Web Page Ad Placement Through Content-Similarity Grouping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current advertising systems face challenges in selecting suitable advertisements for specific website subpages due to the complexity of content diversity, user data privacy concerns, and the need for extensive computing resources, making it difficult to tailor ads to both user interests and website context effectively.
Innovation Solution
A method involving grouping similar web pages and analyzing their content using a Large Language Model to determine ad effectiveness based on click rates, without requiring personal user data, utilizing GPU computing for accelerated processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If user data is collected and processed to personalize advertising, then ad relevance to user interests is improved, but data privacy risks and processing complexity increase
Solution Approach 1:
The patent extracts only the necessary content information from web pages using AI models, eliminating the need to process comprehensive user data. By taking out only the essential features (content similarity metrics) rather than processing all user data, the system achieves ad relevance without the complexity and privacy risks of full user profile analysis
Solution Approach 2:
The patent introduces content similarity as an intermediary metric between web page content and advertising effectiveness. Instead of directly analyzing complex user behavior data, the system uses content similarity scores as a mediator to predict ad performance, simplifying the processing pipeline while maintaining relevance
2Measurement precision
If comprehensive user data is processed in real time, then ad personalization accuracy is improved, but computing resources and processing time increase
Solution Approach 1:
The patent performs preliminary content analysis and similarity computation before ad placement. By pre-processing web page content into similarity metrics, the system prepares data structures that enable fast ad selection without requiring real-time comprehensive data processing, thus improving productivity while maintaining accuracy
Solution Approach 2:
The patent transforms complex user data into simplified content similarity parameters. By changing the representation from detailed user profiles to content similarity scores, the system reduces the computational burden while preserving the essential information needed for accurate ad personalization
3Measurement precision
If detailed website context analysis is performed, then ad context relevance is improved, but data processing capacity requirements increase
Solution Approach 1:
The patent extracts only the essential content features from web pages using AI models, taking out only the necessary information for context analysis. By extracting only the essential features rather than processing all website data, the system achieves context relevance with reduced data volume and processing requirements
4Measurement precision
If ad effectiveness is measured through detailed user behavior tracking, then measurement precision is improved, but data protection compliance complexity increases
Solution Approach 1:
The patent extracts only the necessary content information for ad placement decisions, eliminating the need for comprehensive user behavior tracking. By taking out only essential content features rather than tracking detailed user behavior, the system achieves effectiveness measurement while reducing compliance complexity
Solution Approach 2:
The patent enables ads to be selected and optimized based on content similarity alone, without requiring active user data collection or consent. The system serves itself by using passive content analysis to drive ad placement, eliminating the need for complex GDPR compliance procedures while maintaining measurement capability
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a computer-implemented method for placing an advertisement on a website, comprising the following steps: capturing at least a portion of the respective content of a plurality of websites, transforming the captured content of the captured websites to obtain a description of the content of each website, creating groups of websites containing websites with such descriptions of the respective content that are similar to each other at least to a predetermined degree, placing the same advertisement on a plurality of websites of a first website group and a second website group, recording the number of clicks on the advertisement on the plurality of websites of the first website group and recording the number of clicks on the advertisement on the plurality of websites of the second website group.Comparing the number of clicks on the advertisement on the majority of websites in the first group of websites with the number of clicks on the advertisement on the majority of websites in the second group of websites, continuing to use the advertisement on the majority of websites in the group with the higher number of clicks, and discontinuing its use on the majority of websites in the group with the lower number of clicks. This provides a method for placing an advertisement on a website that requires fewer resources.