Intelligent cabin system
Through the intelligent cockpit system, the electromagnetic field and physiological data are detected in real time, and the emotional detection report and vehicle configuration recommendations are provided, which solves the impact of the electromagnetic field in electric vehicles on human health, and improves the car purchase experience and brand image.
Patent Information
- Application Number
- CN202411296768.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-18
- Publication Date
- 2024-11-26
AI Technical Summary
The complex electromagnetic field environment in electric vehicles poses a threat to human health, especially during the test drive process, it is difficult for users to detect the impact of electromagnetic fields on emotions in real time, affecting safe driving and car purchase decisions.
Design an intelligent cockpit system, including a cabin electromagnetic field detection module, a physiological emotion detection module and a real-time feedback module, and obtain electromagnetic field changes and physiological data in real time through sensors, and use a pre-trained emotional feedback model to provide emotional detection reports and vehicle configuration recommendations.
Real-time detection and evaluation of the electromagnetic field on human emotions is realized, providing users with healthy car purchase references, reducing selection anxiety, and improving car purchase experience and brand humanistic care.
Smart Images

Figure CN119018073A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of automobile intelligent technology, and in particular to an intelligent cockpit system. Background Art
[0002] As new energy vehicles such as electric vehicles become more and more popular and related technologies develop rapidly, electric vehicles have become a hot spot for the development of the automotive industry due to their significant advantages in environmental protection and energy structure improvement. Compared with traditional fuel vehicles, electric vehicles rely on electricity as the power source of the entire vehicle. Due to the complex and diverse models and types of electric vehicles, the numerous and complex components driven by electricity inside, and the body of the vehicle has a certain degree of shielding, and considering the superposition principle of magnetic fields, the distribution of induced magnetic fields in the car is complex, so the electromagnetic radiation scene in the car is becoming more and more complex. Passengers are close to various magnetic field sources and will inevitably be exposed to these magnetic fields. The resulting electromagnetic environment in the car is also increasingly concerned about the safety of the human body. Low-frequency magnetic fields have a variety of biological effects, which will have negative effects on the human body, such as headaches, insomnia, memory loss, increased or decreased blood pressure, and borderline abnormalities in the heart, which seriously endanger human health.
[0003] Current measurement technology can effectively monitor the electromagnetic field levels of different frequencies in the environment. Different organisms have different physical constitutions. When exposed to the same electromagnetic field environment, the physiological changes in the body will also be different. The physiological changes in the body directly determine the emotional state of the individual exposed to the electromagnetic field. Safety psychology research generally believes that it is impossible for a person to think or perform an action without the involvement of the emotional system. Whether it is explicit or implicit, emotional issues are a key factor that cannot be avoided in safe driving. Therefore, by evaluating the emotional changes of individuals exposed to electromagnetic environments, customers can be provided with a purchase reference when purchasing new energy vehicles. Summary of the invention
[0004] In order to enable users to detect the impact of electromagnetic fields on human emotions in real time during a test drive and provide a detection report, the present invention proposes an intelligent cockpit system, which includes:
[0005] Cabin electromagnetic field detection module: used to obtain the electromagnetic field changes of the car in the stationary, driving and charging states in real time through sensors;
[0006] Physiological emotion detection module: used to collect the user's physiological data in real time, and convert the acquired physiological data into emotional state according to the level of emotional arousal and the level of valence. The arousal is used to represent the intensity of the emotion, and the valence is used to represent whether the emotion is positive or negative;
[0007] Real-time feedback module: used to receive data from the cabin electromagnetic field detection module and the physiological emotion detection module in real time, input the received data into the pre-trained emotion feedback model, and obtain feedback results. The feedback results are used to characterize whether the user will have emotional fluctuations when test driving under the corresponding car configuration;
[0008] Prediction and recommendation module: used to input the user's physiological data into the human-vehicle matching model, output the vehicle configuration that will evoke the user's emotional response and the electromagnetic field level corresponding to the vehicle configuration, and output evaluation reports and purchase recommendations in the form of charts.
[0009] Furthermore, the cabin electromagnetic field detection module includes an electromagnetic field detection unit, a vehicle speed collection unit and a charge and discharge detection unit. The electromagnetic field detection unit is used to detect the electromagnetic field of the car in a stationary, moving and charging state. The vehicle speed collection unit is used to determine whether the car is in a stationary or moving state. The charge and discharge detection unit is used to determine whether the car is in a discharging or charging state.
[0010] Furthermore, the physiological emotion detection module includes a physiological data acquisition unit and an emotion conversion unit. The physiological data acquisition unit is signal-connected to the emotion conversion unit. The physiological acquisition unit is used to collect EEG, respiration, ECG, EG, EMG and body temperature data. The emotion conversion unit obtains data from the physiological signal acquisition unit and is used to convert the physiological data into an emotional state according to the level of emotional arousal and the level of valence.
[0011] Furthermore, the physiological data acquisition unit includes an EEG acquisition headband and a physiological acquisition watch. The physiological acquisition watch is used to collect breathing, electrocardiogram, skin electricity, electromyography and body temperature data of the human body exposed to an electromagnetic environment. The EEG acquisition headband is used to collect brain wave data of the human body exposed to an electromagnetic environment.
[0012] Furthermore, the emotion conversion unit includes an emotion recognition subunit and an emotion fusion subunit. The emotion recognition subunit is used to identify the level of emotional arousal and the level of valence corresponding to a single physiological data to obtain the emotional state corresponding to the single physiological data. The emotion fusion subunit is used to fuse the data of the emotion recognition subunit through a neural network to output the user's emotional state.
[0013] Furthermore, the method for the emotion fusion subunit to fuse emotions is:
[0014] S11. Collect physiological data generated by human body exposed to the electromagnetic environment of the car cabin through the EEG collection headband and the physiological collection watch, and perform filtering and denoising on the collected physiological data;
[0015] S12, extracting features from the single physiological data by using a time domain feature extraction method, matching the features with the level of emotional arousal and the level of valence, and obtaining a single emotion type;
[0016] S13, the single emotion types in step S12 are integrated through a neural network, and matched according to the level of emotional arousal and the level of valence to obtain the user's emotional state.
[0017] Furthermore, the real-time feedback module includes a wireless data receiving unit, a data preprocessing unit and an emotion feedback unit. The wireless data receiving unit is used to receive data sent by the cabin electromagnetic field detection module and the physiological emotion detection module. The data preprocessing unit is used to classify and process the data received by the wireless data receiving unit. The emotion feedback unit is used to input the data processed by the data preprocessing unit into a trained emotion feedback model to obtain whether the user will have emotional fluctuations when test driving under a certain vehicle configuration.
[0018] Furthermore, the emotional feedback model is constructed as follows:
[0019] S21, obtaining the electromagnetic fields of the vehicle in different configurations when it is stationary, moving, and charging, extracting features of the electromagnetic fields, and determining the relationship between the changes in the electromagnetic fields of different vehicle configurations when they are stationary, moving, and charging through machine learning;
[0020] S22, obtaining emotional states corresponding to physiological data of people with different physiques exposed to different electromagnetic environments;
[0021] S23. Divide the data sets obtained in step S21 and step S22 into a training set and a verification set, input the training set into the deep learning model, obtain an emotional feedback model corresponding to the emotional state of different physiques under different electromagnetic fields, and verify the accuracy and effectiveness of the model through the verification set.
[0022] Furthermore, the feedback recommendation module includes a person-vehicle matching unit and a report generating unit. The person-vehicle matching unit is used to recommend corresponding vehicle models and accessories according to the person-vehicle matching model. The report generating unit is used to generate an evaluation report and purchase recommendations in the form of charts according to the results output by the person-vehicle matching unit.
[0023] Furthermore, the prediction method of the human-vehicle matching model is:
[0024] S31. Classify the electromagnetic fields generated by cars with different configurations into corresponding levels from low to high, that is, each level of electromagnetic field has a corresponding vehicle configuration;
[0025] S32, matching the user's physiological indicators with electromagnetic fields of different levels to obtain the corresponding electromagnetic field level that will cause emotional fluctuations in the user;
[0026] S33: Output the car model and accessories that have the least impact on the user's emotional fluctuations as recommendations.
[0027] Compared with the prior art, the present invention has the following beneficial effects:
[0028] The present invention provides an intelligent cockpit system, which can obtain electromagnetic field data and physiological emotion state data through the cockpit electromagnetic field detection module and the physiological emotion detection module, and can provide users with real-time test drive emotion detection reports during the test drive through the real-time feedback module, and can also obtain users' physiological data during the test drive through the prediction and recommendation module, and input the data into the pre-trained human-vehicle matching model to provide users with suitable vehicle configurations. The present invention provides users with purchase advice from the perspective of physiological health, reflecting the brand's concept of humanistic care. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0030] Figure 1 The figure is a schematic diagram of the overall structure of an intelligent cockpit system proposed by the present invention. DETAILED DESCRIPTION
[0031] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0032] Reference Figure 1 , this embodiment provides a smart cockpit system, the system comprising:
[0033] Cabin electromagnetic field detection module: used to obtain real-time changes in the electromagnetic field of the car when it is stationary, moving, and charging through sensors. Different combinations of car models and accessories will produce different electromagnetic fields. That is, by detecting the electromagnetic field intensity generated by each car model accessory, and using the electromagnetic field intensity as the basis for classifying the car model configuration, it provides customers with a selection reference and reduces users' choice anxiety from a health perspective.
[0034] The cabin electromagnetic field detection module includes an electromagnetic field detection unit, a vehicle speed collection unit and a charge and discharge detection unit. The electromagnetic field detection unit is used to detect the electromagnetic field of the car when it is stationary, moving, and charging. The vehicle speed collection unit is used to determine whether the car is stationary or moving. The charge and discharge detection unit is used to determine whether the car is discharging or charging.
[0035] The electromagnetic field strength generated by new energy vehicles in different states is also different. For example, as the driving speed increases or decreases, the electromagnetic field strength at the same position will increase accordingly. The location of the battery, motor and inverter will also affect the electromagnetic field distribution in the cabin of the electric vehicle. For example, if the battery is located at the front of the car, the electromagnetic field is smaller in the back seat position, and in a car where the battery is located in the trunk or under the back seat, the electromagnetic field is smaller in the front seat position. The driving mode of the vehicle will also affect the electromagnetic field level generated. The motor and inverter of the rear-wheel drive vehicle are located at the rear, while the situation of the front-wheel drive vehicle is the opposite. The seats closer to the motor and inverter will have higher electromagnetic field exposure. In addition to the electromagnetic field that may be generated by electric drive equipment due to current induction, secondary electromagnetic fields are also generated during driving, such as the low-frequency magnetic field generated by steel tires magnetized by geomagnetic induction. Electric vehicle charging methods can be divided into two types: DC wired charging and wireless charging. The mainstream wireless power transmission technology uses the coil electromagnetic induction method. Compared with wired charging, it is more likely to expose the human body to a higher amplitude electromagnetic field. This electromagnetic field is larger than the electromagnetic field during normal driving and is more likely to cause users to have emotional fluctuations while using the car.
[0036] Physiological emotion detection module: used to collect the user's physiological data in real time, and convert the acquired physiological data into emotional state according to the level of emotional arousal and valence. The arousal is used to characterize the intensity of the emotion, and the valence is used to characterize whether the emotion is positive or negative. The valence-arousal two-dimensional emotion model maps emotions in a two-dimensional coordinate space. Low-valence emotions will reduce driving level, and high-priority necessary driving tasks will be most affected, such as keeping lanes, steering, accelerating and braking. High-arousal emotions will have a negative impact on driving performance in high-mental workload driving tasks. Moderate arousal is the optimal arousal level, which is a sign of a good user experience.
[0037] The physiological emotion detection module includes a physiological data acquisition unit and an emotion conversion unit. The physiological data acquisition unit is connected to the emotion conversion unit signal. The physiological acquisition unit is used to collect EEG, respiration, ECG, skin electricity, myoelectricity and body temperature data. The emotion conversion unit obtains data from the physiological signal acquisition unit and is used to convert the physiological data into an emotional state according to the level of emotional arousal and the level of valence. The physiological data acquisition unit includes an EEG acquisition headband and a physiological acquisition watch. The physiological acquisition watch is used to collect respiration, ECG, skin electricity, myoelectricity and body temperature data of the human body exposed to an electromagnetic environment. The EEG acquisition headband is used to collect brain wave data of the human body exposed to an electromagnetic environment.
[0038] Neurophysiological signals are objective and difficult to disguise. They can measure the level of physiological activation and reflect the state of emotional arousal. Electrodermal activity (EDA), heart rate variability (HRV), breathing rate (BR), and electroencephalogram (EEG) are often used in emotion recognition tasks. For example, different EEG frequency bands are related to the state of consciousness, and breathing rate is related to the valence and arousal of emotions. Monitoring changes in physiological signals in the cockpit helps to pay attention to the driver's state. During the test drive, users collect physiological data by wearing an EEG collection headband and a physiological collection watch. The EEG collection headband can be set in the form of a sun hat to minimize the user's discomfort when collecting physiological data.
[0039] The emotion conversion unit includes an emotion recognition subunit and an emotion fusion subunit. The emotion recognition subunit is used to identify the level of emotional arousal and valence corresponding to a single physiological data, and obtain the emotional state corresponding to the single physiological data. The emotion fusion subunit is used to fuse the data of the emotion recognition subunit through a neural network and output the user's emotional state. Converting a single physiological data into an emotional state and presenting it to the user through a report can allow the user to more intuitively feel the changes in the body during the test drive. A single physiological signal cannot accurately and completely represent the user's emotional state, that is, it is necessary to fuse the multimodal features of the physiological signal to identify the user's emotional state.
[0040] Furthermore, the method for the emotion fusion subunit to fuse emotions is:
[0041] S11. The physiological data generated by the human body exposed to the electromagnetic environment of the car cabin is collected through the EEG collection headband and the physiological collection watch. The collected physiological data is filtered and denoised to make the signal clearer, highlight the important features in the signal, and improve the quality of the data. For the subsequent data processing algorithm, it can significantly improve the performance and accuracy of the algorithm.
[0042] S12. Use the time domain feature extraction method to extract features from single physiological data, match the features with the level of emotional arousal and the level of valence, and obtain a single emotion type. Use a machine learning algorithm to match the extracted physiological data features with emotional valence and arousal, learn the relationship between physiological data features and emotional states through a training model, and match single physiological data features with emotional arousal and valence. Time domain feature extraction directly analyzes the signal on the time axis and can intuitively reflect the original characteristics of the signal, such as amplitude, period, frequency, etc. Compared with frequency domain analysis, time domain feature extraction usually has a smaller amount of calculation, and can quickly obtain results for physiological signals that need to be processed in real time, that is, it can effectively extract key information from physiological data that helps improve the performance of neural networks and prediction accuracy.
[0043] S13, the single emotion type in step S12 is fused through a neural network, and matched according to the emotional arousal and valence to obtain the user's emotional state. In the valence-arousal two-dimensional emotion model, the emotional state can be represented by the position in the two-dimensional space. Through the output of the neural network model, the single emotion type can be mapped to this two-dimensional space to obtain the valence and arousal score of the emotion, that is, the single emotion type is converted into a fused emotional state in the valence-arousal two-dimensional emotion model.
[0044] Real-time feedback module: used to receive data from the cabin electromagnetic field detection module and the physiological emotion detection module in real time, input the received data into a pre-trained emotion feedback model, and obtain feedback results, which are used to characterize whether the user will experience emotional fluctuations when test driving under the corresponding vehicle configuration. The real-time feedback module includes a wireless data receiving unit, a data preprocessing unit, and an emotion feedback unit. The wireless data receiving unit is used to receive data sent by the cabin electromagnetic field detection module and the physiological emotion detection module. The data preprocessing unit is used to classify and process the data received by the wireless data receiving unit. The emotion feedback unit is used to input the data processed by the data preprocessing unit into a trained emotion feedback model to obtain whether the user will experience emotional fluctuations when test driving under a certain vehicle configuration.
[0045] Test driving is an essential step for users before buying a car. Usually, after the test drive, users are prone to impulse buying due to their subjective will and the salesperson's guidance. For a large expenditure like buying a car, the cost of impulse buying is immeasurable according to the consumption level of different users. In order to avoid the negative butterfly effect of user dissatisfaction on the brand, real-time emotional fluctuation detection caused by electromagnetic fields is provided during the user's test drive, providing reference opinions for users when purchasing, and also providing a new angle for sales staff to introduce users to new energy vehicles currently supported by the country.
[0046] The construction method of the emotional feedback model is:
[0047] S21, obtaining the electromagnetic fields of the vehicle in different configurations when it is stationary, moving, and charging, extracting features of the electromagnetic fields, and determining the relationship between the changes in the electromagnetic fields of different vehicle configurations when they are stationary, moving, and charging through machine learning;
[0048] S22, obtaining emotional states corresponding to physiological data of people with different physiques exposed to different electromagnetic environments;
[0049] S23. Divide the data sets obtained in step S21 and step S22 into a training set and a verification set, input the training set into the deep learning model, obtain an emotional feedback model corresponding to the emotional state of different physiques under different electromagnetic fields, and verify the accuracy and effectiveness of the model through the verification set.
[0050] By constructing an emotional feedback model, users can obtain real-time emotional feedback during the test drive, and then understand whether new energy vehicles will have an impact on themselves. From a sales perspective, it provides users with quantifiable purchasing opinions, and from the perspective of promoting new energy vehicles, it also provides users with quantifiable evaluation reports, which not only brings benefits to the brand, but also has a positive effect on the promotion of new energy vehicles.
[0051] Prediction and recommendation module: used to input the user's physiological data into the human-vehicle matching model, output the vehicle configuration that will evoke the user's emotional response and the electromagnetic field level corresponding to the vehicle configuration, and output the evaluation report and purchase recommendation in the form of a chart. The feedback recommendation module includes a human-vehicle matching unit and a report generation unit. The human-vehicle matching unit is used to recommend the corresponding vehicle model and accessories according to the human-vehicle matching model, and the report generation unit is used to generate an evaluation report and purchase recommendation in the form of a chart based on the results output by the human-vehicle matching unit.
[0052] The user is not satisfied with the current test drive vehicle, but test driving every model and configuration will greatly waste the user's time cost and the brand's human resources. That is, during the test drive, the user's physiological data is input into the pre-trained human-vehicle matching model, and the model configuration that will evoke the user's emotional response and the model configuration that is suitable for the user are output, providing reference opinions for the user's next test drive and purchase. The evaluation report includes the electromagnetic field strength of the current test drive model configuration in different states, and the corresponding physiological and emotional state; the emotional state represented by a single physiological signal; and the prediction of suitable models and vehicle accessories based on the physiological and emotional data of the test drive. Through the output evaluation report, users can intuitively understand the changes in their bodies during the test drive and make references for subsequent purchases.
[0053] The prediction method of the human-vehicle matching model is:
[0054] S31. The electromagnetic fields generated by cars with different configurations are divided into corresponding levels from low to high, that is, each level of electromagnetic field has a corresponding vehicle configuration. Different vehicle configurations generate different electromagnetic fields due to the combination of models and accessories. That is, dividing vehicle configurations by the strength of the electromagnetic field can provide users with more intuitive purchase recommendations.
[0055] S32. Match the user's physiological indicators with different levels of electromagnetic fields to obtain the corresponding electromagnetic field level that will cause the user to have emotional fluctuations. Everyone's physiological characteristics are more or less different. From a macro perspective, these small differences have little impact on our daily lives. From the perspective of microscopic electromagnetic fields, a little physiological difference will have a greater impact on the user's emotions. The user's physiological data is input into the human-vehicle matching model, and the model performs feature analysis on the physiological data. By identifying the features, the corresponding electromagnetic field level that may cause emotional fluctuations can be matched.
[0056] S33: Output the vehicle model and accessories that have the least impact on the user's emotional fluctuations as a recommendation. The human-vehicle matching model pre-identifies the characteristics of different physiological parameters and matches them with electromagnetic fields of different intensities. When new data is input, the human-vehicle matching model can quickly identify its characteristics and perform electromagnetic field matching based on the characteristics, thereby outputting a vehicle configuration suitable for the user.
[0057] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. An intelligent cockpit system, characterized in that: The system comprises: Cabin electromagnetic field detection module: used to obtain the electromagnetic field changes of the car in the stationary, driving and charging states in real time through sensors; Physiological emotion detection module: used to collect the user's physiological data in real time, and convert the acquired physiological data into emotional state according to the level of emotional arousal and the level of valence. The arousal is used to represent the intensity of the emotion, and the valence is used to represent whether the emotion is positive or negative; Real-time feedback module: used to receive data from the cabin electromagnetic field detection module and the physiological emotion detection module in real time, input the received data into the pre-trained emotion feedback model, and obtain feedback results. The feedback results are used to characterize whether the user will have emotional fluctuations when test driving under the corresponding car configuration; Prediction and recommendation module: used to input the user's physiological data into the human-vehicle matching model, output the vehicle configuration that will evoke the user's emotional response and the electromagnetic field level corresponding to the vehicle configuration, and output evaluation reports and purchase recommendations in the form of charts.
2. The intelligent cockpit system according to claim 1, characterized in that: The cabin electromagnetic field detection module includes an electromagnetic field detection unit, a vehicle speed collection unit and a charge and discharge detection unit. The electromagnetic field detection unit is used to detect the electromagnetic field of the car when it is stationary, moving, and charging. The vehicle speed collection unit is used to determine whether the car is stationary or moving. The charge and discharge detection unit is used to determine whether the car is discharging or charging.
3. The intelligent cockpit system according to claim 1, characterized in that: The physiological emotion detection module includes a physiological data acquisition unit and an emotion conversion unit. The physiological data acquisition unit is connected to the emotion conversion unit signal. The physiological acquisition unit is used to collect EEG, respiration, ECG, skin electricity, myoelectricity and body temperature data. The emotion conversion unit obtains data from the physiological signal acquisition unit and is used to convert the physiological data into an emotional state according to the level of emotional arousal and the level of valence.
4. The intelligent cockpit system according to claim 3, characterized in that: The physiological data acquisition unit includes an EEG acquisition headband and a physiological acquisition watch. The physiological acquisition watch is used to collect breathing, electrocardiogram, skin electricity, myoelectricity and body temperature data of the human body exposed to an electromagnetic environment. The EEG acquisition headband is used to collect brain wave data of the human body exposed to an electromagnetic environment.
5. The intelligent cockpit system according to claim 3, characterized in that: The emotion conversion unit includes an emotion recognition subunit and an emotion fusion subunit. The emotion recognition subunit is used to identify the level of emotional arousal and valence corresponding to a single physiological data to obtain the emotional state corresponding to the single physiological data. The emotion fusion subunit is used to fuse the data of the emotion recognition subunit through a neural network to output the user's emotional state.
6. The intelligent cockpit system according to claim 5, characterized in that: The method for fusing emotions by the emotion fusion subunit is: S11. Collect physiological data generated by human body exposed to the electromagnetic environment of the car cabin through the EEG collection headband and the physiological collection watch, and perform filtering and denoising on the collected physiological data; S12, extracting features from the single physiological data by using a time domain feature extraction method, matching the features with the level of emotional arousal and the level of valence, and obtaining a single emotion type; S13, the single emotion types in step S12 are integrated through a neural network, and matched according to the level of emotional arousal and the level of valence to obtain the user's emotional state.
7. The intelligent cockpit system according to claim 1, characterized in that: The real-time feedback module includes a wireless data receiving unit, a data preprocessing unit and an emotion feedback unit. The wireless data receiving unit is used to receive data sent by the cabin electromagnetic field detection module and the physiological emotion detection module. The data preprocessing unit is used to classify and process the data received by the wireless data receiving unit. The emotion feedback unit is used to input the data processed by the data preprocessing unit into a trained emotion feedback model to obtain whether the user will have emotional fluctuations when test driving under a certain vehicle configuration.
8. The intelligent cockpit system according to claim 1, characterized in that: The construction method of the emotional feedback model is: S21, obtaining the electromagnetic fields of the vehicle in different configurations when it is stationary, moving, and charging, extracting features of the electromagnetic fields, and determining the relationship between the changes in the electromagnetic fields of different vehicle configurations when they are stationary, moving, and charging through machine learning; S22, obtaining emotional states corresponding to physiological data of people with different physiques exposed to different electromagnetic environments; S23. Divide the data sets obtained in step S21 and step S22 into a training set and a verification set, input the training set into the deep learning model, obtain an emotional feedback model corresponding to the emotional state of different physiques under different electromagnetic fields, and verify the accuracy and effectiveness of the model through the verification set.
9. The intelligent cockpit system according to claim 1, characterized in that: The feedback recommendation module includes a person-vehicle matching unit and a report generation unit. The person-vehicle matching unit is used to recommend corresponding vehicle models and accessories according to the person-vehicle matching model. The report generation unit is used to generate an evaluation report and purchase recommendations in the form of charts based on the results output by the person-vehicle matching unit.
10. The intelligent cockpit system according to claim 1, characterized in that: The prediction method of the human-vehicle matching model is: S31. Classify the electromagnetic fields generated by cars with different configurations into corresponding levels from low to high, that is, each level of electromagnetic field has a corresponding vehicle configuration; S32, matching the user's physiological indicators with electromagnetic fields of different levels to obtain the corresponding electromagnetic field level that will cause emotional fluctuations in the user; S33: Output the car model and accessories that have the least impact on the user's emotional fluctuations as recommendations.
Citation Information
Cited By
Vehicle chassis hybrid simulation test system
CN120686644A
