Intention recognition method and nutritional knowledge question and answer method and device

Abstract

The invention provides an intention recognition method and a nutritional knowledge question and answer method and device. The method comprises the steps of obtaining a session text input by a user; determining text sequence features corresponding to the session text according to a preset knowledge graph, wherein the preset knowledge graph comprises a plurality of nutrition knowledge entities and association relationships among the nutrition knowledge entities; and recognizing the session intention of the user based on the session text and the text sequence features through an intention prediction model obtained by pre-training. According to the invention, the accuracy of intention recognition can be effectively improved, and the user experience is further improved.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to an intention recognition method, a nutritional knowledge question answering method and a device. Background technique [0002] With the development of social economy and the progress of science and technology, people pay more and more attention to their own nutrition and health. Today, the rapid development of artificial intelligence technology has allowed more human-computer interaction robots to enter people's daily lives. Therefore, intelligent dialogue robots that use intelligent nutrition questions and answers as application scenarios have emerged as the times require. The current dialogue robots are mostly two types: retrieval type and generation type. Among them, the retrieval type is based on the search pattern matching method to feed back the question and answer results. Due to the strict requirements on the data input form, it is impossible to ensure that ...

AI Technical Summary

Problems solved by technology

However, the above-mentioned method uses manual extraction of features, which not only consumes a lot of labor and time costs, but also leads to low accuracy of intent recognition, which in turn leads to poor user experience.

Images