Contextual Relationship Graphs for Targeted Content Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for providing targeted content, such as targeted advertising on web pages, face inefficiencies due to inadequate contextual analysis and the inability to handle large numbers of words in relation to each other, leading to inaccurate and non-optimal content selection.
Innovation Solution
A system and method utilizing a hierarchical predictive projection with contextual relationship graphs to select targeted content based on request-associated attributes, enabling efficient and accurate content selection without human intervention, by analyzing and scoring keywords and their relationships to determine the relative strength of classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the bucket of words approach is used for context classification, then the processing speed is fast, but the accuracy of content matching deteriorates due to lack of contextual relationships
Solution Approach 1:
The patent segments the text analysis process into multiple hierarchical levels: first identifying individual words, then grouping them into phrases, and finally analyzing relationships between phrases. This segmentation allows the system to maintain processing speed while progressively building contextual understanding at each level.
Solution Approach 2:
The patent introduces a new dimension of analysis by creating contextual relationship graphs that map relationships between words and phrases. This transforms the flat word-frequency analysis into a multi-dimensional structure that captures semantic relationships, thereby improving matching accuracy without sacrificing processing efficiency.
2Measurement precision
If natural language processing with contextual extraction is used, then the accuracy of content matching is improved, but the processing speed deteriorates due to prefiltering requirements
Solution Approach 1:
The patent performs preliminary action by pre-building contextual relationship graphs and phrase databases offline. This allows the system to have contextual extraction capabilities ready in advance, eliminating the need for time-consuming prefiltering during real-time operation and maintaining both accuracy and speed.
Solution Approach 2:
The system uses self-service by automatically generating contextual relationship graphs from the content itself without requiring manual prefiltering or human intervention. The contextual extraction is performed on-demand using the pre-built frameworks, allowing real-time processing while maintaining high accuracy.
3Measurement precision
If human involvement is added to match web pages and advertisements, then the accuracy of targeted content selection is improved, but the efficiency deteriorates due to manual processing requirements
Solution Approach 1:
The patent introduces an intermediary layer of contextual relationship graphs and automated matching algorithms that mediate between web page content and advertisement content. This intermediary system performs the matching function that would otherwise require human judgment, achieving both high accuracy and automated efficiency.
Solution Approach 2:
The patent replaces the mechanical system of human involvement with an automated computational system based on contextual relationship analysis. The system uses algorithms to evaluate and match content based on extracted contextual features, substituting human cognitive processes with automated mechanical computation that maintains accuracy while dramatically improving efficiency.
4Device complexity
If independent feature models like naïve Bayes classifier are used, then the computational complexity is reduced, but the ability to analyze relationships between large numbers of words deteriorates
Solution Approach 1:
The patent segments the analysis of word relationships into hierarchical levels (words, phrases, contextual relationships) rather than attempting to analyze all words simultaneously. This segmentation reduces computational complexity at each level while maintaining the ability to capture relationships between large numbers of words through the cumulative effect of hierarchical analysis.
Data Source
AI summary
An arrangement for providing targeted content includes data repositories storing information from which targeted content may be selected. The data repositories store at least one contextual relationship graph. The arrangement also includes an input/output interface through which a request for targeted content is made. The arrangement further includes a controller that receives the request for targeted content and selects targeted content using the contextual relationship graph. The controller further provides the selected targeted content through the input/output interface. An arrangement for determining the relative strength of a classification for a group of words includes memory for storing a contextual relationship graph for a given classification and a processor that receives the contextual relationship graph and a plurality of words to be analyzed by the processor, identifies occurrences of the relationships identified in the contextual relationship graph and determines the relative strength of classification based on the identified occurrences.