Generation method of question and answer knowledge base, training method and equipment of neural network

Abstract

The embodiment of the invention provides a generation method of a question and answer knowledge base, a training method and equipment of a neural network. The generation method of the question and answer knowledge base comprises the steps of splitting document data and obtaining multiple knowledge fragments; conducting mapping on each knowledge fragment through the neural network, obtaining questions corresponding to each knowledge fragment, and thus generating and obtaining the question and answer knowledge base. Through the generation method of the question and answer knowledge base, the training method and equipment of the neural network, the difficulty of question and answer knowledge acquirement can be effectively reduced, and the manual workload is greatly reduced.

Description

technical field [0001] The present invention relates to the field of data processing, in particular, to a question-and-answer knowledge base generation method and computer equipment, and to a neural network training method and computer equipment. Background technique [0002] With the continuous development of Internet technology and the increasing amount of data, the question-answering knowledge system has played an increasingly important role in people's lives. The question-answer knowledge base in the current question-answer knowledge system is mainly constructed manually, which consumes a lot of manpower and material resources, and affects the application of the question-answer knowledge system from a single field to the whole field. [0003] In order to solve this major problem hindering the development of intelligent question answering technology, researchers have proposed some solutions. Some existing solutions try to use the matching method based on semantic templat...

AI Technical Summary

Problems solved by technology

[0004] In fact, most of the currently available semantic knowledge bases are general-purpose knowledge bases, and there are few industrial domain semantic knowledge bases, which require a lot of manpower to build

Obviously, this scheme does not reduce the difficulty of constructing the question-answering knowledge base

In addition, due to the limited types of problems in the problem database of this scheme, this scheme is only partially adaptable, and a large amount of manpower is still required to generate other types of problems

Images