System

A system comprising:

• circuitry configured to:
• receive, via a communication interface coupled to a packet-switched network, a voice signal from a terminal device, convert the voice signal into a discrete numerical signal, and apply speech recognition processing comprising an acoustic model and a language model to generate character-string information from the discrete numerical signal;
• perform natural language processing including tokenization and named entity recognition on the character-string information to extract a target index, an aggregation unit, and an extraction condition, and generate a prompt sentence comprising the character-string information and metadata describing a table structure and an item attribute of a data accumulation apparatus;
• input the prompt sentence to a generative neural network model comprising a transformer-based architecture and obtain an inquiry statement comprising a data inquiry command, inspect the inquiry statement for a prohibited command and for consistency with a data structure stored in a storage device, and normalize the inquiry statement;
• transmit the normalized inquiry statement to a query processing mechanism of the data accumulation apparatus, acquire a processing result, and perform post-processing comprising at least one of aggregation processing, sorting processing, or conversion into a visualization data structure;
• extract emotional feature quantities comprising at least one of a fundamental frequency contour, an energy distribution, or a speech rate from the voice signal, estimate an emotional state of a user, and adjust at least one of content of the prompt sentence or a display detail level of the visualization data structure based on the estimated emotional state;
• and
• transmit, via the communication interface, a notification data packet comprising the visualization data structure to the terminal device for presentation.

A method comprising:

• receiving, via a communication interface coupled to a packet-switched network, a voice signal from a terminal device, and converting the voice signal into a discrete numerical signal;
• applying speech recognition processing to the discrete numerical signal to generate character-string information, and performing natural language processing on the character-string information to extract a target index, an aggregation unit, and an extraction condition from the character-string information;
• generating a prompt sentence based on the character-string information and data structure information stored in a storage device, inputting the prompt sentence to a generative neural network model, and obtaining from the generative neural network model an inquiry statement comprising a data inquiry command corresponding to the character-string information;
• inspecting the inquiry statement to detect existence of a prohibited command and to verify consistency of a reference target with the data structure information, and normalizing the inquiry statement based on an inspection result;
• transmitting the normalized inquiry statement to a query processing mechanism of a data accumulation apparatus, causing the query processing mechanism to execute the normalized inquiry statement, and acquiring a processing result;
• and
• analyzing emotional feature quantities extracted from the voice signal and adjusting at least one of content of the prompt sentence or generation conditions of the generative neural network model based on the emotional feature quantities, and transmitting a notification data packet comprising the processing result to the terminal device for presentation as visual information.