Weighted classification method for disaster information importance of blog articles based on deep learning and XGBoost algorithm
A technology of deep learning and classification method, applied in the direction of text database clustering/classification, digital data information retrieval, calculation, etc., can solve the problem of slow cycle of incident rescue and achieve the effect of accurate classification performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0041] The present invention is described in detail below in conjunction with accompanying drawing and embodiment Step (1) receives social media text data and preprocessing
[0042] The training data set used in the present invention is a labeled data set about disaster information officially provided by TREC, which is Twitter text data, but the present invention is not limited to tweets, and can also be applied to other classifications, such as WeChat, Weibo text data on social platforms. The data set contains 30,000 pieces of text data that have been labeled with information categories and warning categories. The information categories and warning categories are the official category tables provided by TREC. There are 25 information categories, including request categories (need help / information, Request for search and rescue), call-to-action (transfer personnel / volunteers, etc.), report (news / weather, etc.), others (discussion / emotion, etc.), each piece of data can contain ...
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