Video Ad Targeting via User Search Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for identifying relevant content for advertisements during video playback are manual, time-consuming, and require explicit metadata, which can discourage advertisers from using video advertising services.
Innovation Solution
A system that aggregates and analyzes user search requests during and after video playback to automatically identify products associated with the content, using a sliding temporal window to correlate search behavior with video playback, allowing for dynamic selection and display of relevant advertisements without the need for explicit metadata.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual tagging of content is used to identify products, then identification accuracy is improved, but time consumption and cost increase
Solution Approach 1:
The system enables content to self-annotate by automatically extracting product information from user search queries and interactions. Instead of manual tagging, the content identification process serves itself by leveraging aggregated user behavior data to generate and update product associations autonomously.
Solution Approach 2:
The patent replaces the mechanical process of manual tagging with an automated computational system that processes user search queries, clickstream data, and interaction patterns to identify products in content. This substitution eliminates human labor while maintaining or improving identification accuracy through data-driven insights.
2Extent of automation
If visual analysis or screen scraping is used to identify content, then automated identification is achieved, but processor intensity and computational resources increase
Solution Approach 1:
The system introduces user search queries and interaction data as an intermediary layer between content and product identification. Instead of directly analyzing video frames or content visuals through intensive processing, the patent uses user-generated search data as a mediator to infer product associations, significantly reducing computational requirements.
Solution Approach 2:
The patent extracts product identification information from user search queries and interaction patterns rather than extracting visual features from content itself. This extraction approach shifts the computational burden from analyzing content to analyzing user behavior data, which is more efficient and scalable.
3Measurement precision
If explicit metadata is required for advertising relevance, then advertisement targeting precision is improved, but device complexity and implementation difficulty increase
Solution Approach 1:
The system automatically generates and maintains product-metadata associations by processing user search queries and interactions. Content and advertising systems self-update their understanding of product relationships without requiring manual metadata creation or complex configuration, simplifying implementation while maintaining targeting precision.
Solution Approach 2:
The patent performs preliminary aggregation and analysis of user search data to pre-establish product associations with content before advertising delivery. This preliminary action creates a ready-to-use mapping between content and relevant products, eliminating the need for complex real-time metadata processing during ad serving.
4Measurement precision
If user search data is aggregated and analyzed in real-time, then product identification accuracy is improved, but data processing time and computational resources increase
Solution Approach 1:
The system performs preliminary aggregation of user search data and pre-computes product associations during off-peak periods or in batch processes. By preparing this data structure in advance, the system can quickly retrieve pre-computed associations during real-time ad serving without incurring heavy processing delays.
Solution Approach 2:
The patent segments the data processing workflow into distinct phases: data collection, aggregation, analysis, and retrieval. By dividing the process into manageable segments that can be executed at different times and with different computational intensities, the system balances accuracy requirements with processing time constraints.
Data Source
AI summary
A method for identifying products associated with items of content, including: receiving, by a server from a first client device, a first request for a first item of content; retrieving, by the server from data storage, the first item of content in response to the first request for the first item of content; retrieving, by the server from data storage, an identification of an Internet search request transmitted by a second client device within a predetermined temporal window of playback of the first item of content by the second client device; retrieving, by the server from data storage, a second item of content selected in response to the Internet search request transmitted by the second client device; and providing, by the server to the first client device, the first and second items of content.