Back to results
US 2026/0288613 A1Published application
System
AssigneeSoftBank Group Corp.
InventorKazuyoshi AKAKURA
Life of this patent
Estimating the term…
Abstract
A system includes a processor that is configured to track activities of a user by using an information processing apparatus and collect data related to the activities of the user, transmit the collected data to a storage device via a communication means and store the collected data in the storage device, and create a prompt for instructing a generative AI model to generate an activity history based on the stored data and input the prompt to the generative AI model.
Claims20
A system comprising:
- circuitry configured to:
- acquire, via a communication interface coupled to a packet-switched network, interaction event data from a terminal device, the interaction event data representing operations performed by a user on an information processing apparatus;
- store the interaction event data in an information storage device by associating each interaction event with a timestamp and a resource identifier;
- execute a feature extraction operation on the interaction event data to generate feature vectors representing characteristics of the interaction events, and classify the feature vectors into topic categories by inputting the feature vectors into a neural network configured to output probability values over a plurality of topic labels;
- construct an instruction sequence comprising a temporal range parameter, the topic categories, and a subset of the interaction event data selected based on the temporal range parameter, and input the instruction sequence into a generative neural network model comprising a transformer-based architecture to generate temporal summary data describing the interaction events within the temporal range;
- and
- transmit the temporal summary data to the terminal device via the communication interface.
4 more elements
A system comprising:
- circuitry configured to:
- acquire interaction event data from a terminal device via a communication interface, the interaction event data representing user operations on an information processing apparatus, each interaction event associated with a timestamp and a resource identifier;
- store the interaction event data in an information storage device, extract content features from information resources corresponding to the resource identifiers, and compute relevance scores based on dwell time values and topic confidence values derived from a classification neural network;
- construct an instruction sequence comprising a temporal range parameter and selected interaction event data exceeding a relevance threshold, and input the instruction sequence into a generative neural network model to generate temporal summary data;
- and
- transmit the temporal summary data to the terminal device.
3 more elements
A method comprising:
- acquiring, by circuitry via a communication interface coupled to a packet-switched network, interaction event data from a terminal device, the interaction event data representing operations performed by a user on an information processing apparatus;
- storing the interaction event data in an information storage device by associating each interaction event with a timestamp and a resource identifier;
- executing a feature extraction operation on the interaction event data to generate feature vectors representing characteristics of the interaction events, and classifying the feature vectors into topic categories by inputting the feature vectors into a neural network configured to output probability values over a plurality of topic labels;
- constructing an instruction sequence comprising a temporal range parameter, the topic categories, and a subset of the interaction event data selected based on the temporal range parameter, and inputting the instruction sequence into a generative neural network model comprising a transformer-based architecture to generate temporal summary data describing the interaction events within the temporal range;
- and
- transmitting the temporal summary data to the terminal device via the communication interface.
3 more elements
Dependencies are inferred from the claim text.