Automated Assistant Expanded Response Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated assistants often require users to provide elongated and multiple user interface inputs to perform technical tasks, leading to inefficient user-device interaction and increased computational resource usage.
Innovation Solution
The implementation generates expanded responses by an automated assistant in response to user interface inputs, including prompts and content related to additional entities, to guide the continuation of human-to-computer dialogs efficiently, reducing the need for multiple user inputs and conserving resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If automated assistants respond only with content directly responsive to recognized requests, then response accuracy is improved, but user interaction efficiency deteriorates
Solution Approach 1:
The system performs preliminary actions by proactively generating and presenting multiple potential user inputs as selectable options before the user actually needs to provide them. This allows users to simply select from pre-prepared options rather than constructing full inputs, thereby improving interaction efficiency while maintaining response accuracy through the use of contextually relevant pre-generated options.
Solution Approach 2:
The system introduces an intermediary layer between the user's intent and the actual input formulation. Instead of requiring users to directly formulate complete inputs, the system generates multiple candidate inputs as intermediate options that the user can select from. This intermediary step bridges the gap between user intent and system understanding, improving efficiency without sacrificing accuracy.
2Reliability
If automated assistants require multiple user interface inputs to perform technical tasks, then task completion thoroughness is improved, but device interaction complexity increases
Solution Approach 1:
The system segments the task completion process into multiple parallel candidate inputs rather than requiring sequential user actions. By generating multiple potential inputs that each represent a complete or near-complete task path, the system allows users to select a single option that encompasses multiple steps, thereby reducing interaction complexity while maintaining thoroughness through the comprehensive nature of the generated options.
Solution Approach 2:
The system merges multiple potential user inputs into a single selection interface. Instead of requiring users to provide multiple separate inputs sequentially, the system combines multiple complete task paths into one set of options, allowing users to accomplish complex tasks through a single selection action. This merging reduces interaction complexity while ensuring thorough task completion through the comprehensive options provided.
3Measurement precision
If users provide elongated user interface inputs, then input specificity is improved, but computational resource consumption increases
Solution Approach 1:
The system creates multiple copies of potential user inputs based on the user's initial brief input. Instead of requiring users to provide detailed, specific inputs, the system generates multiple copied and varied versions of the input intent, each with different levels of specificity. The user can then select the most appropriate copy, achieving input specificity without the computational burden of processing multiple elongated user inputs.
Solution Approach 2:
The system changes the parameter of input length by generating options with varying levels of detail from a single brief user input. Instead of requiring users to provide long, specific inputs, the system transforms the brief input into multiple options with different specificity parameters, allowing users to select the appropriate level of detail. This reduces computational resource consumption while maintaining input specificity through selective option choice.
Data Source
AI summary
Generating expanded responses that guide continuance of a human-to computer dialog that is facilitated by a client device and that is between at least one user and an automated assistant. The expanded responses are generated by the automated assistant in response to user interface input provided by the user via the client device, and are caused to be rendered to the user via the client device, as a response, by the automated assistant, to the user interface input of the user. An expanded response is generated based on at least one entity of interest determined based on the user interface input, and is generated to incorporate content related to one or more additional entities that are related to the entity of interest, but that are not explicitly referenced by the user interface input.