Generative multi-round chat dialogue method, system and computer-readable storage medium

Abstract

The invention discloses a generative multi-round gossip dialogue method, system and computer-readable storage medium, which are divided into two stages: stage one: use the dialogue of the corpus to train the multi-round gossip dialogue model; stage two: use the dialogue model proposed by the user The questions to be answered are input into the trained multi-round chat dialogue model, and the actual answers are output. By mining the keywords in the dialogue history and introducing the attention mechanism into the model, all the words in the dialogue history are treated differently, which expands the role of keywords in the historical dialogue when generating replies. Widen the topic by predicting keywords through the width channel, and predict the weight of keywords in historical conversations through the depth channel, so as to deepen the current topic, and introduce the topic information obtained from the two parts into the decoder to assist decoding, and the guidance of the topic information is effective. Solved the problem of meaningless replies and greatly reduced the number of meaningless replies.

Description

technical field [0001] The invention relates to a generative multi-round chat dialogue method, system and computer-readable storage medium. Background technique [0002] Dialogue systems, also known as intelligent dialogue bodies or chat robots, have been widely used in various life scenarios, including customer service, entertainment chat, emotional escort, knowledge sharing, etc. [0003] In terms of usage, dialogue systems can be roughly divided into chatting dialogue systems and task-oriented dialogue systems. Technically, dialogue systems can be divided into rule-based, retrieval-based, and generation-based dialogue systems. Among them, the rule-based dialogue system requires a lot of human resources to design rules, and the retrieval-based dialogue system relies heavily on the quality of the corpus and size, and rule-based or retrieval-based dialogue systems severely limit the diversity of generated responses. The generation-based dialogue system can generate more fl...

AI Technical Summary

Problems solved by technology

One problem faced by single-turn dialogue systems is that the model ignores the influence of dialogue history on the current reply

[0005] Although a lot of research work has improved the performance of the multi-turn dialogue chat system, it still faces some problems. One of the more prominent problems is that the multi-turn dialogue chat system often generates meaningless responses.

Images