System

A system comprising:

• circuitry configured to:
• receive, via a communication interface coupled to a packet-switched network, condition data transmitted from a terminal device including at least schedule information, a participant count, a location parameter, and a preference parameter, convert the condition data into a normalized structured data set by parsing parameter fields, normalizing values into standardized representations, and calculating derived parameter values, and store the normalized structured data set in a storage device;
• query the storage device using search condition data derived from the normalized structured data set to extract a plurality of candidate data items, perform ranking processing on the candidate data items based on a degree of match, transmit ranked candidate list data to the terminal device, and receive a selection input indicating a selected candidate data item;
• generate a natural-language prompt sentence by inserting parameter values from the normalized structured data set and attribute information of the selected candidate data item into predetermined positions of a sentence template that includes control instructions specifying a detail level and an output format, and transmit the natural-language prompt sentence to a transformer-based generative neural network model;
• convert generated output data received from the transformer-based generative neural network model into a hierarchical structured data format comprising a plurality of segments organized by temporal divisions, each segment including at least an activity identifier, a time allocation, a recommended facility identifier, and associated supplementary context data acquired from at least one external information providing apparatus;
• receive user state data from the terminal device, estimate an emotional state by inputting the user state data to an emotion identification model, adjust a priority ranking of segments within the hierarchical structured data format based on the estimated emotional state, and regenerate the natural-language prompt sentence incorporating the estimated emotional state when a change in the emotional state exceeds a predetermined threshold;
• and
• transmit the hierarchical structured data format to the terminal device via the communication interface for rendering in a display format organized by temporal division.

A method performed by circuitry of a server coupled to a packet-switched network via a communication interface, the method comprising:

• receiving, via the communication interface, condition data transmitted from a terminal device, converting the condition data into a normalized structured data set, and storing the normalized structured data set in a storage device;
• generating, based on the normalized structured data set, a natural-language prompt sentence by inserting parameter values derived from the normalized structured data set into predetermined positions of a sentence template, and transmitting the natural-language prompt sentence to a generative neural network model to obtain generated output data;
• converting the generated output data into a hierarchical structured data format comprising a plurality of segments organized by temporal divisions, each segment including at least an activity identifier, a time allocation, and an associated attribute set;
• and
• transmitting the hierarchical structured data format to the terminal device via the communication interface.