Complex question knowledge base question answering method based on embedded and candidate subgraph pruning
A technology for complex problems and candidate subgraphs, applied in the field of data processing, can solve problems such as reducing the range of candidate subgraphs
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0093] The invention discloses a complex question intelligent question answering model SPE-QA based on question and answer path context coding. Its basic structure diagram is shown in figure 2 ,in, figure 2 (a) including candidate subgraph pruning and semantic matching models based on tail entities; figure 2 (b) Include candidate subgraph pruning and semantic matching model based on relation type. The SPE-QA model proposed by this method can be specifically applied to intelligent question answering based on knowledge graph. Its overall implementation process structure is as follows figure 1 As shown, this embodiment takes the query, pruning, semantic matching, and answering on the graph constructed by FB13 as an example, and the specific steps are as follows:
[0094] Step 1: According to the question q: what faith does George_of_saxony’s child have? Subject entity e identified s :George_of_saxony.
[0095] Step 2: Obtain candidate subgraphs to form a question and ans...
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