Back to results
US 2026/0290140 A1Published application
System
AssigneeSoftBank Group Corp.
InventorHiroyuki MIZUNO
Life of this patent
Estimating the term…
Abstract
A system includes a processor that is configured to detect a drowsiness state of a user by using a sensor and analyze data obtained from the sensor to convert a degree of drowsiness of the user into a numerical value, determine a genre and an intensity of music by using a generative artificial intelligence model on the basis of the determined degree of drowsiness, and input, to the generative artificial intelligence model, a prompt for instructing generation of music on the basis of the determined genre and intensity so as to automatically generate original music.
Claims20
A system comprising:
- circuitry configured to:
- receive, via a communication interface coupled to a packet-switched network, state information from a terminal device, the state information being generated by at least one sensor or detection unit of the terminal device and representing an arousal state of a user, and analyze the state information to convert it into evaluation information indicating a degree of the arousal state;
- determine, based on the evaluation information, a genre and an intensity of audio content, generate a prompt sentence for a generative AI model based on the determined genre and intensity, and input the prompt sentence to the generative AI model to instruct generation of the audio content;
- and
- transmit audio data generated based on the generated audio content 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, state information from a terminal device, the state information representing an arousal state of a user generated by at least one sensor, and analyze the state information to convert it into an evaluation value indicating a degree of the arousal state;
- determine a genre and an intensity of audio content based on the evaluation value, generate a prompt sentence incorporating the determined genre and intensity, and input the prompt sentence to a generative AI model to obtain the audio content;
- analyze a tone of voice and a facial expression of the user from data received from the terminal device via the communication interface, recognize an emotional state of the user, and adjust the genre and intensity in real time based on the recognized emotional state;
- and
- transmit audio data generated based on the audio content to the terminal device via the communication interface.
3 more elements
A method comprising:
- receiving, via a communication interface coupled to a packet-switched network, state information from a terminal device, the state information being generated by at least one sensor and representing an arousal state of a user, and analyzing the state information to convert it into evaluation information indicating a degree of the arousal state;
- determining, based on the evaluation information, a genre and an intensity of audio content, generating a prompt sentence for a generative AI model based on the determined genre and intensity, and inputting the prompt sentence to the generative AI model to instruct generation of the audio content;
- and
- transmitting audio data generated based on the generated audio content to the terminal device via the communication interface.
1 more element
Dependencies are inferred from the claim text.