Shared Task State Platform Decouples Tracking from Execution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Input understanding systems struggle to efficiently manage task states during user interactions, as they need to track various pieces of information, correct misunderstandings, and handle changes in user input, which burdens both the user and the system with complex conversational flows.
Innovation Solution
Decoupling task state tracking from task execution by using a shared task state platform that manages conversational states independently, allowing task owners to focus solely on specifying required parameters without worrying about tracking states like confirmation, clarification, or cancellation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If input understanding systems manage task states during user interactions, then task completion accuracy is improved, but system complexity and processing load increase
Solution Approach 1:
The patent extracts task state tracking functionality from the task execution system and places it in a separate shared task state platform. This allows the input understanding system to focus on processing user inputs while the shared platform independently manages conversation states, confirmation, clarification, and cancellation tracking, thereby reducing system complexity while maintaining accuracy.
Solution Approach 2:
The shared task state platform acts as an intermediary between the input understanding system and task execution systems. It receives task registration data from task owners, manages the conversation state centrally, and provides collected data to task owner resources, serving as a mediator that coordinates complexity across the distributed system.
2Manufacturing precision
If task owners specify required parameters for task execution, then task execution precision is improved, but programming burden increases
Solution Approach 1:
The shared task state platform performs self-service by automatically managing task state tracking, collecting required parameters, and coordinating conversation flows without requiring task owners to implement these functions. Task owners only need to register their tasks and specify required parameters, while the platform handles the complex state management autonomously.
3Measurement precision
If conversational flows include confirmation and clarification steps, then information accuracy is improved, but interaction time increases
Solution Approach 1:
The shared task state platform performs preliminary actions by pre-defining the conversation flow and required parameters before the actual interaction. It maintains a task state tracker that knows in advance what information is needed, allowing the system to efficiently collect only the necessary parameters without unnecessary confirmation or clarification steps, thus reducing interaction time while maintaining accuracy.
Data Source
AI summary
Non-limiting examples of the present disclosure describe decoupling task state tracking that is managed by a shared task completion platform from execution of tasks by a task resource owner. Task registration data is received at a shared task state platform for a task that is executable by a task owner resource. Task registration data comprises parameters to be collected for execution of the task and ancillary information, such as the name of the task and whether to confirm the values of the parameters after collection. During interaction with a user, the shared task completion platform receives an input and determines the task is associated with the received input. During the interaction, parameters of the received task registration data are utilized to collect data for execution of the task. The collected data is transmitted to the task owner resource for execution of the task.


