Search Engine Scoring Adjustment for Query Breadth Bias
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search engines face issues in accurately determining the popularity of documents due to over-representation caused by broad search queries, leading to skewed data and difficulty in assessing user behavior from result sets.
Innovation Solution
The system adjusts the scoring measure for search results by deweighting popularity measures based on the breadth of previously-executed search queries, using metrics such as the quantity of results returned and the frequency of query usage to de-emphasize artificially high rankings from broad queries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If a search engine returns a large number of documents for a broad query, then the search engine can provide comprehensive results, but the popularity count for each result is artificially high due to over-representation from broad queries
Solution Approach 1:
The patent applies parameter changes by modifying the popularity measure based on query breadth characteristics. When a query is identified as broad (returning a large number of results), the system adjusts the popularity count by applying a discount factor or weighting adjustment. This changes the parameter of popularity measurement to account for the artificial inflation caused by broad queries, thereby resolving the contradiction between returning comprehensive results and maintaining accurate popularity measures.
2Adaptability or versatility
If documents from broad queries are included in the result set, then the search engine can capture diverse topics, but the documents are over-represented in popularity counts and skew user behavior data
Solution Approach 1:
The patent introduces an intermediary mechanism that sits between the search results and the popularity measurement process. This intermediary component analyzes query characteristics (specifically query breadth) and applies appropriate adjustments to popularity counts. The intermediary acts as a mediator that preserves the diversity of search coverage while correcting the distortion in popularity data, allowing the system to maintain both broad search coverage and accurate user behavior analysis.
3Productivity
If the search engine uses impression count or click count as popularity measures, then the system can quantify user engagement, but the measures are insufficient when documents are over-represented due to broad queries
Solution Approach 1:
The patent implements a feedback mechanism that continuously monitors query characteristics and adjusts popularity measures accordingly. When the system detects that a query is broad (returning a large number of results), it feeds this information back into the popularity calculation process to apply appropriate discounts or adjustments. This feedback loop enables the system to maintain reliable popularity measures while still utilizing impression and click count data, resolving the contradiction between measurement capability and precision.
Data Source
AI summary
Methods and systems for adjusting a scoring measure of a search result based at least in part on the breadth of a previously-executed search query associated with the search result are described. In one described system, a search engine determines a popularity measure for a search result, and then adjusts the popularity measure based at least in part on a query breadth measure of a previously-executed search query associated with the search result. The search engine may use a variety of query breadth measures. For example, the search engine may use the quantity of results returned by the search query, the length of the query, the IR score drop-off, or some other measure of breadth.