Keyword extraction method and device for document analysis and storage medium

• Main Authors: GAO MEIZHOU, WANG CHENYUAN, FU FENGZHI, LIU MINZHAI, YANG YONGJUN
• Format: Patent
• Language: Chinese; English
• Published: 15.09.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention relates to a keyword extraction method and device for document analysis and a storage medium, and relates to the technical field of text analysis. The method comprises the following steps: extracting candidate words from an original document to form a first word set according to a candidate word extraction rule determined by a preset phrase granularity; screening out a second word set from the first word set according to the first relevancy; generating prediction words for the original document by utilizing a prediction model to form a third word set; determining a union set of the second word set and the third word set; and screening the candidate keywords according to the second correlation degree and the deviation degree of the candidate keywords in the union set to obtain a keyword set of the original literature. The keywords are expanded in a mode of predicting model pre-vocabularies, diffusion of relevance of the keywords is achieved, expression modes of the keywords are enriched, and corp