Contextual Network Graph for Semantic Search Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search engines are inaccurate in searching enterprise data as they fail to consider the semantic meaning of keywords, leading to incorrect results due to the lack of contextual understanding of business objects and documents.
Innovation Solution
A meta-model semantic network is generated to determine relationships between objects, creating a contextual network graph with unique identifiers for nodes and edges, which provides semantic meaning to enterprise data, allowing for accurate retrieval of relevant information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional search engines use keyword matching to search enterprise data, then the search process is simple and fast, but the search accuracy is poor due to lack of semantic understanding
Solution Approach 1:
The patent introduces a semantic network as an intermediary layer between the search engine and enterprise data. This semantic network contains business objects, their attributes, and relationships, serving as a mediator that translates keyword searches into semantically meaningful queries. The semantic network enables the system to understand the meaning and context of keywords without requiring complex changes to the core search engine architecture.
Solution Approach 2:
The patent segments the search system into distinct components: the semantic network (containing business objects and relationships), the search engine, and the data sources. By separating the semantic understanding function into an independent semantic network layer, the system achieves improved search accuracy without making the entire system unnecessarily complex. Each component has a specific function and can be developed independently.
2Reliability
If conventional search engines search only by keyword matching, then the implementation is simple, but the results are inaccurate due to ignoring contextual relationships between business objects
Solution Approach 1:
The semantic network acts as an intermediary data structure that organizes business objects, attributes, and relationships in a structured manner. This intermediary layer provides reliable semantic context without requiring complex relationships to be embedded directly in the search engine or source data systems.
Solution Approach 2:
The patent creates a semantic network that is a simplified copy or representation of the enterprise data structure. Instead of working with the full complexity of actual enterprise data systems, the semantic network captures essential business objects, attributes, and relationships in a manageable format that enables accurate searching while maintaining implementation simplicity.
Data Source
AI summary
A method and apparatus for determining relationships between objects in a meta-model semantic network is described. A contextual network graph comprising nodes and edges representing semantic objects and semantic relationships is generated from a meta-model of business objects from the meta-model semantic network. The contextual network graph is used to generate a unique identifier for each node and associated edge. The unique identifiers are used to compute information of cost and energy between the nodes. The information is stored in a meta-model semantic network database.