Seamless interaction method based on intelligent cockpit audio scenario
By combining seat sensors and cameras with machine learning technology, the system identifies passenger characteristics and adjusts equipment such as the audio system, solving the problem of passengers being unable to seamlessly adjust sound effects and improving their audio experience.
Patent Information
- Authority / Receiving Office
- WO ยท WO
- Patent Type
- Applications
- Current Assignee / Owner
- CHERY AUTOMOBILE CO LTD
- Filing Date
- 2025-09-24
- Publication Date
- 2026-07-30
AI Technical Summary
In existing technologies, passengers need to adjust the sound effects and scenes using a remote control or physical buttons, which cannot achieve seamless intelligent interaction and results in a poor passenger experience.
Passenger location information is obtained through seat sensors, combined with user profiles and overall images collected by cameras, and passenger characteristics are identified using machine learning and neural network models to determine whether the passenger is a regular passenger. Based on preferences and sitting posture, the audio system, massage seats and air conditioning are adjusted.
It achieves seamless intelligent interaction, improves the efficiency of sound effect scene adjustment and the audio experience of passengers, and enhances the comfort of the ride.
Smart Images
Figure CN2025123794_30072026_PF_FP_ABST
Abstract
Claims
1. A method for non-intrusive interaction based on intelligent sound effect scene in cockpit, characterized in that, include: Pressure occupancy signals are obtained through seat sensors, and passenger position information is obtained through these pressure occupancy signals. Based on passenger location information, user profiles and overall images of passengers are obtained through cameras, and personal characteristics of passengers are obtained through the overall images of passengers. By obtaining the overall image of the passenger in the seat and the pressure occupancy signal, the sitting posture of the passenger in the seat is obtained, and the passenger's user profile is used to determine whether the passenger is a frequent passenger. Based on the preferences of frequent passengers, the passenger's sitting posture, user profile, personal characteristics and intelligent sound effect scene are interacted. According to the interactive command, the audio equipment, massage seat and air conditioning are adjusted through the audio system and linkage system.
2. The method of claim 1, wherein, The process of obtaining pressure occupancy signals through seat sensors and acquiring passenger position information through these pressure occupancy signals includes: Based on the pressure occupancy signal of each seat, machine learning and pattern recognition methods are used to obtain passenger position information on the seat; The specific methods of machine learning and pattern recognition are as follows: A classification model is trained using labeled data to identify the position of a person on a seat.
3. The method of claim 1, wherein, The step of acquiring a passenger's user profile and overall image via camera based on passenger location information includes: By adjusting the direction of the cameras inside the cabin using the passenger's location information, it becomes possible to capture an overall image of the passenger and a user profile.
4. The method of claim 1, wherein, The method of obtaining a passenger's personal characteristics through an overall image of the passenger includes: The behavioral and emotional characteristics of all passengers in history are manually labeled to obtain the feature labeling results for each passenger. The overall image is used as the input to the neural network model, and behavioral and emotional features are used as the output. The neural network model is trained using the feature labeling results of all passengers in history and the overall image to obtain the trained neural network model. The neural network model is a convolutional neural network (CNN), and the loss function used in the training process of the CNN model is the cross-entropy loss function. Based on the overall image of the passenger, the trained CNN neural network model is used to classify and judge the passenger's personal characteristics, and obtain the behavioral and emotional characteristics of the passenger's personal characteristics. Among them, all types of personal characteristics include age characteristics, gender characteristics, behavioral characteristics and emotional characteristics. Among them, age characteristics and gender characteristics are directly obtained from passenger information.
5. The method of claim 1, wherein, The process of obtaining the passenger's sitting posture through an overall image of the passenger in the seat and pressure occupancy signals, and determining whether the passenger is a frequent passenger based on the passenger's user profile, includes: Based on the pressure occupancy signal of the passenger in the seat, the sitting posture of the passenger in the seat is obtained by the center of gravity positioning method; Historical passengers are tagged and their user profiles are stored in the user database; The system uses facial recognition technology to compare the passenger's profile with the user profile in the user database to determine whether the passenger is a frequent passenger.
6. The seamless interaction method based on cockpit intelligent sound effects scenario according to claim 1, characterized in that, The system interacts with the intelligent sound effects scene based on the preferences of frequent passengers, passenger posture, user profile, personal characteristics, etc. Based on the interactive commands, the audio system and linkage system are used to adjust the audio equipment, massage chair, and air conditioning, including: The first interaction mode involves issuing commands to the audio system based on the preferences and personal characteristics of regular passengers. The second interaction mode involves issuing commands to the linkage system based on the passenger's posture, pressure occupancy signal, user profile, and cabin temperature. The audio system includes audio equipment; the linkage system includes massage chairs and air conditioning.
7. The seamless interaction method based on cockpit intelligent sound effects scenario according to claim 6, characterized in that, The first interaction mode involves issuing commands to the audio system based on the preferences and personal characteristics of frequent passengers, including: Based on passengers' preferences and personal characteristics, multimodal models are used to issue commands for adjusting sound effects and scenes, which are then used to adjust the audio system. The audio system offers directional sound field adjustment and personalized emotional sound effects space; Directional sound field adjustment includes volume level and sound field type; Personalized emotional sound effects space includes sound effect modes and music tracks.
8. The seamless interaction method based on cockpit intelligent sound effects scenario according to claim 6, characterized in that, The second interaction mode involves issuing commands to the linkage system based on the passenger's posture, pressure occupancy signal, user profile, and cabin temperature, including: The second interaction mode contains three interaction modes: the third interaction mode, the fourth interaction mode, and the fifth interaction mode. The third interaction mode adjusts the ambient lighting in the linkage system through a multimodal model based on the adjustment of the audio system. Based on the interaction results in the first interaction mode, the linkage system issues a command to adjust the ambient lighting so that it can be adjusted through the ambient lighting controller. The system uses a machine learning model to train a correlation between the volume, sound field type, sound effect mode, music mode, and ambient lighting in the audio system. Based on this correlation and the interaction results in the audio system, commands are sent to the linkage system to control the ambient lighting. The fourth interaction mode adjusts the massage seat based on the passenger's posture and pressure occupancy signal. The adjustment process of the massage chair is as follows: based on the pressure occupancy signal of the passenger on the seat and the frequency data of the passenger's sitting posture change, the massage chair is adaptively adjusted through a PID control algorithm; The fifth interaction mode adjusts the cabin air conditioning based on passenger profiles, cabin temperature, and humidity. The cabin air conditioning is adjusted using a multimodal model based on passenger profiles, cabin temperature, and humidity.
9. An electronic device, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the seamless interaction method based on a cockpit intelligent sound effect scenario as described in any one of claims 1-8.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the seamless interaction method based on a cockpit intelligent sound effect scenario as described in any one of claims 1-8.
11. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one computer instruction, the at least one computer instruction being loaded and executed by the processor to implement the seamless interaction method based on cockpit intelligent sound effects as described in any one of claims 1 to 8.
12. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium; the processor reads the computer instructions from the computer-readable storage medium and executes the computer instructions to implement the seamless interaction method based on the cockpit intelligent sound effect scenario as described in any one of claims 1 to 8.