Associated question aggregation model generation method and device, question-and-answer mode aggregation method and device as well as equipment

Abstract

The invention discloses an associated question aggregation model generation method and device, a question-and-answer mode aggregation method and device as well as equipment. The methods include the following steps: obtaining a first quantity of basic training samples according to network behavior data of at least two users, and training a first machine learning model by using the basic training samples to obtain a basic semantic matching model; migrating a semantic representation layer in the basic semantic matching model to a second machine learning model, and training the second machine learning model according to a second quantity of pre-labeled associated question pairs to obtain an associated question aggregation model. According to the embodiment of the invention, the associated question aggregation model that aggregates answers of questions with consistent meanings can be obtained, the basic semantic matching model trained by the network behavior data of the users is adopted toperform migration learning to further generate the associated question aggregation model, so that the number of manually labeled samples and the manual labeling costs can be greatly reduced, and the answer satisfaction rate of the questions in a question-and-answer community can be optimized.

Description

technical field [0001] Embodiments of the present invention relate to data processing technologies, and in particular, relate to a method, device and equipment for generating an aggregation model of associated questions and a question-and-answer aggregation. Background technique [0002] At present, Baidu knows, Zhihu and other question-and-answer communities have a lot of the same problems. Some questions had no answers or were of low quality. When users search for these questions, they cannot find answers to their needs. However, there are other problems with the same meaning but different expressions on the website. (For example, "How to force an Apple phone to shut down?" and "Is there a way to force an IPhone to shut down?" are a pair of questions with the same meaning but different expressions.) These questions with the same meaning may have answers that meet the needs of users. [0003] In the prior art, when a user asks a question, some question-and-answer communi...

AI Technical Summary

Problems solved by technology

[0004] In the process of realizing the present invention, the inventor found that the existing technology can only check the problems with consistent problem expressions, or only individual stop words are different, and the semantic generalization is very poor; and for the problems that already exist in the library, no Check whether there are the same questions. Some of the questions in the library have low-quality answers or no answers, which will affect the overall answer satisfaction rate of the Q&A community.

Images