Task Orchestration for Cross-Device Context Transfer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital personal assistants can only perform limited simple tasks on a single device and lack support for complex tasks that require multiple applications and devices, as well as context information transfer across applications.
Innovation Solution
A system and method for complex task machine learning that includes receiving unknown commands, generating prompts, and determining actions to create complex tasks by processing clarifying instructions, utilizing pre-built application-specific skills and APIs stored in a knowledge base to integrate actions across multiple devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If NLU skills are built for individual applications, then simple tasks can be performed, but complex tasks requiring multiple applications and devices are not supported
Solution Approach 1:
The system segments complex tasks into multiple sub-tasks, where each sub-task is handled by a separate NLU skill. The task orchestration module coordinates these segmented sub-tasks to achieve the overall complex task, allowing the system to handle complex tasks while maintaining the simplicity of individual NLU skills.
Solution Approach 2:
The task orchestration module serves as a universal component that can coordinate multiple different NLU skills and application actions across various devices. This multi-functional module enables the system to handle diverse complex tasks without requiring separate specialized systems for each task type.
2Loss of information
If developers build NLU skills for individual applications, then application-specific actions are enabled, but context information transfer across applications is not supported
Solution Approach 1:
The task orchestration module acts as an intermediary that receives context information from one application's NLU skill and transfers it to another application's NLU skill. This mediator enables seamless context information transfer across applications without requiring direct integration between each application pair.
Solution Approach 2:
Context information is nested within the task orchestration layer, which encapsulates and manages context across multiple application contexts. Each application's context is nested within the overall task context, allowing efficient context transfer and management without exposing the complexity of individual application contexts.
3Productivity
If digital personal assistants perform limited simple tasks, then system complexity is low, but productivity for complex tasks is insufficient
Solution Approach 1:
The system dynamically adapts its complexity based on task requirements. For simple tasks, only the necessary NLU skill is activated. For complex tasks, the task orchestration module dynamically coordinates multiple NLU skills and application actions, allowing the system to scale its complexity according to the task at hand rather than maintaining fixed high complexity.
Data Source
AI summary
An electronic device for complex task machine learning includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive an unknown command for performing a task and generate a prompt regarding the unknown command. The at least one processor is also configured to receive one or more instructions in response to the prompt, where each of the one or more instructions provides information on performing at least a portion of the task. The at least one processor is further configured to determine at least one action for each one of the one or more instructions. In addition, the at least one processor is configured to create a complex action for performing the task based on the at least one action for each one of the one or more instructions.