Similarity calculation method for blog articles
A technology of similarity calculation and original text, applied in the field of similarity calculation for blog posts, it can solve the problem of not fully applicable to Weibo search engine applications, etc., to achieve timeliness and efficiency, reduce the number of matches, and achieve significant effects.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0037] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0038] A blog post contains both the original text and the forwarded text, so the similarity of the blog post should be determined by the original text and the forwarded text, but they all have some spam information that is weakly related to the blog post, such as links, emoticons, and personal names. Therefore, first preprocess the original text and forwarded text to remove spam information such as links, emoticons, and names, and then calculate the weight of each word by word segmentation, and then extract (n+m) words with relatively high weights as the content of this Weibo. Key words.
[0039] The keywords are further divided into two parts. The top n words with the highest weight are used as the core words of the blog post, and the remaining m words of the keywords are used as the second-level matching words of the blog post. The judgment basis is that ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com