A recommendation method for Chinese herbal medicine similar literature based on lda and vsm
A recommendation method and technology of Chinese herbal medicine, applied in the field of recommendation of similar documents of Chinese herbal medicine, can solve the problem of inability to mine similarity in text, and achieve the effect of fast and efficient similar recommendation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0016] The present invention is based on the Chinese herbal medicine similar document recommendation method of LDA and VSM, comprises the following steps:
[0017] 1. For the established Chinese herbal medicine literature database, for each document, based on the special dictionary of Chinese herbal medicine, IKAnalyzer is used to segment the document, filter out stop words, adjectives, prepositions and other useless terms, and keep verbs and nouns. After the word segmentation is completed, the word vector space of the entire Chinese herbal medicine literature database is constructed, and the constructed word vector space is numbered word by word to obtain a mapping dictionary.
[0018] 2. Vectorize each document based on the mapping dictionary to form a parameterized word vector, and then integrate the word vectors of all documents to form a "document-word" matrix.
[0019] 3. For the "document-word" matrix, set the hyperparameters α and β, use the topic model LDA to train, a...
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