Search Query Expansion via Historical Log Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current web search systems often yield few or no results when users enter specific search queries, as they rely solely on search terms and geographic indicators, requiring users to guess how to modify these parameters to receive desired results, leading to frustration and potential abandonment of the service.
Innovation Solution
A search system that automatically executes a second search query by expanding either the search term or geographic indicator based on historical search logs, determining which parameter to expand by calculating a likelihood value and comparing it to a threshold, to provide users with a greater number of relevant results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users enter specific search queries with precise terms and geographic indicators, then search precision is improved, but the quantity of search results decreases
Solution Approach 1:
The system dynamically adjusts search parameters by automatically expanding geographic indicators and modifying search terms based on historical search logs and user behavior patterns. This allows the search system to transition from static precise queries to dynamic queries that adapt between precision and quantity based on real-time analysis of user interactions and search effectiveness.
Solution Approach 2:
The system changes search parameters automatically by expanding geographic indicators (e.g., from specific city to region or country) and modifying search terms (e.g., adding synonyms or related terms) based on historical data analysis. This parameter transformation resolves the contradiction by systematically adjusting the balance between precision and quantity according to user needs and search performance metrics.
2Quantity of substance
If users manually modify search parameters to broaden search scope, then quantity of search results increases, but ease of operation decreases
Solution Approach 1:
The system performs self-service by automatically analyzing historical search logs, determining when and how to expand search parameters, and executing the expanded searches without user intervention. This eliminates the need for users to manually guess how to broaden their searches, thereby maintaining ease of operation while increasing result quantity through automated parameter expansion based on learned user preferences and search patterns.
Solution Approach 2:
The system incorporates feedback loops that continuously monitor search results quality and user interactions, then use this feedback to automatically adjust and expand search parameters. By analyzing whether expanded searches return better results, the system learns optimal expansion strategies and applies them automatically, improving both quantity of results and ease of operation through data-driven automation.
3Productivity
If the system automatically expands search parameters, then productivity increases, but device complexity increases
Solution Approach 1:
The system performs preliminary actions by pre-processing historical search logs to extract patterns, user preferences, and effective expansion strategies before they are needed. This advance preparation stores learned knowledge in structured formats that can be quickly applied during actual search operations, thereby increasing productivity while managing complexity through upfront analysis and caching of decision rules.
Data Source
AI summary
Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries. A search system executes a search query based on a search term and the geographic indicator. In response to determining that a number of the search results is less than a threshold number, the search system determines, based on historical search logs from other users in the first geographic region, a likelihood value indicating a likelihood that the other users in the first geographic region expanded the geographic region of their search queries. The search system compares the likelihood value to a threshold likelihood value, and determines, based on the comparison, that the likelihood value meets or exceeds the threshold likelihood value. The search system then executes an expanded search based on the search term and an expanded geographic indicator that encompasses the first geographic region.