Voice Shortcut Task Sequencing for Multi-Step Assistant Actions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Digital assistants often fail to provide an intuitive system for performing multiple tasks simultaneously without requiring users to interact with multiple interfaces and confirm multiple tasks or parameters.
Innovation Solution
Associating tasks with voice shortcuts corresponding to user activities based on user activity and contextual data, allowing users to efficiently execute multiple tasks through voice commands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If digital assistants require users to interact with multiple interfaces and confirm multiple tasks or parameters, then task execution accuracy is improved, but user operation complexity increases
Solution Approach 1:
The patent combines multiple task confirmations and interface interactions into a single unified confirmation dialog. When a user requests multiple tasks, the system merges all task parameters and confirmation requirements into one consolidated interface, allowing the user to confirm or modify all tasks simultaneously rather than interacting with multiple separate interfaces sequentially.
Solution Approach 2:
The confirmation dialog is designed as a universal interface that can handle multiple different task types and parameters in a single interaction. This multi-functional dialog adapts to display and manage various task configurations (notifications, messages, media playback, etc.) together, eliminating the need for separate confirmation steps for each task.
2Measurement precision
If digital assistants require users to confirm multiple tasks through multiple interfaces, then task parameter accuracy is improved, but time consumption increases
Solution Approach 1:
The system performs preliminary organization of multiple tasks and their parameters before presenting the confirmation dialog to the user. Tasks are pre-grouped, pre-configured, and pre-invalidated in a single batch operation, so that when the user views the confirmation dialog, all task parameters are already prepared and can be reviewed together, eliminating the need for multiple sequential confirmation steps.
Solution Approach 2:
Multiple task confirmations are merged into a single unified confirmation action. The system combines all task parameters, validation results, and user confirmation requirements into one consolidated interaction, allowing the user to review and confirm multiple tasks simultaneously rather than spending time on multiple separate confirmation dialogs.
3Reliability
If users interact with multiple interfaces to perform multiple tasks, then task completion thoroughness is improved, but device energy consumption increases
Solution Approach 1:
The system merges multiple interface interactions and task execution processes into a single unified operation. By consolidating multiple task confirmations and interface transitions into one batch operation, the system reduces the cumulative energy consumption that would result from multiple separate interface activations, task initializations, and confirmation dialog displays.
Solution Approach 2:
The system maintains continuous processing of multiple tasks within a single user interaction session, avoiding the energy-intensive state transitions and interface re-initializations that would occur with multiple separate interactions. All tasks are processed, validated, and confirmed in a continuous workflow, minimizing energy consumption while ensuring thorough task completion.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Systems and processes for accelerating task performance are provided. An example method includes, at an electronic device with a display, displaying a candidate shortcut affordance associated with a user activity, detecting a first set of inputs corresponding to a selection of the candidate shortcut affordance, in response to detecting the first set of inputs, displaying a first set of candidate task affordances, detecting a second set of inputs corresponding to a selection of a candidate task affordance associated with a first task, displaying a second set of candidate task affordances, detecting a third set of inputs corresponding to a selection of a candidate task affordance associated with a second task, and in response to detecting the second set of inputs and the third set of inputs, associating the first task and the second task with a task sequence for a voice shortcut corresponding to the user activity.