Query Routing via Intent Vector Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for query routing on websites lack contextual intelligence, often providing granular results that fail to direct users to relevant resources, whether general, specific, or off-topic, leading to unsuitable responses and user dissatisfaction.
Innovation Solution
A computer-implemented method and system that analyzes user queries to identify entities and intent, generating a vector to dynamically route queries to appropriate answer resources, such as chatbots or human agents, based on intent classification and entity recognition, ensuring relevant responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pure topic-based routing or pre-chat surveys are used to route queries, then query routing functionality is provided, but contextual intelligence is insufficient leading to granular results that fail to direct users to relevant resources
Solution Approach 1:
The system transforms the query routing approach by changing parameters from simple topic matching to a comprehensive analysis including entity recognition, intent classification, and vector generation. This multi-parameter approach enables the system to capture nuanced user intent and route queries to appropriately scoped resources, resolving the contradiction between routing precision and contextual intelligence
Solution Approach 2:
The patent introduces additional dimensions to query analysis by generating vectors that capture semantic meaning beyond traditional topic categorization. This dimensional expansion allows the system to evaluate queries from multiple perspectives (entities, intent, semantics) simultaneously, achieving both precision and contextual understanding
2Reliability
If confidence polling of failed results from chat bots is used to route future visitor queries, then routing strategy is improved, but system complexity increases
Solution Approach 1:
The system performs preliminary entity recognition and intent classification on incoming queries before routing, rather than relying on post-hoc confidence polling from failed chat bot attempts. This proactive approach establishes routing accuracy through structured analysis while avoiding the complexity of iterative confidence polling and failed attempt tracking
3Manufacturing precision
If multiple chat bots are fused to provide query responses with variability in effort, then response suitability is improved, but processing time and complexity increase
Solution Approach 1:
The patent segments the query response process into distinct stages: entity recognition, intent classification, vector generation, and resource routing. This segmentation allows the system to process queries efficiently through a structured pipeline rather than fusing multiple chat bots simultaneously, maintaining response suitability while reducing processing time and complexity
Data Source
AI summary
A method, system, and computer program product for routing queries to answer resources based on component parts and intents of a received query is provided. The method receives a query from a user. The query is analyzed to identify a set of entities associated with the query and generate an utterance representing the query. The method generates an intent classification for the utterance and a vector for the query. The vector is generated based on the set of entities, the utterance, and the intent classification. The method determines an answer resource for the query based on the vector and the intent classification of the query. In response to determining the answer resource, the method provides an answer interface based on the query, the vector, and the intent classification. The answer interface dynamically provides a response to the query.