Information processing system

Abstract

Improve the search accuracy of the knowledge base. [Solution] The information processing system (1) includes a storage means (40) that stores the user's evaluation of the answer output from the large-scale language model and the user's evaluation of the answer, associating them with each other, when one or more text data extracted from the database (30) based on the user's question and the user's question are input to the large-scale language model; an acquisition means (111) that acquires a question generated by the large-scale language model based on one text data newly registered in the database; an extraction means (112) that extracts a user's question similar to the generated question from the storage means; and a determination means (113) that determines not to register one text data in the database if the evaluation associated with the extracted user's question is a predetermined evaluation.

Claims

[Claim 1] A storage means that stores, in association with the user's evaluation of the answer output from the large-scale language model, one or more text data extracted from a database based on the user's question, and the user's question, as input to a large-scale language model. An acquisition means for acquiring a question sentence generated by the large-scale language model based on a text data newly registered in the database, An extraction means for extracting user question sentences similar to the generated question sentence from the storage means, A determination means that determines whether to register the text data in the database if the evaluation associated with the extracted user question is a predetermined evaluation, An information processing system equipped with the following features. [Claim 2] The extraction means extracts user questions similar to the generated question based on the similarity between the generated question and the user question. The information processing system according to claim 1. [Claim 3] The extraction means extracts user questions similar to the generated question based on the distance between the vector relating to the generated question and the vector relating to the user question. The information processing system according to claim 1.

Images