System

A system comprising:

• a communication interface coupled to a packet-switched network;
• a storage device;
• and
• circuitry configured to:
• acquire attribute information from an information processing apparatus, analyze a logical structure and relationships between items of structured information based on the attribute information, construct a logical structure graph, and store the logical structure graph in the storage device as a learning result;
• receive, via the communication interface, an information acquisition request in a natural language from a terminal device, extract an intention, a condition, and a target item from the information acquisition request using natural language processing and similarity computation against the learning result;
• generate a schema-aware prompt sentence for a generative neural network model by embedding relevant attribute information, the extracted intention, the condition, and the target item, input the prompt sentence to the generative neural network model, and acquire a query formal language expression;
• inspect the query formal language expression against the learning result, and, when nonconforming, modify the prompt sentence with a corrective instruction and instruct the generative neural network model to regenerate the query formal language expression;
• execute the query formal language expression on the information processing apparatus, perform aggregation processing and formatting processing on acquired information to generate a display data set, and generate visualization information comprising graphical elements based on the display data set;
• and
• transmit, via the communication interface, the visualization information and the display data set to the terminal device.

A method comprising:

• acquiring attribute information related to a structure of structured information stored in an information processing apparatus, analyzing a logical structure and relationships between items of the structured information based on the attribute information, and storing an analysis result as a learning result in a storage device;
• receiving, via a communication interface coupled to a packet-switched network, an information acquisition request expressed in a natural language from a terminal device, and extracting an intention and a condition from the information acquisition request;
• generating, based on the learning result and the extracted intention and condition, a schema-aware prompt sentence for a generative neural network model, and inputting the prompt sentence to the generative neural network model to acquire a query formal language expression;
• inspecting whether a referenced information structure and item name in the query formal language expression conform to the structure of the structured information, and, when nonconforming, modifying the prompt sentence and instructing the generative neural network model to regenerate the query formal language expression;
• and
• executing a query process on the information processing apparatus using the query formal language expression, processing acquired information into output information by at least one of aggregation processing and formatting processing, and transmitting the output information to the terminal device via the communication interface.