Unified ML Model for Parallel Query Intent and Complexity Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for automating responses to user queries are inefficient due to the need for multiple data processing systems and serial processing of query intent and complexity, leading to increased response time and resource usage.
Innovation Solution
A method and system that use machine learning models to determine query intent and complexity in parallel, generating a query vector that is processed by both an intent model and a complexity model to route queries efficiently, reducing preprocessing overhead and improving response time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple separate data processing systems are used to analyze query intent and complexity, then analysis comprehensiveness is improved, but processing time and resource usage increase
Solution Approach 1:
The patent combines multiple separate data processing systems into a single unified model that simultaneously performs query intent classification and complexity assessment. This consolidation merges the preprocessing, feature extraction, and analysis functions into one integrated system, eliminating the need for sequential processing across multiple systems while maintaining comprehensive analysis capabilities.
Solution Approach 2:
The unified model internally segments different analysis functions (intent classification and complexity assessment) as separate output streams from a single processing pipeline. This allows the system to maintain comprehensive multi-dimensional analysis while executing these functions in parallel within the same model, rather than requiring separate external systems.
2Measurement precision
If multiple separate data processing systems are used to process queries, then analysis depth is improved, but device complexity increases
Solution Approach 1:
The patent merges multiple data processing systems into a single unified model that handles both query intent and complexity analysis. This consolidation reduces device complexity by eliminating redundant infrastructure, multiple model deployments, and inter-system communication overhead, while maintaining deep analysis capabilities through integrated feature sharing and joint training.
Solution Approach 2:
The unified model serves multiple functions simultaneously - it performs both query intent classification and complexity assessment, making it a multi-functional system. This universality eliminates the need for separate specialized systems, reducing overall device complexity while maintaining comprehensive analysis depth through a single versatile processing engine.
3Ease of manufacture
If separate preprocessing is performed for each data processing system, then system modularity is improved, but processing efficiency decreases
Solution Approach 1:
The patent merges separate preprocessing operations into a single shared preprocessing stage that feeds both intent classification and complexity assessment within the unified model. This eliminates redundant feature extraction and text normalization operations, significantly improving processing efficiency while the internal modular architecture of the unified model maintains ease of deployment and updates.
Data Source
AI summary
Certain aspects of the present disclosure provide techniques for determining query intent and complexity based on text input. One example method generally includes receiving, from a user device, a text query and preprocessing the text query to generate a query vector. The method further includes providing the query vector to an intent model configured to output a user intent of the text query and providing the query vector to a complexity model configured to output a complexity of the text query. The method further includes receiving the user intent of the text query from the intent model and receiving the complexity of the text query from the complexity model. The method further includes determining, based on the user intent and the complexity of the query, a routing target for the text query and routing the text query to the routing target.