Partial Action Execution for Incomplete User Inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional speech recognition services are limited in processing user inputs that lack necessary information, leading to incomplete task execution and inefficiencies in performing actions based on partial user inputs.
Innovation Solution
An electronic device system that receives partial user inputs, transmits data to a server with an intelligence system, performs part of the action sequence, and requests additional inputs to complete tasks, allowing for stepwise action execution and efficient service matching user intent.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional speech recognition service processes only complete user inputs with all necessary information, then task execution accuracy is improved, but user input convenience and system responsiveness deteriorate
Solution Approach 1:
The system performs partial task execution based on the subset of parameters that are available in the user input, rather than requiring all parameters to be present. This allows the system to act on what is given (partial action) while maintaining accuracy for the aspects that can be executed, and subsequently complete the remaining parts when additional information becomes available.
Solution Approach 2:
The system implements a feedback mechanism where it transmits the current execution status and missing parameter requirements back to the user, then receives additional inputs to complete the task. This closed-loop feedback process ensures that partial executions are properly tracked and completed with subsequent user inputs, maintaining overall task accuracy while improving convenience.
2Reliability
If conventional speech recognition service waits for all necessary information before performing actions, then task completion accuracy is improved, but response time and productivity deteriorate
Solution Approach 1:
The system performs preliminary actions using the parameters that are already available in the initial user input, without waiting for all parameters to be collected. This preliminary execution starts the task immediately with what is known, improving response time, while the remaining parameters are acquired and used to complete the task subsequently, ensuring final accuracy.
Solution Approach 2:
The system executes the portion of the task that can be completed with available information (partial action), rather than delaying the entire task until all information is gathered. This approach improves productivity by making immediate progress while maintaining reliability through subsequent completion steps.
3Reliability
If electronic device performs all action states in sequence, then task completeness is improved, but system complexity and processing overhead increase
Solution Approach 1:
The system segments the task execution into multiple phases: initial execution with available parameters, status transmission to server, and subsequent completion with additional parameters. This segmentation divides the complex full-sequence execution into manageable parts, reducing processing overhead while ensuring task completeness through coordinated phases.
Solution Approach 2:
The system performs partial action sequences based on available information, transmitting intermediate status rather than executing the complete sequence upfront. This reduces immediate processing overhead while ensuring task completeness through subsequent execution phases when additional parameters become available.
4Measurement precision
If speech recognition service requests additional user inputs for incomplete tasks, then task accuracy is improved, but user interaction time and system complexity increase
Solution Approach 1:
The system provides feedback to the user about which parameters are missing and what additional input is needed to complete the task. This targeted feedback minimizes unnecessary interactions by clearly communicating what information is required, improving task accuracy while reducing overall interaction time compared to generic request-and-wait approaches.
Data Source
AI summary
The electronic device according to an embodiment may receive a first user input including a first request for performing a first task requiring one or more first parameters for execution, to transmit first data associated with the first user input through the communication circuit to a server including an intelligence system providing a sequence of action states for the electronic device performing at least one task using the at least one application program, to receive the first sequence of the action states for performing the first task, from the server through the communication circuit, to perform not all but part of the first sequence of the action states, based at least on the first user input, and to transmit second data associated with an action state of the electronic device caused from the performing of the part of the first sequence, to the server through the communication circuit.