Household appliance control method, device and system, and intelligent air conditioner by determining user sound source location based on analysis of mouth shape
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing household appliance voice recognition systems, particularly air conditioners, suffer from low accuracy due to signal attenuation and misidentification of voice commands when users are far from the device or in environments with multiple users, leading to poor user experience.
Innovation Solution
A method and system that uses a camera to determine the sound source location of the user, enhancing the audio signal pickup with an array type dual microphone, and performing control operations based on recognized voice information, including gesture and voice instructions to improve recognition accuracy and user interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If voice control is implemented for household appliances, then operational convenience is improved, but recognition accuracy deteriorates when users are far from the device
Solution Approach 1:
The camera serves as a positioning intermediary that independently determines user location regardless of distance from the appliance. By combining this visual positioning information with the audio signal processing, the system can enhance audio signals from users at any distance, maintaining voice recognition accuracy while preserving the convenience of voice control operation.
Solution Approach 2:
The system dynamically changes the audio signal processing parameters based on the user's position and distance determined by the camera. When users are far from the appliance, the system adjusts gain, filtering, and beamforming parameters to optimize signal pickup and recognition accuracy, thereby maintaining both operational convenience and recognition accuracy across different distances.
2Ease of operation
If a single gesture action is used for image-based gesture interaction, then interaction simplicity is improved, but reliability deteriorates when the gesture is irregular
Solution Approach 1:
The patent transitions from static, pre-defined gesture recognition to dynamic, continuous gesture tracking. The system captures a sequence of user images and analyzes the temporal evolution of hand positions and movements, allowing it to recognize gestures even when they are irregular or vary from standard forms. This dynamic approach maintains interaction simplicity while significantly improving recognition reliability.
Solution Approach 2:
The system performs preliminary capture of user images and analysis of movement trajectories before making a final gesture recognition determination. By preparing and analyzing the sequence of gestures in advance, the system can identify irregular gestures more reliably, reducing misrecognition while maintaining the simplicity of single-gesture interaction modes.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances voice recognition accuracy and user interaction by accurately locating the user and enhancing audio signals, leading to improved control operations and overall user experience for household appliances like air conditioners.
Implementation Method 1
acquiring image information in a household appliance scenario by means of the camera; analyzing the image information to recognize user information in the household appliance scenario; and determining the sound source location according to the user information
Implementation Method 2
enhancing at least one pickup audio signal of an array type dual microphone at the sound source location; and picking up the voice information of the user according to the at least one pickup audio signal
Data Source
AI summary
A household appliance control method, device and system, and an intelligent air conditioner are provided. The method includes that: a sound source location is determined by means of a camera; voice information of a user is picked up according to the sound source location; and at least one control operation is performed on a household appliance according to the voice information. The voice information matches at least one corresponding control instruction. By means of the method, a location of at least one user can be detected according to the camera, thereby enhancing at least one pickup audio signal at the location of the at least one user.