Back to results
US 2026/0288765 A1Published application
System
AssigneeSoftBank Group Corp.
InventorHiroshi SHIBASAKI
Life of this patent
Estimating the term…
Abstract
A system includes a processor that is configured to receive information from a user, analyze the received information and input, into a generative artificial intelligence model, a prompt for instructing generation of a presentation material, and adjust the generated presentation material based on an emotional state of the user.
Claims20
A system comprising:
- circuitry configured to:
- acquire, via a communication interface coupled to a packet-switched network, input data from a terminal device, the input data comprising structured numerical data and unstructured text data associated with a content generation request;
- analyze the structured numerical data to extract data type classifications, temporal attributes, and measurement values, and determine candidate data representation methods comprising visualization type selections and axis mapping specifications;
- execute a natural language processing operation on the unstructured text data to extract keyword data, phrase importance scores, and a content type classification, and determine structural element data comprising section identifiers and a logical ordering;
- compute a visualization specification comprising a graph type, axis item assignments, aggregation method selections, and a layout configuration based on the candidate data representation methods and the structural element data, and generate data visualization image data in accordance with the visualization specification;
- construct a prompt data structure comprising the structural element data, the visualization specification, a formatting specification, and constraint parameters, and transmit the prompt data structure to a generative neural network model comprising a transformer-based architecture to acquire generated text data comprising section structure data, title data, and content item data;
- execute a formatting operation on the generated text data to enforce length constraints and style normalization, and combine the formatted text data with the data visualization image data and the formatting specification to generate composite document data;
- and
- transmit the composite document data to the terminal device via the communication interface.
6 more elements
A system comprising:
- circuitry configured to:
- acquire input data comprising structured numerical data and unstructured text data from a terminal device via a communication interface;
- analyze the structured numerical data to determine candidate data representation methods and analyze the unstructured text data using natural language processing to determine structural element data;
- compute a visualization specification and generate data visualization image data based on the candidate data representation methods;
- construct a prompt data structure comprising the structural element data and the visualization specification, transmit the prompt data structure to a generative neural network model, and acquire generated text data;
- combine the generated text data with the data visualization image data to generate composite document data;
- and
- transmit the composite document data to the terminal device.
5 more elements
A method performed by circuitry via a communication interface coupled to a packet-switched network, the method comprising:
- acquiring input data from a terminal device, the input data comprising structured numerical data and unstructured text data;
- analyzing the structured numerical data to extract data type classifications, temporal attributes, and measurement values, and determining candidate data representation methods;
- executing a natural language processing operation on the unstructured text data to extract keyword data, phrase importance scores, and a content type classification, and determining structural element data;
- computing a visualization specification and generating data visualization image data in accordance with the visualization specification;
- constructing a prompt data structure comprising the structural element data, the visualization specification, and constraint parameters, and transmitting the prompt data structure to a generative neural network model comprising a transformer-based architecture to acquire generated text data;
- executing a formatting operation on the generated text data and combining the formatted text data with the data visualization image data to generate composite document data;
- and
- transmitting the composite document data to the terminal device.
5 more elements
Dependencies are inferred from the claim text.