Knowledge base question-answering system construction method based on template matching and deep learning

Abstract

The invention discloses a knowledge base question-answering system construction method based on template matching and deep learning, and the method comprises the following steps: S1, designing and constructing a question-answering template, wherein when the question-answering template is designed, question-answering completeness must be achieved, each question possibly asked by a user must contain a corresponding question-answering template, and this part requires a designer to fully investigate business problems; s2, designing and constructing an ontology map, and designing the ontology map according to the entity data, the relational data, the scene business and the intention template; s3, constructing a marking layer; s4, constructing a trigger layer; s5, constructing a matching layer; s6, constructing an alignment layer; and S7, constructing a query layer. According to the invention, a mode of combining template matching and model prediction and combining ES search and model prediction is used, so that the coverage rate and the accuracy rate of the question-answering system are higher, the robustness of the question-answering system is enhanced, the diversity of questions is considered, the range and the form of questions and answers are expanded, and the question-answering system becomes richer.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence natural language processing, in particular to a method for constructing a knowledge base question answering system based on template matching and deep learning. Background technique [0002] There are currently two types of question answering systems based on knowledge bases: template-based question answering systems and model inference-based question answering systems. The template-based question answering system has a high accuracy rate, but it needs to write question and answer templates related to business scenarios in advance, and it is difficult to cover the flexible and changeable questions of users; although the model-based question answering system can cover more question forms and contents, it often Relying on a large amount of training data related to the scene, the ideal effect cannot be achieved in actual application. [0003] In addition to the main solution of the q...

AI Technical Summary

Problems solved by technology

[0006] 1. The above invention patents are only a question-and-answer method in the medical field, and it is difficult to build a more flexible question-and-answer system in combination with specific scenarios in various fields;

[0007] 2. The above-mentioned invention patent uses coding and reinforcement learning path to infer user intent, resulting in low accuracy of question and answer

[0008] 3. The question answering system in the above invention patent can only answer the inherent template answers corresponding to the questions in the knowledge base, and it is difficult to give specific quantitative answers

Images