Task-class intelligent dialogue construction method and system based on knowledge graph

Abstract

The invention discloses a task type intelligent dialogue construction method and system based on a knowledge graph, and the method comprises the steps: firstly constructing the knowledge graph, and setting an intention entity and a word slot entity in the knowledge graph; and then setting that the intention entity points to a word slot entity or points to other intention entities, wherein the word slot entities do not have a mutual relationship. By linking intentions and word slots in task questions and answers into the construction process of the knowledge graph, the structural advantages of the knowledge graph are fully utilized, the relationship between different intentions and word slots is obtained, the configuration of the intentions and word slots is reduced, and correlation between different tasks is facilitated; and the intention entities are set to point to the word slot entities or other intention entities in one direction in the transfer direction of the tasks between the entities in the atlas, and the word slot entities do not have mutual relations, so that the atlas entity structure is simplified, it is guaranteed that the intention entities can efficiently search for the word slot entities or other intention entities related to the intention entities, and skipping between intentions and reverse inquiry of the intentions are realized.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method and system for constructing task-type intelligent dialogues based on knowledge graphs. Background technique [0002] With the continuous development of Internet technology, technologies such as natural language processing, knowledge graph, and machine learning have been continuously developed and widely used. A good human-computer dialogue system can not only greatly reduce the labor cost of customer service, but also has entertainment and practicality, which brings great convenience to people's life and becomes a tool for people to obtain massive information that cannot be obtained, causing more and more More research and application. [0003] As an important part of the intelligent dialogue system, task-based dialogue is mainly used for task-specific dialogue, and there are usually contextual interactions, such as weather query, train ticket su...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the above-mentioned technical deficiencies, and propose a method and system for constructing task-type intelligent dialogues based on knowledge graphs to solve the problems of complex scenes, small training samples and over-fitting existing in small samples in the prior art

Images