System

A system comprising:

• circuitry configured to:
• receive, via a communication interface coupled to a packet-switched network, audio data and text data from a terminal device, apply a speech recognition model to the audio data to generate character string data, and preprocess the character string data to generate analysis text information;
• construct a prompt sentence embedding the analysis text information into an instruction template, transmit the prompt sentence to a generative AI model, and obtain structured information comprising an intent type, time information, and event information;
• apply a prosody analysis model to the audio data to extract prosodic features, apply an emotion recognition model to the prosodic features and linguistic emotional indicators extracted from the character string data to generate an emotional state representation;
• generate a schedule information object based on the structured information and store it in a storage device, generate a service proposal adjusted based on the emotional state representation, and cooperate with an external processing service via the communication interface to perform at least one of schedule registration, task assignment, and information provision;
• and
• transmit notification information and the service proposal to the terminal device via the communication interface.

A method comprising:

• receiving, via a communication interface coupled to a packet-switched network, input information expressed in natural language from a terminal device, and preprocessing the input information by removing unnecessary elements and normalizing character information to generate analysis text information;
• constructing a prompt sentence by embedding the analysis text information into an instruction template, transmitting the prompt sentence to a generative AI model, and obtaining structured information representing a semantic interpretation and extracted information comprising at least an intent type, time information, and event information;
• applying a speech recognition model to audio data received from the terminal device to generate character string data, and applying a natural language processing model to the character string data to extract request information and schedule information;
• generating a schedule information object comprising time information and event information converted into an internal data format based on the structured information, and storing the schedule information object in a storage device;
• generating notification information based on the schedule information object and transmitting the notification information to the terminal device via the communication interface;
• and
• cooperating with an external processing service via the communication interface based on the schedule information object to perform at least one of schedule registration, task assignment, and information provision.