Voice-Driven Mobile User Recognition for Reliable Task Execution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices face challenges in executing tasks, such as transferring messages, when communication with external devices fails or the target user's location information is unavailable, leading to incomplete or invalid task execution.
Innovation Solution
An electronic device equipped with a processor, microphone, communication circuit, driving module, and sensor module that infers the target user's location and moves to that location to execute tasks, even without initial location information, by processing user utterances and recognizing the target user using stored information and sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the electronic device transmits message data to an external device for task execution, then the task can be performed remotely, but the task execution becomes invalid or incomplete when communication fails or the external device is powered off
Solution Approach 1:
The patent introduces a location inference mechanism that acts as an intermediary between the electronic device and the target user. Instead of directly communicating with the external device or user, the system infers the user's location through multiple data sources (communication circuits, sensor modules, driving modules) and physically moves to that location, thereby mediating the task execution process and ensuring completion even when direct communication fails
Solution Approach 2:
The system performs preliminary actions by inferring the target user's location before attempting task execution. The electronic device uses stored user information, communication data, and sensor information to predict and navigate to the user's location in advance, ensuring that the device is positioned correctly before the actual task (e.g., message delivery) is performed, thus preventing failed executions
2Reliability
If the electronic device requires location information of the target user to execute tasks, then task execution can be precise, but task execution becomes impossible when location information is unavailable
Solution Approach 1:
The patent implements beforehand cushioning by storing multiple types of user-related information (communication information, sensor information, location history) in advance. When the target location is unavailable, the system has pre-stored data to infer the location, cushioning against the failure scenario and ensuring task execution can proceed without requiring the original location information to be available at execution time
Solution Approach 2:
The system replaces the mechanical requirement for direct location input with an information processing and inference mechanism. Instead of mechanically requiring the user to provide or the system to obtain direct location data, the patent uses computational inference based on communication patterns, sensor data, and stored information to substitute the missing location parameter, enabling task execution without traditional location input
3Reliability
If the electronic device moves to the target user's location to execute tasks, then task execution reliability is improved, but the device consumes additional energy and time for movement
Solution Approach 1:
The patent applies dynamics by making the electronic device mobile rather than stationary. The driving module enables the device to dynamically move to the inferred target user location, adapting its position based on the task requirements and inferred user position, thereby ensuring reliable task execution while managing energy consumption through controlled, purposeful movement rather than continuous operation
Data Source
AI summary
An apparatus and method are provided for processing a user input in an electronic device. The method includes storing information associated with each of a plurality of users; receiving a user utterance associated with task execution of the electronic device; transmitting, to an external device, first data associated with the user utterance; receiving, from the external device, second data including information about at least one operation of the electronic device associated with the task execution, and at least one parameter for performing the at least one operation; identifying, as a target of the task execution, a first user from among the plurality of users based on the at least one parameter; inferring a location of the target based on information associated with the first user, which is included in the information associated with each of the plurality of users; moving the electronic device to a first location based on the inferred location; searching for the first user at the first location by comparing the information about the first user with information obtained at the first location; and in response to recognizing the first user at the first location, perform the at least one operation of the electronic device associated with the task execution.