Enterprise Relationship Mining via Frequent Item Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing enterprise knowledge graph systems provide only simple and incomplete representations of enterprise relationships, lacking depth and comprehensiveness, which limits their effectiveness in industry analysis, risk monitoring, and understanding the rise and fall of industries.
Innovation Solution
A method and device for mining enterprise relationships by acquiring and processing Internet data using a frequent item mining algorithm, identifying enterprise names through models like Hidden Markov or deep neural networks, and extracting relationships based on pre-established extraction rules or machine learning models, to obtain deeper and more comprehensive relational degrees among enterprises.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If industrial and commercial data is used to obtain enterprise relationships, then the data processing is simple, but the relationship representation is incomplete and lacks depth
Solution Approach 1:
The patent combines multiple data sources including industrial and commercial data with news data, financial data, and other Internet data to comprehensively construct enterprise relationships. This merging of diverse data sources resolves the contradiction by maintaining processing feasibility while significantly improving relationship completeness and depth
Solution Approach 2:
The patent creates a composite enterprise relationship knowledge graph by integrating different types of data (industrial and commercial data, news data, financial data) similar to creating composite materials. This composite approach enables the system to achieve both processing simplicity through unified methodology and relationship completeness through diverse data sources
2Loss of information
If multiple types of Internet data are acquired and processed using frequent item mining algorithms, then the enterprise relationship comprehensiveness is improved, but the system complexity increases
Solution Approach 1:
The patent segments the complex data processing task into distinct modules: data acquisition module, text extraction module, enterprise name identification module, and relationship extraction module. Each module handles a specific aspect of processing, making the overall complex system manageable and maintainable while achieving comprehensive relationship extraction
Solution Approach 2:
The patent introduces an intermediary enterprise name identification model (using techniques like Hidden Markov Models or deep neural networks) that bridges the gap between raw Internet data and relationship extraction. This intermediary component simplifies the overall process by standardizing the input for the relationship extraction stage
3Measurement precision
If enterprise names are identified using advanced models like Hidden Markov or deep neural networks, then the identification accuracy is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary text extraction and cleaning before enterprise name identification, preprocessing the data to reduce complexity. This preliminary action enables the use of advanced identification models with higher accuracy while reducing the actual processing time during the identification stage itself
Data Source
AI summary
A method, device, apparatus and computer-readable storage medium for mining an enterprise relationship. The method can include acquiring Internet data of multiple types, identifying enterprise names from the Internet data by an enterprise name identification model, performing data mining to the Internet data in a frequent item mining algorithm to obtain relational degrees among the enterprise names, and according to the relational degrees among the enterprise names, extracting the enterprise relationship from the Internet data by an extractor. A deeper and more comprehensive enterprise relationship can be obtained by performing data mining to Internet data of multiple types by using an enterprise name recognition model. By using the frequent items mining algorithm, enterprises among which there are higher relational degrees can further be obtained, so as to obtain a more accurate enterprise relationship.