Back to results
US 2026/0289648 A1Published application
System
AssigneeSoftBank Group Corp.
InventorYota MASUDA
Life of this patent
Estimating the term…
Abstract
A system includes a processor that is configured to receive information from a user, analyze the received information and, using a generative artificial intelligence model, generate a cooking method according to at least one of a price, a nutritional value, and an inventory status, and analyze a purchase history and an emotional state of the user and, based on a result of the analysis, propose a cooking method suitable for at least one of a specific nutritional value, a budget, and an emotion.
Claims20
A system comprising:
- a communication interface coupled to a packet-switched network;
- and
- circuitry configured to:
- receive, via the communication interface, input data from a terminal device, the input data comprising a request and user identification information;
- acquire, from a storage device, history data and attribute data associated with the user identification information;
- acquire, via the communication interface, item data from an external data source, the item data comprising attribute parameters including a numerical value parameter, a quantity parameter, and a classification parameter;
- perform a normalization operation and an aggregation operation on the history data and the item data to generate constraint data;
- generate a prompt sentence based on the input data and the constraint data, the prompt sentence being configured to instruct a generative neural network model to generate structured output data satisfying at least one constraint condition extracted from the input data;
- and
- transmit the structured output data to the terminal device via the communication interface.
7 more elements
A system comprising:
- a communication interface coupled to a packet-switched network;
- and
- circuitry configured to:
- receive, via the communication interface, input data from a terminal device comprising a request and user identification information;
- acquire history data and attribute data from a storage device and item data from an external data source via the communication interface;
- perform normalization, aggregation, and association operations on the history data and the item data to generate constraint data;
- analyze the input data using a natural language processing operation to extract constraint conditions;
- estimate an emotional state of the user based on text feature data extracted from the input data;
- generate a prompt sentence based on the constraint conditions, the constraint data, and the emotional state, the prompt sentence being configured to instruct a generative neural network model comprising a transformer architecture;
- input the prompt sentence to the generative neural network model and obtain structured output data;
- verify that the structured output data satisfies each constraint condition and trigger regeneration when a deviation is detected;
- and
- transmit verified structured output data to the terminal device via the communication interface.
10 more elements
A method comprising:
- receiving, via a communication interface coupled to a packet-switched network, input data from a terminal device, the input data comprising a request and user identification information;
- acquiring, from a storage device, history data and attribute data associated with the user identification information;
- acquiring, via the communication interface, item data from an external data source, the item data comprising attribute parameters;
- performing a normalization operation and an aggregation operation on the history data and the item data to generate constraint data;
- generating a prompt sentence based on the input data and the constraint data, the prompt sentence being configured to instruct a generative neural network model to generate structured output data satisfying at least one constraint condition extracted from the input data;
- and
- transmitting the structured output data to the terminal device via the communication interface.
4 more elements
Dependencies are inferred from the claim text.