Entity relationship extraction method based on multi-target fusion
An entity relationship, multi-objective technology, applied in the field of natural language processing, can solve the problems of low accuracy, low accuracy, and different user cognition in user portrait discovery and matching, achieve accurate entity relationship extraction methods, and improve accuracy. Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0055] An entity relationship extraction method based on multi-objective fusion, such as figure 1 shown, including the following steps:
[0056] Include the following steps:
[0057] Step 1.1: Determine the validity of the collected data.
[0058] Step 1.2: Determine the Keyword training corpus of the user portrait entity relation word set.
[0059] In the present embodiment, personal user messages in WeChat, Tencent QQ, and whatsapp are selected and released dynamically to form the training corpus Keyword, which contains a total of 140,000 texts.
[0060] Step 1.3: Build a specific user portrait entity relationship word set.
[0061] Include the following steps:
[0062] Step 1.3.1: Construction of word vectorization model.
[0063] Include the following steps:
[0064] Step 1.3.1.1: For the Keyword corpus obtained in Step 1.2, use LSTM+CRF to segment all the text in the Keyword to obtain a single-sided user portrait after word segmentation.
[0065] Step 1.3.1.2: Scre...
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