Master Bot Classifier for Unrelated Chatbot Utterance Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing chatbot systems face challenges in efficiently routing user inputs to the appropriate skill bots, often leading to unnecessary resource utilization when inputs are unrelated to available chatbots, resulting in suboptimal performance and user experience.
Innovation Solution
A master bot system is trained to utilize a classifier model that generates input feature vectors and compares them to training feature vectors, determining whether the input falls within defined clusters or composite feature vectors, thereby identifying unrelated inputs and routing them appropriately.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a master bot routes all user inputs to skill bots for processing, then comprehensive coverage of user needs is achieved, but computational resources are wasted on unrelated inputs
Solution Approach 1:
The master bot performs preliminary classification of user inputs before routing to skill bots. By using a classifier model to predict whether an input is related to any skill bot, the system takes preliminary action to filter out unrelated inputs, preventing wasted computational resources on skill bot processing while maintaining comprehensive coverage for related inputs.
2Ease of operation
If the system processes all input utterances through skill bots, then user experience is maintained, but network bandwidth is consumed unnecessarily
Solution Approach 1:
The master bot performs preliminary determination of input relevance using a classifier model before initiating network communication with skill bots. This preliminary action filters out unrelated inputs, preventing unnecessary network bandwidth consumption while ensuring that related inputs are still processed and delivered to users, maintaining user experience.
3Productivity
If the master bot uses a classifier model to filter inputs, then resource efficiency is improved, but system complexity increases
Solution Approach 1:
The master bot introduces a classifier model as an intermediary component between user inputs and skill bot routing. This intermediary filters and classifies inputs before they reach skill bots, improving resource efficiency by preventing unrelated inputs from being processed. The classifier model acts as a mediating layer that adds computational overhead only for classification rather than full processing.
4Speed
If the system routes inputs to skill bots without classification, then routing speed is maintained, but unnecessary processing occurs
Solution Approach 1:
The master bot performs preliminary classification at the point of input reception before routing decisions are made. By using the classifier model to quickly determine input relevance, the system maintains fast routing speeds while improving processing efficiency by preventing skill bots from processing unrelated inputs, thus eliminating unnecessary computational work.
Data Source
AI summary
Techniques are described to determine whether an input utterance is unrelated to a set of skill bots associated with a master bot. In some embodiments, a system described herein includes a training system and a master bot. The training system trains a classifier of the master bot. The training includes accessing training utterances associated with the skill bots and generating training feature vectors from the training utterances. The training further includes generating multiple set representations of the training feature vectors, where each set representation corresponds to a subset of the training feature vectors, and configuring the classifier with the set representations. The master bot accesses an input utterance and generates an input feature vector. The master bot uses the classifier to compare the input feature vector to the multiple set representations so as to determine whether the input feature falls outside and, thus, cannot be handled by the skill bots.