Resource Matching System Using Query Log Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for providing relevant resources to users based on query logs and advertiser data are inefficient, as they fail to effectively filter and rank matching resources, leading to irrelevant or mismatched results.
Innovation Solution
A system that identifies example resources, evaluates query logs and advertiser data to find matching resources, filters them based on criteria such as geo-location, business size, spend data, and historical clicks, and ranks them for relevance, providing filtered and ranked results to consumers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If comprehensive filtering criteria are applied to match resources, then matching precision is improved, but device complexity increases
Solution Approach 1:
The system segments the resource matching process into distinct functional modules: query log evaluation module, advertiser creative evaluation module, advertiser keyword evaluation module, filtering module, and ranking module. Each module handles a specific aspect of the matching process, allowing comprehensive filtering criteria to be applied systematically without overwhelming system complexity.
Solution Approach 2:
The system introduces intermediary components such as the query log evaluator and advertiser data evaluator that act as mediators between the input resources and the final matching results. These intermediaries process and transform data according to multiple filtering criteria, enabling precise matching while managing complexity through structured intermediate processing steps.
2Reliability
If multiple evaluation criteria are used to filter matching resources, then resource relevance is improved, but processing time increases
Solution Approach 1:
The system performs preliminary evaluation of query logs and advertiser data before the actual resource matching process. By pre-processing and organizing evaluation criteria in advance, the system can apply multiple filtering conditions efficiently during the matching phase, reducing overall processing time while maintaining high resource relevance.
Solution Approach 2:
The system implements continuous processing pipelines where query log evaluation, advertiser creative evaluation, and resource matching occur in an integrated flow. This continuous action approach eliminates idle time between processing stages and maintains high resource relevance through uninterrupted application of multiple evaluation criteria.
3Measurement precision
If comprehensive query log and advertiser data evaluation is performed, then lead generation accuracy is improved, but computational energy consumption increases
Solution Approach 1:
The system extracts and evaluates only the most relevant features from query logs and advertiser creatives, rather than processing all available data. By identifying and focusing on key evaluation criteria such as query term frequency, advertiser creative quality metrics, and keyword relevance scores, the system achieves high lead generation accuracy with reduced computational energy consumption.
Data Source
AI summary
Methods, systems, and computer program products are provided for providing matching resources. One example method includes identifying example resources, evaluating query logs to determine queries including query terms that resolved to a given example resource, identifying matching resources other than the example resources that also were provided as a solution to the determined queries, filtering the matching resources based on one or more criteria to identify matching resources that are relevant to a consumer, and providing the filtered matching resources for output to the consumer.