System

A system comprising:

• circuitry configured to:
• receive, via a communication interface coupled to a packet-switched network, audio information from a terminal device, transmit the audio information to an information processing apparatus for speech recognition processing, and obtain character information;
• apply natural language processing based on a machine learning model to the character information to perform grammatical and semantic correction, generating corrected character information;
• generate a prompt sentence specifying summary content, output format, and information extraction targets, input the prompt sentence and the corrected character information into a generative neural network model to generate summary information, and aggregate the summary information on a session unit basis or a time-interval unit basis;
• input aggregated summary information into the generative neural network model with an overall summarization prompt to generate overall summary information, and store the summary information and overall summary information in association with time information of the audio information in a storage device;
• analyze acoustic characteristics and linguistic content of the audio information to recognize an emotional state of a speaker, and evaluate at least one of a progress degree, a discussion activity level, or a consensus degree of a session based on the recognized emotional state and the summary information;
• and
• transmit the summary information and session evaluation information to the terminal device via the communication interface.

A method comprising:

• receiving, via a communication interface coupled to a packet-switched network, audio information from a terminal device, and converting the audio information into digital signals in a predetermined format;
• transmitting the digital signals to an information processing apparatus via the communication interface to perform speech recognition processing, obtaining character information, and storing the character information in a storage device;
• applying natural language processing based on a machine learning model to the character information to perform grammatical and semantic correction, and generating corrected character information as input information for summarization;
• generating a prompt sentence that defines a content, an output format, and target information for extraction based on the corrected character information, and inputting the prompt sentence and the corrected character information into a generative neural network model to cause the generative neural network model to generate summary information;
• and
• storing the summary information in association with the character information in the storage device, and transmitting the summary information to the terminal device via the communication interface.