System

A system comprising:

• circuitry configured to:
• receive, via a communication interface coupled to a packet-switched network, schedule data from a terminal device comprising time parameters and content parameters for a plurality of activity entries, execute format validation and completeness verification on the schedule data, and store validated schedule data as structured records with temporal indexes in a storage device;
• query the storage device to retrieve activity entries within a specified time window, extract temporal attributes and content attributes, tokenize a prompt sentence incorporating the extracted attributes, and transmit the tokenized prompt sentence to an inference engine executing a generative neural network model;
• decode an output token sequence from the inference engine to obtain a proposal text string, parse the proposal text string using a temporal alignment procedure to map proposal records to corresponding time segments of the structured records, and compute overlay geometry parameters for each mapped proposal record;
• and
• generate display control information encoding the overlay geometry parameters and transmit the display control information to the terminal device via the communication interface, and update the storage device with merged proposal records and a proposal acceptance rate used to adjust inference parameters in subsequent transmissions.

A method comprising:

• receiving, via a communication interface coupled to a packet-switched network, schedule data from a terminal device comprising time parameters and content parameters for a plurality of activity entries, executing format validation and completeness verification on the schedule data, and storing validated schedule data as structured records with temporal indexes in a storage device in association with identification information;
• querying the storage device to retrieve activity entries within a specified time window, extracting temporal attributes and content attributes from the retrieved structured records, tokenizing a prompt sentence incorporating the extracted attributes and an instruction for a generative neural network model to generate structured proposals, and transmitting the tokenized prompt sentence to an inference engine executing the generative neural network model;
• and
• decoding an output token sequence from the inference engine to obtain a proposal text string, parsing the proposal text string to extract proposal records and map each proposal record to a corresponding time segment of the structured records, generating display control information that superimposes the mapped proposal records on a time-axis display representation of the schedule data, and transmitting the display control information to the terminal device via the communication interface.