Automated Response Tool Using Parse Tree for Intent Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated call response systems require multiple prompts and questions to determine how to handle calls, degrading user experience and increasing computing strain by prolonging calls and repetitive interactions.
Innovation Solution
An automated call response system that processes the entirety of a user's spoken statement to determine intent and invoke appropriate services, reducing the need for multiple questions and conserving computing resources through a language processor with a parser, invoker, and extractor that generate a parse tree to identify potential services and parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple prompts and questions are presented to determine call handling, then call routing accuracy is improved, but call duration increases and user experience degrades
Solution Approach 1:
The system performs preliminary analysis of the caller's initial statement by generating a parse tree and identifying potential services before any follow-up questions are asked. This preliminary action allows the system to have a head start in determining call routing, reducing the need for multiple sequential questions and thereby shortening overall call duration while maintaining routing accuracy.
Solution Approach 2:
The system dynamically adjusts the questioning process by using the parse tree to identify potential services and then selectively asking only the necessary follow-up questions to disambiguate between potential services. This dynamic approach adapts the call flow to the specific context, asking fewer questions when the initial statement is clear and more questions only when needed, thus reducing average call duration while preserving routing accuracy.
2Measurement precision
If multiple prompts and questions are used to handle calls, then service identification accuracy is improved, but computing resources are consumed
Solution Approach 1:
The system performs preliminary processing by generating a parse tree from the initial caller statement and identifying potential services before any follow-up interaction. This preliminary action structures the information in advance, allowing the system to efficiently determine which specific questions are needed, thereby reducing overall computing resource consumption while maintaining service identification accuracy.
Solution Approach 2:
The system segments the call handling process into distinct phases: initial statement parsing, potential service identification, and targeted question generation. By segmenting the process and using the parse tree to guide which questions are necessary, the system avoids the computational overhead of processing multiple unnecessary questions, thus reducing computing resource consumption while preserving service identification accuracy.
3Productivity
If the entirety of spoken statement is processed to determine intent, then response speed is improved, but language processing complexity increases
Solution Approach 1:
The language processing system is segmented into distinct functional components: a parser that generates a parse tree from the spoken statement, an analyzer that identifies potential services from the parse tree, and a question generator that creates targeted follow-up questions. This segmentation allows the system to process the entire spoken statement efficiently by dividing the complex task into manageable stages, improving response speed while making the complexity more tractable through modular architecture.
Solution Approach 2:
The system performs preliminary language processing by generating a parse tree from the complete spoken_statement before any follow-up questions are asked. This preliminary action extracts and structures all relevant information from the initial statement, allowing the system to identify potential services and determine the most efficient questioning path, thereby improving response speed while managing processing complexity through advance preparation.
Data Source
AI summary
A language processor includes a parser, an invoker, and an extractor. The parser parses a spoken statement to detect a plurality of words in the spoken statement and generates a parse tree based on the detected plurality of words. The invoker determines, based on the parse tree, a plurality of potential services to invoke to respond to the spoken statement. The extractor determines, for each potential service of the plurality of potential services, a parameter used during execution of that potential service and a value of the determined parameter based on the parse tree. The invoker is further configured to issue a command to invoke a potential service of the plurality of potential services using a value of a determined parameter.