Digital Assistant Subsequent Action Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital assistants do not efficiently provide suggested subsequent user actions during extended interactions, requiring users to repeatedly instantiate the assistant and perform separate determinations for each request.
Innovation Solution
An electronic device with one or more processors and memory receives an utterance, determines a domain associated with the user request, and identifies subsequent user actions and their parameters based on the domain, selecting the action with the higher score as a suggested subsequent action.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If users interact with digital assistant for extended period providing multiple requests, then user needs to instantiate assistant multiple times for each request, but this increases time consumption and reduces interaction efficiency
Solution Approach 1:
The system performs preliminary analysis of the current user request to predict and prepare suggested subsequent actions before the user actually formulates them. By anticipating user needs in advance and presenting relevant follow-up actions, the system eliminates the need for users to restart the assistant for each new request, thereby reducing time loss and improving interaction efficiency.
2Productivity
If digital assistant provides suggested subsequent user actions during interaction, then efficiency of digital assistant increases, but this requires additional processing and analysis
Solution Approach 1:
The system implements a feedback mechanism where the digital assistant continuously monitors the conversation context and user interactions, then provides suggested subsequent actions based on this feedback. This feedback loop enables the assistant to adapt to user needs dynamically, improving efficiency while managing processing complexity through iterative refinement rather than exhaustive analysis.
Solution Approach 2:
The system changes parameters such as the depth of analysis, the number of suggested actions generated, and the specificity of predictions based on the current interaction state. By dynamically adjusting these parameters, the system optimizes the balance between providing useful suggestions and managing processing complexity, ensuring that additional processing requirements scale appropriately with user needs.
3Ease of operation
If digital assistant analyzes user requests to provide suggestions, then user experience becomes more immersive and efficient, but this increases power usage
Solution Approach 1:
The system performs partial analysis of user requests by focusing only on the most relevant aspects of the conversation context needed to generate suggestions, rather than analyzing every possible parameter. This selective approach maintains immersive and efficient user experience while significantly reducing the computational power required compared to exhaustive analysis methods.
Data Source
AI summary
Systems and processes for operating an intelligent automated assistant are provided. An example process includes receiving an utterance including a user request, determining, based on the user request, a domain associated with the user request, determining, based on the domain, a first subsequent user action and a second subsequent user action, determining, based on the domain, a first parameter for the first subsequent user action and a second parameter for the second subsequent user action, in accordance with a determination that a first score associated with the first subsequent user action is higher than a score associated with the second subsequent user action, selecting the first subsequent user action as a suggested subsequent user action, and providing the suggested subsequent user action.