Text abstract generation method and device, electronic equipment and storage medium

Abstract

The invention is suitable for the technical field of artificial intelligence and data mining, and provides a text abstract generation method and device, electronic equipment and a storage medium. The method comprises the following steps: calculating a similarity score between sentences in a target text, and calculating a similarity score between the sentences by taking the sentences as nodes and the weight of the similarity score between the sentences as edges; constructing a graph structure model of the target text; carrying out iterative updating on the graph structure model by adopting a sorting algorithm, and judging whether the graph structure model subjected to the iterative updating meets a preset convergence condition or not; according to the importance score value of each node in the iteratively updated graph structure model, selecting a preset number of sentences corresponding to each node from high to low as candidate sentences of the abstract; and performing component compression processing on the candidate sentences according to a preset dependency analysis rule to generate an abstract of the target text. The method is low in cost, high in speed, few in consumed computing resources, few in abstract redundant information, correct in grammar and complete in semantics.

Description

technical field [0001] The present application relates to the technical fields of artificial intelligence and data mining, and in particular to a method, device, electronic equipment and storage medium for generating text abstracts. Background technique [0002] With the explosive growth of Internet information, how to effectively obtain the required information from the massive Internet information is the key technical issue of information retrieval at present. Text summarization refers to the key information extracted from a long, semantically complete article. Text summarization is very important in the process of information retrieval. Extracting key information through summarization can shorten the length of articles, reduce the interference of redundant information, effectively improve the efficiency of information retrieval, and greatly improve user experience. Currently, there are two existing algorithms for obtaining text summaries: extractive and generative. Most...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the embodiment of the present application provides a text abstract generation method, device, electronic equipment and storage medium, which can solve the problems of traditional extractive algorithms and generative algorithms that require a large amount of labeled text and high cost due to the use of supervised models. Problems and the traditional extractive algorithm has a lot of redundant information in the summary, and the traditional generative algorithm needs to generate word by word when generating text summaries, which is slow and consumes a lot of computing resources.

Images