System

A system comprising:

• circuitry configured to:
• receive, via a communication interface coupled to a packet-switched network, from a terminal device, attribute data and preference data of a user;
• store the attribute data and the preference data in a storage device;
• acquire, from the storage device, profile data of a plurality of other entities;
• perform preprocessing on the attribute data and the profile data to generate numerical feature data and character string feature data;
• convert the numerical feature data and the character string feature data into feature vectors and execute a similarity calculation to compute a similarity score for each of the plurality of other entities;
• select candidate entities for which the similarity score satisfies a predetermined threshold;
• generate, based on the preference data, the similarity score, and attribute information of the candidate entities, a prompt sentence for instructing a generative neural network model to generate evaluation information and a recommendation text in natural language;
• input the prompt sentence to the generative neural network model to acquire analysis result data;
• generate recommendation result data by ranking the candidate entities based on the analysis result data;
• transmit the recommendation result data to the terminal device via the communication interface;
• receive, from the terminal device, selection data indicating a selection by the user;
• and
• store the selection data as behavior history information and update the preference data based on the behavior history information for subsequent prompt sentence generation.

A method performed by circuitry, the method comprising:

• receiving, via a communication interface coupled to a packet-switched network, from a terminal device, attribute data and preference data of a user;
• storing the attribute data and the preference data in a storage device;
• acquiring, from the storage device, profile data of a plurality of other entities;
• generating, based on the preference data and the profile data, a prompt sentence for instructing a generative neural network model to perform an analysis and identify candidate entities corresponding to the preference data;
• inputting the prompt sentence to the generative neural network model to acquire analysis result data comprising evaluation information for the candidate entities;
• generating recommendation result data by ranking the candidate entities based on the evaluation information;
• and
• transmitting the recommendation result data to the terminal device via the communication interface for presentation on the terminal device.