Search Result Interleaving via Target Ratio Exposure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines struggle to accurately reflect the relative relevance of search results from disparate information formats, such as auction, known fixed-price, and unknown fixed-price formats, due to non-comparable scoring systems, leading to suboptimal presentation of search results.
Innovation Solution
A method and system that determine the order of search results based on a target ratio of exposure percentages for each format, optimizing the presentation by iteratively selecting items to achieve a desired ratio, such as 60% for auction, 30% for known fixed-price, and 10% for unknown fixed-price formats, while dynamically adjusting these ratios based on revenue monitoring to maximize revenue generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search results from disparate information formats are sorted using their respective scoring algorithms, then each format's items are ranked according to its own relevance criteria, but the scores from different formats become non-comparable and the overall relevance accuracy deteriorates
Solution Approach 1:
The patent transforms the scoring system by introducing a common reference scale that converts scores from different information formats into comparable parameters. Instead of maintaining separate scoring systems for auctions and fixed-price items, the system recalibrates scores against a unified relevance metric, enabling direct comparison while preserving format-specific ranking nuances.
Solution Approach 2:
The patent introduces a intermediary normalization layer that acts as a mediator between disparate scoring algorithms. This intermediary component translates scores from different formats into a common language, allowing the search engine to compare and rank items across formats without losing the unique characteristics of each format's relevance criteria.
2Ease of operation
If search results are presented in a uniform format, then the presentation simplicity is improved, but the ability to optimize for different information formats and their unique characteristics deteriorates
Solution Approach 1:
The patent applies local quality by allowing different presentation formats for different information types within the same search results. Auction items, fixed-price items, and other formats can each display their characteristic information (bids, prices, timers) in format-appropriate ways while maintaining overall result list coherence and uniform positioning.
3Productivity
If the search results list is optimized to maximize revenue by favoring high-revenue formats, then the revenue generation is improved, but the accurate reflection of relative relevance across all formats deteriorates
Solution Approach 1:
The patent implements dynamic adjustment of result presentation based on multiple factors including revenue potential and relevance. The system can adaptively modify the composition and ordering of search results in real-time, balancing revenue optimization with relevance accuracy by adjusting the weight given to different formats based on current query context and performance metrics.
Data Source
AI summary
A method and system for determining an order of presentation of the search results is provided. An example system comprises a search request detector, a search engine, and an intermingler. The search request detector may be configured to receive a search request, and the search engine may be configured to determine search results based on the search request. The search results may comprise a first set of items of a first type and a second set of items of a second type. The number of items in the first set and the number of items in the second may reflect a predetermined target ratio. The intermingler may be configured to determine an order of presentation of the search results in a list of search results based on the target ratio.