Cross-Industry Knowledge Graph Construction with Standardized Attributes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing knowledge graphs are limited to describing relations within a single domain and fail to establish connections between entities across different industries, leading to inadequate cross-industry recommendations and applications.
Innovation Solution
A method and apparatus for constructing a cross-industry knowledge graph by obtaining a target entity identifier, determining its industry type label, and using a public database to obtain attribute values, which are then used to construct a knowledge graph that connects entities across various industries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a knowledge graph is constructed using traditional methods within a single domain, then the construction process is simple and manageable, but the knowledge graph cannot establish connections between entities across different industries
Solution Approach 1:
The patent segments the knowledge graph construction process into distinct modules: entity recognition module, industry type identification module, attribute extraction module, and relation construction module. Each module handles a specific aspect of the construction process, making the overall complex task manageable while enabling cross-industry connections through standardized interfaces between modules
Solution Approach 2:
The patent creates a universal knowledge graph framework that can handle multiple industries simultaneously. The system uses industry type labels and standardized attribute schemas that can be applied across different domains (e.g., electronics, appliances, furniture), allowing the same construction process to work universally across industries while maintaining the ability to establish cross-industry relations
2Adaptability or versatility
If industry type labels and attribute tables are introduced to enable cross-industry knowledge graph construction, then entities from different industries can be connected, but the data processing complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-defining industry type labels, industry attribute tables, and entity-attribute correspondence relationships before the actual knowledge graph construction. This preparation work is done once and reused across multiple construction tasks, reducing the processing complexity during actual operation while maintaining cross-industry capability
Solution Approach 2:
The patent introduces industry type labels as intermediary elements that mediate between entities from different industries. These labels serve as a common language that allows entities from diverse domains to be connected through standardized attribute comparisons, simplifying the cross-industry connection process
3Loss of information
If a comprehensive attribute extraction process is used to obtain detailed entity information from public databases, then the knowledge graph becomes more informative and useful for recommendations, but the time and computational resources required increase
Solution Approach 1:
The patent applies partial action by extracting only the most relevant attributes for each entity based on its industry type label, rather than extracting all possible attributes. The system identifies and extracts only the necessary attributes needed for cross-industry comparison and recommendation, reducing extraction time while maintaining sufficient information completeness
Data Source
AI summary
The disclosure relates to a method and apparatus for knowledge graph construction, a storage medium, and an electronic device. The method comprises: obtaining a target entity identifier and determining an industry type label corresponding to the target entity identifier; determining a target industry attribute table based on a predetermined correspondence among the industry type label, an industry type, and an industry attribute table; obtaining target attribute values of the target entity identifier from a public database based on respective target attribute names in the target industry attribute table, to obtain a target attribute of the target entity identifier, wherein the target attribute characterizes a key-value pair consisting of the target attribute name and the target attribute value; and constructing a knowledge graph based on an entity characterized by the target entity identifier, the industry type label, and the target attribute.