Keyword Extraction Using TextRank and TFIDF with Title Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing keyword extraction methods, such as TextRank, TFIDF, and LDA, do not adequately consider the text name and title, leading to incomplete and less accurate keyword extraction.
Innovation Solution
A keyword extraction method that combines the TFIDF and TextRank algorithms with the inclusion of text name and title features, using a trained keyword extraction model to improve the accuracy and recall of keyword extraction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional keyword extraction methods (TextRank, TFIDF, LDA) are used, then the extraction process is simple and fast, but the accuracy and recall rate are insufficient because text name and title are not considered
Solution Approach 1:
The patent combines multiple extraction methods (TextRank, TFIDF, and title/name-based extraction) into a unified keyword extraction system. The results from different methods are integrated and ranked to produce the final keyword list, thereby improving accuracy while managing complexity through systematic integration
Solution Approach 2:
The patent performs preliminary extraction of keywords using TextRank and TFIDF algorithms before the final ranking stage. Additionally, text names and titles are pre-processed and segmented into words that are then used as important features in the subsequent ranking process, allowing these methods to contribute their results in advance
2Reliability
If text name and title are included in the extraction process, then important keywords are captured with higher recall rate, but the processing time and computational complexity increase
Solution Approach 1:
The patent performs word segmentation on text names and titles in advance, preparing these important features before the main keyword extraction and ranking process. This preliminary processing allows the system to efficiently incorporate name and title information without significantly increasing the overall processing time
Solution Approach 2:
The patent focuses computational resources on processing only the text name and title portions separately from the main body, rather than applying complex processing to the entire document. This partial action approach captures the most important keywords from structured parts of the document while avoiding unnecessary computational overhead on less critical content
Data Source
AI summary
Provided are a keyword extraction method applicable to a Word text, an electronic device, and a computer-readable storage medium. The method includes: acquiring a text and extracting a body of the text; extracting a set number of keywords in the body by a TFIDF algorithm and a set number of keywords in the body by a TextRank algorithm, respectively; acquiring a text name and a text title of the text and segmenting the text name and the text title into words of the text name and words of the text title; constructing text feature vectors of the text and inputting the text feature vectors into a trained keyword extraction model; and extracting a keyword set from the keywords extracted by the TextRank algorithm by using the keyword extraction model to achieve text keyword extraction.