Entity Relationship Criteria Generation for Content Targeting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current content distribution systems face challenges in generating effective selection criteria for content items, as they often rely on predefined keywords and bids, which may overlook non-intuitive relationships between entities, limiting the ability to create focused and robust advertising strategies.
Innovation Solution
The method involves receiving a seed entity and iteratively updating a set of selected entities based on relationship dimensions, allowing users to explore and select additional entities and relationships, thereby defining a concept focus that generates selection criteria from emergent relationships, and providing key metrics for performance estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If predefined keywords are used for content item selection, then the system operation is simple, but the selection criteria completeness deteriorates as non-intuitive relationships are overlooked
Solution Approach 1:
The patent transitions from one-dimensional keyword matching to multi-dimensional entity relationship exploration. The system presents multiple relationship dimensions (e.g., hierarchical, associative, contextual) that allow advertisers to navigate entity relationships across different dimensions, discovering non-intuitive connections that predefined keywords would miss.
Solution Approach 2:
The system dynamically adapts the entity relationship exploration based on user selections. As advertisers select entities and relationship dimensions, the system iteratively updates and refines the selection criteria, transforming a static keyword list into a dynamic, evolving set of targeted criteria that captures emerging relationships.
2Reliability
If the system explores non-intuitive relationships between entities, then the selection criteria robustness improves, but the device complexity increases
Solution Approach 1:
The patent introduces an intermediary entity relationship map that mediates between the advertiser's initial keywords and the final selection criteria. This intermediary structure organizes entities and their relationships in a manageable format, allowing the system to explore complex non-intuitive relationships without overwhelming the user or requiring excessive computational complexity.
Solution Approach 2:
The system implements iterative refinement where advertisers can progressively explore relationship dimensions at different depths. Rather than requiring complete exploration of all possible relationships at once, the system allows partial exploration through multiple iterations, adding relationship dimensions and entities gradually until the desired selection criteria robustness is achieved.
3Measurement precision
If advertisers manually define selection criteria, then the criteria precision can be high, but the productivity decreases due to time-consuming processes
Solution Approach 1:
The system performs preliminary action by automatically generating an initial entity relationship map and pre-computing relationship dimensions based on the advertiser's seed keywords. This preliminary processing reduces the workload for subsequent manual refinement, allowing advertisers to start with a prepared framework rather than building selection criteria from scratch, thus improving productivity without sacrificing precision.
Solution Approach 2:
The system implements feedback mechanisms where the exploration of entity relationships provides information that refines the selection criteria. As advertisers interact with the entity relationship map and select entities, the system uses this feedback to iteratively improve the selection criteria precision, maintaining high accuracy while reducing the time required through intelligent guidance and automated refinement.
Data Source
AI summary
Selection of content selection criteria based on entities related by relationship dimensions. In one aspect, a method receives a selection of a seed entity described in entity relation data, the entity relation data defining instances of entities, and for each entity one or more relationship dimensions; generating a set of selected entities; iteratively updating the set of selected entities, each iteration comprising: determining a set of relationship dimensions from the entities in the set of selected entities, each relationship dimension in the set being selected from the one or more relationship dimensions of the entities in the set of selected entities, receiving a selection of one of the relationship dimensions and in response: determining a set of candidate entities from the relationship dimensions and in response to receiving a selection of one or more candidate entities, updating the set of selected entities to include the one or more candidate entities.