Back to results
US 2026/0289449 A1Published application
System
AssigneeSoftBank Group Corp.
InventorMasato TAKAHASHI
Life of this patent
Estimating the term…
Abstract
A system includes a processor that is configured to collect information for attracting visitors to a facility from at least one sensor or at least one database and analyze the collected information by using a machine learning algorithm, acquire attributes of visitors by using at least one camera or at least one RFID sensor and analyze the acquired attributes by using a data mining technique, and generate, by using a natural language processing technique, a prompt sentence for instructing a generative artificial intelligence model to generate event content and input the prompt sentence to the generative artificial intelligence model.
Claims20
A system comprising:
- circuitry configured to:
- receive, via a communication interface coupled to a packet-switched network, sensor data from detection devices, the sensor data comprising visit count data, visit time data, attribute data, and behavior history records;
- integrate the sensor data as visit session information, and perform preprocessing comprising at least missing-value completion, normalization, attribute encoding, and time-domain feature extraction to generate analysis feature data;
- execute a machine learning model process on the analysis feature data, the machine learning model process comprising classification processing, clustering processing, and time-series prediction processing, to generate segment information of visitor groups, peak-time information, and event-participation probability information;
- generate plan information based on the segment information and the peak-time information, the plan information comprising event type data, target segment data, a holding time period, and a resource allocation plan;
- extract context information from the plan information, combine the context information with a request sentence received from a terminal device, generate a prompt sentence for a generative neural network model, transmit the prompt sentence to the generative neural network model, and receive generated-result information comprising event content data, execution procedure data, and notification text data;
- and
- update the plan information based on the generated-result information, and transmit the updated plan information to the terminal device via the communication interface.
5 more elements
A system comprising:
- circuitry configured to:
- receive, via a communication interface coupled to a packet-switched network, sensor data from detection devices comprising visit count data, attribute data, and behavior history records;
- integrate the sensor data as visit session information, and perform preprocessing comprising missing-value completion, normalization, attribute encoding, and time-domain feature extraction to generate analysis feature data;
- execute classification processing, clustering processing, and time-series prediction processing on the analysis feature data to generate segment information of visitor groups, peak-time information, and event-participation probability information;
- generate plan information comprising event type data, target segment data, a holding time period, and a resource allocation plan based on the segment information and the peak-time information;
- construct a prompt sentence by embedding context information from the plan information and a natural language request sentence from a terminal device, execute inference processing using a generative neural network model with the prompt sentence as input to obtain generated-result information comprising event content data and notification text data;
- and
- update the plan information based on the generated-result information and transmit the updated plan information to the terminal device via the communication interface.
5 more elements
A method comprising:
- receiving, via a communication interface coupled to a packet-switched network, sensor data from detection devices, the sensor data comprising visit count data, visit time data, attribute data, and behavior history records;
- integrating the sensor data as visit session information, and performing preprocessing comprising at least missing-value completion, normalization, attribute encoding, and time-domain feature extraction to generate analysis feature data;
- executing a machine learning model process on the analysis feature data, the machine learning model process comprising classification processing, clustering processing, and time-series prediction processing, to generate segment information of visitor groups, peak-time information, and event-participation probability information;
- generating plan information based on the segment information and the peak-time information, the plan information comprising event type data, target segment data, a holding time period, and a resource allocation plan;
- extracting context information from the plan information, combining the context information with a request sentence received from a terminal device, generating a prompt sentence for a generative neural network model, transmitting the prompt sentence to the generative neural network model, and receiving generated-result information comprising event content data, execution procedure data, and notification text data;
- and
- updating the plan information based on the generated-result information, and transmitting the updated plan information to the terminal device via the communication interface.
4 more elements
Dependencies are inferred from the claim text.