A method and system for adjusting and controlling the massage function of a car seat

Abstract

The present invention discloses a method and system for regulating and controlling a massage function of an automobile seat, and specifically relates to the technical field of automobile seats: by acquiring real-time pressure data and weight distribution data from a seat sensor, and extracting air bag pressure reference data and weight distribution data under historical normal operating conditions, then by analyzing the difference between real-time and historical data, an error model is constructed, and a comprehensive error index of sensor data is calculated. According to the error index, the system compares it with a gradient standard threshold: if it is less than a first threshold, the system considers that the sensor is normal; if it is between the two thresholds, the sensor has a slight abnormality, and an early warning is generated and the massage mode and intensity are dynamically adjusted; if the error index exceeds a second threshold, a fault signal is generated, and the system immediately stops the massage function to prevent further damage, thereby effectively improving the safety, stability and user experience of the system, and avoiding incorrect adjustments and safety hazards caused by sensor failure.

Description

Technical Field

[0001] The invention relates to the technical field of automobile seats, and in particular to a method and system for regulating and controlling a massage function of an automobile seat. Background Art

[0002] The adjustment control of the car seat massage function refers to the user adjusting the operating mode and intensity of the seat's built-in massage system through a specific control system. This function usually allows the user to select different massage types, massage areas, and massage strength and speed. Overall, the adjustment control function is intended to provide users with a personalized comfort experience and reduce fatigue during long-term driving. In the prior art, some advanced seat massage systems achieve a variety of massage effects by embedding multiple inflatable and deflated air bags inside the seat. These air bags are usually located in the back, waist and hip areas of the seat, and simulate kneading, squeezing or pushing massage techniques through changes in the rhythm of inflation and deflation. Users can adjust different massage modes, intensities and action areas to meet personal needs.

[0003] The prior art has the following deficiencies:

[0004] In the prior art, many advanced seat massage systems usually rely on sensors in the seat to monitor weight distribution and posture to adjust the inflation state of the air bag. However, if the sensor fails after a long period of operation, the system may adjust the air bag based on the wrong information, resulting in a poor massage experience or even strong pressure in the wrong part, affecting the driver's comfort and reaction time. At the same time, incorrect air pressure adjustment may change the driver's seat posture or support at critical moments (such as turning or emergency braking), causing the driver to lose precise control of the vehicle, especially at high speeds or in complex road conditions. Summary of the invention

[0005] The object of the present invention is to provide a method and system for adjusting and controlling the massage function of a car seat, so as to solve the deficiencies in the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for adjusting and controlling the massage function of a car seat, comprising the following steps:

[0007] S1; acquiring real-time pressure sensor data and real-time seat occupancy detection data within a certain time period from a seat sensor, wherein the real-time pressure sensor data is real-time air bag pressure data, and the real-time seat occupancy detection data is real-time weight distribution data;

[0008] S2: Based on the historical data of the car seat massage system, the historical air bag pressure reference data and the historical weight distribution data of the seat sensor under normal operating conditions are extracted respectively;

[0009] S3: Compare and analyze the real-time data with the corresponding historical data, build an error test model based on the difference between the air bag pressure reference data and the weight distribution data, and determine the weight assignment of the seat sensor data in each time period based on the model output results, and calculate the comprehensive error index of the seat sensor data after performing weighted average calculation;

[0010] S4: Compare the obtained comprehensive error index with a gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold. If the comprehensive error index is less than the first standard threshold, the sensor is in a normal state and does not need to be adjusted.

[0011] S5: If the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the degree of abnormality of the sensor is low. At this time, a warning signal is generated, and the massage mode and intensity are dynamically adjusted; if the comprehensive error index is greater than the second standard threshold, the degree of abnormality of the sensor is high. At this time, a fault signal is generated, and the massage function is stopped immediately.

[0012] Preferably, in S3, an air bag cumulative pressure deviation index is generated according to the deviation between the real-time air bag pressure reference data and the historical air bag pressure reference data, and the method for obtaining the air bag cumulative pressure deviation index is:

[0013] Get the real-time air bag pressure data at time t and with historical reference pressure Compare and calculate the pressure deviation value , the expression is: ; The mean of the pressure deviation values and variance Converted to normal distribution, the expression is: ; is the prior distribution; based on the prior distribution and real-time air bag pressure data Construct the likelihood function, the expression is: ; is the variance of the measurement error. According to Bayes’ theorem, the updated posterior distribution is It is calculated based on the prior distribution and likelihood function, and the expression is: ;in, is a normalization constant; whenever new real-time pressure data is obtained , according to the deviation of the data , the posterior distribution of the air bag cumulative pressure deviation is adjusted by the Bayesian update formula, where the updated mean for: ; Updated variance for: ; For the data at t time points , the air bag cumulative pressure deviation index is calculated by continuously updating the posterior distribution.

[0014] Preferably, in S3, a weight distribution abnormality index is generated according to the deviation between the real-time weight distribution data and the historical weight distribution data, and the method for obtaining the weight distribution abnormality index is:

[0015] Get real-time weight distribution data from the seat sensor, indicating the user's weight distribution status at the current moment is marked as , is an n×1 vector, which indicates the distribution of weight in different areas of the seat. The weight distribution data under normal operation is extracted from the historical records, and the reference state under the usage scenario is marked as , is an n×m matrix, where n is the dimension of weight distribution and m is the number of samples of historical data. They are standardized respectively, and the covariance matrix C is calculated for the standardized historical data, which is expressed as: ; In the formula, is the standardized historical data, T is the matrix transpose, and the covariance matrix C is decomposed to obtain the eigenvalue and the corresponding eigenvector , these eigenvectors define the new principal component directions: ; Select the first k largest principal components according to the eigenvalue size, and the principal component directions form a matrix , which is an n×k matrix, representing the first k principal components; projecting the standardized historical data into the principal component space , the expression is: ; Project the standardized real-time weight distribution data into the same principal component space , ; For the standardized real-time data, the real-time data projection is calculated Projection with historical data The distance between them is used to calculate the abnormal weight distribution index, and the expression is: ; Where LK is the abnormal weight distribution index, is the mean of historical data in the principal component space, It is the covariance matrix, which represents the distribution of historical data in the principal component space.

[0016] Preferably, the air bag cumulative pressure deviation index and the weight distribution abnormality index are normalized, and the weight assignment of the seat sensor data in each time period is calculated by using the normalized air bag cumulative pressure deviation index and the weight distribution abnormality index, and the comprehensive error index of the seat sensor data is calculated after weighted averaging.

[0017] Preferably, in S4, the obtained comprehensive error index is compared with a gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold, specifically:

[0018] Comparing the acquired comprehensive error index of the seat sensor data with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the comprehensive error index of the seat sensor data with the first standard threshold and the second standard threshold respectively;

[0019] If the comprehensive error index of the seat sensor data is greater than the second standard threshold, it means that the error of the seat sensor data is high and the abnormality is high, and the sensor is classified as abnormal and needs further monitoring;

[0020] If the comprehensive error index of the seat sensor data is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the error of the seat sensor data is normal and the abnormality is low, the sensor is classified as abnormal and the sensor is adjusted;

[0021] If the comprehensive error index of the seat sensor data is less than the first standard threshold, it means that the error of the seat sensor data is low, and the sensor is classified as an abnormal state and does not need to be adjusted.

[0022] Preferably, in S5, if the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the degree of abnormality of the sensor is low, and an early warning signal is generated at this time, and the massage mode and intensity are dynamically adjusted, specifically:

[0023] The first standard threshold is marked as , the second standard threshold is marked as According to the size of the comprehensive error index, when the comprehensive error index of the seat sensor data is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the system dynamically adjusts the massage mode and intensity, and defines the adjustment coefficient as , used to adjust the massage mode and intensity: adjust the massage mode parameters , the expression is: ; is the massage mode parameter after adjustment, is the default massage mode parameter, is an adjustment coefficient that controls the adjustment range. is the normalized error index; adjust the massage intensity parameter , the expression is: ; In the formula, is the adjusted massage intensity, It is the default massage intensity.

[0024] The present invention also provides a control system for the massage function of a car seat, comprising a data acquisition module, a historical data extraction module, an error calculation module, a comparison module and an adjustment module;

[0025] A data acquisition module; acquiring real-time pressure sensor data and real-time seat occupancy detection data within a certain time period from a seat sensor, wherein the real-time pressure sensor data is real-time air bag pressure data, and the real-time seat occupancy detection data is real-time weight distribution data;

[0026] Historical data extraction module: Based on the historical data of the car seat massage system, the historical air bag pressure reference data and historical weight distribution data of the seat sensor under normal operating conditions are extracted respectively;

[0027] Error calculation module: compares and analyzes real-time data with corresponding historical data, builds an error test model based on the difference between air bag pressure reference data and weight distribution data, and determines the weight assignment of seat sensor data in each time period based on the model output results, and calculates the comprehensive error index of seat sensor data after performing weighted average calculation;

[0028] Comparison module: compares the obtained comprehensive error index with the gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold. If the comprehensive error index is less than the first standard threshold, the sensor is in a normal state and does not need to be adjusted.

[0029] Adjustment module: If the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the degree of abnormality of the sensor is low. At this time, a warning signal is generated, and the massage mode and intensity are dynamically adjusted; if the comprehensive error index is greater than the second standard threshold, the degree of abnormality of the sensor is high. At this time, a fault signal is generated, and the massage function is stopped immediately.

[0030] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0031] 1. The present invention obtains real-time pressure sensor data and weight distribution data in multiple time periods, compares and analyzes them with historical reference data, builds an error model, and calculates a comprehensive error index. The system automatically determines the health status of the sensor based on the error index, and generates early warning signals or fault signals in a timely manner through the set gradient standard threshold, thereby dynamically adjusting the massage mode and intensity, or immediately stopping the massage function in severe cases to ensure the safety and effectiveness of the system.

[0032] 2. The present invention accurately evaluates the abnormal conditions of air bag pressure and weight distribution through advanced mathematical models, and improves the accuracy and real-time performance of error detection through normalization and weight calculation. The system can flexibly adjust massage parameters to avoid discomfort or safety hazards caused by sensor errors, thereby ensuring the user's driving experience. At the same time, when the sensor abnormality is high, the system will automatically stop related functions to avoid hardware damage or potential dangers. This intelligent control mechanism greatly improves the reliability, stability and user experience of the seat massage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0034] Figure 1 The present invention is a flow chart of the method.

[0035] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Example 1, please refer to Figure 1 As shown, the adjustment and control method of the massage function of a car seat described in this embodiment includes the following steps:

[0038] S1; acquiring real-time pressure sensor data and real-time seat occupancy detection data within a certain time period from a seat sensor, wherein the real-time pressure sensor data is real-time air bag pressure data, and the real-time seat occupancy detection data is real-time weight distribution data;

[0039] S2: Based on the historical data of the car seat massage system, the historical air bag pressure reference data and the historical weight distribution data of the seat sensor under normal operating conditions are extracted respectively;

[0040] S3: Compare and analyze the real-time data with the corresponding historical data, build an error test model based on the difference between the air bag pressure reference data and the weight distribution data, and determine the weight assignment of the seat sensor data in each time period based on the model output results, and calculate the comprehensive error index of the seat sensor data after performing weighted average calculation;

[0041] S4: Compare the obtained comprehensive error index with a gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold. If the comprehensive error index is less than the first standard threshold, the sensor is in a normal state and does not need to be adjusted.

[0042] S5: If the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the degree of abnormality of the sensor is low. At this time, a warning signal is generated, and the massage mode and intensity are dynamically adjusted; if the comprehensive error index is greater than the second standard threshold, the degree of abnormality of the sensor is high. At this time, a fault signal is generated, and the massage function is stopped immediately.

[0043] Among them, in S1, real-time pressure sensor data and real-time seat occupancy detection data within several time periods are obtained from the seat sensor, the real-time pressure sensor data is real-time air bag pressure data, and the real-time seat occupancy detection data is real-time weight distribution data.

[0044] When the vehicle is started or the seat massage function is turned on, the system activates various sensors embedded in the seat, including pressure sensors and seat occupancy detection sensors. Each seat's built-in air bag is equipped with a pressure sensor to monitor the real-time pressure status of the air bag in different massage modes. The sensor feeds back the detected pressure value to the system in real time. The system collects air bag pressure data over several time periods (for example, every few seconds or minutes) to ensure that the pressure changes at each stage during the dynamic massage process are recorded and analyzed. Seat occupancy detection sensors (such as pressure sensors, load sensors) are used to monitor the user's weight distribution and sitting posture in real time. These data help determine the user's position and posture on the seat, thereby assisting the system in adjusting the massage area and strength. Like the air bag pressure data, the system obtains weight distribution data over several time periods to continuously track the user's weight distribution changes and posture adjustments.

[0045] S2: Based on the historical data of the car seat massage system, the historical air bag pressure reference data and the historical weight distribution data of the seat sensor under normal operating conditions are extracted respectively.

[0046] Car seat massage systems usually have a storage module to save historical data. The data storage includes air bag pressure data and seat occupancy (weight distribution) data recorded when the sensor is running. After the system is initialized, the data under normal operating conditions will be recorded and archived for reference. Normal operating conditions usually refer to data when the sensor is not faulty and the seat massage function is working according to the preset mode. These conditions can be defined based on the factory calibration data of the vehicle or stable operating data when used by the user over a period of time.

[0047] From the historical data records, filter out the air bag pressure data collected when the system is operating normally. These data should reflect the pressure changes of the air bag in different massage modes, such as normal pressure values ​​in rolling, hammering, vibration and other modes. Eliminate abnormal pressure values ​​caused by errors or sensor failures to ensure that the extracted data only comes from records when the system is running stably. De-noise the data to eliminate unreasonable pressure fluctuations. Calculate and extract the air bag pressure reference value for each massage mode. The average, maximum, minimum or other statistical values ​​of the data can be used to ensure that the pressure reference data for each mode has sufficient accuracy.

[0048] Extract weight distribution data collected by the seat sensor in normal operation. Weight distribution data is usually detected by pressure sensors or load sensors to detect the user's posture and weight distribution on the seat, especially the pressure distribution in the back, waist and hip areas. Extract weight distribution reference data according to different user body types, weights and sitting postures. For example, extract historical weight distribution data that matches users of different body types. Perform statistical analysis on the data to generate weight distribution reference data for different body types and usage scenarios. The median or weighted average of the data can be used to ensure that the reference data is representative and stable.

[0049] S3: Compare and analyze the real-time data with the corresponding historical data, build an error test model based on the difference between the air bag pressure reference data and the weight distribution data, and determine the weight assignment of the seat sensor data in each time period based on the model output results. Calculate the comprehensive error index of the seat sensor data after performing weighted average calculation.

[0050] Comparing real-time data with corresponding historical data means that the system compares the real-time air bag pressure and weight distribution data collected by the current sensor with the historical reference data collected under normal operating conditions to evaluate the difference between the two. If the deviation between the real-time data and the historical data is small, it indicates that the system is operating normally; however, if the deviation is large, it may indicate that the sensor is abnormal or the system is malfunctioning. Through this comparison, the system can dynamically monitor and adjust the massage function to ensure its accuracy and stability.

[0051] The air bag cumulative pressure deviation index is generated according to the deviation between the real-time air bag pressure reference data and the historical air bag pressure reference data. The method for obtaining the air bag cumulative pressure deviation index is:

[0052] Get the real-time air bag pressure data at time t and with historical reference pressure Compare and calculate the pressure deviation value , the expression is: ; The mean of the pressure deviation values and variance Converted to normal distribution, the expression is: ; is the prior distribution; based on the prior distribution and real-time air bag pressure data Construct the likelihood function, the expression is: ; is the variance of the measurement error. According to Bayes’ theorem, the updated posterior distribution is It is calculated based on the prior distribution and likelihood function, and the expression is: ;in, is a normalization constant; whenever new real-time pressure data is obtained , according to the deviation of the data , the posterior distribution of the air bag cumulative pressure deviation is adjusted by the Bayesian update formula, where the updated mean for: ; Updated variance for: ; For the data at t time points , the air bag cumulative pressure deviation index is calculated by continuously updating the posterior distribution.

[0053] The larger the air bag cumulative pressure deviation index is, the lower the accuracy of the seat sensor data is. The cumulative pressure deviation index reflects the deviation between the real-time pressure data and the historical reference data. The larger the index is, the more serious the deviation of the sensor from the normal range is over a long period of time, which means that the sensor may have measurement errors or failures, resulting in its data being inaccurate.

[0054] The weight distribution abnormality index is generated according to the deviation between the real-time weight distribution data and the historical weight distribution data. The method for obtaining the weight distribution abnormality index is as follows:

[0055] Get real-time weight distribution data from the seat sensor, indicating the user's weight distribution status at the current moment is marked as , is an n×1 vector, which indicates the distribution of weight in different areas of the seat. The weight distribution data under normal operation is extracted from the historical records, and the reference state under normal use scenario is marked as , is an n×m matrix, where n is the dimension of weight distribution and m is the number of samples of historical data. They are standardized respectively, and the covariance matrix C is calculated for the standardized historical data, which is expressed as: ; In the formula, is the standardized historical data, T is the matrix transpose, and the covariance matrix C is decomposed to obtain the eigenvalue and the corresponding eigenvector , these eigenvectors define the new principal component directions: ; Select the first k largest principal components according to the eigenvalue size, and the principal component directions form a matrix , which is an n×k matrix, representing the first k principal components; projecting the standardized historical data into the principal component space , the expression is: ; Project the standardized real-time weight distribution data into the same principal component space , ; For the standardized real-time data, the real-time data projection is calculated Projection with historical data The distance between them is used to calculate the abnormal weight distribution index, and the expression is: ; Where LK is the abnormal weight distribution index, is the mean of historical data in the principal component space, It is the covariance matrix, which represents the distribution of historical data in the principal component space.

[0056] The larger the weight distribution anomaly index, the lower the accuracy of the seat sensor data. This is because the anomaly index reflects the deviation between the real-time weight distribution data and the historical normal data. The larger the index, the more the real-time data deviates from the historical reference value, which means that the sensor may not be able to accurately detect the user's weight distribution or seat occupancy. This may be due to sensor failure, increased data noise, improper calibration, etc., resulting in data that is no longer reliable, which in turn affects the normal functional adjustment of the seat massage system and user experience.

[0057] The air bag cumulative pressure deviation index and the weight distribution abnormality index are normalized, and the weight assignment of the seat sensor data in each time period is calculated by the normalized air bag cumulative pressure deviation index and the weight distribution abnormality index. The comprehensive error index of the seat sensor data is calculated after weighted average calculation.

[0058] For example, the present invention may use the following formula to calculate the weight assignment of the seat sensor data in each time period, and the calculation expression is: ; In the formula, MY is the weight assignment of the seat sensor data in each time period, QS is the air bag cumulative pressure deviation index, LK is the weight distribution abnormality index, is the proportionality coefficient of the air bag cumulative pressure deviation index and the weight distribution abnormality index, and .

[0059] S4: Compare the obtained comprehensive error index with a gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold. If the comprehensive error index is less than the first standard threshold, the sensor is in a normal state and does not need to be adjusted.

[0060] Comparing the acquired comprehensive error index of the seat sensor data with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the comprehensive error index of the seat sensor data with the first standard threshold and the second standard threshold respectively;

[0061] If the comprehensive error index of the seat sensor data is greater than the second standard threshold, it means that the error of the seat sensor data is high and the abnormality is high, and the sensor is classified as abnormal and needs further monitoring;

[0062] If the comprehensive error index of the seat sensor data is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the error of the seat sensor data is normal and the abnormality is low, the sensor is classified as abnormal and the sensor is adjusted;

[0063] If the comprehensive error index of the seat sensor data is less than the first standard threshold, it means that the error of the seat sensor data is low, and the sensor is classified as an abnormal state and does not need to be adjusted.

[0064] S5: If the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the degree of abnormality of the sensor is low. At this time, a warning signal is generated, and the massage mode and intensity are dynamically adjusted; if the comprehensive error index is greater than the second standard threshold, the degree of abnormality of the sensor is high. At this time, a fault signal is generated, and the massage function is stopped immediately.

[0065] If the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the sensor is abnormal to a low degree, and an early warning signal is generated at this time, and the massage mode and intensity are dynamically adjusted, specifically:

[0066] The first standard threshold is marked as , the second standard threshold is marked as According to the size of the comprehensive error index, when the comprehensive error index of the seat sensor data is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the system dynamically adjusts the massage mode and intensity. The adjustment strategy is usually based on the size of the error. An adjustment coefficient is defined as , used to adjust the massage mode or intensity: adjust the massage mode parameters , the expression is: ; are the massage mode parameters that have been adjusted (such as the intensity or area coverage of a certain massage), is the default massage mode parameter, Is an adjustment coefficient, which controls the adjustment range. ,when When , the adjustment range is the largest. is the normalized error index, which means the error index is arrive The relative position between them; adjust the massage intensity parameters , the expression is: ; In the formula, is the adjusted massage intensity, It is the default massage intensity (such as the initial setting intensity).

[0067] If the comprehensive error index is greater than the second standard threshold, the sensor is highly abnormal, a fault signal is generated, and the massage function is immediately stopped. If the comprehensive error index of the seat sensor data is greater than the second standard threshold, it means that the sensor has a high degree of error, the sensor data has seriously deviated from the normal range, and the system determines that the sensor is seriously abnormal. At this time, the system generates a fault signal, indicating that the seat massage function may be seriously affected or fail. To avoid further damage to the seat components or affecting the safety and comfort of the user, the system will immediately stop the operation of the massage function, shut down all related control operations, and send a warning notification to the user, suggesting system inspection or maintenance.

[0068] In this embodiment, the car seat sensor data is analyzed and controlled through multiple steps. First, the real-time air bag pressure data and weight distribution data are obtained from the seat sensor, and the historical data of the system in normal state is extracted as a reference. Next, the real-time data is compared with the historical data, an error test model is constructed, the sensor weights of each time period are calculated, and a comprehensive error index is obtained. Then, the comprehensive error index is compared with the gradient standard threshold. If the error index is lower than the first standard threshold, the sensor state is normal and no adjustment is required; if the error index is between the first and second standard thresholds, the sensor has a slight abnormality, an early warning signal is generated, and the massage mode and intensity are dynamically adjusted; if the error index exceeds the second standard threshold, the sensor has a serious abnormality, the system generates a fault signal and immediately stops the massage function to prevent further damage.

[0069] Example 2, please refer to Figure 2 As shown, the control system for the massage function of a car seat described in this embodiment includes a data acquisition module, a historical data extraction module, an error calculation module, a comparison module and an adjustment module;

[0070] A data acquisition module; acquiring real-time pressure sensor data and real-time seat occupancy detection data within a certain time period from a seat sensor, wherein the real-time pressure sensor data is real-time air bag pressure data, and the real-time seat occupancy detection data is real-time weight distribution data;

[0071] Historical data extraction module: Based on the historical data of the car seat massage system, the historical air bag pressure reference data and historical weight distribution data of the seat sensor under normal operating conditions are extracted respectively;

[0072] Error calculation module: compares and analyzes real-time data with corresponding historical data, builds an error test model based on the difference between air bag pressure reference data and weight distribution data, and determines the weight assignment of seat sensor data in each time period based on the model output results, and calculates the comprehensive error index of seat sensor data after performing weighted average calculation;

[0073] Comparison module: compares the obtained comprehensive error index with the gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold. If the comprehensive error index is less than the first standard threshold, the sensor is in a normal state and does not need to be adjusted.

[0074] Adjustment module: If the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the degree of abnormality of the sensor is low. At this time, a warning signal is generated, and the massage mode and intensity are dynamically adjusted; if the comprehensive error index is greater than the second standard threshold, the degree of abnormality of the sensor is high. At this time, a fault signal is generated, and the massage function is stopped immediately.

[0075] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0076] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0077] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0078] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0079] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0080] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for adjusting and controlling the massage function of a car seat, characterized in that: The steps include: S1； Acquiring real-time pressure sensor data and real-time seat occupancy detection data within a plurality of time periods from a seat sensor, wherein the real-time pressure sensor data is real-time air bag pressure data, and the real-time seat occupancy detection data is real-time weight distribution data; S2: Based on the historical data of the car seat massage system, the historical air bag pressure reference data and the historical weight distribution data of the seat sensor under normal operating conditions are extracted respectively; S3: Compare and analyze the real-time data with the corresponding historical data, build an error test model based on the difference between the air bag pressure reference data and the weight distribution data, and determine the weight assignment of the seat sensor data in each time period based on the model output results. After performing a weighted average calculation, calculate the comprehensive error index of the seat sensor data, which includes: The air bag cumulative pressure deviation index is generated according to the deviation between the real-time air bag pressure reference data and the historical air bag pressure reference data. The method for obtaining the air bag cumulative pressure deviation index is as follows: obtain the real-time air bag pressure data at time t and with historical reference pressure Compare and calculate the pressure deviation value , the expression is: ; The mean of the pressure deviation values and variance Converted to normal distribution, the expression is: ; is the prior distribution; based on the prior distribution and real-time air bag pressure data Construct the likelihood function, the expression is: ; is the variance of the measurement error. According to Bayes’ theorem, the updated posterior distribution is It is calculated based on the prior distribution and likelihood function, and the expression is: ;in, is a normalization constant; whenever new real-time pressure data is obtained , according to the deviation of the data , the posterior distribution of the air bag cumulative pressure deviation is adjusted by the Bayesian update formula, where the updated mean for: ; Updated variance for: ; For the data at t time points , the air bag cumulative pressure deviation index is calculated by continuously updating the posterior distribution; The weight distribution abnormality index is generated according to the deviation between the real-time weight distribution data and the historical weight distribution data. The method for obtaining the weight distribution abnormality index is as follows: the real-time weight distribution data is obtained from the seat sensor, indicating that the weight distribution state of the user at the current moment is marked as , is an n×1 vector, which indicates the distribution of weight in different areas of the seat. The weight distribution data under normal operation is extracted from the historical records, and the reference state under the usage scenario is marked as , is an n×m matrix, where n is the dimension of weight distribution and m is the number of samples of historical data. They are standardized respectively, and the covariance matrix C is calculated for the standardized historical data, which is expressed as: ; In the formula, is the standardized historical data, T is the matrix transpose, and the covariance matrix C is decomposed to obtain the eigenvalue and the corresponding eigenvector , these eigenvectors define the new principal component directions: ; Select the first k largest principal components according to the eigenvalue size, and the principal component directions form a matrix , which is an n×k matrix, representing the first k principal components; projecting the standardized historical data into the principal component space , the expression is: ; Project the standardized real-time weight distribution data into the same principal component space , ; For the standardized real-time data, the real-time data projection is calculated Projection with historical data The distance between them is used to calculate the abnormal weight distribution index, and the expression is: ; Where LK is the abnormal weight distribution index, is the mean of historical data in the principal component space, is the covariance matrix, which represents the distribution of historical data in the principal component space; The air bag cumulative pressure deviation index and the weight distribution abnormality index are normalized, and the weight assignment of the seat sensor data in each time period is calculated by using the normalized air bag cumulative pressure deviation index and the weight distribution abnormality index, and the comprehensive error index of the seat sensor data is calculated after performing weighted average calculation; S4: Compare the obtained comprehensive error index with a gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold. If the comprehensive error index is less than the first standard threshold, the sensor is in a normal state and does not need to be adjusted. S5: If the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the degree of abnormality of the sensor is low. At this time, a warning signal is generated, and the massage mode and intensity are dynamically adjusted; if the comprehensive error index is greater than the second standard threshold, the degree of abnormality of the sensor is high. At this time, a fault signal is generated, and the massage function is stopped immediately.

2. The method for adjusting and controlling the massage function of a car seat according to claim 1, characterized in that: In S4, the obtained comprehensive error index is compared with a gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold, specifically: Comparing the acquired comprehensive error index of the seat sensor data with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the comprehensive error index of the seat sensor data with the first standard threshold and the second standard threshold respectively; If the comprehensive error index of the seat sensor data is greater than the second standard threshold, it means that the error of the seat sensor data is high and the abnormality is high, and the sensor is classified as abnormal and needs further monitoring; If the comprehensive error index of the seat sensor data is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the error of the seat sensor data is normal and the abnormality is low, the sensor is classified as abnormal and the sensor is adjusted; If the comprehensive error index of the seat sensor data is less than the first standard threshold, it means that the error of the seat sensor data is low, and the sensor is classified as an abnormal state and does not need to be adjusted.

3. The method for adjusting and controlling the massage function of a car seat according to claim 1, characterized in that: In S5, if the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the sensor abnormality is low, and an early warning signal is generated, and the massage mode and intensity are dynamically adjusted, specifically: The first standard threshold is marked as , the second standard threshold is marked as According to the size of the comprehensive error index, when the comprehensive error index of the seat sensor data is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the system dynamically adjusts the massage mode and intensity, and defines the adjustment coefficient as γ to adjust the massage mode and intensity: Adjust the massage mode parameters , the expression is: ; is the massage mode parameter after adjustment, is the default massage mode parameter, γ is an adjustment coefficient that controls the adjustment range, is the normalized error index; Adjust massage intensity parameters , the expression is: ; In the formula, is the adjusted massage intensity, It is the default massage intensity.

4. A control system for a car seat massage function, used to implement a control method for a car seat massage function as claimed in any one of claims 1 to 3, characterized in that: It includes data acquisition module, historical data extraction module, error calculation module, comparison module and adjustment module; A data acquisition module; acquiring real-time pressure sensor data and real-time seat occupancy detection data within a certain time period from a seat sensor, wherein the real-time pressure sensor data is real-time air bag pressure data, and the real-time seat occupancy detection data is real-time weight distribution data; Historical data extraction module: Based on the historical data of the car seat massage system, the historical air bag pressure reference data and historical weight distribution data of the seat sensor under normal operating conditions are extracted respectively; Error calculation module: compares and analyzes real-time data with corresponding historical data, builds an error test model based on the difference between air bag pressure reference data and weight distribution data, and determines the weight assignment of seat sensor data in each time period based on the model output results, and calculates the comprehensive error index of seat sensor data after performing weighted average calculation; Comparison module: compares the obtained comprehensive error index with the gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold. If the comprehensive error index is less than the first standard threshold, the sensor is in a normal state and does not need to be adjusted. Adjustment module: if the comprehensive error index is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the sensor is abnormal to a low degree, and an early warning signal is generated at this time, and the massage mode and intensity are dynamically adjusted; If the comprehensive error index is greater than the second standard threshold, the sensor is highly abnormal, and a fault signal is generated, and the massage function is immediately stopped.

Images