Augmentation Query System for Search Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines often return results that are not of interest to users due to queries with misweighted terms, poor expression of information, or misspelled words, leading to unsatisfactory search outcomes.
Innovation Solution
The implementation of an augmentation query system that identifies high-performing queries from user interactions and structured document data to generate synthetic queries, which are stored and used to augment search operations, improving search results by selecting relevant queries that match user inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If search engines use standard query processing, then search operations are simple and fast, but search results are often not of interest to users due to misweighted terms, poor expression, or misspelled words
Solution Approach 1:
The system performs preliminary actions by identifying high-performing queries from query logs and generating synthetic queries from structured document data before actual search operations occur. These pre-identified augmentation queries are stored and ready to be applied when users submit search queries, thereby improving search result relevance without adding complexity to the real-time search processing.
Solution Approach 2:
The patent introduces an intermediary mechanism that matches user queries against a pre-generated set of augmentation queries. This intermediary layer translates user queries into enhanced search operations by selecting relevant augmentation queries, thereby improving search result relevance while maintaining simple user interaction and search processing.
2Reliability
If the system stores and processes augmentation queries from query logs and structured data, then search result quality improves, but data processing and storage requirements increase
Solution Approach 1:
The system extracts only the essential information needed for query augmentation from the query logs and structured document data. By identifying high-performing queries and generating synthetic queries from structured data, the system takes out only the necessary patterns and relationships, storing them as augmentation queries rather than retaining the entire raw data volume, thus reducing storage requirements while maintaining search result quality.
Solution Approach 2:
The patent transforms raw query data and structured document data into transformed augmentation queries with modified parameters. This parameter transformation process converts the original data into a condensed format that captures the essential search patterns and relationships, reducing the quantity of stored data while preserving the information needed for high-quality search results.
3Adaptability or versatility
If the system generates synthetic queries from structured document data, then search coverage expands, but query generation complexity increases
Solution Approach 1:
The system uses a universal query generation approach that processes different types of structured document data (directories, catalogs, databases) through the same mechanism to generate augmentation queries. This multi-functional approach expands search coverage across diverse data sources while maintaining a simple, unified query generation process, avoiding the need for complex specialized processing for each data type.
Data Source
AI summary
Methods, systems, and apparatus, including computer program products, for generating or using augmentation queries. In one aspect, a first query stored in a query log is identified and a quality signal related to the performance of the first query is compared to a performance threshold. The first query is stored in an augmentation query data store if the quality signal indicates that the first query exceeds a performance threshold.