Method and system used for generating knowledge graphs

A knowledge map and knowledge technology, applied in the field of knowledge map generation, can solve problems such as the inability to generate knowledge maps, and achieve the effect of saving labor costs

Inactive Publication Date: 2017-01-25
CHINA PETROLEUM & CHEM CORP +1
View PDF7 Cites 71 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem solved by the present invention is to overcome the technical defect in the prior art that the know

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
  • Method and system used for generating knowledge graphs
  • Method and system used for generating knowledge graphs
  • Method and system used for generating knowledge graphs

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0056] Example one

[0057] figure 1 It is a flowchart of the steps of the method for generating a knowledge graph provided by this embodiment. The method generates an initial knowledge graph based on the initial knowledge graph framework and seed knowledge sets that include the attributes and association relationships between named entity types (step S110). Specifically, a common knowledge classification system in the industry can be used to perform the named entity Classification, and establish a binding framework for various types of petroleum exploration knowledge according to the knowledge form and the conceptual categories of various entity objects (project category, geological object category, and geological age category). This constraint framework stipulates whether there are (potential) association relationships between named entity types in multiple dimensions, and vividly and intuitively displays the relationships among various knowledge in the field of petroleum expl...

Example Embodiment

[0073] Example two

[0074] image 3 It is a schematic structural diagram of the system for generating a knowledge graph provided by this embodiment. The system includes an initialization unit, a type judgment unit (not shown in the figure), a single image-text knowledge item recognition unit, a graphic-text collection knowledge item recognition unit, and a correction unit.

[0075] Among them, the single graphic knowledge item recognition unit includes a single text knowledge discovery and extraction unit and a single image knowledge discovery and extraction unit. The unit of knowledge discovery and extraction in a single text consists of two consecutive modules: a named entity recognition module in a single text and a named entity association relationship discovery module in a single text.

[0076] The main purpose of the named entity recognition module in a single text is to recognize named entities involved in a single text. Based on the existing professional dictionaries in t...

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 discloses a method and system used for generating knowledge graphs. The method includes: generating the initial knowledge graphs; judging types of graphic units; identifying association relations among named entities in the singular graphic unit by taking an initial knowledge graph framework as a constraint condition and on the basis of the types of the graphic units; extracting the association relations among newly-added named entities and the named entities in a graphic unit set to form candidate knowledge items; modifying the candidate knowledge items and updating the initial knowledge graphs according to the modified candidate knowledge items. The association relations among the multiple and abundant named entities are automatically discovered, extracted and organized from a huge number of graphic datum by the aid of computers starting from the basic knowledge graph framework and a small seed-knowledge set, a knowledge graph structure can be rapidly, effectively and elaborately presented after determination of an expert system, and a great deal of labor cost is obviously saved in the process for generating the knowledge graphs.

Description

technical field [0001] The present invention relates to the technical field of computer graphics and text processing, in particular to a method and system for generating a knowledge map. Background technique [0002] Text is the most basic and commonly used information carrier. With the increasing popularity of the Internet, text information expands rapidly. Therefore, it is necessary to effectively organize the knowledge in the text. Especially in professional fields such as geological exploration, it is often necessary to discover knowledge that should be collected systematically from massive text data, and then structure the collected knowledge for future query and modification. [0003] In the prior art, knowledge is often organized through knowledge graphs (or knowledge networks). The knowledge map (network) is generally generated based on some general methods and displayed through a series of visualization methods. The more commonly used methods are co-occurrence a...

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
IPC IPC(8): G06T11/60
Inventor 唐先明陶鹏王晓丽邓达康郭攀红韩宝东陈长胜赵志成成尧
Owner CHINA PETROLEUM & CHEM CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products