Cabin driving comfort assessment method and system based on human intelligence, electronic equipment and medium

Abstract

The invention provides a cockpit driving comfort assessment method and system based on human intelligence, electronic equipment and a medium. The method comprises the following steps: acquiring input data for cockpit driving comfort assessment; wherein the input data comprises physiological data collected by a physiological sensor and vehicle motion data collected by a vehicle-mounted sensor when a person takes the cabin; inputting the input data into the pre-trained comfort evaluation model to obtain an output cockpit driving comfort evaluation result; wherein the comfort level evaluation model takes the acquired subjective evaluation of the cockpit driving comfort level as a label, and learns the correlation between the input data and the subjective evaluation of the cockpit driving comfort level based on a machine learning mode. According to the invention, subjective evaluation, physiological indexes and vehicle motion parameters can be fused, and a high-precision comfort level evaluation model is constructed by using a machine learning algorithm, so that real-time data acquisition and analysis in the vehicle driving process are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of personnel status assessment, and in particular to a cockpit driving comfort assessment method and system based on human factor intelligence, electronic equipment and medium. Background Art

[0002] The technology for evaluating the driving comfort of vehicle cabins is crucial to the design and manufacture of modern automobiles. It is not only directly related to the passengers' riding experience, but also has a profound impact on the market competitiveness and brand image of the vehicle. As consumers' requirements for automobile quality continue to increase, the comfort of the cabin has become one of the important considerations in car purchase decisions. Therefore, the continuous research and development and application of advanced comfort evaluation technology is the key path for the automotive industry to keep up with market trends, promote technological innovation and industrial upgrading.

[0003] At present, the evaluation of vehicle cabin driving comfort mainly relies on the following methods: (1) Subjective evaluation method: Obtain the occupants' feelings about vehicle comfort through questionnaires, subjective scoring and other means. This method is simple and direct, but it is greatly affected by the occupants' personal emotions, experience and subjective preferences, and the objectivity and consistency of the evaluation results are poor. (2) Vehicle dynamic parameter analysis: Using the vehicle's acceleration, vibration, noise and other dynamic parameters as evaluation indicators, the comfort is evaluated by using spectrum analysis, weighted acceleration evaluation and other methods. However, this method does not take into account the individual differences and physiological reactions of the occupants, and the evaluation results may deviate from the actual feelings. (3) Physiological indicator monitoring: By monitoring the occupants' heart rate, skin resistance, brain waves and other physiological signals, the comfort state of the occupants during vehicle driving is evaluated. However, existing research focuses on the collection of physiological signals, and the in-depth analysis of the signals and the correlation with comfort are insufficient.

[0004] However, the prior art has at least the following problems:

[0005] (1) Single data source, lack of multi-source data fusion, and one-sided evaluation: Only subjective evaluation, vehicle parameters or physiological indicators are considered separately, and the physiological reactions and psychological feelings of the occupants are not comprehensively considered. Multi-source data cannot be effectively integrated, and the evaluation results are not comprehensive enough to fully reflect the comfort of the occupants.

[0006] (2) Lack of real-time performance and real-time monitoring and feedback mechanisms: Most evaluation methods require post-analysis and are unable to monitor and evaluate passenger comfort in real time while the vehicle is driving. It is difficult to take timely measures to improve comfort and it is difficult to adjust vehicle parameters in a timely manner to improve comfort.

[0007] (3) Insufficient intelligence, model accuracy and adaptability: Existing methods mostly use static simple models and linear analysis, and fail to combine machine learning and / or artificial intelligence technology to capture complex nonlinear relationships. They are unable to adapt to complex and changing driving environments and individual differences, which affects the accuracy and reliability of the evaluation.

[0008] Therefore, how to provide a method and corresponding system for multi-source data fusion, real-time monitoring and feedback, and intelligent evaluation of cockpit driving comfort is a technical problem that needs to be solved urgently. Summary of the invention

[0009] In view of this, an embodiment of the present invention provides a method and system for evaluating cabin driving comfort based on human factors intelligence, an electronic device and a medium to eliminate or improve one or more defects existing in the prior art.

[0010] One aspect of the present invention provides a method for evaluating the cabin driving comfort based on human factors intelligence, the method comprising the following steps: obtaining input data for evaluating the cabin driving comfort; wherein the input data includes physiological data collected by physiological sensors when a person is riding in the cabin and vehicle motion data collected by on-board sensors; inputting the input data into a pre-trained comfort evaluation model to obtain an output cabin driving comfort evaluation result; wherein the comfort evaluation model uses the collected subjective evaluation of the cabin driving comfort as a label, and learns the correlation between the input data and the subjective evaluation of the cabin driving comfort based on machine learning.

[0011] In some embodiments of the present invention, the input data also includes external environment information obtained through vehicle-road cooperative communication; the machine learning-based method learns the correlation between the input data and the subjective evaluation of cabin driving comfort, including: learning the correlation coefficient between the physiological data, vehicle motion data and external environment information contained in the input data and the subjective evaluation of cabin driving comfort based on machine learning, so that the trained comfort assessment model can predict the output cabin driving comfort assessment result based on the input data.

[0012] In some embodiments of the present invention, the physiological data includes multiple types of electrocardiogram data, electrodermal data and electroencephalogram data; the vehicle motion data includes multiple types of speed, acceleration, vibration, steering wheel angle and brake pressure; the external environment information includes multiple types of road surface flatness, curve radius, road surface slope, traffic conditions and weather conditions.

[0013] In some embodiments of the present invention, before inputting the input data into a pre-trained comfort assessment model, the method also includes performing data cleaning, feature extraction and feature fusion processing on the input data, including: performing data cleaning on the input data including outlier processing and missing value filling; performing time domain and frequency domain analysis on the physiological data, vehicle motion data and external environment information in the input data to extract multi-dimensional features; performing feature fusion on the multi-dimensional features extracted based on the input data to construct the input data in the form of feature vectors.

[0014] In some embodiments of the present invention, the initial model used to train the comfort assessment model is a multiple linear regression model, a support vector machine model, a random forest model or a deep neural network model.

[0015] In some embodiments of the present invention, the method also includes a step of pre-training the comfort assessment model, including: obtaining subjective comfort evaluation of people riding in the cabin, using the subjective comfort evaluation as a labeled label, and constructing a training set based on the subjective comfort evaluation and the acquired input data; wherein the subjective comfort evaluation and the input data are synchronized on the timeline; determining an initial comfort assessment model and a corresponding training optimization algorithm; using the constructed training set to iteratively optimize the comfort assessment model according to the determined training optimization algorithm, and achieving pre-training of the comfort assessment model when the training meets the expected conditions.

[0016] In some embodiments of the present invention, after obtaining the output of the cabin driving comfort evaluation result, the method further includes: responding according to the real-time obtained cabin driving comfort evaluation result according to a preset feedback mechanism, and when the cabin driving comfort evaluation result is lower than a preset threshold, triggering the response mechanism of the vehicle system or providing real-time feedback to the cabin driving.

[0017] Corresponding to the above method, the present invention also provides an electronic device, including a processor, a memory, and a computer program / instructions stored in the memory, wherein the processor is used to execute the computer program / instructions, and when the computer program / instructions are executed, the electronic device implements the steps of the method described in any one of the above embodiments.

[0018] Corresponding to the above method, the present invention also provides a cockpit driving comfort evaluation system based on human factors intelligence, which includes physiological sensors for collecting physiological data, vehicle-mounted sensors for collecting vehicle motion data, a vehicle-road cooperative communication system for acquiring external environment information, and electronic equipment.

[0019] Corresponding to the above method, the present invention also provides a computer-readable storage medium on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the steps of the method described in any one of the above embodiments are implemented.

[0020] Corresponding to the above method, the present invention also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any one of the above embodiments when executed by a processor.

[0021] The cockpit driving comfort evaluation method and system based on human factors intelligence proposed in the present invention can integrate subjective evaluation, physiological indicators and vehicle motion parameters, and use machine learning algorithms to build a high-precision comfort evaluation model, thereby realizing real-time data collection and analysis during vehicle driving, timely evaluating occupant comfort, and providing feedback and response.

[0022] Additional advantages, purposes, and features of the present invention will be described in part in the following description, and will become apparent to those skilled in the art after studying the following, or may be learned from the practice of the present invention. The purposes and other advantages of the present invention may be achieved and obtained by the structures specifically indicated in the specification and the accompanying drawings.

[0023] Those skilled in the art will appreciate that the objectives and advantages that can be achieved with the present invention are not limited to the above specific description, and the above and other objectives that can be achieved by the present invention will be more clearly understood from the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention, constitute a part of the present application, and do not constitute a limitation of the present invention. In the drawings:

[0025] Figure 1 The present invention is a flowchart of a method for evaluating cabin driving comfort in one embodiment of the present invention.

[0026] Figure 2 The flowchart is a method for training a comfort assessment model in one embodiment of the present invention.

[0027] Figure 3 The present invention is a flowchart of performing cabin driving comfort assessment based on a trained comfort assessment model in one embodiment of the present invention.

[0028] Figure 4 A schematic diagram of the structure of the computer equipment included in the system. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0030] It should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only structures and / or processing steps closely related to the solutions according to the present invention are shown in the accompanying drawings, while other details that are not closely related to the present invention are omitted.

[0031] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0032] It should also be noted that, unless otherwise specified, the term “connection” herein may refer not only to a direct connection but also to an indirect connection involving an intermediate.

[0033] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0034] In order to overcome the problems of lack of multi-source data fusion, insufficient real-time performance, and low intelligence in the existing technology, a cockpit driving comfort evaluation method and system based on human factors intelligence, electronic equipment and medium are proposed. This method integrates the physiological data of the cockpit occupants, subjective evaluation data (psychological perception data) and vehicle motion parameters to perform intelligent evaluation of cockpit driving comfort, and performs intelligent evaluation of cockpit driving comfort based on a pre-trained machine learning-based comfort quantification model, which can achieve real-time, accurate and intelligent evaluation and prediction of cockpit driving comfort.

[0035] Figure 1 The flowchart of the cockpit driving comfort evaluation method in one embodiment of the present invention. The method comprises: obtaining input data for cockpit driving comfort evaluation, inputting the input data into a pre-trained comfort evaluation model, and obtaining an output cockpit driving comfort evaluation result. The input data comprises physiological data collected by physiological sensors during passengers' cockpit riding and vehicle motion data collected by on-board sensors. The comfort evaluation model uses the collected subjective evaluation of cockpit driving comfort as a label, and learns the correlation between the input data and the subjective evaluation of cockpit driving comfort based on machine learning.

[0036] The cockpit driving comfort evaluation method and system based on human factors intelligence proposed in the present invention can integrate subjective evaluation, physiological indicators and vehicle motion parameters, and use machine learning algorithms to build a high-precision comfort evaluation model, thereby realizing real-time data collection and analysis during vehicle driving, timely evaluating occupant comfort, and providing feedback and response.

[0037] In some embodiments of the present invention, the input data also includes external environment information obtained through vehicle-road cooperative communication.

[0038] Figure 1 The machine learning-based method shown in the figure learns the correlation between the input data and the subjective evaluation of the cabin driving comfort, including: learning the correlation coefficient between the physiological data, vehicle motion data and external environmental information contained in the input data and the subjective evaluation of the cabin driving comfort based on the machine learning method, so that the trained comfort evaluation model can predict the output cabin driving comfort evaluation result based on the input data.

[0039] By adopting this embodiment of the invention, the evaluation results can be combined with the vehicle-road intelligent network system, and the vehicle-road intelligent network collaborative information can be applied to comfort evaluation, optimizing vehicle operating parameters and improving overall comfort and safety.

[0040] In some embodiments of the present invention, physiological data includes but is not limited to multiple types of electrocardiogram data, electrodermal data and electroencephalogram data; vehicle motion data includes but is not limited to multiple types of speed, acceleration, vibration, steering wheel angle and brake pressure; the external environment information includes but is not limited to multiple types of road surface flatness, curve radius, road surface slope, traffic conditions and weather conditions.

[0041] By adopting this embodiment of the invention, the comfort level of cabin occupants can be comprehensively evaluated based on multi-dimensional physiological data, making the result more scientific.

[0042] In some embodiments of the present invention, before inputting the input data into a pre-trained comfort assessment model, the method further includes performing data cleaning, feature extraction and feature fusion processing on the input data, and the above preprocessing steps include: (1) performing data cleaning including outlier processing and missing value filling on the input data; (2) performing time domain and frequency domain analysis on the physiological data, vehicle motion data and external environment information in the input data to extract multi-dimensional features; (3) performing feature fusion on the multi-dimensional features extracted based on the input data to construct the input data in the form of feature vectors.

[0043] By adopting the embodiment of the invention, features of different dimensions can be extracted and integrated, and the data format can be standardized, so as to be better used in the training and testing stages of the comfort assessment model.

[0044] In some embodiments of the present invention, the initial model used to train the comfort evaluation model is a multiple linear regression model, a support vector machine model, a random forest model or a deep neural network model. The above are only examples. In essence, the comfort evaluation model is a prediction model. By learning the correlation between input data and subjective evaluation, the comfort evaluation model is learned and trained to predict the "subjective evaluation" based on the input data.

[0045] By adopting this embodiment of the invention, training can be carried out based on the initial model to obtain a comfort assessment model for predicting cabin driving comfort.

[0046] Figure 2 The flowchart of the method for training the comfort evaluation model in one embodiment of the present invention is shown in FIG. The method proposed in the present invention also includes the step of pre-training the comfort evaluation model, including:

[0047] Step S210: Obtain the subjective comfort evaluation of the passengers in the cabin, use the subjective comfort evaluation as a label, and construct a training set based on the subjective comfort evaluation and the acquired input data; wherein the subjective comfort evaluation and the input data are synchronized on the time axis.

[0048] Step S220: Determine an initial comfort evaluation model and a corresponding training optimization algorithm.

[0049] Step S230: using the constructed training set to iteratively optimize the comfort assessment model according to the determined training optimization algorithm, and achieving pre-training of the comfort assessment model when the training reaches the expected conditions.

[0050] By adopting this embodiment of the invention, a comfort evaluation model for predicting cabin driving comfort evaluation can be obtained through training, thereby realizing the method proposed by the present invention.

[0051] Furthermore, based on the above embodiments, after obtaining the output cockpit driving comfort evaluation result, the method also includes: responding according to the real-time cockpit driving comfort evaluation result according to a preset feedback mechanism, and when the cockpit driving comfort evaluation result is lower than a preset threshold, triggering the response mechanism of the vehicle system or providing real-time feedback to the cockpit driving.

[0052] By adopting this embodiment of the invention, adjustments can be made based on the real-time predicted cabin driving comfort evaluation results, including but not limited to automatic adjustment of seats, adjustment of in-vehicle temperature, adjustment of driving assistance algorithms, etc.

[0053] Figure 3 is a flow chart of performing cockpit driving comfort evaluation based on a trained comfort evaluation model in one embodiment of the present invention, Figure 3 The specific process can be summarized into the following 5 steps.

[0054] Step 1: Data collection and labeling.

[0055] (1) Physiological data collection of cockpit personnel:

[0056] Physiological sensors (such as electrocardiogram sensors, skin conductivity sensors, brain wave sensors, etc.) are used to collect physiological indicators of passengers in real time, including but not limited to heart rate (HR), heart rate variability (HRV), galvanic skin response (GSR) and brain wave (EEG).

[0057] Data labeling refers to the process of manually or automatically processing the collected raw data to add labels or attributes to it. These labels or attributes represent the category, characteristics or meaning of the data, converting unstructured data into a structured form so that machine learning models can understand and learn.

[0058] (2) Subjective comfort evaluation of cabin crew:

[0059] Obtain the occupants’ subjective evaluation of the current riding comfort through questionnaires, mobile applications or voice interaction. Subjective evaluation can be obtained using a Likert scale, such as 1-10 points, as label data y i .

[0060] (3) Vehicle motion data collection:

[0061] The vehicle motion parameters are collected by using on-board sensors such as IMU and CAN bus, including but not limited to speed (v), acceleration (α), vibration (γ), steering wheel angle and brake pressure.

[0062] (4) Data synchronization:

[0063] Establish a unified time series data set to synchronize physiological data, vehicle data, and subjective evaluation of cockpit occupants on the timeline. This step can be achieved through the timestamp of the data.

[0064] Step 2: Data preprocessing and feature analysis.

[0065] (1) Data cleaning, using outlier processing and / or missing value filling:

[0066] Outlier processing: Use the 3 times standard deviation method or box plot method to remove outliers.

[0067] Missing value imputation: Use mean imputation, interpolation, or Lagrangian method to handle missing data.

[0068] (2) Feature extraction:

[0069] Including but not limited to: feature extraction of physiological data, for example, time domain and frequency domain analysis of physiological signals such as ECG data, electrodermal data and EEG data to extract relevant features. Taking ECG as an example, time domain features include average heart rate (HR) and standard deviation of heart rate (SDNN), etc.; frequency domain features include high frequency (HF), low frequency (LF) power and LF / HF ratio, etc.

[0070] The feature extraction of vehicle data includes, but is not limited to: extracting features such as the mean, peak and root mean square (RMS) value of vehicle acceleration.

[0071] (3) Feature Fusion:

[0072] The physiological features, vehicle features and subjective evaluation data are fused to construct the feature vector Xi, which is expressed as follows:

[0073] X i =[physiological characteristics, vehicle characteristics];

[0074] Step 3: Model building and training.

[0075] (1) Correlation analysis:

[0076] Calculate the physiological and vehicle characteristics and the subjective evaluation of comfort y i The correlation coefficient r between them is used to screen important features.

[0077] (2) Model establishment:

[0078] Select appropriate machine learning algorithms, such as multivariate linear regression, support vector machine (SVM), random forest, deep neural network (DNN), etc., to establish a comfort assessment model.

[0079] Taking multiple linear regression as an example, the model expression is:

[0080] y i =β0+β1X i1 +β2X i2 +…+β p X ip +∈ i ;

[0081] Among them, β0 is the intercept, β j For feature X ij The regression coefficient, ∈ i is the error term.

[0082] (3) Model training and verification:

[0083] Divide the dataset into training set and test set (e.g., 8:2 ratio).

[0084] Use the training set to train the model and use gradient descent or other optimization algorithms to solve the model parameters.

[0085] Evaluate the model performance on the test set and calculate the mean square error (MSE), coefficient of determination (R 2 ) and other indicators.

[0086] MSE calculation:

[0087]

[0088] Coefficient of determination:

[0089]

[0090] Among them, N represents the total number, y i represents the real comfort rating value, represents the predicted comfort rating value, Indicates the average comfort level.

[0091] (4) Model optimization:

[0092] Adjust model hyperparameters and select the best model.

[0093] If a neural network is used, parameter regularization, adding a Dropout layer, and other methods can be used to prevent overfitting.

[0094] Step 4: Intelligent prediction and real-time evaluation.

[0095] (1) Real-time data input:

[0096] During the operation of the vehicle, the physiological data Xphysiological(t) of the occupants and the vehicle motion data Xvehicle(t) are collected in real time.

[0097] (2) Comfort prediction:

[0098] Input the real-time features into the trained model to predict the occupant comfort at the current moment

[0099]

[0100] (3) Feedback and Adjustment:

[0101] Based on predicted comfort If it is lower than the set threshold, the vehicle system's response mechanism is triggered, such as adjusting the suspension system, changing the driving mode, etc.

[0102] Provide real-time feedback to the driver or passengers, and prompt the current comfort status through the in-car display or voice.

[0103] Step 5: Collaborative optimization of cloud-based vehicle-road intelligent networking.

[0104] (1) External data integration:

[0105] Through vehicle-to-road cooperative communication (V2X), obtain road information (such as road surface flatness, curve radius, road surface slope), traffic conditions, weather conditions and other external environmental dataX 外部 (t).

[0106] (2) Collaborative optimization model:

[0107] Incorporating external data into the comfort assessment model can further improve prediction accuracy.

[0108]

[0109] (3) Vehicle operating parameters optimization:

[0110] Based on a comprehensive comfort assessment, the operating parameters of the intelligent driving vehicle are adjusted, such as pre-deceleration, avoiding bumpy roads, and selecting the best path, to improve the comfort of the cabin occupants.

[0111] The key points and advantages of the cockpit driving comfort evaluation method and system based on human factor intelligence proposed in the present invention are:

[0112] (1) Improving evaluation accuracy: By integrating subjective evaluation, physiological indicators, and vehicle motion parameters and using machine learning algorithms, a high-precision comfort evaluation model is constructed.

[0113] (2) Real-time monitoring and feedback: Data can be collected and analyzed in real time during vehicle driving, occupant comfort can be evaluated in a timely manner, and optimization suggestions can be provided.

[0114] (3) Enhanced intelligence level: The use of machine learning technology can handle complex nonlinear relationships and improve the adaptability and predictive ability of the model.

[0115] (4) Support vehicle-road collaborative optimization: Combine the evaluation results with the vehicle-road intelligent network system, apply the vehicle-road intelligent network collaborative information to comfort evaluation, optimize vehicle operating parameters, and improve overall comfort and safety.

[0116] Corresponding to the above method, the present invention also provides an electronic device, wherein the computer device includes a processor and a memory, the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the electronic device implements the steps of the method described above.

[0117] Corresponding to the above method, the present invention also provides a cockpit driving comfort evaluation system based on human factors intelligence, which includes physiological sensors for collecting physiological data, vehicle-mounted sensors for collecting vehicle motion data, a vehicle-road cooperative communication system for obtaining external environment information, and the electronic equipment as described above.

[0118] See also Figure 4The computer device 00 includes: a processor 01, a memory 02, and a computer program stored in the memory 02 and executable on the processor 01. When the processor 01 executes the computer program, the human factor data server access control method provided in the above method embodiment is implemented.

[0119] Among them, the processor 01 is connected to the memory 02, such as through a bus 03. The processor 01 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in combination with the contents disclosed in this application. The processor 01 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of DSP and microprocessors, etc. The bus 03 may include a path to transmit information between the above components. The bus 03 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 130 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The memory 02 is used to store a computer program corresponding to the human factor data server access control method of the above embodiment of the present application, and the computer program is controlled and executed by the processor 01. The processor 01 is used to execute the computer program stored in the memory 02 to implement the content shown in the above method embodiment.

[0120] Corresponding to the above method, the present invention also provides a computer-readable storage medium, on which a computer program / instruction is stored, and when the computer program / instruction is executed by a processor, the steps of the method described in any one of the above embodiments are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0121] Corresponding to the above method, the present invention also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any one of the above embodiments when executed by a processor.

[0122] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0123] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0124] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0125] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A cockpit driving comfort evaluation method based on human factor intelligence, characterized in that: include: Acquiring input data for evaluating cabin driving comfort; wherein the input data includes physiological data collected by physiological sensors when a person is sitting in the cabin and vehicle motion data collected by on-board sensors; Input the input data to the pre-trained comfort evaluation model to obtain the output cockpit driving comfort evaluation result; The comfort evaluation model uses the collected subjective evaluation of cockpit driving comfort as a label, and learns the correlation between the input data and the subjective evaluation of cockpit driving comfort based on machine learning.

2. The method according to claim 1, characterized in that The input data also includes external environment information obtained through vehicle-road cooperative communication; The method based on machine learning learns the correlation between the input data and the subjective evaluation of cabin driving comfort, including: learning the correlation coefficient between the physiological data, vehicle motion data and external environment information contained in the input data and the subjective evaluation of cabin driving comfort based on machine learning, so that the trained comfort evaluation model can predict the output cabin driving comfort evaluation result based on the input data.

3. The method according to claim 2, characterized in that The physiological data includes multiple types of electrocardiogram data, electrodermal data and electroencephalogram data; The vehicle motion data includes multiple of speed, acceleration, vibration, steering wheel angle and brake pressure; The external environment information includes multiple types of road surface flatness, curve radius, road surface slope, traffic conditions and weather conditions.

4. The method according to claim 3, characterized in that Before inputting the input data into the pre-trained comfort evaluation model, the method further includes performing data cleaning, feature extraction and feature fusion processing on the input data, including: Perform data cleaning on input data, including outlier processing and missing value filling; Perform time domain and frequency domain analysis on the physiological data, vehicle motion data and external environment information in the input data to extract multi-dimensional features; The multi-dimensional features extracted based on the input data are fused to construct the input data in the form of feature vectors.

5. The method according to claim 1, characterized in that The initial model used to train the comfort assessment model is a multiple linear regression model, a support vector machine model, a random forest model or a deep neural network model.

6. The method according to claim 5, characterized in that The method further comprises the step of pre-training the comfort assessment model, comprising: Obtain the subjective comfort evaluation of the passengers in the cockpit, use the subjective comfort evaluation as the label, and build a training set based on the subjective comfort evaluation and the obtained input data; wherein the subjective comfort evaluation and the input data are synchronized on the time axis; Determine the initial comfort assessment model and the corresponding training optimization algorithm; The comfort assessment model is iteratively optimized using the constructed training set according to the determined training optimization algorithm, and the comfort assessment model is pre-trained when the training reaches the expected conditions.

7. The method according to claim 1, characterized in that After obtaining the output cockpit driving comfort evaluation result, the method further includes: According to the preset feedback mechanism, a response is made based on the real-time cockpit driving comfort evaluation result. When the cockpit driving comfort evaluation result is lower than a preset threshold, the response mechanism of the vehicle system is triggered or real-time feedback is given to the cockpit driving.

8. An electronic device comprising a processor, a memory and a computer program / instruction stored in the memory, characterized in that: The processor is used to execute the computer program / instructions. When the computer program / instructions are executed, the electronic device implements the steps of the method according to any one of claims 1 to 7.

9. A cockpit driving comfort evaluation system based on human factors intelligence, comprising a physiological sensor for collecting physiological data, an on-board sensor for collecting vehicle motion data, a vehicle-road cooperative communication system for acquiring external environmental information, and the electronic device described in claim 8.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images