Intelligent question and answer reasoning method and system based on natural language entity relationship

Abstract

The invention discloses an intelligent question and answer reasoning method and system based on a natural language entity relationship, and belongs to the field of natural language processing. The method the following steps: performing word segmentation and entity word extraction on each statement in a corpus; taking natural statements as edges of entity association to form entity relationships, and summarizing entity connection relationships in the corpus to form a semantic network database based on the natural language entity relationships; designing an intelligent reasoning deep learning model based on a BERT pre-training language model and a graph neural network; inputting an entity connection diagram related to questions submitted by a user into a network for reasoning, and screening the results through a multi-layer perceptron to give a final answer. Herein, the entity relation database is automatically constructed through any given natural language text corpus, entity extraction and labeling through a manual intervention means are avoided, and answers are automatically found and inferred by analyzing complex questions of the user, so that the user is helped to obtain required results more quickly and more accurately.

Description

technical field [0001] The invention belongs to the field of natural language processing, and more specifically relates to an intelligent question-answer reasoning method and system based on natural language entity relations. Background technique [0002] With the vigorous and rapid development of the information industry, people's demand for information search and analysis in various fields is also increasing day by day. Facing the daily increase of information and content on the Internet at an alarming rate, how to quickly retrieve what people want from the explosive information has become increasingly important and urgent. This involves the trade-off between ease of use and accuracy when querying: on the one hand, although you can design and use a structured query language to accurately describe your goals and quickly obtain the desired results, but master and flexibly apply These professional query languages ​​will increase the learning cost sharply, so they are not sui...

AI Technical Summary

Problems solved by technology

A highly structured corpus is more convenient for node retrieval and is also conducive to automatic reasoning, but its disadvantages are that it is difficult to generate large-scale and maintain data timeliness updates, and it cannot be well sampled in the face of natural language with complex semantics It is even more difficult to produce a densely connected network structure data, especially in the face of actual needs, and it is becoming more and more unrealistic to face these huge amounts of data

Images