood of the user booking the recommended trip. The device obtains bids from a plurality of systems associated with potential destinations for the recommended trip for the user, in part by sending the trip parameters and the associated likelihood to the plurality of systems. The device provides one or more of the bids from the plurality of systems associated with the potential destinations for display to the user.

Abstract: A first application generates a first user interface to display a pricing quote to a user. The first application is configured to detect a request by the user for an enhanced view of the pricing quote. In response to detecting such a request, the first application retrieves first data from a second application and second data from a pricing and configuration service. Also, the first application populates a temporary database with the first data and the second data. Additionally, the first application performs data enrichment of the first data and the second data to create third data by translating technical information of the first data and the second data into a user-friendly notation. Finally, the first application generates a second user interface to display, to the user, the third data associated with the pricing quote.

Abstract: The present disclosure is directed to determining purchase suggestions for an online shopping concierge platform. In particular, the methods and systems of the present disclosure may receive, from a computing device associated with a customer of an online shopping concierge platform, data indicating one or more interactions of the customer with the online shopping concierge platform; determine, based at least in part on one or more machine learning (ML) models and the data indicating the interaction(s), a likelihood that the customer will purchase a particular item if presented, at a specific time, with a suggestion to purchase the particular item; and generate and communicate data describing a graphical user interface (GUI) comprising at least a portion of a listing of one or more purchase suggestions including the suggestion to purchase the particular item.

Abstract: In some cases, a delivery service system may include a handheld electronic device for use with a delivery service (e.g., a grocery delivery service). When operating in a voice input mode, the handheld electronic device may record and store audio data in memory. The stored audio data may be communicated from the handheld electronic device (e.g., via a Wi-Fi connection) to the delivery service for speech processing. When operating in a scanner input mode, the handheld electronic device may record and store item identifier information (e.g., barcode data) in memory. The stored data may be communicated to the delivery service for item identification processing. In some cases, a user interface associated with the delivery service may allow the user to review and confirm an order prior to submission of the order for delivery.

Abstract: A computer-implemented method is provided. The computer-implemented method includes obtaining one or more attributes of one or more entities; performing a vectorized representation on a respective attribute of the one or more attributes, the vectorized representation being encoded as a vector of d dimensions; and performing computation on vectorized representation of the one or more attributes based on attention mechanism to construct a graph neural network model. Vectors of m number of dimensions are used to represent an individual entity in the graph neural network model, (m?1) dimensions out of m dimensions represent (m?1) number of attributes, and one out of the m dimensions represents a flag bit. Constructing the graph neural network model includes performing self-attention on the individual entity, during which the flag bit is converted into a fused flag bit by fusing the individual entity's own attributes.

Abstract: Various methods, apparatuses/systems, and media for automatically providing context-based product recommendation are disclosed. A processor establishes a communication link between an application and one or more Internet of Things (IoT) devices wearable by a customer having an account relationship with an institution; receives input data from the IoT devices; assesses surroundings of the customer based on the received input data; generates surroundings data based on the assessed surroundings of the customer; generates customer context data based on the received input data and the surroundings data; implements a classification algorithm to identify products with matching offerings provided by the institution corresponding to the generated customer context data; receives input corresponding to customer consent to receive the identified products; and displays, in response to receiving the customer consent, the identified products onto the application via a predefined communication channel.