A method and device for controlling a seat based on a seat controller

By obtaining the driver's breathing and heartbeat information, calculating the fatigue development curve and automatically adjusting the seat, the problem that traditional seat adjustment cannot accurately alleviate fatigue and improve driving safety and comfort.

CN118514577BActive Publication Date: 2024-11-15上海佳昌智联汽车科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410985259.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-15
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

Traditional car seats need to be manually adjusted to adapt to the body shape and comfort preferences of different drivers, resulting in the inability to accurately and effectively alleviate driver fatigue and affect driving safety.

Method used

By obtaining the driver's breathing and heartbeat information, detecting using millimeter-wave radar, calculating the fatigue development curve, generating a fatigue relief strategy, and automatically adjusting the seat posture and support function to relieve fatigue.

Benefits of technology

Accurate monitoring and mitigation of driver fatigue status is achieved, driving safety is improved, and accident risk is reduced due to fatigue.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118514577B_ABST
    Figure CN118514577B_ABST
Patent Text Reader

Abstract

The present application relates to a method and device for controlling a seat based on a seat controller. The method comprises: obtaining the breathing information and heartbeat information of the target object; detecting and obtaining the breathing information and heartbeat information of the target object through a millimeter wave radar; determining the fatigue development curve of the target object according to the breathing information and heartbeat information when the fatigue information of the target object represented by the breathing information and / or heartbeat information exceeds the fatigue threshold; generating fatigue relief execution information of the target object according to the breathing information, heartbeat information and fatigue development curve; controlling the seat to assist the target object in adjusting according to the fatigue relief execution information until the fatigue development curve meets the driving safety information. The use of this method enables the seat of the car to achieve accurate and effective fatigue relief for the occupants according to the actual situation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of automatic control technology, and in particular to a method and device for controlling a seat based on a seat controller. Background Art

[0002] With the development of automatic control technology, automotive fatigue relief technology has emerged. The key to this technology lies in its ergonomic design, which can provide support and comfort. By using high-quality foam materials, adjustable lumbar support, appropriate seat contours and adjustable seat positions, these seats can reduce the discomfort caused by long-term driving, thereby helping drivers maintain good posture and physical health. The addition of heating, ventilation and massage functions further enhances the comfort of the seats, making long-term driving easier and more enjoyable.

[0003] Traditionally, car seats have to be manually adjusted to suit different drivers’ body shapes, weights, and personal comfort preferences. This means that every time a driver changes, the seat needs to be manually readjusted, which is not only time-consuming, but can also cause the driver to be in an inappropriate posture for a long time if not adjusted properly. As a result, traditional technology has resulted in car seats being unable to accurately and effectively relieve fatigue for the occupants based on actual conditions. Summary of the invention

[0004] Based on this, it is necessary to provide a method and device for controlling a car seat based on a seat controller, which can enable the car seat to accurately and effectively relieve fatigue of the occupants according to actual conditions, in order to address the above technical problems.

[0005] In a first aspect, the present application provides a method for controlling a seat based on a seat controller, comprising:

[0006] Acquire breathing information and heartbeat information of a target object; the breathing information and the heartbeat information are acquired by detecting the target object through a millimeter wave radar;

[0007] In the case where the respiratory information and / or the heartbeat information indicate that the fatigue information of the target object exceeds the fatigue threshold, determining a fatigue development curve of the target object according to the respiratory information and the heartbeat information; the fatigue development curve is a prediction curve of the fatigue development trend of the target object in a period of time after the current moment;

[0008] Wherein, determining the fatigue development curve of the target object according to the breathing information and the heartbeat information includes: calculating the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information; fusing the fatigue fluctuation information and the long-term fatigue information to obtain the cumulative fatigue information; using spline interpolation to perform smooth fitting on the short-term fatigue information and the cumulative fatigue information to generate an initial fatigue development curve; acquiring the real-time breathing information and real-time heartbeat information of the target object; and correcting the initial fatigue development curve according to the real-time breathing information and the real-time heartbeat information to obtain the fatigue development curve;

[0009] generating fatigue relief execution information of the target object according to the breathing information, the heartbeat information and the fatigue development curve;

[0010] The step of generating fatigue relief execution information of the target object according to the breathing information, the heartbeat information and the fatigue development curve includes:

[0011] Determining fatigue relief strategy information according to the breathing information and the heartbeat information; the fatigue relief strategy information is guidance information for relieving fatigue of the target object;

[0012] generating the fatigue relief execution information according to the biofeedback information of the target object, the fatigue development curve, and the fatigue relief strategy information;

[0013] The biofeedback information is parameters about the overall condition of the target object obtained using different sensing technologies;

[0014] The fatigue relief execution information is compiled by the seat controller to generate information for controlling the seat and related equipment connected to the seat to adjust, so as to relieve the fatigue state of the target object;

[0015] According to the fatigue relief execution information, the seat is controlled to assist the target object in making adjustments until the fatigue development curve meets the driving safety information.

[0016] In a second aspect, the present application further provides a device for controlling a seat based on a seat controller, comprising:

[0017] A physiological information acquisition module is used to acquire the breathing information and heartbeat information of the target object; the breathing information and the heartbeat information are acquired by detecting the target object through a millimeter wave radar;

[0018] a development curve determination module, configured to determine a fatigue development curve of the target object according to the breathing information and the heartbeat information, when the fatigue information of the target object represented by the breathing information and / or the heartbeat information exceeds a fatigue threshold; the fatigue development curve is a prediction curve of the fatigue development trend of the target object in a period of time after the current moment;

[0019] Wherein, determining the fatigue development curve of the target object according to the breathing information and the heartbeat information includes: calculating the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information; fusing the fatigue fluctuation information and the long-term fatigue information to obtain the cumulative fatigue information; using spline interpolation to perform smooth fitting on the short-term fatigue information and the cumulative fatigue information to generate an initial fatigue development curve; acquiring the real-time breathing information and real-time heartbeat information of the target object; and correcting the initial fatigue development curve according to the real-time breathing information and the real-time heartbeat information to obtain the fatigue development curve;

[0020] a relief information generating module, configured to generate fatigue relief execution information of the target object according to the breathing information, the heartbeat information and the fatigue development curve;

[0021] The step of generating fatigue relief execution information of the target object according to the breathing information, the heartbeat information and the fatigue development curve includes:

[0022] Determining fatigue relief strategy information according to the breathing information and the heartbeat information; the fatigue relief strategy information is guidance information for relieving fatigue of the target object;

[0023] generating the fatigue relief execution information according to the biofeedback information of the target object, the fatigue development curve, and the fatigue relief strategy information;

[0024] The biofeedback information is parameters about the overall condition of the target object obtained using different sensing technologies;

[0025] The fatigue relief execution information is compiled by the seat controller to generate information for controlling the seat and related equipment connected to the seat to adjust, so as to relieve the fatigue state of the target object;

[0026] The relief information execution module is used to control the seat to assist the target object in adjusting according to the fatigue relief execution information until the fatigue development curve meets the driving safety information.

[0027] The above-mentioned method and device for controlling a seat based on a seat controller obtains the breathing information and heartbeat information of the target object; the breathing information and heartbeat information are detected and obtained by the millimeter wave radar of the target object; when the fatigue information of the target object represented by the breathing information and / or the heartbeat information exceeds the fatigue threshold, the fatigue development curve of the target object is determined according to the breathing information and the heartbeat information; the fatigue development curve is a prediction curve of the development trend of the fatigue situation of the target object for a period of time after the current moment; wherein, the fatigue development curve of the target object is determined according to the breathing information and the heartbeat information, including: calculating the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information; fusing the fatigue fluctuation information and the long-term fatigue information to obtain the cumulative fatigue information; using spline interpolation to smoothly fit the short-term fatigue information and the cumulative fatigue information to generate an initial fatigue development curve; obtaining the real-time breathing information and real-time heartbeat information of the target object; according to the real-time breathing information and the real-time heartbeat information The initial fatigue development curve is corrected according to the breathing information, the heartbeat information and the fatigue development curve to obtain the fatigue development curve; the fatigue relief execution information of the target object is generated according to the breathing information, the heartbeat information and the fatigue development curve; wherein, the fatigue relief execution information of the target object is generated according to the breathing information, the heartbeat information and the fatigue development curve, including: determining the fatigue relief strategy information according to the breathing information and the heartbeat information; the fatigue relief strategy information is the guidance information for fatigue relief of the target object; the fatigue relief execution information is generated according to the biofeedback information, the fatigue development curve and the fatigue relief strategy information of the target object; the biofeedback information is the parameters about the overall condition of the target object obtained by using different sensing technologies; the fatigue relief execution information is compiled by the seat controller to generate information for controlling the seat and the related equipment connected to the seat for adjustment, so as to relieve the fatigue state of the target object; according to the fatigue relief execution information, the seat is controlled to assist the target object to adjust until the fatigue development curve meets the driving safety information.

[0028] By using millimeter-wave radar to detect the target object's breathing and heartbeat information with high precision, its fatigue state is dynamically monitored. When the system recognizes that the breathing rate or heartbeat data indicates that the object is overly fatigued, it will generate a fatigue development curve based on these physiological parameters to predict its fatigue change trend. Then, based on the breathing information, heartbeat information and the predicted fatigue development curve, a personalized fatigue relief strategy is generated. By automatically adjusting the seat's posture and support function, the target object is assisted in comfort adjustment, which enables the car's seat to accurately and effectively relieve fatigue for the occupants according to actual conditions. At the same time, it can improve the real-time perception and response capabilities of the driver's fatigue state, significantly reduce the risk of accidents caused by fatigue driving through active intervention mechanisms, and improve overall driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0030] Figure 1 A diagram of an application environment of a method for controlling a seat based on a seat controller in one embodiment;

[0031] Figure 2 A schematic flow chart of a method for controlling a seat based on a seat controller in one embodiment;

[0032] Figure 3 A schematic diagram of a process for determining a fatigue development curve in one embodiment;

[0033] Figure 4 A schematic diagram of a flow chart of a method for calculating short-term fatigue information in an embodiment;

[0034] Figure 5 A schematic diagram of a flow chart of a method for calculating fatigue fluctuation information and long-term fatigue information in one embodiment;

[0035] Figure 6 A schematic diagram of a flow chart of a method for generating fatigue relief execution information in one embodiment;

[0036] Figure 7 A schematic flow chart of a method for generating fatigue relief execution information in another embodiment;

[0037] Figure 8 A schematic diagram of a flow chart of a method for obtaining stable emotion regulation parameters and stable physiological regulation parameters in one embodiment;

[0038] Fig. 9 A schematic flow chart of a method for generating fatigue relief execution information in yet another embodiment;

[0039] Fig.10 A schematic diagram of a flow chart of a fatigue relief execution method in an embodiment;

[0040] Fig.11 It is a flowchart of a method for executing a first backup plan in one embodiment;

[0041] Fig.12 It is a flowchart of a method for executing the second backup plan in one embodiment;

[0042] Fig.13 is a structural block diagram of a device for controlling a seat based on a seat controller in one embodiment;

[0043] Fig.14 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] The method for controlling a seat based on a seat controller provided in an embodiment of the present application can be applied to Figure 1In the application environment shown, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 obtains the breathing information and heartbeat information of the target object from the terminal 102; the breathing information and heartbeat information are detected and obtained by the millimeter wave radar of the target object; when the fatigue information of the target object represented by the breathing information and / or the heartbeat information exceeds the fatigue threshold, the fatigue development curve of the target object is determined according to the breathing information and the heartbeat information; the fatigue development curve is a prediction curve of the fatigue development trend of the target object in a period of time after the current moment; wherein, the fatigue development curve of the target object is determined according to the breathing information and the heartbeat information, including: calculating the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information; fusing the fatigue fluctuation information and the long-term fatigue information to obtain the cumulative fatigue information; using spline interpolation to smoothly fit the short-term fatigue information and the cumulative fatigue information to generate an initial fatigue development curve; obtaining the real-time breathing information and real-time heartbeat information of the target object; according to the real-time breathing information and the real-time heartbeat information , correct the initial fatigue development curve to obtain the fatigue development curve; generate fatigue relief execution information of the target object according to the breathing information, heartbeat information and fatigue development curve; wherein, the fatigue relief execution information of the target object is generated according to the breathing information, heartbeat information and fatigue development curve, including: determining fatigue relief strategy information according to the breathing information and heartbeat information; fatigue relief strategy information is guidance information for fatigue relief of the target object; generating fatigue relief execution information according to the biofeedback information, fatigue development curve and fatigue relief strategy information of the target object; biofeedback information is a parameter about the overall condition of the target object obtained by using different sensing technologies; fatigue relief execution information is compiled by the seat controller to generate information for controlling the seat and related equipment connected to the seat for adjustment, which is used to relieve the fatigue state of the target object; according to the fatigue relief execution information, the seat is controlled to assist the target object to adjust until the fatigue development curve meets the driving safety information. wherein, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable device may be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0046] In an exemplary embodiment, Figure 2 As shown, a method for controlling a seat based on a seat controller is provided, and the method is applied to Figure 1The server in the example is used to illustrate, including the following steps 202 to 208. Among them:

[0047] Step 202: Acquire the target object's breathing information and heartbeat information.

[0048] The breathing information may be information about the breathing condition of the target object on the seat of the car collected through a sensor or radar over a period of time.

[0049] The heartbeat information may be information about the heartbeat of the target object on the seat of the car collected through a sensor or radar over a period of time.

[0050] Specifically, the millimeter wave sensing technology uses FMCW millimeter wave radar (Frequency Modulated Continuous Wave Radar) to emit continuous frequency modulated pulse signals, which are embedded with two intermediate frequency physiological signals of breathing and heartbeat after being reflected by the human chest cavity. Breathing and heartbeat can be extracted by means of fast Fourier transform, phase extraction, bandpass filtering, etc., so as to obtain the breathing information and heartbeat information of the target object. Specifically, the intermediate frequency signal IF (Intermediate Frequency) obtained by ranging the continuous frequency modulated pulse signal emitted by the FMCW millimeter wave radar is:

[0051]

[0052] Where A is the transmitted signal amplitude, is the radar operating frequency, At this time, the linear frequency modulation pulse phase of the transmitter Phase with linear frequency modulation pulse at the receiving end The difference between t and m is the time of the continuous frequency modulated pulse signal emitted by the millimeter wave radar.

[0053] Distance FFT: Since there are multiple objects reflecting FMCW pulses and they are very close sine waves, there is only a single peak in the spectrum. However, by increasing the IF observation length in the time domain and combining it with the Fast Fourier Transform (FFT), the bandwidth of FMCW can be potentially increased, that is, a larger bandwidth can correspond to a higher distance resolution, thereby resolving multiple peaks in the frequency domain. The distance resolution satisfies the formula:

[0054] Where c is the speed of light, B is the bandwidth, is the distance resolution.

[0055] Phase extraction: A sine wave in the time domain will generate a peak in the frequency domain. The frequency of the peak is the frequency of the sine wave. The phase of the peak in the spectrum after FFT corresponds to the initial phase of the sine wave. The frequency is very insensitive to small changes in the heart and chest, while the phase of the IF signal is very sensitive to this. Therefore, phase extraction is crucial for measuring heart rate and respiration.

[0056] Phase unwrapping and phase difference: The target tracking part obtains the distance of the target and then calculates the phase. The phase formula of the distance unit satisfies:

[0057]

[0058] in is the FFT value of the distance unit, is the phase of the distance unit.

[0059] exist The previous phase unwrapping is the actual phase change of the chest vibration. The phase difference is completed by subtracting the continuous window phase values, which is very helpful for enhancing the heart rate signal and eliminating phase drift.

[0060] Bandpass filtering: After the phase signal is processed, the millimeter-level small-scale displacement of the chest vibration is obtained. Since the motion trajectory of the chest vibration includes two movements, heartbeat and breathing, it is necessary to extract and analyze the mixed signal through a bandpass filter. The human breathing frequency is about 6-30 times per minute, that is, [6,30] / 60=[0.1,0.5]; the human heartbeat frequency is about 48-198 times per minute, that is, [48,198] / 60=[0.8,3.3]. The bandpass filter separates the breathing signal and the heartbeat signal from the phase difference signal to obtain the frequency domain waveform of the breathing signal and the frequency domain waveform of the heartbeat signal. The frequency of the peak with the highest energy in the spectrum is the rate value of the breathing and heartbeat signals.

[0061] Chrip-Z Transform (CZT): Since the spectrum resolution of the frequency domain waveform of the respiratory signal and the heartbeat signal separated by bandpass filtering is too low, it is impossible to obtain the accurate value of the frequency where the peak is located. At this time, spectrum refinement is required to improve the resolution. CZT uses different mathematical processing methods to interpolate within the selected frequency band without increasing the data length, thereby increasing the number of FFT transformation points, thereby improving the calculation resolution of the signal and realizing the refinement of the local frequency band. After spectrum refinement, the respiratory spectrum diagram and heartbeat spectrum diagram can obtain clear respiratory information and heartbeat information respectively.

[0062] Step 204 : when the fatigue information of the target object represented by the respiratory information and / or heartbeat information exceeds the fatigue threshold, determine the fatigue development curve of the target object according to the respiratory information and heartbeat information.

[0063] The fatigue information may be the current fatigue condition of the target object on the car seat.

[0064] The fatigue threshold may be a fatigue value that may affect safe driving, and is a standard for evaluating whether a target object needs fatigue relief.

[0065] Among them, the fatigue development curve can be a prediction curve of the fatigue development trend of the target object in a period of time after the current moment, which is generated by a short-term fatigue prediction curve and a long-term fatigue prediction curve, and also includes the results of instantaneous fatigue prediction information.

[0066] Specifically, when the fatigue information of the target object represented by the respiratory information or / and heartbeat information exceeds the fatigue threshold, that is, the fatigue information calculated by the respiratory information or / and heartbeat information, or the fatigue information read from the respiratory information or / and heartbeat information, there is a case where the fatigue information obtained by one of the methods cannot meet the fatigue threshold of the target object in the car, which will lead to increased driving risk. Therefore, the signal processing algorithm is used to filter and denoise the respiratory information and heartbeat information to extract key physiological characteristics such as respiratory frequency, heart rate and heart rate variability. Then the obtained life characteristics are input into the time series deep learning model (such as long short-term memory network LSTM or variational autoencoder VAE) to model these characteristics. The model combines nonlinear dynamic analysis and multi-task learning technology to identify potential fatigue deterioration mode and fatigue relief mode; based on the fatigue deterioration mode and fatigue relief mode, combined with the extracted life characteristics, a fatigue development curve is generated, wherein the fatigue development curve includes relevant information that integrates short-term trends, fatigue fluctuations and long-term trends.

[0067] In an exemplary embodiment, Figure 3 As shown, step 204 determines the fatigue development curve of the target object according to the breathing information and the heartbeat information, including steps 302 to 310. Among them:

[0068] Step 302: Calculate the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information.

[0069] Among them, the short-term fatigue information can be the fatigue development trend of the target object in a short-term time window in the future. Generally speaking, the short-term window is selected within 5 minutes.

[0070] Among them, the long-term fatigue information can be the fatigue development trend of the target object in a long-term time window in the future. Generally speaking, the long-term window is selected to be more than 5 minutes and within 2 hours.

[0071] The fatigue fluctuation information may be a factor causing the long-term fatigue information to change within a long time window.

[0072] Specifically, according to the breathing information and heartbeat information of the target object, the seat controller first performs signal processing on these physiological data to filter out noise and interference, and then uses time domain and frequency domain analysis to extract features (such as average heart rate, breathing rate and its variability). After that, the seat controller uses short-term Fourier transform and wavelet analysis to calculate short-term fatigue information to reflect the current fatigue level. In order to capture fatigue fluctuation information, the seat controller uses sliding window technology and multiple time scale analysis to evaluate the dynamic changes of physiological parameters; while for long-term fatigue information, the seat controller applies cumulative and trend analysis in a long window, such as exponential smoothing or recursive neural network, to reveal the long-term trend and accumulation pattern of fatigue.

[0073] Step 304: Fusing the fatigue fluctuation information and the long-term fatigue information to obtain cumulative fatigue information.

[0074] The accumulated fatigue information may be long-term fatigue information taking fatigue fluctuation information into consideration.

[0075] Specifically, the calculation module of the seat controller uses Kalman filtering or particle filtering technology to dynamically fuse fatigue fluctuation information and long-term fatigue information at different time scales, eliminate noise and mutations in the fusion process, and smooth the transition to construct a cumulative fatigue curve; or use a weighted method to weight the fatigue fluctuation information to the long-term fatigue information based on different time scales to obtain cumulative fatigue information.

[0076] Step 306: Use spline interpolation to perform smooth fitting on the short-term fatigue information and the cumulative fatigue information to generate an initial fatigue development curve.

[0077] The initial fatigue development curve may be a curve obtained by fitting the data using spline interpolation, but if the target curve is obtained, it still needs to be optimized.

[0078] Specifically, the discrete data points of short-term fatigue information and cumulative fatigue information are represented as time series data; the data points of the time series data are smoothly fitted using quintic spline interpolation technology, which connects the data points of the time series data into a smooth curve by constructing quintic polynomial fragments containing continuous derivatives and high-order continuity. This quintic spline interpolation method can not only handle complex fatigue data fluctuations, but also effectively suppress the influence of noise and outliers, ensuring the smoothness and accuracy of the generated initial fatigue development curve on the time axis, reflecting the subtle change trend of fatigue status at different time points.

[0079] Step 308: Acquire the target object's real-time breathing information and real-time heartbeat information.

[0080] The real-time breathing information may be the target object's real-time breathing information collected through sensors or radars while sitting on a car seat.

[0081] The real-time heartbeat information may be the real-time heartbeat information collected by sensors or radars when the target object is sitting on a car seat.

[0082] Specifically, the seat controller controls the millimeter-wave radar sensor on the vehicle to continuously emit microwave signals and receive reflected data. The slight changes in breathing and heartbeat are extracted by passing the echo data through a signal processing algorithm (such as fast Fourier transform FFT or adaptive filter). The seat controller then converts these raw signals into real-time breathing information and real-time heartbeat information.

[0083] Step 310: Correct the initial fatigue development curve according to the real-time breathing information and the real-time heartbeat information to obtain the fatigue development curve.

[0084] Specifically, short-term fatigue information and cumulative fatigue information are updated according to real-time breathing information and real-time heartbeat information; an adaptive filtering algorithm (such as Kalman filtering or particle filtering) is applied to dynamically adjust the initial fatigue development curve, and the updated short-term fatigue information and cumulative fatigue information are integrated to correct the previous fatigue trend prediction; this process gradually adjusts the curve to more accurately reflect the current fatigue state by comparing the deviation between the real-time data and the initial curve, and finally generates a fatigue development curve.

[0085] In this embodiment, the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object are calculated, and the accumulated fatigue information is generated by integrating this information. Then, the initial fatigue development curve is generated by spline interpolation smooth fitting, and the real-time breathing and heartbeat data are dynamically corrected to form an accurate fatigue development curve. This method realizes continuous and accurate monitoring and prediction of the driver's fatigue state during car driving. It can reflect the driver's fatigue accumulation and change trend in real time, provide personalized fatigue warning and management measures, significantly reduce the risk of accidents caused by fatigue, and ensure the driver's continuous alertness and safety during long-distance driving, thereby improving the overall driving safety and driving experience.

[0086] Step 206: Generate fatigue relief execution information of the target object according to the breathing information, heartbeat information and fatigue development curve.

[0087] Among them, the fatigue relief execution information can be compiled by the seat controller to generate information for controlling the seat and related equipment connected to the seat for adjustment, so as to relieve the fatigue state of the target object.

[0088] Specifically, the respiratory information, heart rate information and fatigue development curve are simultaneously input into the fatigue relief model. Through the reinforcement learning algorithm of the fatigue relief model, the intervention strategy is adaptively adjusted, and the fatigue development curve is continuously optimized according to the real-time feedback of the object's respiratory information and heart rate information. In the feedback process, the fatigue relief model introduces sensor fusion technology to integrate environmental factors (such as in-vehicle temperature and noise level) and personalized physiological baselines to ensure that in the process of fatigue relief simulation for the target object, the fatigue development curve network conforms to the direction of driving safety information. After the simulation results are confirmed, the fatigue relief execution information for the target object is constructed according to the output results of the fatigue relief model.

[0089] In an exemplary embodiment, Figure 6 As shown, step 206 generates fatigue relief execution information of the target object according to the breathing information, heartbeat information and fatigue development curve, including steps 602 to 604. Among them:

[0090] Step 602: Determine fatigue relief strategy information based on the breathing information and the heartbeat information.

[0091] The fatigue relief strategy information may be guidance information for relieving fatigue of the target object.

[0092] Specifically, the breathing information and heartbeat information are analyzed to extract key indicators (such as breathing frequency, heart rate and heart rate variability), and the current fatigue state is evaluated in combination with the key indicators; rule-based reasoning or machine learning models (such as random forests or support vector machines) are used to identify the most suitable fatigue relief measures based on historical data, current fatigue state and the target's physiological state, such as adjusting the seat posture, playing soothing music or suggesting deep breathing exercises. Due to the timeliness of breathing information and heartbeat information, these strategies are adaptively optimized and personalized according to the different physiological response patterns of the target object to ensure that the relief measures provided can effectively improve the target object's fatigue state, thereby generating personalized fatigue relief strategy information.

[0093] Step 604: Generate fatigue relief execution information according to the biofeedback information of the target object, the fatigue development curve, and the fatigue relief strategy information.

[0094] The biofeedback information may be parameters regarding the overall condition of the target object obtained from the target object using different sensing technologies.

[0095] Specifically, the biofeedback information of the target object (such as electromyographic signals, galvanic skin response, etc.), the real-time updated fatigue development curve and the personalized fatigue relief strategy information are integrated; then, the biofeedback information and the fatigue development curve are correlated and analyzed through multimodal data fusion technology to evaluate the effectiveness of the current relief measures; when it is determined to be effective for the target object, an optimization algorithm (such as reinforcement learning or fuzzy logic control) is applied, and the biofeedback information and the updated fatigue development curve are used to dynamically adjust the fatigue relief strategy information, and specific execution instructions are generated according to the adjusted fatigue relief strategy information, including seat adjustment, environmental control or behavioral suggestions. These execution instructions are updated in real time to reflect the current fatigue status and feedback effect, ensuring that the fatigue relief measures are efficient and personalized, and ultimately generating the optimal fatigue relief execution information.

[0096] In this embodiment, fatigue relief strategies are determined through real-time breathing and heartbeat information, and execution information is generated by combining the driver's biofeedback, fatigue development curve, and fatigue relief strategies, thereby providing a highly personalized fatigue management solution in car driving. By dynamically adjusting the driving environment (such as seat posture, in-car temperature, and sound settings), the system can effectively relieve driving fatigue, enhance the driver's concentration and reaction speed, and reduce the risk of accidents caused by fatigue. At the same time, it can continuously monitor the driver's status and adjust intervention measures in a timely manner to ensure that the driver maintains the best condition during long-term driving or adverse conditions, thereby significantly improving driving safety and comfort.

[0097] Step 208 , according to the fatigue relief execution information, controlling the seat to assist the target object in making adjustments until the fatigue development curve complies with the driving safety information.

[0098] The driving safety information may be information used to evaluate whether the influence of the driver or other factors is not sufficient to cause driving danger.

[0099] Specifically, the optimal seat adjustment parameters are determined based on the fatigue relief execution information of the target object, including adjusting the seat angle, support strength and vibration mode, etc., to provide immediate comfort and support. The seat controller controls the built-in intelligent motor and sensor to obtain information on seat position and user response feedback in real time, and makes timely fine-tuning of seat parameters through adaptive control algorithms (such as fuzzy logic control). At the same time, the seat controller also uses biofeedback technology to automatically adjust the seat comfort settings according to the target object's muscle tension, micro-potential and other data until the fatigue development curve returns to the safe range, that is, the fatigue development curve meets the driving safety information.

[0100] In the above-mentioned method for controlling a seat based on a seat controller, the breathing information and heartbeat information of the target object are obtained; the breathing information and heartbeat information are detected and obtained by the millimeter wave radar of the target object; when the fatigue information of the target object represented by the breathing information and / or the heartbeat information exceeds the fatigue threshold, the fatigue development curve of the target object is determined according to the breathing information and the heartbeat information; the fatigue development curve is a prediction curve of the development trend of the fatigue situation of the target object for a period of time after the current moment; wherein, the fatigue development curve of the target object is determined according to the breathing information and the heartbeat information, including: calculating the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information; fusing the fatigue fluctuation information and the long-term fatigue information to obtain the cumulative fatigue information; using spline interpolation to smoothly fit the short-term fatigue information and the cumulative fatigue information to generate an initial fatigue development curve; obtaining the real-time breathing information and real-time heartbeat information of the target object; according to the real-time breathing information and real-time heartbeat information, correct the initial fatigue development curve to obtain the fatigue development curve; generate fatigue relief execution information of the target object according to the breathing information, heartbeat information and the fatigue development curve; wherein, the fatigue relief execution information of the target object is generated according to the breathing information, heartbeat information and the fatigue development curve, including: determining fatigue relief strategy information according to the breathing information and the heartbeat information; the fatigue relief strategy information is the guidance information for fatigue relief of the target object; generating fatigue relief execution information according to the biofeedback information, the fatigue development curve and the fatigue relief strategy information of the target object; the biofeedback information is the parameters about the overall condition of the target object obtained by using different sensing technologies; the fatigue relief execution information is compiled by the seat controller to generate information for controlling the seat and the related equipment connected to the seat for adjustment, so as to relieve the fatigue state of the target object; according to the fatigue relief execution information, the seat is controlled to assist the target object to adjust until the fatigue development curve meets the driving safety information.

[0101] By using millimeter-wave radar to detect the target object's breathing and heartbeat information with high precision, its fatigue state is dynamically monitored. When the system recognizes that the breathing rate or heartbeat data indicates that the object is overly fatigued, it will generate a fatigue development curve based on these physiological parameters to predict its fatigue change trend. Then, based on the breathing information, heartbeat information and the predicted fatigue development curve, a personalized fatigue relief strategy is generated. By automatically adjusting the seat's posture and support function, the target object is assisted in comfort adjustment, which enables the car's seat to accurately and effectively relieve fatigue for the occupants according to actual conditions. At the same time, it can improve the real-time perception and response capabilities of the driver's fatigue state, significantly reduce the risk of accidents caused by fatigue driving through active intervention mechanisms, and improve overall driving safety.

[0102] In an exemplary embodiment, Figure 4 As shown, the short-term fatigue information of the target object is calculated according to the breathing information and the heartbeat information, including steps 402 to 406. Among them:

[0103] Step 402: Calculate the local fatigue index of the target object according to the breathing information and the heartbeat information.

[0104] Among them, the local fatigue index can refer to the quantitative measurement of the fatigue state of the target object in a specific time period, reflecting the abnormal changes in physiological parameters (such as respiratory rate, heart rate variability, etc.) in a short period of time. It captures instantaneous fatigue signals, such as rapid heart rate acceleration, irregular breathing, etc., by analyzing physiological data over a period of time, and provides an instantaneous value to measure the fatigue state. The local fatigue index can quickly identify sudden fatigue or fatigue deterioration by calculating the degree of deviation of short-term fatigue characteristics, and serves as an important reference indicator in overall fatigue assessment and management.

[0105] Specifically, key features (such as respiratory frequency, heart rate, and heart rate variability) are extracted from respiratory and heartbeat information, and these key features are converted into time series data using signal processing algorithms (such as fast Fourier transform or wavelet analysis). The seat controller uses anomaly detection models based on statistics and machine learning (such as support vector machines, K-means clustering, or random forests) to analyze the short-term abnormality and change range in the time series data, and comprehensively calculates each key feature and the corresponding short-term abnormality and change range into an instant local fatigue index.

[0106] Step 404: filter the local fatigue index to obtain transient fatigue information.

[0107] Among them, transient fatigue information can be a fatigue measurement of the target object's physiological state in a very short period of time (such as a few seconds or minutes). It reflects the acute fatigue state caused by stress, load or other factors in a short period of time by capturing the real-time fluctuations of physiological parameters such as respiratory rate, heart rate, and heart rate variability. This information can identify short-term fatigue peaks or fluctuations through fast-response data analysis methods such as real-time signal processing and anomaly detection.

[0108] Specifically, the seat controller uses a digital filter (such as a low-pass filter or a wavelet filter) to perform filtering processing to remove noise and high-frequency interference from the local fatigue index calculated in real time, thereby smoothing data fluctuations; the seat controller further captures transient characteristics by analyzing the filtered data, especially marking and paying attention to sharp changes and short-term fluctuations, identifying changes in fatigue status in a very short time, and obtaining transient fatigue information.

[0109] Step 406, calculating short-term fatigue information according to the local fatigue index and the transient fatigue information; the short-term fatigue information includes a short-term fatigue prediction curve.

[0110] Specifically, time series analysis techniques (such as sliding average and exponential smoothing) are used to perform short-term trend modeling on local fatigue index and transient fatigue information. Short-term trend modeling predicts the fatigue state in a short future time (such as a few minutes to half an hour) through machine learning algorithms (such as recursive neural networks (RNN) or long short-term memory networks (LSTM)) to generate short-term fatigue information. The short-term fatigue information includes a short-term fatigue prediction curve, which shows the trend of fatigue changes in a short period of time, reflecting the current fatigue state of the target object and its short-term changes.

[0111] In this embodiment, the local fatigue index is calculated by analyzing the breathing and heartbeat information of the target object, and is filtered to obtain transient fatigue information. Combining these two parts of data, the system calculates short-term fatigue information and short-term fatigue prediction curves. This multi-level fatigue assessment method can not only accurately capture the immediate changes in fatigue status, but also reveal the fatigue trend in the short term through the prediction curve, providing an accurate basis for real-time fatigue monitoring and early warning. This method improves the sensitivity and predictive ability of fatigue detection, helps to take targeted intervention measures in a timely manner, prevent fatigue accumulation, and improve overall safety and response efficiency.

[0112] In an exemplary embodiment, Figure 5 As shown, the fatigue fluctuation information and long-term fatigue information of the target object are calculated according to the breathing information and the heartbeat information, including steps 502 to 504. Among them:

[0113] Step 502: Perform trend prediction on the breathing information and the heartbeat information to obtain fatigue trend information.

[0114] Among them, fatigue trend information can refer to the analysis results of the change trajectory and development direction of the fatigue state of the target object over a period of time. It identifies the rising, stable or falling trend of fatigue through physiological data of respiratory information and heartbeat information, such as respiratory frequency, heart rate variability, etc.

[0115] Specifically, a causal model is constructed using a Bayesian network, with the features of breathing information and heartbeat information as nodes. The state of the model is updated through dynamic Bayesian reasoning, and the historical breathing information and heartbeat information stored in the car are combined with the current breathing information and heartbeat information to infer future fatigue trends. The learning mechanism of the Bayesian network can integrate prior knowledge and data-driven probabilistic inference to generate fatigue trend information.

[0116] Step 504, performing trend decomposition on the fatigue trend information to obtain fatigue fluctuation information and long-term fatigue information.

[0117] Specifically, the seat controller processes the fatigue trend information through time series decomposition technology (such as empirical mode decomposition (EMD) or seasonal trend decomposition (STL). This process splits the time series into different frequency components, separating the high-frequency part to represent fatigue fluctuation information, reflecting short-term fatigue changes and fluctuations; the low-frequency part represents long-term fatigue information, revealing the long-term trend and accumulation pattern of fatigue.

[0118] In this embodiment, fatigue trend information is generated by predicting the trend of respiratory information and heartbeat information, and the trend information is further decomposed to obtain fatigue fluctuation information and long-term fatigue information. This method realizes a refined analysis of fatigue status, which can not only capture short-term fatigue fluctuations and reflect the immediate fatigue status of the target object, but also reveal the trend of long-term fatigue accumulation and provide an assessment of chronic fatigue. Through this comprehensive and hierarchical fatigue analysis, the system can more accurately monitor and predict fatigue development, optimize fatigue management strategies, effectively prevent fatigue accumulation, and improve the overall health and operational safety of the target object.

[0119] In an exemplary embodiment, Figure 7 As shown, according to the biofeedback information of the target object, the fatigue development curve and the fatigue relief strategy information, the fatigue relief execution information is generated, including steps 702 to 704. Among them:

[0120] Step 702, using the fatigue development curve as a constraint condition, inputting the biofeedback information into the emotion-physiology feedback loop model to obtain stable emotion regulation parameters and stable physiological regulation parameters.

[0121] Among them, the emotional physiological feedback loop model can be a closed-loop model that integrates emotional state and physiological response, which is used to evaluate and regulate the individual's emotional and physiological state in real time. The model captures the individual's emotional changes by continuously monitoring physiological indicators (such as heart rate, skin galvanic response, breathing rate, etc.) and emotional signals (such as facial expressions, voice intonation). Based on these data, the model uses computational models (such as physiological signal processing and emotion recognition algorithms) to generate emotional feedback, and regulates physiological reactions and emotional states through appropriate interventions (such as music regulation, situational simulation, or breathing exercises). Through the feedback mechanism, the model continuously optimizes intervention measures to maintain or improve emotional balance and physiological stability, forming a closed-loop regulation process that helps emotional management and mental health intervention.

[0122] Among them, the stable emotion regulation parameter can be a regulation parameter that can optimize the emotional emotions of the target object for a long time and can relieve the fatigue of the target object for a long time.

[0123] Among them, the stable physiological regulation parameters may be regulation parameters that can optimize the physiological condition of the target object for a long time and relieve the fatigue of the target object for a long time.

[0124] Specifically, with the fatigue development curve as a constraint, that is, using the fatigue development curve as a regulation guide, input biofeedback information (such as heart rate, electromyographic activity, skin galvanic response, etc.) into the emotional physiological feedback loop model. The emotional physiological feedback loop model uses the fatigue development curve to set the target range of physiological and emotional states, and identifies the degree to which the current emotional and physiological states deviate from the target by analyzing the biofeedback information. Apply optimization algorithms (such as particle swarm optimization or genetic algorithms) to dynamically adjust the regulation parameters (such as breathing rhythm, relaxing music volume) in the feedback loop, and iteratively optimize the emotional and physiological regulation strategies until the model outputs stable emotional regulation parameters and stable physiological regulation parameters.

[0125] Step 704, using the fatigue relief strategy information as a constraint condition, and generating fatigue relief execution information according to the stable emotion regulation parameters and the stable physiological regulation parameters.

[0126] Specifically, with fatigue relief strategy information as a constraint, that is, with fatigue relief strategy information as a guide, the stable emotional regulation parameters (such as emotional relaxation techniques) and stable physiological regulation parameters (such as suitable seat adjustment angles) obtained from the emotional physiological feedback loop model are comprehensively analyzed. By parsing these parameters, the seat controller uses a decision algorithm (such as fuzzy logic or multi-objective optimization) to generate a specific fatigue relief execution plan, which may include dynamically adjusting the seat position, adjusting environmental conditions (such as lighting, temperature), or triggering specific emotional and physiological intervention measures (such as playing soothing music, reminding deep breathing, etc.). Ultimately, the fatigue relief execution information generated according to the specific fatigue relief execution plan is an optimized and personalized intervention strategy to ensure that the fatigue state of the target object is effectively alleviated.

[0127] In this embodiment, by combining biofeedback information with the fatigue development curve and inputting it into the emotional physiological feedback loop model, stable emotional regulation parameters and physiological regulation parameters are generated, and then fatigue relief execution information is formulated in combination with fatigue relief strategy information, a highly intelligent fatigue management system is provided in car driving. This system can adapt to the driver's physiological and emotional state in real time, dynamically adjust the in-car environment and driving assistance systems (such as seat support, audio, and temperature adjustment), effectively relieve driving fatigue, and improve the driver's attention and reaction ability. Its intelligent adjustment function can not only prevent fatigue accumulation, but also reduce the risk of accidents caused by fatigue, improve the safety and comfort of long-distance driving, and thus enhance the overall driving experience and road safety.

[0128] In an exemplary embodiment, Figure 8As shown, the biofeedback information includes real-time emotional feedback information and real-time physiological feedback information; taking the fatigue development curve as a constraint condition, the biofeedback information is input into the emotional physiological feedback loop model to obtain stable emotional regulation parameters and stable physiological regulation parameters, including steps 802 to 808. Among them:

[0129] Step 802: generating real-time emotion adjustment parameters according to the real-time emotion feedback information, and generating real-time physiological adjustment parameters according to the real-time physiological feedback information.

[0130] The real-time emotional feedback information may be parameters about the emotional state of the target object obtained in real time from the target object using different sensing technologies.

[0131] Among them, the real-time emotion adjustment parameter can be an adjustment parameter that can optimize the emotional feelings of the target object in a short time and relieve the fatigue of the target object in a short time.

[0132] The real-time physiological feedback information may be parameters about the physiological condition of the target object obtained in real time from the target object using different sensing technologies.

[0133] The real-time physiological adjustment parameter may be an adjustment parameter that can optimize the physiological condition of the target object in a short time and relieve the fatigue of the target object in a short time.

[0134] Specifically, an emotion analysis algorithm (such as a convolutional neural network (CNN) or a support vector machine (SVM)) is used to process real-time emotion feedback information, identify changes in the current emotion state, and generate adaptive real-time emotion adjustment parameters (such as playing music that adapts to the mood or adjusting the data of the interactive interface). At the same time, a signal processing algorithm (such as a Kalman filter or a wavelet analysis) is used to analyze real-time physiological feedback information, evaluate the current physiological state (such as heart rate variability), and generate real-time physiological adjustment parameters (such as adjusting seat comfort or suggesting deep breathing). In one embodiment, the biofeedback information also includes machine vision fatigue detection, which is performed by calculating the local face area through image projection to complete the fine and rough positioning of the eyes, and then based on the significant changes in the gray value around the eyes, the local image binarization and differential projection methods are used to complete the precise positioning of the eyes, and finally the PERCLOS method is used to detect the degree of eyelid droop to obtain the facial feedback information of the target object (as biofeedback information, it is input into the emotion physiological feedback loop model together, and the same processing method is adopted as other feedback information), and the fatigue state of the target object can also be directly judged. For results without fatigue representation, the facial fatigue state during the fatigue process is continuously monitored, and for those with fatigue representation, a rest reminder is immediately issued.

[0135] Step 804: Perform virtual adjustment on the target object according to the real-time emotion adjustment parameter and the real-time physiological adjustment parameter to obtain object virtual adjustment data.

[0136] The object virtual adjustment data may be simulation data obtained by simulating in a virtual adjustment model of a computer using the above two adjustment parameters.

[0137] Specifically, the seat controller inputs real-time emotional adjustment parameters (such as emotional relaxation suggestions) and real-time physiological adjustment parameters (such as recommended breathing rhythm) into the virtual simulation model. Through a virtual simulation engine (such as a physics-based simulator or a data-driven virtual reality system), the actual adjustment process is simulated, such as adjusting the seat position, ambient light, playing audio adapted to emotions, etc. in a virtual environment. The simulation engine calculates the effect of the adjustment measures in real time and generates the response data of the target object in the virtual environment, including posture changes, improvement of emotional state, and adjustment of physiological responses. This virtual adjustment process provides a safe testing platform for verifying and optimizing adjustment strategies, and ultimately generates virtual adjustment data of the object containing detailed adjustment records and effects.

[0138] Step 806: When the object virtual adjustment data fails to satisfy the optimized fatigue development curve, bidirectionally adjust the real-time emotional adjustment parameters and the real-time physiological adjustment parameters according to the object virtual adjustment data.

[0139] Specifically, when the virtual adjustment data of the object fails to meet the optimized fatigue development curve, that is, after the simulation, it is found that the real-time emotional adjustment parameters and real-time physiological adjustment parameters cannot make the fatigue development curve shift in the direction that meets the driving safety information, the seat controller first analyzes the virtual adjustment data of the object and evaluates the response of the target object in the virtual adjustment environment, such as emotional changes (through the emotional analysis model) and physiological responses (through physiological signal processing). Then, the seat controller inputs these response data into the feedback control algorithm (such as proportional integral differential control PID, adaptive control, Bayesian optimization or reinforcement learning model), and gradually adjusts and optimizes the real-time emotional adjustment parameters and real-time physiological adjustment parameters according to the virtual performance of the target object. For example, if the virtual adjustment shows that the target object has a good emotional relaxation effect but the physiological state has not improved significantly, the seat controller will adjust the physiological adjustment parameters (such as increasing the intensity of breathing training) and fine-tune the emotional adjustment parameters accordingly (such as modifying the background audio). This two-way adjustment ensures that the adjustment parameters can adapt to the actual needs of the object in real time through repeated optimization, achieve the best emotional and physiological state adjustment, and finally generate a more accurate adjustment strategy.

[0140] Step 808, use the adjusted real-time emotion regulation parameters and the adjusted real-time physiological regulation parameters to perform cyclic virtual adjustment until the object's virtual adjustment data has satisfied the optimized fatigue development curve, and use the adjusted real-time emotion regulation parameters as stable emotion regulation parameters, and use the adjusted real-time physiological regulation parameters as stable physiological regulation parameters.

[0141] Specifically, the adjusted real-time emotional adjustment parameters and the adjusted real-time physiological adjustment parameters are re-entered into the virtual simulation model, and the virtual simulation engine is used to simulate the effects of these parameters in the virtual environment, such as seat adjustment, ambient light changes, or emotional adjustment strategies. The system monitors the virtual adjustment data generated after each adjustment, and evaluates the impact of the virtual adjustment data on the fatigue development curve (for example, the degree of improvement of the fatigue index). If the virtual adjustment data of the object still fails to meet the optimized fatigue development curve, the adjustment parameters are continuously corrected using a feedback control algorithm or a loop feedback control. The above process is repeated continuously, gradually approaching the optimization target. Until the virtual adjustment data indicates that the fatigue development curve can be offset to meet the driving safety information, or has reached the driving safety information, the system uses the adjusted real-time emotional adjustment parameters at this time as stable emotional adjustment parameters, and the adjusted real-time physiological adjustment parameters as stable physiological adjustment parameters.

[0142] In this embodiment, by using real-time emotional feedback information and physiological feedback information to generate initial adjustment parameters, virtual adjustments are made, and these parameters are repeatedly optimized through two-way adjustment when necessary, and finally stable emotional and physiological adjustment parameters are determined, which significantly improves the driver's safety and comfort during car driving. Through this intelligent, cyclically optimized virtual adjustment method, the system can dynamically simulate and adjust the in-car environment and driving assistance settings (such as seat adjustment, in-car lighting, and audio environment) to ensure that these adjustments meet the best fatigue management effect. This method can not only quickly respond to the driver's immediate emotional and physiological changes, but also predict and prevent fatigue accumulation in advance, reduce fatigue-related risks during long-distance driving, and ensure that the driver maintains a good state under various driving conditions.

[0143] In an exemplary embodiment, Fig. 9 As shown, with fatigue relief strategy information as a constraint condition, according to stable emotion regulation parameters and stable physiological regulation parameters, fatigue relief execution information is generated, including steps 902 to 908. Among them:

[0144] Step 902, using the fatigue relief strategy information as a constraint condition, according to the stable emotion regulation parameters and the stable physiological regulation parameters, determines the visual relief information, the sound relief information and the tactile relief strategy.

[0145] The visual relief information and the sound relief information are specific execution information for alleviating the fatigue state of the target object by visual means and sound means respectively.

[0146] The tactile relief strategy may be guidance information for alleviating the fatigue state of the target object by means of touch.

[0147] Specifically, with fatigue relief strategy information as a constraint condition, that is, with fatigue relief strategy information as a guide condition, combined with stable emotional regulation parameters (such as reduced visual stimulation, auditory relaxation frequency) and stable physiological regulation parameters (such as vibration intensity, contact surface pressure), using multimodal optimization algorithms (such as multi-objective genetic algorithms or fuzzy logic control), the seat controller comprehensively analyzes these parameters to generate specific visual relief information, sound relief information and tactile relief strategies. For example, the system will adjust the execution data of the interior lighting (soft tones) according to the emotional regulation needs, the execution data of playing appropriate background audio (low-frequency soothing music) according to the physiological regulation needs, and the guidance of optimizing the vibration mode of the seat according to contact feedback.

[0148] Step 904 : determining a tactile relief area and tactile relief parameters for the target object according to the tactile relief strategy.

[0149] The tactile relief area may be a contact area for relieving contact fatigue of the target object.

[0150] The tactile relief parameter may be a contact parameter implemented in the tactile relief area for contact fatigue relief of the target object.

[0151] Specifically, the seat controller analyzes the tactile relief strategy, identifies the specific parts that need intervention (such as the back, waist, neck) and the appropriate tactile types (such as vibration, heating, pressure); dynamically detects the target object's body position and pressure distribution through biofeedback information (such as pressure sensors, contact surface distribution data). When the above data is obtained, the seat controller uses a pattern recognition algorithm (such as K-means clustering or support vector machine SVM) based on the above data to identify the area that needs tactile adjustment and obtain the tactile relief area; then, in the tactile relief area, the tactile relief parameters are set in combination with the above data and an optimization algorithm (such as particle swarm optimization or gradient descent), including vibration frequency, intensity and mode, to maximize comfort and relief effects, and obtain tactile relief parameters. Finally, the seat controller adjusts the output of the tactile relief area and tactile relief parameters in real time to provide personalized tactile intervention in these key areas.

[0152] Step 906 : Generate tactile relief information according to the tactile relief area and the tactile relief parameter.

[0153] The tactile relief information may be specific execution information for alleviating the fatigue state of the target object by means of touch.

[0154] Specifically, the tactile relief areas (such as back, waist, neck) and tactile relief parameters (such as vibration frequency, intensity, heating temperature) are combined and converted into specific execution information through control algorithms (such as adaptive control or fuzzy logic). The seat controller integrates biofeedback data (such as real-time pressure distribution and temperature feedback) to dynamically adjust the mode and intensity of the tactile output. The generated tactile relief information contains detailed tactile adjustment plans, such as gentle vibration in specific areas, intermittent heating, or applying uniform pressure. These instructions are transmitted to tactile devices (such as seats and massage pads).

[0155] Step 908: Generate fatigue relief execution information according to the visual relief information, the sound relief information and the tactile relief information.

[0156] Specifically, the seat controller integrates information from different dimensions, including visual relief information (such as lighting adjustment and color change), sound relief information (such as playing relaxing audio, adjusting volume and frequency), and tactile relief information (such as vibration mode and heating area), through multimodal fusion algorithms (such as weighted comprehensive scoring or Bayesian networks), to ensure that various sensory adjustment measures are coordinated with each other. Then, the seat controller generates a comprehensive fatigue relief execution plan, including specific operation instructions (such as changing the seat vibration frequency, adjusting the interior lighting tone, and playing soothing music of a specific frequency). These instructions are sent synchronously to each execution unit (such as seat, audio system, and lighting system) to achieve all-round synchronous intervention.

[0157] In this embodiment, by integrating stable emotions and physiological adjustment parameters, combined with fatigue relief strategy information, visual, sound and tactile relief strategies for the driver are generated, and finally comprehensive fatigue relief execution information is formed, realizing personalized, multi-sensory fatigue management in car driving. This system can intelligently adjust the visual environment (such as lighting color), sound environment (such as background music and volume), and tactile settings (such as seat vibration and heating area) in the car according to the real-time status of the driver. This multi-sensory coordinated relief method can effectively improve the driver's comfort and attention during long-term driving or fatigue accumulation, reduce driving risks caused by fatigue, and enhance driving experience and overall driving safety, thereby providing a comprehensive fatigue management solution.

[0158] In an exemplary embodiment, Fig.10 As shown, according to the fatigue relief execution information, the seat is controlled to assist the target object to adjust until the fatigue development curve meets the driving safety information, including steps 1002 to 1008. Among them:

[0159] Step 1002, according to the fatigue relief execution information, controlling the seat to assist the target object in adjusting, and obtaining updated breathing information, updated heartbeat information and updated biofeedback information.

[0160] Among them, updating the breathing information, updating the heartbeat information and updating the biofeedback information may be obtaining new breathing data, heartbeat data and biological status data after the seat controller controls the seat to relieve fatigue or after fatigue relief.

[0161] Specifically, the seat controller parses the specific instructions in the fatigue relief execution information, such as adjusting the seat's tilt angle, support strength, vibration mode, etc.; through the seat's built-in intelligent adjustment device (such as motor, vibration module), it performs relevant adjustments in real time, prompting the seat to change the target object's posture or provide physical stimulation, and also sends execution instructions to the lighting system and sound system in the car through the seat. The seat controller continuously monitors the target object's response, obtains updated breathing information, updated heartbeat information, and other updated biofeedback data through millimeter-wave radar and biosensors, analyzes and processes these updated data, and systematically evaluates the effect of the adjustment and records the new physiological state.

[0162] Step 1004, generating vehicle auxiliary control information according to the updated breathing information, the updated heartbeat information and the updated biofeedback information.

[0163] The automobile auxiliary control information may be data for assisting a target object in controlling the automobile.

[0164] Specifically, based on the updated breathing information, the updated heartbeat information, and the updated biofeedback information, the data analysis algorithm (such as real-time signal processing and pattern recognition) is used to evaluate the current physiological state and fatigue level of the target object. Then, the seat controller generates auxiliary control information for assisted driving through rule-based reasoning or machine learning models (such as decision trees or random forests), such as modifying the driving mode, taking over the steering wheel of the car, automatic parking, automatic alarm, etc.

[0165] Step 1006, according to the vehicle auxiliary control information, control the vehicle to enter a safe driving state, and obtain the vehicle safe driving information.

[0166] Among them, the automobile safe driving information may be data generated by the automobile during the assisted driving process.

[0167] Specifically, the vehicle auxiliary control information is converted into specific vehicle auxiliary instructions, and the assisted driving is performed in real time through the vehicle's on-board control system (such as CAN bus) to ensure that the vehicle does not cause an emergency accident due to fatigue of the target object. For example, the seat controller automatically evaluates driving safety and adjusts the driving mode (such as activating adaptive cruise control and lane keeping assist) to adapt to the driver's fatigue level and reaction ability. At the same time, the effects of these assists are continuously monitored, and combined with sensor feedback (such as driver behavior and vehicle dynamic data), the vehicle's safe driving information is generated and recorded.

[0168] Step 1008, based on the automobile safe driving information, the updated breathing information is used as the breathing information, the updated heartbeat information is used as the heartbeat information, and the updated biofeedback information is used as the biofeedback information, and the step of determining the fatigue relief strategy information according to the breathing information and the heartbeat information is returned to be executed until the fatigue development curve meets the driving safety information.

[0169] Specifically, based on the safe driving information of the car, the seat controller takes the updated breathing information, updated heartbeat information and updated biofeedback information as new inputs, replaces the original data and feeds back to the data input terminal of the seat controller, and returns to execute the step of determining the fatigue relief strategy information. That is, the seat controller uses the updated breathing information, updated heartbeat information and updated biofeedback information to re-evaluate the fatigue state of the current target object, and generates a new fatigue relief strategy through an algorithm (such as machine learning or rule-based reasoning). The seat controller continuously cycles this process, continuously optimizes fatigue relief measures using the latest physiological feedback, and adjusts the driving environment and strategy in real time until the fatigue development curve shows that the fatigue state is within a safe range, that is, the fatigue development curve meets the driving safety information.

[0170] In this embodiment, the seat is automatically adjusted using fatigue relief execution information to obtain updated breathing, heartbeat and biofeedback data, generate vehicle auxiliary control information and control the vehicle to enter a safe driving state, and cyclically optimize fatigue management, which significantly improves driving safety and comfort. Through this closed-loop system, the driver's physiological state is fed back to the in-vehicle system in real time, and the system automatically adjusts the vehicle control parameters (such as seat position, in-vehicle temperature, audio settings, etc.), and continuously updates and optimizes fatigue relief strategies. This ensures that the driver is always in the best physiological and psychological state, reduces the risk of accidents caused by fatigue, and improves the comfort and safety of long-distance driving, providing a dynamic, adaptive, intelligent management solution for driving.

[0171] In one embodiment, when a slight change in the breathing information and heartbeat information of the target object is detected, the first backup plan or the second backup plan is executed, wherein the execution logic of the first backup plan is as follows: Fig.11 As shown, the execution logic of the second backup plan is as follows Fig.12shown.

[0172] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0173] Based on the same inventive concept, the embodiment of the present application also provides a device for controlling a seat based on a seat controller for implementing the method for controlling a seat based on a seat controller. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more devices for controlling a seat based on a seat controller provided below can refer to the limitations of the method for controlling a seat based on a seat controller above, and will not be repeated here.

[0174] In an exemplary embodiment, Fig.13 As shown, a device for controlling a seat based on a seat controller is provided, comprising: a physiological information acquisition module 1302, a development curve determination module 1304, a relief information generation module 1306 and a relief information execution module 1308, wherein:

[0175] The physiological information acquisition module 1302 is used to acquire the breathing information and heartbeat information of the target object; the breathing information and the heartbeat information are acquired by detecting the target object through the millimeter wave radar;

[0176] The development curve determination module 1304 is used to determine the fatigue development curve of the target object according to the breathing information and the heartbeat information when the fatigue information of the target object represented by the breathing information and / or the heartbeat information exceeds the fatigue threshold; the fatigue development curve is a prediction curve of the fatigue development trend of the target object for a period of time after the current moment; wherein, the fatigue development curve of the target object is determined according to the breathing information and the heartbeat information, including: calculating the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information; fusing the fatigue fluctuation information and the long-term fatigue information to obtain the cumulative fatigue information; using spline interpolation to smoothly fit the short-term fatigue information and the cumulative fatigue information to generate an initial fatigue development curve; obtaining the real-time breathing information and the real-time heartbeat information of the target object; and correcting the initial fatigue development curve according to the real-time breathing information and the real-time heartbeat information to obtain the fatigue development curve;

[0177] The relief information generating module 1306 is used to generate fatigue relief execution information of the target object according to the breathing information, the heartbeat information and the fatigue development curve; wherein, the fatigue relief execution information of the target object is generated according to the breathing information, the heartbeat information and the fatigue development curve, including: determining fatigue relief strategy information according to the breathing information and the heartbeat information; the fatigue relief strategy information is the guidance information for fatigue relief of the target object; generating fatigue relief execution information according to the biofeedback information, the fatigue development curve and the fatigue relief strategy information of the target object; the biofeedback information is the parameters about the overall condition of the target object obtained by using different sensing technologies; the fatigue relief execution information is compiled by the seat controller to generate information for controlling the seat and the related equipment connected to the seat for adjustment, so as to relieve the fatigue state of the target object;

[0178] The relief information execution module 1308 is used to control the seat to assist the target object to adjust according to the fatigue relief execution information until the fatigue development curve meets the driving safety information.

[0179] In one embodiment, the development curve determination module 1304 is also used to calculate the local fatigue index of the target object based on the breathing information and heartbeat information; filter the local fatigue index to obtain transient fatigue information; calculate short-term fatigue information based on the local fatigue index and the transient fatigue information; the short-term fatigue information includes a short-term fatigue prediction curve.

[0180] In one embodiment, the development curve determination module 1304 is further used to perform trend prediction on the respiratory information and the heartbeat information to obtain fatigue trend information; and perform trend decomposition on the fatigue trend information to obtain fatigue fluctuation information and long-term fatigue information.

[0181] In one embodiment, the relief information generation module 1306 is also used to input the biofeedback information into the emotion-physiology feedback loop model with the fatigue development curve as a constraint condition to obtain stable emotion regulation parameters and stable physiological regulation parameters; and to generate fatigue relief execution information based on the stable emotion regulation parameters and stable physiological regulation parameters with the fatigue relief strategy information as a constraint condition.

[0182] In one embodiment, the relief information generation module 1306 is also used to generate real-time emotion regulation parameters based on real-time emotion feedback information, and to generate real-time physiological regulation parameters based on real-time physiological feedback information; to virtually adjust the target object according to the real-time emotion regulation parameters and the real-time physiological regulation parameters to obtain object virtual adjustment data; when the object virtual adjustment data fails to meet the optimized fatigue development curve, to bidirectionally adjust the real-time emotion regulation parameters and the real-time physiological adjustment parameters according to the object virtual adjustment data; to use the adjusted real-time emotion regulation parameters and the adjusted real-time physiological adjustment parameters for cyclic virtual adjustment until the object virtual adjustment data has met the optimized fatigue development curve, and to use the adjusted real-time emotion regulation parameters as stable emotion regulation parameters, and to use the adjusted real-time physiological adjustment parameters as stable physiological adjustment parameters.

[0183] In one embodiment, the relief information generation module 1306 is also used to determine the visual relief information, sound relief information and tactile relief strategy based on the stable emotion regulation parameters and the stable physiological regulation parameters with the fatigue relief strategy information as a constraint condition; determine the tactile relief area and tactile relief parameters for the target object according to the tactile relief strategy; generate tactile relief information according to the tactile relief area and tactile relief parameters; generate fatigue relief execution information according to the visual relief information, sound relief information and tactile relief information.

[0184] In one embodiment, the relief information execution module 1308 is also used to control the seat to assist the target object in adjusting according to the fatigue relief execution information, and obtain updated breathing information, updated heartbeat information and updated biofeedback information; generate vehicle auxiliary control information according to the updated breathing information, updated heartbeat information and updated biofeedback information; control the vehicle to enter a safe driving state according to the vehicle auxiliary control information, and obtain vehicle safe driving information; based on the vehicle safe driving information, use the updated breathing information as breathing information, the updated heartbeat information as heartbeat information, and the updated biofeedback information as biofeedback information, and return to execute the step of determining the fatigue relief strategy information according to the breathing information and heartbeat information until the fatigue development curve meets the driving safety information.

[0185] Each module in the above-mentioned device for controlling a seat based on a seat controller can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0186] The various modules in the above embodiments can be integrated into a seat controller, and the real-time data of the target object obtained by the sensor can be sent to the seat controller in real time. The seat controller controls the seat to assist the target object in adjustment according to various quantity sets until the fatigue development curve meets the driving safety information.

[0187] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig.14 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store server data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for controlling a seat based on a seat controller is implemented.

[0188] Those skilled in the art will understand that Fig.14 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0189] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0190] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0191] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0192] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0193] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0194] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0195] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for controlling a seat based on a seat controller, characterized in that: Applied to a seat controller, the method comprises: Acquire breathing information and heartbeat information of a target object; the breathing information and the heartbeat information are acquired by detecting the target object through a millimeter wave radar; In the case where the respiratory information and / or the heartbeat information indicate that the fatigue information of the target object exceeds the fatigue threshold, determining a fatigue development curve of the target object according to the respiratory information and the heartbeat information; the fatigue development curve is a prediction curve of the fatigue development trend of the target object in a period of time after the current moment; Wherein, determining the fatigue development curve of the target object according to the breathing information and the heartbeat information includes: calculating the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information; fusing the fatigue fluctuation information and the long-term fatigue information to obtain the cumulative fatigue information; using spline interpolation to perform smooth fitting on the short-term fatigue information and the cumulative fatigue information to generate an initial fatigue development curve; acquiring the real-time breathing information and real-time heartbeat information of the target object; and correcting the initial fatigue development curve according to the real-time breathing information and the real-time heartbeat information to obtain the fatigue development curve; generating fatigue relief execution information of the target object according to the breathing information, the heartbeat information and the fatigue development curve; The step of generating fatigue relief execution information of the target object according to the breathing information, the heartbeat information and the fatigue development curve includes: Determining fatigue relief strategy information according to the breathing information and the heartbeat information; the fatigue relief strategy information is guidance information for relieving fatigue of the target object; generating the fatigue relief execution information according to the biofeedback information of the target object, the fatigue development curve, and the fatigue relief strategy information; The step of generating the fatigue relief execution information according to the biofeedback information of the target object, the fatigue development curve and the fatigue relief strategy information includes: Taking the fatigue development curve as a constraint condition, the biofeedback information is input into the emotional physiological feedback loop model to obtain stable emotional regulation parameters and stable physiological regulation parameters; the emotional physiological feedback loop model captures individual emotional changes through continuously monitored physiological indicators and emotional signals, uses a computational model to generate emotional feedback, and regulates physiological reactions and emotional states according to the emotional feedback; Taking the fatigue relief strategy information as a constraint condition, generating the fatigue relief execution information according to the stable emotion regulation parameter and the stable physiological regulation parameter; The biofeedback information includes real-time emotional feedback information and real-time physiological feedback information; the fatigue development curve is used as a constraint condition, and the biofeedback information is input into the emotional physiological feedback loop model to obtain stable emotional regulation parameters and stable physiological regulation parameters, including: Generating real-time emotion adjustment parameters according to the real-time emotion feedback information, and generating real-time physiological adjustment parameters according to the real-time physiological feedback information; According to the real-time emotion adjustment parameter and the real-time physiological adjustment parameter, the target object is virtually adjusted to obtain object virtual adjustment data; In the case where the object virtual adjustment data fails to meet the requirements for optimizing the fatigue development curve, bidirectionally adjusting the real-time emotion adjustment parameter and the real-time physiological adjustment parameter according to the object virtual adjustment data; Using the adjusted real-time emotion adjustment parameters and the adjusted real-time physiological adjustment parameters to perform cyclic virtual adjustment until the object virtual adjustment data has satisfied the optimization of the fatigue development curve, using the adjusted real-time emotion adjustment parameters as the stable emotion adjustment parameters, and using the adjusted real-time physiological adjustment parameters as the stable physiological adjustment parameters; The step of generating the fatigue relief execution information based on the fatigue relief strategy information as a constraint condition and the stable emotion regulation parameter and the stable physiological regulation parameter includes: Taking the fatigue relief strategy information as a constraint condition, determining visual relief information, sound relief information and tactile relief strategy according to the stable emotional regulation parameter and the stable physiological regulation parameter; Determining a tactile relief area and tactile relief parameters for the target object according to the tactile relief strategy; generating tactile relief information according to the tactile relief area and the tactile relief parameter; generating the fatigue relief execution information according to the visual relief information, the sound relief information and the tactile relief information; The biofeedback information is parameters about the overall condition of the target object obtained using different sensing technologies; The fatigue relief execution information is compiled by the seat controller to generate information for controlling the seat and related equipment connected to the seat to adjust, so as to relieve the fatigue state of the target object; According to the fatigue relief execution information, the seat is controlled to assist the target object in making adjustments until the fatigue development curve meets the driving safety information.

2. The method according to claim 1, characterized in that The calculating the short-term fatigue information of the target object according to the breathing information and the heartbeat information includes: Calculating a local fatigue index of the target object according to the breathing information and the heartbeat information; Performing filtering processing on the local fatigue index to obtain transient fatigue information; The short-term fatigue information is calculated according to the local fatigue index and the transient fatigue information; the short-term fatigue information includes a short-term fatigue prediction curve.

3. The method according to claim 2, characterized in that The step of calculating the fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information includes: Performing trend prediction on the breathing information and the heartbeat information to obtain fatigue trend information; The fatigue trend information is subjected to trend decomposition to obtain the fatigue fluctuation information and the long-term fatigue information.

4. The method according to claim 1, characterized in that: According to the fatigue relief execution information, controlling the seat to assist the target object in adjusting until the fatigue development curve meets the driving safety information includes: According to the fatigue relief execution information, controlling the seat to assist the target subject in adjusting, and obtaining updated breathing information, updated heartbeat information, and updated biofeedback information; generating automobile auxiliary control information according to the updated breathing information, the updated heartbeat information and the updated biofeedback information; According to the automobile auxiliary control information, the automobile is controlled to enter a safe driving state, and automobile safe driving information is obtained; Based on the automobile safe driving information, the updated breathing information is used as the breathing information, the updated heartbeat information is used as the heartbeat information, and the updated biofeedback information is used as the biofeedback information, and the step of determining the fatigue relief strategy information based on the breathing information and the heartbeat information is returned to be executed until the fatigue development curve meets the driving safety information.

5. A device for controlling a seat based on a seat controller, characterized in that: Applied to a seat controller, the device comprises: A physiological information acquisition module is used to acquire the breathing information and heartbeat information of the target object; the breathing information and the heartbeat information are acquired by detecting the target object through a millimeter wave radar; a development curve determination module, configured to determine a fatigue development curve of the target object according to the breathing information and the heartbeat information, when the fatigue information of the target object represented by the breathing information and / or the heartbeat information exceeds a fatigue threshold; the fatigue development curve is a prediction curve of the fatigue development trend of the target object in a period of time after the current moment; Wherein, determining the fatigue development curve of the target object according to the breathing information and the heartbeat information includes: calculating the short-term fatigue information, fatigue fluctuation information and long-term fatigue information of the target object according to the breathing information and the heartbeat information; fusing the fatigue fluctuation information and the long-term fatigue information to obtain the cumulative fatigue information; using spline interpolation to perform smooth fitting on the short-term fatigue information and the cumulative fatigue information to generate an initial fatigue development curve; acquiring the real-time breathing information and real-time heartbeat information of the target object; and correcting the initial fatigue development curve according to the real-time breathing information and the real-time heartbeat information to obtain the fatigue development curve; a relief information generating module, configured to generate fatigue relief execution information of the target object according to the breathing information, the heartbeat information and the fatigue development curve; The step of generating fatigue relief execution information of the target object according to the breathing information, the heartbeat information and the fatigue development curve includes: Determining fatigue relief strategy information according to the breathing information and the heartbeat information; the fatigue relief strategy information is guidance information for relieving fatigue of the target object; generating the fatigue relief execution information according to the biofeedback information of the target object, the fatigue development curve, and the fatigue relief strategy information; The step of generating the fatigue relief execution information according to the biofeedback information of the target object, the fatigue development curve and the fatigue relief strategy information includes: Taking the fatigue development curve as a constraint condition, the biofeedback information is input into the emotional physiological feedback loop model to obtain stable emotional regulation parameters and stable physiological regulation parameters; the emotional physiological feedback loop model captures individual emotional changes through continuously monitored physiological indicators and emotional signals, uses a computational model to generate emotional feedback, and regulates physiological reactions and emotional states according to the emotional feedback; Taking the fatigue relief strategy information as a constraint condition, generating the fatigue relief execution information according to the stable emotion regulation parameter and the stable physiological regulation parameter; The biofeedback information includes real-time emotional feedback information and real-time physiological feedback information; the fatigue development curve is used as a constraint condition, and the biofeedback information is input into the emotional physiological feedback loop model to obtain stable emotional regulation parameters and stable physiological regulation parameters, including: Generating real-time emotion adjustment parameters according to the real-time emotion feedback information, and generating real-time physiological adjustment parameters according to the real-time physiological feedback information; According to the real-time emotion adjustment parameter and the real-time physiological adjustment parameter, the target object is virtually adjusted to obtain object virtual adjustment data; In the case where the object virtual adjustment data fails to meet the requirements for optimizing the fatigue development curve, bidirectionally adjusting the real-time emotion adjustment parameter and the real-time physiological adjustment parameter according to the object virtual adjustment data; Using the adjusted real-time emotion adjustment parameters and the adjusted real-time physiological adjustment parameters to perform cyclic virtual adjustment until the object virtual adjustment data has satisfied the optimization of the fatigue development curve, using the adjusted real-time emotion adjustment parameters as the stable emotion adjustment parameters, and using the adjusted real-time physiological adjustment parameters as the stable physiological adjustment parameters; The step of generating the fatigue relief execution information based on the fatigue relief strategy information as a constraint condition and the stable emotion regulation parameter and the stable physiological regulation parameter includes: Taking the fatigue relief strategy information as a constraint condition, determining visual relief information, sound relief information and tactile relief strategy according to the stable emotional regulation parameter and the stable physiological regulation parameter; Determining a tactile relief area and tactile relief parameters for the target object according to the tactile relief strategy; generating tactile relief information according to the tactile relief area and the tactile relief parameter; generating the fatigue relief execution information according to the visual relief information, the sound relief information and the tactile relief information; The biofeedback information is parameters about the overall condition of the target object obtained using different sensing technologies; The fatigue relief execution information is compiled by the seat controller to generate information for controlling the seat and related equipment connected to the seat to adjust, so as to relieve the fatigue state of the target object; The relief information execution module is used to control the seat to assist the target object in adjusting according to the fatigue relief execution information until the fatigue development curve meets the driving safety information.