Back to results
US 2026/0289123 A1Published application
System
AssigneeSoftBank Group Corp.
InventorShizuka GOTO
Life of this patent
Estimating the term…
Abstract
A system includes a processor that is configured to use a generative AI model, in response to a prompt, to receive and analyze information from a user and to determine a current location of the user, use the generative AI model, in response to a prompt, to extract a request of the user, to generate a plurality of options corresponding to the request, to analyze an emotion of the user, and to adjust a conversation with the user based on the analyzed emotion.
Claims20
A system comprising:
- circuitry configured to:
- receive, from a client terminal via a packet-switched network, inquiry data expressed in natural language and position data associated with a user;
- analyze the inquiry data and the position data to extract intent information and a target category, and generate a first prompt sentence for a generative neural network model based on the intent information, the target category, and the position data;
- input the first prompt sentence to the generative neural network model and obtain first response data in natural language comprising candidate information items corresponding to the intent information;
- search a geographic information database based on the first response data and the position data, and acquire related information comprising entity records and location coordinates from the geographic information database;
- integrate the related information with the first response data to generate combined result data associating each candidate information item with corresponding entity records and location coordinates;
- generate conversational output data and map display data based on the combined result data, and transmit the conversational output data and the map display data to the client terminal via the packet-switched network;
- and
- analyze an emotional state of the user based on expression data included in the inquiry data, and adjust at least one of content, tone, and level of detail of the conversational output data according to the emotional state.
6 more elements
A system comprising:
- circuitry configured to:
- receive, from a client terminal via a packet-switched network, inquiry data in natural language and position data associated with a user;
- analyze the inquiry data to extract intent information and a target category;
- generate a first prompt sentence based on the intent information, the target category, and the position data;
- input the first prompt sentence to a generative neural network model and obtain first response data;
- search a geographic information database based on the first response data and the position data to acquire entity records and location coordinates;
- integrate the first response data with the entity records to generate combined result data;
- generate conversational output data and map display data based on the combined result data;
- analyze an emotional state of the user based on expression data in the inquiry data;
- adjust at least one of content and tone of the conversational output data based on the emotional state;
- and
- transmit the conversational output data and the map display data to the client terminal via the packet-switched network.
9 more elements
A method performed by circuitry, the method comprising:
- receiving, from a client terminal via a packet-switched network, inquiry data in natural language and position data associated with a user;
- analyzing the inquiry data to extract intent information and a target category;
- generating a first prompt sentence based on the intent information, the target category, and the position data;
- inputting the first prompt sentence to a generative neural network model and obtaining first response data;
- searching a geographic information database based on the first response data and the position data to acquire entity records and location coordinates;
- integrating the first response data with the entity records to generate combined result data;
- generating conversational output data and map display data based on the combined result data;
- analyzing an emotional state of the user based on expression data in the inquiry data;
- adjusting at least one of content and tone of the conversational output data based on the emotional state;
- and
- transmitting the conversational output data and the map display data to the client terminal via the packet-switched network.
8 more elements
Dependencies are inferred from the claim text.