Warm low-potential intelligent cabin system, control method and storage medium

Abstract

The invention relates to the technical field of intelligent cabins and health detection, in particular to a warm low-potential intelligent cabin system, a control method and a storage medium, and the system comprises a low-potential warm treatment module, a physiological parameter monitoring module, a vehicle-mounted central control system, an intelligent regulation and control system and a data visualization module. The vehicle-mounted central control system is respectively connected with the low-potential thermotherapy module, the physiological parameter monitoring module, the intelligent regulation and control system and the data visualization module; according to the invention, through the low-potential thermotherapy module, a thermotherapy function and a low-potential therapy function are integrated in the intelligent cabin, an omnibearing physiotherapy environment is created, a user can enjoy professional services during driving, the integration of driving and health maintenance is realized, and the health experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent cockpits and health detection, and more specifically, to an intelligent cockpit system with warm and low potential, a control method, and a storage medium. Background Art

[0002] With the continuous development of communication and Internet technologies, a high-quality driving environment has become an important part of modern life. Against the background of the rapid development of new energy vehicle intelligent driving technology, the importance of intelligent driving has become increasingly prominent. Its intuitive, convenient, and easy-to-accept characteristics have gradually made it the mainstream trend of driving methods. In recent years, many new energy vehicle manufacturers have launched a series of convenient driving functions to significantly improve the driving experience. Taking the intelligent cockpit as an example, this innovative function has not only strongly promoted the widespread popularity of new energy vehicles but also brought a more excellent driving experience to consumers, further expanding the comfort and convenience of driving. However, with the continuous development of the new energy vehicle industry, the deficiencies of the intelligent cockpit have gradually emerged. In terms of health physiotherapy, most cars are only equipped with a basic seat heating function, which requires manual temperature setting and is difficult to adjust immediately during driving to meet personal needs, and its heating effect is difficult to reach the physiotherapy standard for relieving fatigue.

[0003] The prior art discloses a far-infrared heating physiotherapy car seat and its usage method, including a seat body, a fixing structure is provided on the seat body, and a hip physiotherapy structure and a back physiotherapy structure are provided on the fixing structure; the fixing structure includes: two telescopic sleeves, two telescopic columns, two positioning seats, a positioning groove, two telescopic belts, and two buckles. However, this aspect does not have a low-potential function and is difficult to reach the physiotherapy standard. It cannot provide a more comfortable experience. Summary of the Invention

[0004] The purpose of the present invention is to disclose an intelligent cockpit system and a storage medium with warm and low-potential functions.

[0005] To achieve the above purpose, the present invention provides an intelligent cockpit system with warm and low potential, including:

[0006] A low-potential warm treatment module, a physiological parameter monitoring module, an in-vehicle central control system, an intelligent regulation system, and a data visualization module; the in-vehicle central control system is respectively connected to the low-potential warm treatment module, the physiological parameter monitoring module, the intelligent regulation system, and the data visualization module;

[0007] The low-potential warm treatment module is integrated into the intelligent cockpit through embedded technology, and the operation parameters of the low-potential warm treatment module are regulated by the in-vehicle central control system;

[0008] The physiological parameter monitoring module consists of a multi-modal biosensor array, which acquires multiple physiological indicators of the driver in real time and transmits them to the vehicle-mounted central control system;

[0009] The data visualization module presents the processed physiological data on the vehicle-mounted display screen in real time;

[0010] The intelligent regulation module acquires physiological data, dynamically optimizes treatment parameters, and feeds back the optimal parameters to the central control system.

[0011] Furthermore, the low-potential thermotherapy module includes: a warming sub-module and a low-potential sub-module;

[0012] Among them, the warming sub-module transmits the voltage value read from the temperature sensor inside the warming low-potential seat cushion to the CPU. The CPU obtains the temperature value T0 inside the seat cushion at this time. The CPU sends this temperature value T0 to the vehicle-mounted central control system through the Bluetooth module. The vehicle-mounted central control system obtains the temperature value and conducts comprehensive analysis and calculation through the health monitoring data, and sends the T1 value required to maintain the seat cushion temperature to the CPU control module of the warming low-potential controller through the Bluetooth module. The CPU control module controls the output voltage at both ends of the heating wire in a PWM manner, thereby controlling the heating power of the heating wire and maintaining the current T0 temperature stable at T1.

[0013] Furthermore, the low-potential sub-module includes:

[0014] When the fatigue index of the health-monitored driver increases, the vehicle-mounted central control system sends low-potential intensity index data to the warming low-potential controller. Inside the controller, the negative potential frequency conversion and voltage transformation module circuit is controlled to apply the low potential to the heating wire, so as to output an appropriate low potential intensity to relieve fatigue for the current driver's fatigue state. When it is monitored that the driver's mental state recovers, the vehicle-mounted central control system will control the output of the low potential in real time to form a closed loop.

[0015] Furthermore, the physiological parameter monitoring module includes:

[0016] Heart rate measurement: Measure the heart rate based on the camera detection method; Use the camera in the intelligent cockpit to capture the facial video of the driver, with a recording frame rate of 30fps and a resolution of 1980*1240, to capture the subtle physiological changes in the face; Use the face detection algorithm of the dlib library in python to detect the face in each frame of the image, obtain the bounding box of the face and crop the face to obtain the driver's facial area; Extract the G-channel value of each pixel from the face and calculate the average RGB value of all pixels in this area:

[0017]

[0018] The value of the G channel of the i-th pixel at time t is denoted as Gi(t), and N is the total number of pixels in the region.

[0019] Perform band-pass filtering on G(t); the band-pass filter uses a Butterworth filter, with a sampling frequency of 30 HZ, a low cut-off frequency of 0.5 HZ, and a high cut-off frequency of 3 HZ to remove high-frequency noise and remaining low-frequency interference; the order of the filter is set to 4 to balance the filtering effect and computational complexity.

[0020] G f (t) = filter(G(t))

[0021] Normalize the filtered signal to eliminate the influence of amplitude variations, and then perform a fast Fourier transform to obtain the spectrum; find the peak fpeak from the spectrum, which is the spectrum corresponding to the heart rate.

[0022]

[0023] X(f) = FFT(G n (t))

[0024] HR = 60 * f peak

[0025] Furthermore, the physiological parameter monitoring module further includes:

[0026] Heart rate variability: Detect heart rate variability based on photoplethysmography; the PPG sensor emits green light into the skin tissue, and the change in light absorption caused by subcutaneous blood flow generates a pulse wave signal x(t); then use a band-pass filter to remove low-frequency drift and high-frequency noise, and use a moving average filter to smooth the signal.

[0027]

[0028] After preprocessing, extract the pulse wave features. First, check the peak-to-peak value of the pulse wave in the PPG signal. The peak sequence is denoted as T = {t1, t2, t3, …, tn}, calculate the intervals between adjacent peaks to generate a PPI sequence, and calculate the SDNN (standard deviation during RR), where RR is the mean of the intervals during the wave peaks.

[0029] PPI i = t i+1 - t i (i = 1, 2, …, n - 1)

[0030] RR i = PPI i (i = 1, 2, …, n - 1)

[0031]

[0032] Furthermore, the physiological parameter monitoring module further includes:

[0033] Blood oxygen saturation: The skin is irradiated with red light and infrared light. The collected PPG signal includes a red light PPG signal and an infrared light PPG signal, and the two are separated according to different wavelengths; a low-pass filter is used to decompose the DC component and the AC component of each of them; then, the eigenvalue R of blood oxygen is obtained according to linear regression, and the blood oxygen saturation is calculated by a formula;

[0034] For red light:

[0035] I red,DC = LPF(I red (t))

[0036] I red,AC = I red (t) - I red,DC

[0037] For infrared light:

[0038] I IR,DC = LPF(I IR (t))

[0039] I IR,AC = I IR (t) - I IR,DC

[0040] Calculate the ratio R of the DC component and the AC component of the red light and infrared light PPG signals:

[0041]

[0042] Through an empirical formula, the R value can be converted into blood oxygen saturation:

[0043] SPO2 = 110 - 25R.

[0044] Furthermore, the intelligent regulation module includes:

[0045] Prediction target: According to the human body index parameters at time t, predict the two control parameters, namely voltage and temperature, of the warm and low potential at time t + 1 to achieve intelligent regulation of the parameters; prevent the physical state of the driver from being abnormal due to improper setting of temperature or voltage;

[0046] Data collection: The human body index, voltage and temperature values at time t, the model predicts the voltage and temperature at time t + 1, and the human body index at time t + 1 after the control parameters are changed;

[0047] Settings for reinforcement learning training:

[0048] Environment: An external system that interacts with the prediction model, providing status and reward feedback.

[0049] Status: Human body metric parameters at time t, such as heart rate ht, heart rate variability Vt, blood oxygen saturation SOt, etc.;

[0050] Action: Predicted voltage Ut+1 and temperature value Tt+1.

[0051] Reward: Based on the predicted voltage and temperature, change the set value, obtain the human body metrics at time t+1 through sensors, and use the difference from the normal and stable state as the reward function; if the human body metrics after adjusting the voltage and temperature are far from the normal value, it is regarded as a penalty, otherwise it is regarded as a reward;

[0052] Model Architecture

[0053] Encoder: An LSTM-based encoder that can capture long-term dependencies in time series data. Stack 3 LSTM layers, and the output is the hidden state of the LSTM, encoding the human body metric parameters into a 256-dimensional feature vector;

[0054] Predictor: Based on three linear fully connected layers, with output dimensions of 64, 16, and 2 respectively; the fully connected layers learn the mapping relationship between the human feature vector and the set parameters, mapping the 256-dimensional feature vector of the encoder into voltage values and temperature values;

[0055] Initialize the encoder and predictor in the way of the deep learning pytorch framework. Select the adaptive momentum optimizer to update the model parameters. At the same time, use the learning rate warm-up algorithm to update the learning rate, that is, at the beginning of training, gradually increase the learning rate to accelerate the convergence speed of the model, and then after iterating to a certain number of rounds, gradually decrease the learning rate to help the model converge to the optimal solution; the initial learning rate is set to 0.001, and the weight decay is set to 0.9 to prevent overfitting. The learning rate warm-up algorithm adopts the cosine increase strategy, and the learning rate increases from 0 according to the cosine function to the initial learning rate;

[0056] Train based on the reinforce algorithm.

[0057] Furthermore, training based on the reinforce algorithm includes:

[0058] The reinforce algorithm is a reinforcement learning algorithm based on gradient strategy, which directly updates the parameters to maximize the cumulative expected return and is suitable for continuous value parameter prediction tasks;

[0059] The core idea of the reinforce algorithm is to calculate the policy gradient by sampling trajectories and update the policy network parameters to maximize the expected cumulative reward.

[0060] In the driving environment, a sampling period of 5 minutes is used for sampling. For each second, the values of the voltage U and temperature T for the next second are predicted, and after obtaining the set parameters, the human body indicators are recorded as Xi = {Ht, Vt, SOt}, and the normal indicators x normal = {h = 80, V = 150, SO = 0.96}.

[0061] Reward for single prediction:

[0062]

[0063] Collect data for one period from the environment and calculate the cumulative return expectation:

[0064] G t = τ t + γτ t+1 + γ 2 τ t+2 +…+ γ T-1 τ T

[0065] where t is the time step, τ t is the immediate reward, γ is the discount factor (γ = 0.95), and T is the termination time step of the sampling trajectory. Let the parameters of the policy network be π(α t \s t ), where a is the predicted value of voltage and temperature, s is the human body indicator state, and θ is the neural network parameter. The policy gradient update formula is:

[0066]

[0067] where logπ(α t \s t ) represents the probability of the output value of the LSTM model, G t is the cumulative return weight parameter, and α = 0.001 is the learning rate.

[0068] In addition, the present invention provides an intelligent cockpit system control method for warm low potential, which is applied to the above-mentioned intelligent cockpit system for warm low potential, and includes:

[0069] Integrate the low potential warm therapy module into the intelligent cockpit through embedded technology, and regulate the operation parameters of the low potential warm therapy module through the vehicle-mounted central control system;

[0070] Obtain multiple physiological indicators of the driver in real time through the physiological parameter monitoring module and transmit them to the vehicle-mounted central control system;

[0071] Present the processed physiological data on the vehicle-mounted display screen in real time through the data visualization module;

[0072] Obtain physiological data through the intelligent control module, dynamically optimize the treatment parameters, and feedback the optimal parameters to the central control system.

[0073] In addition, the present invention also provides an intelligent cockpit storage medium with warm and low potential, characterized in that a computer program is stored thereon, and when the computer program is executed by a processor, the intelligent cockpit system with warm and low potential as described in the above claims is realized.

[0074] Compared with the prior art, the beneficial effects of the technical solution of the present invention are:

[0075] The present invention integrates the functions of warm and low potential therapy in the intelligent cockpit through the low potential warm therapy module, creates an all-round physiotherapy environment, enables users to enjoy professional services during driving, realizes the integration of driving and health preservation, and improves the health experience. The real-time feedback function is introduced through the physiological parameter monitoring module and the data visualization module. With the help of high-precision sensors and fast transmission technology, the physical indicators such as the driver's heart rate and blood pressure are displayed on the central control screen in real time, facilitating the driver to master their physical condition at any time and accurately judge whether they meet the requirements of safe driving, thus ensuring driving safety. The intelligent control module automatically and precisely adjusts the warm and low potential parameters to achieve real-time dynamic optimization and ensure the physiotherapy effect. Description of the Drawings

[0076] Figure 1 It is a system diagram of the intelligent cockpit with warm and low potential described in Embodiment 1;

[0077] Figure 2 It is a flowchart of the intelligent cockpit method with warm and low potential described in Embodiment 3; Detailed Embodiments

[0078] The drawings are only for illustrative purposes and should not be construed as a limitation of this patent;

[0079] The technical solution of the present invention will be further described below in conjunction with the drawings and embodiments.

[0080] Embodiment 1:

[0081] This embodiment provides an intelligent cockpit with warm and low potential as Figure 1 shown, including:

[0082] A low potential warm therapy module, a physiological parameter monitoring module, an in-vehicle central control system, an intelligent control system, and a data visualization module; the in-vehicle central control system is respectively connected to the low potential warm therapy module, the physiological parameter monitoring module, the intelligent control system, and the data visualization module;

[0083] The low potential warm therapy module is integrated into the intelligent cockpit through embedded technology, and the operation parameters of the low potential warm therapy module are regulated by the in-vehicle central control system;

[0084] The physiological parameter monitoring module is composed of a multi-modal biosensor array, which acquires multiple physiological indicators of the driver in real time and transmits them to the in-vehicle central control system;

[0085] The data visualization module presents the processed physiological data on the in-vehicle display screen in real time;

[0086] The intelligent regulation module acquires physiological data, dynamically optimizes treatment parameters, and feeds back the optimal parameters to the central control system.

[0087] In this embodiment, the low-potential warm therapy module integrates the functions of warm and low-potential healing in the intelligent cockpit to create an all-round physiotherapy environment, enabling users to enjoy professional services during driving, realizing the integration of driving and health preservation, and enhancing the health experience. By introducing a real-time feedback function through the physiological parameter monitoring module and the data visualization module, with the help of high-precision sensors and fast transmission technology, the physical indicators such as the driver's heart rate and blood pressure are displayed on the central control screen in real time, facilitating the driver to grasp their physical condition at any time and accurately judge whether they meet the requirements for safe driving, thus ensuring driving safety. The intelligent regulation module automatically and precisely adjusts the warm and low-potential parameters to achieve real-time dynamic optimization and ensure the physiotherapy effect.

[0088] Embodiment Two:

[0089] This embodiment further discloses on the basis of Embodiment One:

[0090] Further, the low-potential warm therapy module includes: a warm sub-module and a low-potential sub-module;

[0091] Among them, the warm sub-module transmits the voltage value read from the temperature sensor inside the warm and low-potential seat cushion to the CPU. The CPU obtains the internal temperature value T0 of the seat cushion at this time, and the CPU sends this temperature value T0 to the in-vehicle central control system through the Bluetooth module. The in-vehicle central control system obtains the temperature value and conducts comprehensive analysis and calculation through health monitoring data, and sends the T1 value required to maintain the seat cushion temperature to the CPU control module of the warm and low-potential controller through the Bluetooth module. The CPU control module controls the output voltage at both ends of the heating wire in a PWM manner, thereby controlling the heating power of the heating wire and maintaining the current T0 temperature stable at T1.

[0092] Further, the low-potential sub-module includes:

[0093] When the fatigue index of the health-monitored driver increases, the in-vehicle central control system sends low-potential intensity index data to the warm and low-potential controller. Inside the controller, the negative potential frequency conversion and voltage transformation module circuit is controlled to apply the low potential to the heating wire, so as to output an appropriate low-potential intensity for the current driver's fatigue state to relieve fatigue. When it is monitored that the driver's mental state recovers, the in-vehicle central control system will control the output of the low potential in real time to form a closed loop.

[0094] Furthermore, the physiological parameter monitoring module includes:

[0095] Heart rate measurement: Measuring the heart rate based on the camera detection method; using the camera in the intelligent cockpit to capture the facial video of the driver, with a recording frame rate of 30fps and a resolution of 1980*1240 to capture subtle physiological changes in the face; using the face detection algorithm of the dlib library in python to detect the face in each frame of the image, obtaining the bounding box of the face and cropping the face to obtain the facial area of the driver; extracting the value of the G channel of each pixel from the face and calculating the average RGB value of all pixels in this area:

[0096]

[0097] Gi(t) corresponds to the value of the G channel of the i-th pixel at time t, and N is the total number of pixels in the area.

[0098] Perform band-pass filtering on G(t); the band-pass filter uses a Butterworth filter, with a sampling frequency of 30HZ, a low cut-off frequency of 0.5HZ, and a high cut-off frequency of 3HZ to remove high-frequency noise and remaining low-frequency interference; the order of the filter is set to 4 to balance the filtering effect and computational complexity.

[0099] G f (t) = filter(G(t))

[0100] Normalize the filtered signal to eliminate the influence of amplitude changes, and then perform a fast Fourier transform to obtain the spectrum; find the peak fpeak according to the spectrum, which is the spectrum corresponding to the heart rate;

[0101]

[0102] X(f) = FFT(G n (t))

[0103] HR = 60*f peak

[0104] Furthermore, the physiological parameter monitoring module also includes:

[0105] Heart rate variability: Detecting heart rate variability based on photoplethysmography; the PPG sensor emits green light into the skin tissue, and the change in light absorption caused by the subcutaneous blood flow generates a pulse wave signal x(t); then use a band-pass filter to remove low-frequency drift and high-frequency noise, and use a moving average filter to smooth the signal;

[0106]

[0107] Extract the pulse wave features after preprocessing. First, check the peak-to-peak value of the pulse wave in the PPG signal. The peak sequence is denoted as T = {t1, t2, t3, …, tn}. Calculate the intervals between adjacent peaks to generate the PPI sequence, and calculate the SDNN (standard deviation during the RR interval), where RR is the mean of the intervals during the peaks.

[0108] PPI i = t i+1 - t i (i = 1, 2, …, n - 1)

[0109] RR i = PPI i (i = 1, 2, …, n - 1)

[0110]

[0111] Furthermore, the physiological parameter monitoring module further includes:

[0112] Blood oxygen saturation: Irradiate the skin with red light and infrared light. The collected PPG signal includes the red light PPG signal and the infrared light PPG signal, and separate the two according to different wavelengths; use a low-pass filter to decompose the DC component and the AC component of each of them respectively; then calculate the eigenvalue R of the blood oxygen according to linear regression, and calculate the blood oxygen saturation by the formula;

[0113] For red light:

[0114] I red,DC = LPF(I red (t))

[0115] I red,AC = I red (t) - I red,DC

[0116] For infrared light:

[0117] I IR,DC = LPF(I IR (t))

[0118] I IR,AC = I IR (t) - I IR,DC

[0119] Calculate the ratio R of the DC component and the AC component of the red light and infrared light PPG signals:

[0120]

[0121]

[0122] Through the empirical formula, the R value can be converted into blood oxygen saturation:

[0123] SPO2 = 110 - 25R.

[0124] Furthermore, the intelligent regulation module includes:

[0125] Prediction target: According to the human body index parameters at time t, predict the two control parameters of the warm low potential at time t + 1, namely voltage and temperature, to achieve intelligent regulation of the parameters; prevent the abnormal physical state of the driver due to improper setting of temperature or voltage;

[0126] Data collection: The human body index, voltage and temperature values at time t, the model predicts the voltage and temperature at time t + 1, and the human body index at time t + 1 after the control parameters are changed;

[0127] Settings for reinforcement learning training:

[0128] Environment: The external system that interacts with the prediction model, providing state and reward feedback.

[0129] State: The human body index parameters at time t, such as heart rate ht, heart rate variability Vt, blood oxygen saturation SOt, etc.;

[0130] Action: The predicted voltage Ut+1 and temperature value Tt+1.

[0131] Reward: According to the predicted voltage and temperature, change the setting value, obtain the human body index at time t + 1 through the sensor, and use the difference from the normal and stable state as the reward function; if the human body index after adjusting the voltage and temperature is far from the normal value, it is regarded as a penalty, otherwise it is regarded as a reward;

[0132] Model architecture

[0133] Encoder: An encoder based on LSTM can capture the long-term dependencies in time series data. Stack 3 LSTM layers, and the output is the hidden state of the LSTM, encoding the human body index parameters into a 256-dimensional feature vector;

[0134] Predictor: Based on three linear fully connected layers, the output dimensions are 64, 16, and 2 respectively; the fully connected layer learns the mapping relationship between the human body feature vector and the setting parameters, and maps the 256-dimensional feature vector of the encoder into voltage values and temperature values;

[0135] Initialize the encoder and predictor in the way of the deep learning pytorch framework. Select the adaptive momentum optimizer to update the model parameters. At the same time, use the learning rate warm-up algorithm to update the learning rate, that is, at the beginning of training, gradually increase the learning rate to accelerate the convergence speed of the model, and then after iterating to a certain number of rounds, gradually reduce the learning rate to help the model converge to the optimal solution; the initial learning rate is set to 0.001, and the weight decay is set to 0.9 to prevent overfitting. The learning rate warm-up algorithm adopts the cosine increase strategy, and the learning rate increases from 0 to the initial learning rate according to the cosine function;

[0136] Train based on the reinforce algorithm.

[0137] Furthermore, training based on the reinforce algorithm includes:

[0138] The reinforce algorithm is a reinforcement learning algorithm based on gradient strategy, which directly updates the parameters to maximize the cumulative expected return and is applicable to the parameter prediction task of continuous values;

[0139] The core idea of the reinforce algorithm is to calculate the policy gradient by sampling trajectories and update the policy network parameters to maximize the expected cumulative reward.

[0140] In the driving environment, sample for 5 minutes as a sampling period, and predict the values of voltage U and temperature T for the next second every second to obtain the human body indicators after setting the parameters, denoted as Xi = {Ht, Vt, SOt}, and the normal indicators x normal = {h = 80, V = 150, SO = 0.96}.

[0141] Reward for a single prediction:

[0142]

[0143] Collect data for one period from the environment and calculate the expected cumulative return:

[0144] G t = τ t + γτ t+1 + γ 2 τ t+2 +…+ γ T-1 τ T

[0145] where t is the time step, τ t is the immediate reward, γ is the discount factor (γ = 0.95), and T is the termination time step of the sampling trajectory. Let the parameters of the policy network be π(α t \s t) where a is the predicted values of voltage and temperature, s is the human body index status, and θ is the neural network parameter. The policy gradient update formula is:

[0146]

[0147] where logπ(α t \s t ) represents the probability of the output value of the LSTM model, G t is the cumulative return weight parameter, and α = 0.001 is the learning rate.

[0148] In this embodiment, the low-potential heat therapy module integrates the functions of heat and low-potential therapy in the intelligent cockpit to create an all-round physiotherapy environment, enabling users to enjoy professional services during driving, realizing the integration of driving and health preservation, and enhancing the health experience. Through the physiological parameter monitoring module and the data visualization module, a real-time feedback function is introduced. With the help of high-precision sensors and fast transmission technology, the driver's physical indicators such as heart rate and blood pressure are displayed on the central control screen in real time, facilitating the driver to grasp their physical condition at any time and accurately judge whether they meet the requirements for safe driving, thus ensuring driving safety. Through the intelligent regulation module, the heat and low-potential parameters are automatically and precisely adjusted to achieve real-time dynamic optimization and ensure the physiotherapy effect.

[0149] Embodiment 3:

[0150] This embodiment provides a control method for an intelligent cockpit system with heat and low potential as shown in Figure 2 , which is applied to the above-mentioned intelligent cockpit system with heat and low potential, and includes:

[0151] Integrate the low-potential heat therapy module into the intelligent cockpit through embedded technology, and regulate the operating parameters of the low-potential heat therapy module through the vehicle-mounted central control system;

[0152] Obtain multiple physiological indicators of the driver in real time through the physiological parameter monitoring module and transmit them to the vehicle-mounted central control system;

[0153] Present the processed physiological data on the vehicle-mounted display screen in real time through the data visualization module;

[0154] Obtain physiological data through the intelligent regulation module, dynamically optimize the treatment parameters, and feedback the optimal parameters to the central control system.

[0155] In this embodiment, the low-potential warm therapy module integrates the functions of warm and low-potential therapy in the intelligent cockpit to create a full-range physiotherapy environment, enabling users to enjoy professional services during driving, realizing the integration of driving and health preservation, and enhancing the health experience. The real-time feedback function is introduced through the physiological parameter monitoring module and the data visualization module. With the help of high-precision sensors and fast transmission technology, the physical indicators of the driver, such as heart rate and blood pressure, are displayed on the central control screen in real time, facilitating the driver to grasp their physical condition at any time, accurately judge whether they meet the requirements for safe driving, and ensure driving safety. The intelligent regulation module automatically and precisely adjusts the warm and low-potential parameters to achieve real-time dynamic optimization and ensure the physiotherapy effect.

[0156] Embodiment 4:

[0157] In addition, this embodiment also provides a storage medium for the intelligent cockpit of warm and low-potential, characterized in that a computer program is stored thereon, and when the computer program is executed by a processor, the intelligent cockpit system of warm and low-potential described in the above claims is realized.

[0158] In this embodiment, the low-potential warm therapy module integrates the functions of warm and low-potential therapy in the intelligent cockpit to create a full-range physiotherapy environment, enabling users to enjoy professional services during driving, realizing the integration of driving and health preservation, and enhancing the health experience. The real-time feedback function is introduced through the physiological parameter monitoring module and the data visualization module. With the help of high-precision sensors and fast transmission technology, the physical indicators of the driver, such as heart rate and blood pressure, are displayed on the central control screen in real time, facilitating the driver to grasp their physical condition at any time, accurately judge whether they meet the requirements for safe driving, and ensure driving safety. The intelligent regulation module automatically and precisely adjusts the warm and low-potential parameters to achieve real-time dynamic optimization and ensure the physiotherapy effect.

[0159] Obviously, the above embodiments of the present invention are merely examples for clearly explaining the present invention, rather than limitations on the implementation manners of the present invention. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the claims of the present invention.

Claims

1. An intelligent cockpit system with warm low potential, characterized in that, Including: A low - potential heat therapy module, a physiological parameter monitoring module, a vehicle - mounted central control system, an intelligent regulation module, and a data visualization module; The vehicle - mounted central control system is respectively connected to the low - potential heat therapy module, the physiological parameter monitoring module, the intelligent regulation system, and the data visualization module; The low - potential heat therapy module is integrated into the intelligent cockpit through embedded technology, and the operating parameters of the low - potential heat therapy module are regulated by the vehicle - mounted central control system; The physiological parameter monitoring module is composed of a multi - modal biosensor array, which obtains multiple physiological indicators of the driver in real - time and transmits them to the vehicle - mounted central control system; The data visualization module presents the processed physiological data on the vehicle - mounted display screen in real - time; The intelligent regulation module obtains physiological data, dynamically optimizes the treatment parameters, and feeds back the optimal parameters to the central control system.

2. The intelligent cockpit system with warm temperature and low potential according to claim 1, characterized in that The low - potential heat therapy module includes: a heat sub - module and a low - potential sub - module; Among them, the heat sub - module transmits the voltage value read from the temperature sensor inside the heat - low - potential seat cushion to the CPU. The CPU obtains the temperature value T0 inside the seat cushion at this time. The CPU sends this temperature value T0 to the vehicle - mounted central control system through the Bluetooth module. The vehicle - mounted central control system obtains the temperature value and conducts comprehensive analysis and calculation through the health monitoring data, and sends the T1 value required to maintain the seat cushion temperature to the CPU control module of the heat - low - potential controller through the Bluetooth module. The CPU control module controls the output voltage at both ends of the heating wire in a PWM manner, thereby controlling the heating power of the heating wire, and maintaining the current T0 temperature stable at T1.

3. The intelligent cockpit system with warm temperature and low potential according to claim 2, characterized in that, The low - potential sub - module includes: When the fatigue index of the healthy - monitored driver increases, the vehicle - mounted central control system sends low - potential intensity index data to the heat - low - potential controller. Inside the controller, the negative - potential frequency - conversion and voltage - transformation module circuit is controlled to apply a low - potential to the heating wire, so as to output an appropriate low - potential intensity for the current driver's fatigue state to relieve fatigue. When it is monitored that the driver's mental state recovers, the vehicle - mounted central control system will control the output of the low - potential in real - time to form a closed - loop.

4. The intelligent cockpit system with warm temperature and low potential according to claim 1, characterized in that, The physiological parameter monitoring module includes: Heart rate measurement: Measuring the heart rate based on the camera detection method; Using the camera in the intelligent cockpit to shoot the driver's face video, with a recording frame rate of 30fps and a resolution of 1980 * 1240 to capture subtle physiological changes in the face; Using the face detection algorithm of the dlib library in python to perform face detection on each frame of the image, obtaining the bounding box of the face and cropping the face to obtain the driver's facial area; Extracting the value of the G channel of each pixel from the face and calculating the average RGB value of all pixels in this area: Gi(t) corresponds to the value of the G channel of the i - th pixel at time t, and N is the total number of pixels in the area; Performing band - pass filtering on G(t); The band - pass filter uses a Butterworth filter, with a sampling frequency of 30HZ, a low - cut - off frequency of 0.5HZ, and a high - cut - off frequency of 3HZ to remove high - frequency noise and remaining low - frequency interference; The order of the filter is set to 4 to balance the filtering effect and computational complexity; G f (t) = filter(G(t)) Normalize the filtered signal to eliminate the influence of amplitude variation, and then perform a fast Fourier transform to obtain the spectrum; find the peak fpeak from the spectrum, which is the spectrum corresponding to the heart rate. X(f) = FFT(G n (t)) HR = 60 * f peak .

5. The intelligent cockpit system with warm low potential according to claim 1, characterized in that The physiological parameter monitoring module further includes: Heart rate variability: Detect heart rate variability based on photoplethysmography; the PPG sensor emits green light into the skin tissue, and the change in light absorption caused by subcutaneous blood flow generates a pulse wave signal x(t); then use a band-pass filter to remove low-frequency drift and high-frequency noise, and use a moving average filter to smooth the signal. After preprocessing, extract the pulse wave features. First, check the peak-to-peak value of the pulse wave in the PPG signal. The peak sequence is denoted as T = {t1, t2, t3, …, tn}, calculate the interval between adjacent peaks to generate the PPI sequence, and calculate the SDNN (standard deviation during the RR interval), where RR is the mean of the intervals during the wave peaks. PPI i = t i+1 -t i (i = 1, 2, …, n - 1) RR i = PPI i (i = 1, 2, …, n - 1) 6. The intelligent cockpit system with warm temperature and low potential according to claim 1, characterized in that, The physiological parameter monitoring module further includes: Blood oxygen saturation: Irradiate the skin with red light and infrared light. The collected PPG signal includes a red light PPG signal and an infrared light PPG signal, and separate the two according to different wavelengths; use a low-pass filter to decompose the DC component and the AC component of each of them respectively; then calculate the eigenvalue R of blood oxygen according to linear regression, and calculate the blood oxygen saturation from the formula. For red light: I red,DC = LPF(I red (t)) I red,AC = I red (t) - I red,DC For infrared light: I IR,DC = LPF(I IR (t)) I IR,AC = I IR (t) - I IR,DC Calculate the ratio R of the DC component and the AC component of the red light and infrared light PPG signals: Through an empirical formula, the R value can be converted into blood oxygen saturation: SPO2 = 110 - 25R.

7. The intelligent cockpit system with warm temperature and low potential according to claim 1, characterized in that, The intelligent regulation module includes: Prediction target: According to the human body index parameters at time t, predict the two control parameters of the warm low potential at time t + 1, namely voltage and temperature, to achieve intelligent regulation of the parameters; prevent the abnormal physical state of the driver caused by improper setting of temperature or voltage. Data collection: The human body index, voltage and temperature values at time t, the model predicts the voltage and temperature at time t + 1, and the human body index at time t + 1 after the control parameters are changed. Settings for reinforcement learning training: Environment: The external system that interacts with the prediction model, providing state and reward feedback. State: The human body index parameters at time t, such as heart rate ht, heart rate variability Vt, blood oxygen saturation SOt, etc. Action: The predicted voltage Ut+1 and temperature value Tt+1. Reward: According to the predicted voltage and temperature, change the setting value, and obtain the human body index at time t + 1 through the sensor. The difference from the normal and stable state is used as the reward function; if the human body index after adjusting the voltage and temperature is far from the normal value, it is used as a penalty, otherwise it is used as a reward. Model architecture Encoder: An encoder based on LSTM can capture the long-term dependencies in time series data; stack 3 LSTM layers, and the output is the hidden state of the LSTM, encoding the human body index parameters into a 256-dimensional feature vector. Predictor: Based on three linear fully connected layers, the output dimensions are 64, 16, and 2 respectively; the fully connected layer learns the mapping relationship between the human body feature vector and the setting parameters, and maps the 256-dimensional feature vector of the encoder into voltage values and temperature values. Initialize the encoder and predictor in the way of the deep learning pytorch framework; select the adaptive momentum optimizer to update the model parameters. At the same time, use the learning rate warm-up algorithm to update the learning rate, that is, at the beginning of training, gradually increase the learning rate to accelerate the convergence speed of the model, and then after iterating to a certain number of rounds, gradually decrease the learning rate to help the model converge to the optimal solution; the initial learning rate is set to 0.001, and the weight decay is set to 0.9 to prevent overfitting. The learning rate warm-up algorithm adopts the cosine increase strategy, and the learning rate increases from 0 to the initial learning rate according to the cosine function; Train based on the reinforce algorithm.

8. The intelligent cockpit system with warm temperature and low potential according to claim 1, characterized in that Training based on the reinforce algorithm includes: The reinforce algorithm is a reinforcement learning algorithm based on gradient policy, which directly updates the parameters to maximize the cumulative expected return and is applicable to the parameter prediction task of continuous values; The core idea of the reinforce algorithm is to calculate the policy gradient by sampling trajectories and update the parameters of the policy network to maximize the expected cumulative reward; In the driving environment, a 5-minute sampling period is used. For each second, the values of voltage U and temperature T for the next second are predicted, and the human body indicators after obtaining the set parameters are denoted as Xi = {Ht, Vt, SOt}, and the normal indicators x normal = {h = 80, V = 150, SO = 0.96}; Reward for a single prediction: Collect data for one cycle from the environment and calculate the expected cumulative return: G t = τ t + γτ t+1 + γ 2 τ t+2 +…+ γ T-t τ T where \(t\) is the time step, \(\tau\) t is the immediate reward, \(\gamma\) is the discount factor (\(\gamma = 0.95\)), \(T\) is the termination time step of the sampled trajectory; let the parameters of the policy network be \(\pi(\alpha\) t \s t ), where \(a\) is the predicted value of voltage and temperature, \(s\) is the state of human body metrics, \(\theta\) is the neural network parameter; the policy gradient update formula is: where logπ(α t \s t ) represents the probability of the output value of the LSTM model, G t is the cumulative return weight parameter, and α = 0.001 is the learning rate.

9. The control method of the intelligent cockpit system with warm and low potential is applied to the intelligent cockpit system with warm and low potential as claimed in claim 1, and is characterized in that, Including: Integrate the low-potential thermotherapy module into the intelligent cockpit through embedded technology, and regulate the operating parameters of the low-potential thermotherapy module through the vehicle-mounted central control system; Obtain multiple physiological indicators of the driver in real time through the physiological parameter monitoring module and transmit them to the vehicle-mounted central control system; Present the processed physiological data on the vehicle-mounted display screen in real time through the data visualization module; Obtain physiological data through the intelligent regulation module, dynamically optimize the treatment parameters, and feedback the optimal parameters to the central control system.

10. An intelligent cockpit storage medium with warm temperature and low potential, characterized in that, It stores a computer program, and when the computer program is executed by a processor, it realizes the intelligent cockpit system of the warm low potential described in any one of claims 1 to 8.

Images