Virtual Assistant Task Mapping via Action-Object Pairs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Virtual assistants often incorrectly determine tasks requested by users due to ambiguous input, leading to inaccurate task execution and a suboptimal user experience.
Innovation Solution
The implementation of a task mapping system that utilizes action-object pairs, contextual information, and user customization to accurately identify tasks, where a task map is personalized based on user interactions, industry applications, and device contexts, enabling the virtual assistant to learn and adapt over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a virtual assistant uses basic input processing to determine tasks, then the system complexity is low, but the task determination accuracy is poor
Solution Approach 1:
The patent segments the task determination process into multiple components: extracting action-object pairs from input, retrieving candidate tasks from a task map, selecting the most appropriate task, and providing feedback. This segmentation allows each component to be optimized independently, improving overall accuracy without proportionally increasing complexity.
Solution Approach 2:
The patent implements feedback mechanisms where the virtual assistant learns from user corrections and interactions. When users correct misidentified tasks, the system updates its task map and action-object pair associations, progressively improving accuracy while maintaining manageable complexity through iterative learning.
2Adaptability or versatility
If the virtual assistant uses a fixed task map, then the device complexity is low, but the adaptability to different users and contexts is poor
Solution Approach 1:
The patent transforms the task map from a static structure to a dynamic one that evolves based on user interactions. The task map is continuously updated with learned action-object pair associations, allowing it to adapt to individual user preferences and behaviors while maintaining a manageable structure through systematic update rules.
Solution Approach 2:
The virtual assistant performs self-learning by automatically updating its task map based on user feedback and interactions. The system serves itself by identifying patterns in user corrections and autonomously adjusting its task associations, reducing the need for manual configuration while improving personalization.
Data Source
AI summary
Techniques for mapping actions and objects to tasks may include identifying a task to be performed by a virtual assistant for an action and/or object. The task may be identified based on a task map of the virtual assistant. In some examples, the task may be identified based on contextual information of a user, such as a conversation history, content output history, user preferences, and so on. The techniques may also include customizing a task map for a particular context, such as a particular user, industry, platform, device type, and so on. The customization may include assigning an action, object, and/or variable value to a particular task.