Social network body constructing method based on machine learning
A social network and machine learning technology, applied in the field of ontology construction, can solve the problems of unsatisfactory construction effect, failure to meet practical requirements, and inability to dig deep into the semantic relationship of tags.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0043] The present invention will be further described below in conjunction with embodiment and accompanying drawing.
[0044] The ontology construction method based on machine learning of the present invention comprises the following steps:
[0045] 1) Use crawler technology to grab tags from social networks. The number of label pairs in the original data set can be adjusted according to the needs of the ontology construction scale. The more label pairs in the original data set, the larger the scale of the final ontology construction
[0046] 2) Generate a training data set.
[0047] (2a) Use an existing random function to randomly generate m pairs of label pairs from the original dataset.
[0048] (2b) Manually select n pairs of label pairs with hyponymy relationship from the original data set. These n pairs of labels are evenly distributed throughout the original dataset, rather than concentrated in a certain region.
[0049] (2c) The ratio of m and n can be between 3:1...
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