Contextual Content Targeting System for Network Documents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing dynamic content retrieval systems face challenges in selecting relevant content for network documents, as they require advertisers to understand multiple ontologies and taxonomies, identify relevant keywords across different web sites, and constantly update keyword sets to maintain relevance, which is burdensome and inefficient.
Innovation Solution
Implementing contextual content targeting that allows advertisers to input their intent using natural language, with a computer system translating this intent into contexts based on historical behavior data and ontologies, automatically selecting relevant content for insertion into network documents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If advertisers manually identify and update keywords across multiple ontologies and taxonomies, then content relevance can be maintained, but the complexity and time required increases significantly
Solution Approach 1:
The patent introduces an intermediary system that acts as a mediator between advertisers and the complex ontology/taxonomy structures. This system automatically translates advertiser intent into relevant content selections without requiring advertisers to directly navigate or understand multiple ontologies and taxonomies, thereby maintaining content relevance while reducing the complexity burden on advertisers
Solution Approach 2:
The system enables self-service by automatically performing keyword identification, ontology mapping, and content selection tasks that would otherwise require manual advertiser intervention. The automated processes continuously maintain content relevance through intent-based matching, eliminating the need for advertisers to manually update keyword sets across different taxonomies
2Measurement precision
If advertisers constantly update keyword sets to maintain relevance, then content accuracy improves, but the time and effort required increases
Solution Approach 1:
The system performs preliminary actions by pre-establishing intent definitions and context mappings before content selection is needed. Advertisers define their intent once, and the system automatically applies this intent to select relevant content across multiple ontologies and taxonomies, eliminating the need for constant keyword updates while maintaining content accuracy
Solution Approach 2:
The system implements feedback mechanisms that automatically monitor content performance and relevance. When content accuracy needs improvement, the system receives feedback signals and automatically adjusts content selection based on the predefined intent, rather than requiring manual keyword updates. This closed-loop approach maintains precision while minimizing time investment
3Adaptability or versatility
If the system requires advertisers to understand multiple ontologies and taxonomies, then content selection can be customized, but the ease of operation decreases
Solution Approach 1:
The system introduces an intermediary layer that handles the complexity of multiple ontologies and taxonomies internally. Advertisers interact with a simplified intent-definition interface, while the intermediary automatically manages the complex mappings and translations across different taxonomies, thereby maintaining content selection flexibility while dramatically improving ease of operation
Solution Approach 2:
The system creates simplified copies or representations of complex ontology structures that are easier for advertisers to interact with. Instead of requiring advertisers to navigate actual complex taxonomies, the system uses simplified intent models that capture the essential meaning while abstracting away the underlying complexity, allowing flexible content selection without operational burden
Data Source
AI summary
Techniques for improving dynamic content retrieval are described. In an example, a system may receive a request for content. The request may be associated with an access by a computing device to a network document. The system may determine a context associated with the network document based on the request. The content may be pre-computed based on historical accesses to a network resource. The system may determine a match between the context and a pre-computed context that is associated with content and may select the content from a set of candidate content based on an intent description of a content provider and historical behavior data of visitors to the network resource. The intent description may be associated with a presentation of the content at the network resource. The system may provide an identifier of the content. The identifier may be usable to present the content at the computing device.