Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A knowledge map management method and system based on semantic space mapping

A technology of knowledge graph and space mapping, applied in electrical digital data processing, special data processing applications, instruments, etc., can solve problems such as poor adaptability, unreasonable processing methods, and difficulty in knowledge graph management.

Inactive Publication Date: 2017-07-07
FUDAN UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, what is finally extracted in the current knowledge graph construction is a deterministic relationship representation, and this deterministic description is not adaptable to word deformation, synonym change, grammatical form change, etc., such as two semantic Since similar edges are described by different words, they will be regarded as two completely different edges. This processing method is not only unreasonable, but also brings problems to the management of knowledge graphs such as edge / node clustering, edge / node clustering, and edge / node clustering. Node deduplication, edge / node labeling, etc. bring huge difficulties, which affect the effective application of knowledge graphs

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A knowledge map management method and system based on semantic space mapping
  • A knowledge map management method and system based on semantic space mapping
  • A knowledge map management method and system based on semantic space mapping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] Demonstrate the specific embodiment of the present invention with example below, each module of system is processed as follows successively:

[0083] (1) Semantic vector construction

[0084] Based on the text corpus of the entire English Wikipedia (http: / / www.wikipedia.org / ), Word2Vec is used for training, and the vector dimension of the training output is 500 dimensions.

[0085] (2) Semantic Space Mapping

[0086] For the words on the edge / node, after removing the stop words, take the corresponding semantic vector from the trained semantic vector library, and then perform vector accumulation to obtain the semantic vector representation of the edge / node.

[0087] (3) Semantic clustering

[0088] (3.1) Edge Semantic Clustering

[0089] Input example, the format is:

[0090] Sequence number: {node 1}, {edge}, {node 2}

[0091] 1: {Shanghai}, {large city}, {China}

[0092] 2: {ipad}, {product}, {Apple}

[0093] 3: {Barack Obama}, {president}, {USA}

[0094] 4: {K...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical fields of text semantic processing and semantic web, and specifically relates to a knowledge graph management method and system based on semantic space mapping. The method of the present invention includes: semantic vector construction, semantic space mapping, and knowledge map management; the knowledge map management further includes three types: semantic clustering, semantic deduplication, and semantic labeling. For the edges / nodes of the knowledge graph, first project the text unit describing it to the semantic space, and obtain its vector representation in the semantic space through vector accumulation; on this basis, realize multiple management tasks of the knowledge graph; the system It includes three modules: corresponding semantic vector construction, semantic space mapping, and knowledge map management. The invention overcomes the shortcomings of the traditional knowledge map management method that is sensitive to factors such as word deformation, synonym change, and grammatical form change when performing semantic comparison, and the way of vector accumulation makes it easy to cope with the difference in the number of words, and it is easy to realize further Knowledge map management tasks such as semantic clustering, semantic deduplication, and semantic annotation.

Description

technical field [0001] The invention belongs to the technical fields of text semantic processing and semantic web, and in particular relates to a knowledge map management method and system based on semantic space mapping. Background technique [0002] Building a knowledge graph is a major project in the era of big data. It can associate messy data and organize it into structured knowledge for users. This feature determines that it will have important applications in many fields. For example, at present The search engine is based on keyword matching, and when the knowledge map is established, after entering a keyword, it can return the keyword's attributes, categories, and other related information such as the relationship between entities, so that It can provide users with the information they need more accurately and comprehensively. The knowledge map is the cornerstone of a series of applications such as semantic search, machine automatic question answering, Internet adve...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/27G06F17/30
Inventor 王晓平肖仰华汪卫
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products