Unsupervised Hierarchical Graph Construction for Search Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines often return irrelevant results due to outdated taxonomy graphs, especially in dynamic or multi-domain environments, where manual updates are impractical and costly.
Innovation Solution
An automated method for constructing a hierarchical graph from search queries and their semantic relationships, using pairwise relation calculations and edge adjustments to create a directed acyclic graph or tree graph that reflects the ontological meanings of terms, allowing for unsupervised and dynamic search engine optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual updates are used to maintain taxonomy graphs, then the accuracy and relevance of search results are improved, but the time and cost required for updates increase significantly
Solution Approach 1:
The system automatically updates the taxonomy graph by analyzing search query data and user behavior patterns without requiring manual intervention. The taxonomy graph self-updates by detecting emerging terms, changing relationships, and evolving ontological structures from the search data, eliminating the need for manual maintenance while keeping search results relevant and accurate
Solution Approach 2:
The system uses search query data and user interaction patterns as feedback to continuously refine and update the taxonomy graph. By analyzing which terms are searched, how users refine their queries, and what results they click on, the system automatically adjusts the taxonomy structure to improve search relevance over time without manual input
2Measurement precision
If manual updates are used to maintain taxonomy graphs, then the accuracy and relevance of search results are improved, but the cost of maintenance increases
Solution Approach 1:
The system performs automatic taxonomy graph maintenance by processing search data and updating relationships autonomously, eliminating the need for human experts to manually curate the taxonomy. This self-maintaining approach significantly reduces labor costs and operational expenses while sustaining high search result relevance
Solution Approach 2:
The system replaces the manual mechanical process of expert taxonomy curation with an automated computational process that analyzes search data patterns. Instead of human experts manually reviewing and updating taxonomy relationships, algorithms automatically detect and implement updates based on search behavior, reducing maintenance costs while maintaining accuracy
3Adaptability or versatility
If taxonomy graphs are updated frequently to reflect changing ontological domains, then the relevance of search results is improved, but the complexity of the system increases
Solution Approach 1:
The taxonomy graph automatically adapts to changing ontological domains by monitoring search query patterns and user behavior. When new terms emerge or relationships change, the system self-updates the taxonomy structure without requiring complex external management systems, maintaining high adaptability while keeping system complexity manageable
Solution Approach 2:
The taxonomy graph is designed as a dynamic structure that can evolve over time based on search data. Relationships between terms are not fixed but can be created, modified, or removed automatically as search patterns change, allowing the system to adapt to new domains and ontologies while maintaining a relatively simple update mechanism
Data Source
AI summary
A method involves receiving search queries, having search terms, submitted to at least one computerized search engine. For each query, a corresponding pairwise relation in the search queries is calculated. The corresponding pairwise relation is a corresponding probability of a potential edge relationship between at least two terms. Thus, potential edges are formed. A general graph of the terms is constructed by selecting edges from the potential edges. The general graph is nodes representing the terms used in the search queries. The general graph also is edges representing semantic relationships among the nodes. A hierarchical graph is constructed from the general graph by altering at least one of the edges among the nodes in the general graph to form the hierarchical graph.