Classification method and device for multiple rounds of conversations

Abstract

The embodiment of the invention provides a classification method and device for multiple rounds of conversations. The classification method comprises the steps: obtaining multiple rounds of conversations between a target user and a robot; respectively inputting the user questions of each round of conversation in the multiple rounds of conversations into a first feature extraction model, and respectively outputting a first feature vector corresponding to each round of conversation through the first feature extraction model; according to the sequence of each round of conversation, adopting a self-attention mechanism for the first feature vector corresponding to the conversation before each round of conversation, and generating a second feature vector corresponding to each round of conversation; inputting the behavior characteristics of the preset historical behaviors of the target user into a second characteristic extraction model, and outputting a third characteristic vector through thesecond characteristic extraction model; and determining the category of the multi-round conversation at least according to the second feature vector and the third feature vector corresponding to eachround of conversation. The classification method can guarantee the effect of classifying multiple rounds of conversations.

Description

technical field [0001] One or more embodiments of this specification relate to the computer field, and in particular to a classification method and device for multi-round dialogues. Background technique [0002] When the robot answers user questions, it often involves the classification of user questions. For example, a standard question sentence corresponding to a user question sentence is determined, so that the robot provides an answer corresponding to the standard question sentence. Wherein, the standard questions are also referred to as standard questions, which are questions that some users may ask according to business. Each question has a question ID. Since user questions are usually colloquial, it often takes several rounds of dialogue between the robot and the user to determine the user's request. [0003] In the prior art, the classification effect for multiple rounds of dialogue is not good, and often fails to meet user requirements. [0004] Therefore, it is...

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, the classification effect for multiple rounds of dialogue is not good, and often cannot meet the needs of users

Images