Back to results
US 2026/0289356 A1Published application
System
AssigneeSoftBank Group Corp.
InventorKazuya NAKASHIMA
Life of this patent
Estimating the term…
Abstract
A system includes a processor that is configured to analyze big data and process data using a generative artificial intelligence model that extracts variable factors, input generated variable factors into the generative artificial intelligence model as a prompt sentence, and recognize an emotional state of a user and adjust a prediction based on the emotional state of the user.
Claims20
A system comprising:
- circuitry configured to:
- receive, via a communication interface coupled to a packet-switched network, large-scale input data from one or more data sources, the input data including past operational data, external environment data, and economic condition data, and store the input data in a storage device;
- preprocess the input data to generate training input data, train a multilayer computational model using the training input data, and input variable factors extracted by the computational model as a prompt sentence to a generative AI model to obtain a prediction result;
- and
- recognize an emotional state of a user based on data received from a terminal device via the communication interface, adjust the prediction result based on the recognized emotional state, and transmit the adjusted prediction result to the terminal device via the communication interface.
2 more elements
A system comprising:
- circuitry configured to:
- receive, via a communication interface coupled to a packet-switched network, large-scale input data from one or more data sources and store the input data in a storage device;
- preprocess the input data to generate training input data, train a multilayer computational model, extract variable factors from the trained model, generate a prompt sentence incorporating the variable factors, and input the prompt sentence to a generative AI model to obtain a prediction result;
- recognize an emotional state of a user based on data received from a terminal device via the communication interface, and adjust the prediction result based on the recognized emotional state;
- and
- transmit the adjusted prediction result to the terminal device via the communication interface, and update the multilayer computational model based on feedback received from the terminal device.
3 more elements
A method comprising:
- receiving, via a communication interface coupled to a packet-switched network, large-scale input data from one or more data sources and storing the input data in a storage device;
- preprocessing the input data to generate training input data, training a multilayer computational model using the training input data, and inputting variable factors extracted by the computational model as a prompt sentence to a generative AI model to obtain a prediction result;
- and
- recognizing an emotional state of a user based on data received from a terminal device via the communication interface, adjusting the prediction result based on the recognized emotional state, and transmitting the adjusted prediction result to the terminal device via the communication interface.
1 more element
Dependencies are inferred from the claim text.