Query Segment Scoring for Content Selection Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current content selection methods for user queries do not effectively evaluate the self-sufficiency of queries in relation to content items, leading to suboptimal matching and presentation of relevant content.
Innovation Solution
A computer-implemented method that processes user queries by determining stand-alone and query-independent scores for query segments, using historical logs to adjust scores, and applying functions to identify self-sufficiency scores for content items, enabling more accurate content selection and auction processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional content selection methods are used, then the content selection process is simple, but the matching accuracy and relevance of content to user queries deteriorate
Solution Approach 1:
The query is divided into multiple segments, and each segment is scored independently using query-independent scoring. This allows the system to evaluate the self-sufficiency of each segment separately, improving matching accuracy without requiring complex overall query analysis.
Solution Approach 2:
Query-independent scores are pre-computed for each query segment based on historical query logs before the actual content selection process. This preliminary scoring enables faster and more accurate content matching during runtime without adding complexity to the real-time selection process.
2Reliability
If query-independent scoring is implemented, then content relevance is improved, but computational resources and processing time increase
Solution Approach 1:
The system pre-computes query-independent scores for all query segments using historical query logs before actual content selection occurs. This preliminary action stores scoring information that can be quickly retrieved during runtime, ensuring reliable content selection without significant processing delays.
Solution Approach 2:
Each query segment independently retrieves its pre-computed query-independent score without requiring complex inter-segment analysis or iterative processing. This self-service approach to scoring reduces computational overhead and processing time while maintaining selection reliability.
Data Source
AI summary
Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium, including a method for responding to queries. A first user query is received. The first user query is processed including identifying one or more segments in the first user query, a segment representing a word or a phrase. A stand-alone score is determined for each segment of the first user query, wherein the stand-alone score is an indication of a likelihood that the segment represents a stand-alone query and that the segment represents a main topic of the first user query. A historical log of queries is processed to determine query-independent scores for segments that are included in queries represented by the log. The final query-independent scores are used to determine the stand-alone score for each segment of the first query.