Search Intent Routing via Scoring Modules
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search systems face challenges in reliably determining which search queries should be handled by general purpose search systems and which by special purpose search systems, particularly in integrating special purpose search results into general search results, especially for users who may not recognize that applications can satisfy their search intent.
Innovation Solution
A method and device that assess the special purpose search intent of a query by using multiple scoring modules, including partner data, metadata, search confidence, and feedback modules, to determine whether to forward the query to a special purpose search system, thereby integrating special purpose search results into general search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If search queries are automatically routed to special purpose search systems, then special purpose search results can be integrated into general search results, but the system complexity increases due to the need for intent assessment mechanisms
Solution Approach 1:
The system segments the search processing function by separating general purpose search from special purpose search. A recommendation device is introduced that independently assesses search intent and routes queries appropriately, allowing the general purpose search system to remain simple while enabling special purpose integration through modular addition of the recommendation component.
Solution Approach 2:
The recommendation device serves as an intermediary between the general purpose search system and special purpose search systems. It receives search queries, assesses special purpose search intent using multiple scoring modules, and determines whether to forward queries to special purpose systems, thereby mediating the integration process and managing system complexity.
2Measurement precision
If multiple scoring modules are used to assess search intent, then the accuracy of routing decisions improves, but the processing time and computational resources increase
Solution Approach 1:
The system employs multiple scoring modules that provide partial assessments of search intent rather than requiring a single comprehensive analysis. Each module (partner data, metadata, search confidence, feedback) contributes independently to the overall assessment, allowing the system to achieve high accuracy through aggregated partial evaluations without requiring any single module to perform exhaustive analysis.
Solution Approach 2:
The scoring modules perform preliminary assessments of search intent before queries are forwarded to special purpose search systems. By pre-evaluating queries using multiple criteria and generating recommendations in advance, the system reduces the computational burden during actual search execution and minimizes processing delays.
3Ease of operation
If special purpose search results are integrated into general search results, then user satisfaction improves, but the difficulty of detecting and measuring search intent increases
Solution Approach 1:
The recommendation device performs multiple functions: it assesses special purpose search intent, generates routing recommendations, and integrates results from both general and special purpose search systems. This multi-functional approach consolidates the complexity of intent detection and measurement into a single universal component, making the overall system easier to operate while maintaining high user satisfaction.
Solution Approach 2:
The system incorporates feedback modules that analyze user interactions and search outcomes to improve intent detection accuracy. By continuously learning from user behavior patterns and search result effectiveness, the system refines its ability to detect and measure search intent, making the integration process more accurate and user-friendly over time.
Data Source
AI summary
A method includes receiving, at a computing device, a search query from a general purpose search system or a user device in communication with the general purpose search system and assessing, at the computing device, a special purpose search intent of the search query. The method also includes sending a recommendation from the computing device to at least one of the general purpose search system or the user device, the recommendation indicating whether to send the search query to a special purpose search system to obtain special purpose search results.