Dialogue generation and corpus expansion method and device, computer equipment and storage medium

Abstract

The invention relates to a dialogue generation and corpus expansion method and device, computer equipment and a storage medium. The dialogue generation method comprises the steps of obtaining a current question text, wherein the current question text is obtained according to a current input question of a user; performing text vectorization processing on the current problem text, and then inputtingthe current problem text into a pre-created dialogue generation model, wherein the dialogue generation model is obtained by taking a question text vector and an answer text of the question text vector as model training samples for training, and the question text vector is obtained by performing text vectorization processing, synonym conversion and/or sentence pattern rewriting on an initial question text and conversion from a word vector to a semantic vector; and responding to the input question according to the target answer text, the input question and the response to the input question being the generated dialogues. By adopting the method, the number of samples can be increased, the sample availability is enhanced, and the dialogue quality can be improved.

Description

technical field [0001] The present application relates to the field of electric power technology, in particular to a dialog generation and corpus expansion method, device, computer equipment and storage medium. Background technique [0002] With the development of power technology and the gradual growth of business and data volume in the power industry, a large number of business scenarios that require interaction have emerged within power companies, such as intelligent assistants for operation management and control, and intelligent customer service. Among them, the process of information interaction with machines through natural language understanding to realize business requirements and data calls has important research significance and application value. [0003] Natural language processing and human-computer dialogue are the main components of speech semantic technology, and integrating various semantic analysis algorithms is one of the key supporting applications of ar...

AI Technical Summary

Problems solved by technology

[0004] The effect of the human-computer dialogue system depends on the quality and scale of the labeled data, but in specific scenarios such as enterprise intelligent assistants, the corpus required by the dialogue management module at the start-up stage is lacking, which may easily lead to insufficient generalization capabilities of the model, making it difficult to achieve good training results

For vertical fields, it is very difficult to collect dialogue data on a large scale. When the amount of data is insufficient, satisfactory intent recognition and slot filling accuracy cannot be achieved, which will affect the quality of dialogue.

Images