Entity Property-Based Content Selection via Query Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current content selection methods for web pages rely heavily on keywords and synonyms, failing to effectively utilize entity properties and relationships to match user queries with relevant content, leading to suboptimal content display.
Innovation Solution
A system and method that utilize a data processing system with a query reference module to identify entities and generate query graphs, matching them with content selection criteria graphs to select content based on confidence scores and semantic relevancy, incorporating entity properties and relationships to determine suitable content for display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If content selection methods rely heavily on keywords and synonyms, then the implementation is simple, but the relevance and accuracy of content displayed is insufficient
Solution Approach 1:
The patent transforms the content selection approach by changing the fundamental parameters from keyword-based matching to entity property-based matching. It introduces new parameters such as entity types, relationships, and structured properties that enable more precise content relevance assessment while systematically managing the increased complexity through standardized data models.
Solution Approach 2:
The patent introduces entity graphs and structured data models as intermediary layers between user queries and content selection. These intermediaries transform unstructured keywords into structured entity representations, enabling accurate matching without directly comparing raw keywords, thus improving precision while managing complexity through abstraction.
2Reliability
If content selection uses basic keyword matching, then the processing speed is fast, but the semantic relevancy and user experience are suboptimal
Solution Approach 1:
The patent implements preliminary action by pre-processing and structuring content into entity graphs with defined properties and relationships before the actual content selection process. This advance preparation enables faster and more accurate matching during query processing, as the system doesn't need to perform complex semantic analysis in real-time, thus improving both reliability and productivity.
3Measurement precision
If the system processes multiple entity properties and relationships, then the content matching accuracy improves, but the computational complexity increases
Solution Approach 1:
The patent applies segmentation by breaking down complex entity matching into distinct, manageable components: entity identification, property extraction, relationship mapping, and criteria comparison. This modular approach allows the system to process multiple entity properties and relationships systematically, improving matching precision while controlling computational complexity through divided processing stages.
Data Source
AI summary
Systems and methods of the disclosure relate to selecting content via a computer network. A search query provided by a user device can be received. An entity of a search query, a corresponding confidence score, and a property can be identified via a data structure having information about entities. A match between a property of an entity of content selection criteria and the property of the entity of the search query can be determined. The content item can be selected as a candidate for display on the user device based on the match and the confidence score.