Dialog Manager for Intent Determination in Messaging Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conversational agents face limitations in accurately determining the intent behind user messages, particularly in distinguishing between inquiries and statements, which can lead to misunderstandings and unforeseen consequences in natural language interactions.
Innovation Solution
A computer-implemented method using machine learning models to identify interrogative, imperative, and declarative statements by training on sentence embeddings and syntactic features, allowing for seamless transitions between topics in messaging dialog systems by determining whether user entries expect a response or not.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a conversational agent is designed for a limited number of use cases with specific response domains, then the agent can maintain focused expertise in those domains, but the agent cannot handle user entries that digress from those domains
Solution Approach 1:
The patent introduces a dialog manager as an intermediary component that sits between the user and the conversational agent. The dialog manager analyzes user entries to determine intent and manages transitions between different response domains, allowing the agent to handle digressive entries while maintaining its core domain expertise. This mediator resolves the contradiction by adding a layer that handles adaptability without compromising the agent's focused reliability in its primary domain.
2Measurement precision
If the system uses machine learning models to determine response expectations, then intent determination accuracy is improved, but the system complexity increases
Solution Approach 1:
The patent segments the intent determination process into distinct components: a response expectation model that analyzes whether a response is expected, a topic model that identifies the subject matter, and a dialog manager that coordinates these components. This segmentation allows each component to specialize in a specific aspect of intent determination, improving overall precision while making the complex system more manageable and modular.
3Measurement precision
If the system analyzes sentence embeddings and syntactic features to determine response expectations, then the accuracy of distinguishing questions from statements improves, but the processing time increases
Solution Approach 1:
The patent implements preliminary action by pre-training machine learning models on sentence embeddings and syntactic features during an offline phase. The response expectation model and topic model are trained in advance to recognize patterns in language that indicate whether a response is expected. During actual conversation, these pre-trained models can quickly analyze user entries without requiring complex real-time computations, thus maintaining high accuracy while reducing processing time.
Data Source
AI summary
Computer-implemented methods, computer program products, and computer systems for improving intent determination in a messaging dialog manager system. The computer-implemented method for improving intent determination in a messaging dialog manager system may include one or more processors configured for receiving first agent entry data corresponding to a first agent communicating in a messaging dialog interface, determining that the first agent entry data expects a response that is within a first response domain, determining that a first user entry entered in the messaging dialog interface is not within the first response domain. Further, the computer-implemented may include identifying a second agent configured with a second response domain that includes the first user entry and transmitting the first user entry to the second agent to facilitate a seamless transition of an established communicational flow between the first agent and a first user.