Chatbot Skill Context Switching for Out-of-Scope Utterances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing chatbot systems struggle to automatically switch between skills within the same domain effectively, leading to difficulties in handling out-of-scope utterances and providing proper responsive actions.
Innovation Solution
A computer-implemented method that involves receiving a user utterance, inputting it into a candidate skills model to rank potential skills, determining the highest ranked skill, and changing the skill context to that skill. The method further involves inputting the utterance into a candidate flows model to rank intents within the skill and determining the highest ranked intent for processing the utterance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a chatbot system uses a single skill context for processing user utterances, then the system structure remains simple, but the system cannot effectively handle out-of-scope utterances within the same domain
Solution Approach 1:
The patent implements dynamic skill context switching by evaluating candidate skills models and transitioning between different skill contexts based on the processed utterance. The system dynamically determines whether to switch from a first skill context to a second skill context within the same domain, allowing the chatbot to adapt its processing capabilities to handle out-of-scope utterances effectively.
Solution Approach 2:
The patent creates a universal skill context management mechanism that can handle multiple types of utterances (in-scope and out-of-scope) within the same domain. By implementing a candidate skills model that evaluates and ranks multiple skills, the system achieves multi-functionality in processing diverse user inputs without requiring separate dedicated systems for each skill type.
2Reliability
If the chatbot system implements automatic skill switching, then the handling of out-of-scope utterances improves, but the processing time and computational complexity increase
Solution Approach 1:
The patent implements preliminary action by pre-evaluating candidate skills models and maintaining a ranked list of potential skills for each domain. The candidate skills model is prepared in advance to quickly retrieve and evaluate relevant skills when an utterance is received, reducing the real-time processing burden while maintaining high accuracy in skill selection.
Solution Approach 2:
The patent utilizes parameter changes by adjusting confidence score thresholds and skill ranking parameters to optimize the balance between accuracy and processing speed. By dynamically adjusting these parameters based on the specific utterance and context, the system can quickly filter candidate skills and make accurate selections without exhaustive evaluation of all possible skills.
Data Source
AI summary
Techniques for automatically switching between chatbot skills in the same domain. In one particular aspect, a method is provided that includes receiving an utterance from a user within a chatbot session, where a current skill context is a first skill and a current group context is a first group, inputting the utterance into a candidate skills model for the first group, obtaining, using the candidate skills model, a ranking of skills within the first group, determining, based on the ranking of skills, a second skill is a highest ranked skill, changing the current skill context of the chatbot session to the second skill, inputting the utterance into a candidate flows model for the second skill, obtaining, using the candidate flows model, a ranking of intents within the second skill that match the utterance, and determining, based on the ranking of intents, an intent that is a highest ranked intent.