Geographic Feature Identification via Query Log Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Interactive mapping systems face challenges in efficiently identifying and ranking geographic features from query prefixes, leading to suboptimal user experience and increased time in finding relevant information.
Innovation Solution
The system computes feature-query scores by analyzing query logs to rank geographic features based on their relevance, providing potential results and expanded suggestions as the user types, and attributing query occurrences to features using prominence scores and query log data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If geographic features are identified using traditional query matching methods, then the system is simple to operate, but the identification accuracy and relevance ranking are insufficient
Solution Approach 1:
The system pre-computes feature-name scores by analyzing query logs before users submit queries. This preliminary analysis stores the frequency and relevance of geographic feature names in the query log, enabling fast and accurate feature identification when users search, without performing complex real-time analysis.
Solution Approach 2:
The system uses query logs as feedback data to continuously improve feature identification accuracy. By analyzing actual user queries and their associated geographic features, the system refines feature-name scores and prominence scores, creating a self-improving mechanism that enhances identification precision over time.
2Loss of time
If the system provides potential results after the entire query is submitted, then the processing is simpler, but the user waiting time is increased
Solution Approach 1:
The system pre-computes and stores feature-name scores and prominence scores in advance by analyzing query logs. When a user submits a query, the system immediately retrieves pre-computed scores and ranks geographic features without performing time-consuming real-time analysis, significantly reducing user waiting time while maintaining processing efficiency.
3Reliability
If the system ranks geographic features without using query log data, then the computation is faster, but the relevance of results to user interests is reduced
Solution Approach 1:
The system pre-computes feature-name scores by analyzing query logs to determine how frequently each geographic feature name appears in user queries. These pre-computed scores are stored and readily available when users search, ensuring results are highly relevant to user interests without requiring time-consuming real-time computation.
Solution Approach 2:
The query log data serves itself by automatically providing relevance information. The system uses its own accumulated query data to generate feature-name scores and prominence scores, which then automatically improve result relevance without requiring external input or manual configuration.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying geographic features. In one aspect, a method includes receiving a query. Geographic features are identified, each geographic feature being associated with one or more names, each geographic feature being associated with at least one name that includes the query. A feature-query score is computed for each geographic feature, including: for each name of the geographic feature that includes the query, identifying a computed feature-name score, wherein the feature-name score is computed based on a count of a number of occurrences of the name in a query log, wherein each occurrence is attributed to the feature; and computing the feature-query score based on the identified feature-name scores. The geographic features are ranked according to the feature-query scores.