Adjusting method and system for vehicle seat

Abstract

The invention discloses a method and system for adjusting a vehicle seat, and the method comprises the steps: determining at least one first pressure parameter and a first weight parameter corresponding to each first pressure parameter under the condition of determining that a user exists in the vehicle seat, and enabling the first pressure parameters to be the pressure parameters of the user on the vehicle seat; determining at least one first inflation parameter according to the first pressure parameter, the first weight parameter and a neural network model; and according to the first inflation parameters, an air bag which is arranged in the vehicle seat and corresponds to the first inflation parameters is adjusted, so that adjustment of the vehicle seat is completed, and the adjusting operation comprises one of inflation operation, deflation operation and non-operation. Thus, the vehicle seat can be correspondingly adjusted based on the pressure of the user on the vehicle seat, so that the adjusted seat is more fit with the human body and can better meet the use requirement of the user on the vehicle seat, manual adjustment by the user is not needed, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle seat adjustment, and particularly to a method and system for adjusting a vehicle seat. Background Art

[0002] With the development of automotive technology, more and more manufacturers have defined more scenario functions in the seat cabin. For example, enabling the vehicle seat to be adjusted based on user needs to make the seat fit the human body better, so as to improve the user experience.

[0003] In the prior art, the vehicle seat provides a comfort mode. When the user wants to adjust the seat to make it more suitable for their own needs, by triggering a one-key start button, the vehicle will control the seat to complete the adjustment of reclining the backrest and raising the leg rest, so that the user can lie more comfortably on the seat. In this way, since the backrest lies flat, the restraint function of the seat belt on the human body will fail, which is very unsafe to use during driving, and there is only one type of seat adjustment, which is too single to meet the different needs of users for seat adjustment. In addition, the existing vehicle seats also provide some fixed-mode back and waist massage modes. When the user wants to use them, by controlling the button to enable the vehicle seat to turn on the massage mode for massage. In this way, the types of seat adjustment are limited and cannot meet the needs of users with different body types and sitting postures for seat adjustment.

[0004] Therefore, the seat adjustment method provided by the prior art has the problem that the types of seat adjustment are limited and cannot meet the seat adjustment needs of different users. Summary of the Invention

[0005] The purpose of the present application is to solve the problem in the prior art that the types of seat adjustment are limited and cannot meet the seat adjustment needs of different users.

[0006] In a first aspect, an implementation manner of the present application provides a method for adjusting a vehicle seat. The method includes: when it is determined that there is a user on the vehicle seat, determining at least one first pressure parameter and a first weight parameter corresponding to each first pressure parameter, where the first pressure parameter is a pressure parameter of the user on the vehicle seat; determining at least one first inflation parameter according to the first pressure parameter and the first weight parameter; and performing an adjustment operation on the airbag corresponding to the first inflation parameter provided in the vehicle seat according to each first inflation parameter to complete the adjustment of the vehicle seat, and the adjustment operation includes one of an inflation operation, a deflation operation, and no operation.

[0007] With the above technical solution, when it is determined that there is a user on the vehicle seat, at least one pressure parameter of the user on the vehicle seat and the corresponding first weight parameter are determined. At least one first inflation parameter is obtained according to the first pressure parameter and the first weight parameter. Adjustment operations such as inflation operation, deflation operation, and no operation are performed on the airbags corresponding to the first inflation parameters arranged in the vehicle seat according to the first inflation parameter, so as to complete the adjustment of the vehicle seat. In this way, the vehicle seat can be adjusted correspondingly based on the pressure exerted by the user on the vehicle seat, so that the adjusted seat fits the human body better and can better meet the user's needs for using the vehicle seat. Moreover, the user does not need to manually adjust it, and automatic adjustment can still be achieved according to the pressure of the user on the vehicle seat during driving, improving the user experience.

[0008] According to another specific embodiment of the present application, the method for adjusting a vehicle seat disclosed in the embodiment of the present application further includes: determining a first mean square error according to at least one first pressure parameter; determining at least one second pressure parameter when it is determined that the adjustment of the vehicle seat is completed; determining a second mean square error according to at least one second pressure parameter; performing corresponding processing according to the first mean square error and the second mean square error when it is determined that the second mean square error does not converge to zero; ending the adjustment of the vehicle seat when it is determined that the second mean square error converges to zero.

[0009] In the implementation manner of the present application, after it is determined that the adjustment of the vehicle seat is completed, a second pressure parameter and a second mean square error are determined. When the second mean square error does not converge to zero, corresponding processing is performed according to the first mean square error of the first pressure parameter and the second mean square error of the second pressure parameter. When it is determined that the second mean square error converges to zero, the adjustment of the vehicle seat is ended. In this way, multiple adjustments of the vehicle seat can be realized, making the vehicle seat fit the human body better and improving the user's seat usage experience.

[0010] According to another specific embodiment of the present application, for the method for adjusting a vehicle seat disclosed in the embodiment of the present application, performing corresponding processing according to the first mean square error and the second mean square error includes: when it is determined that the first mean square error is less than the second mean square error, adjusting each first weight parameter to obtain a second weight parameter, determining at least one second inflation parameter according to the second pressure parameter, the second weight parameter, and a neural network model, and performing adjustment operations on the airbags corresponding to the second inflation parameters arranged in the vehicle seat according to each second inflation parameter, so as to complete the adjustment of the vehicle seat; when it is determined that the first mean square error is greater than or equal to the second mean square error, determining at least one third inflation parameter according to the second pressure parameter, the first weight parameter, and a neural network model, and performing adjustment operations on the airbags corresponding to the third inflation parameters arranged in the vehicle seat according to the third inflation parameter, so as to complete the adjustment of the vehicle seat.

[0011] By adopting the above technical solution, according to the magnitude relationship between the first mean square error and the second mean square error, the first weight parameter is adjusted so that the inflation parameter is calculated based on the latest weight parameter, making the obtained inflation parameter more accurate. Moreover, the second adjustment of the vehicle seat based on the inflation parameter is more precise and can better meet the user's needs.

[0012] According to another specific embodiment of the present application, for the adjustment method of the vehicle seat disclosed in the embodiment of the present application, adjusting each first weight parameter to obtain a second weight parameter includes: determining a corresponding first average pressure parameter according to at least one first pressure parameter; determining a first squared value of the difference between the first average pressure parameter and the first pressure parameter according to the first pressure parameter and the first average pressure parameter; when the first squared value is greater than a preset first threshold, adjusting the weight parameter related to the first pressure parameter in the first weight parameter to obtain a second weight parameter; when the first squared value is less than or equal to the preset first threshold, not adjusting the weight parameter related to the first pressure parameter in the first weight parameter and taking the first weight parameter as the second weight parameter.

[0013] By adopting the above technical solution, determining whether to adjust the weight parameter based on the squared value of the difference between the pressure parameter and the average pressure parameter and the magnitude of the preset threshold makes the inflation parameter calculated by inputting the finally obtained weight parameter and the latest pressure parameter into the neural network model better meet the user's needs, and makes the finally adjusted vehicle seat better meet the user's needs.

[0014] According to another specific embodiment of the present application, for the adjustment method of the vehicle seat disclosed in the embodiment of the present application, adjusting the weight parameter related to the first pressure parameter in the first weight parameter includes: when the first average pressure parameter is greater than the first pressure parameter, determining a first adjustment parameter according to the first squared value to increase the weight parameter related to the first pressure parameter in the first weight parameter according to the first adjustment parameter to obtain a second weight parameter; when the first average pressure parameter is less than the first pressure parameter, determining a second adjustment parameter according to the first squared value to decrease the weight parameter related to the first pressure parameter in the first weight parameter according to the second adjustment parameter to obtain a second weight parameter.

[0015] By adopting the above technical solution, determining to increase or decrease the weight parameter based on the magnitude of the pressure parameter and the average pressure parameter makes the inflation parameter calculated by inputting the finally adjusted weight parameter and the latest pressure parameter into the neural network model more accurate, and makes the finally adjusted vehicle seat better meet the user's needs.

[0016] According to another specific embodiment of the present application, the adjustment method of the vehicle seat disclosed in the embodiment of the present application determines at least one first inflation parameter according to the first pressure parameter, the first weight parameter and the neural network model, including obtaining the first inflation parameter in the following manner:

[0017]

[0018] Wherein, b ij is the first inflation parameter, 1≤i≤n, 1≤j≤n, b ij ∈[0, 1], n*n corresponds to the number of airbags, and σ is a preset activation function, a km is the first pressure parameter, 1≤k≤i, 1≤m≤i, i*i corresponds to the number of the first pressure parameters, x km is the first weight parameter, 1≤k≤i, 1≤m≤i, i*i corresponds to the number of the first weight parameters, |W| = 1.

[0019] By adopting the above technical solution, the first inflation parameter is obtained by using the calculation formula of the preset neural network model, so that the obtained inflation parameter is more accurate. And based on the neural network model for vehicle seat adjustment, the parameter data of the neural network model can be updated in real time, making the neural network model more accurate.

[0020] According to another specific embodiment of the present application, the adjustment method of the vehicle seat disclosed in the embodiment of the present application adjusts the airbag corresponding to the first inflation parameter set in the vehicle seat according to each first inflation parameter, including: if the first inflation parameter is greater than or equal to the first inflation threshold and less than or equal to the second inflation threshold, inflate the airbag corresponding to the first inflation parameter set in the vehicle seat according to the first inflation parameter; if the first inflation parameter is greater than the second inflation threshold and less than or equal to the third inflation threshold, do not operate on the airbag corresponding to the first inflation parameter set in the vehicle seat; if the first inflation parameter is greater than the third inflation threshold and less than or equal to the fourth inflation threshold, deflate the airbag corresponding to the first inflation parameter set in the vehicle seat according to the first inflation parameter.

[0021] By adopting the above technical solution, it is determined whether to inflate, deflate or not operate on the corresponding airbag according to the size relationship between the inflation parameter and the inflation threshold. In this way, the adjustment methods for different airbags are different, making the finally adjusted vehicle seat fit the human body better and making the user more satisfied.

[0022] According to another specific embodiment of the present application, in the adjustment method of the vehicle seat disclosed in the embodiment of the present application, the first pressure parameter is obtained by correspondingly processing the voltage value or current value collected by at least one pressure sensor arranged in the vehicle seat.

[0023] With the above technical solution, a pressure sensor is used to collect a pressure value or a current value, and the pressure value or the current value is correspondingly processed to obtain a pressure parameter. In this way, using a pressure sensor can reduce the bandwidth requirement for determining the pressure parameter.

[0024] According to another specific embodiment of the present application, in the adjustment method of the vehicle seat disclosed in the embodiment of the present application, the first pressure parameter is obtained in the following manner: if the pressure sensors are connected in series, determine the pressure value of each pressure sensor and the total pressure value, and obtain the first pressure parameter corresponding to each pressure sensor according to the ratio of the voltage value of each pressure sensor to the total voltage value; if the pressure sensors are connected in parallel, determine the current value of each pressure sensor, determine the pressure value of each pressure sensor and the total pressure value according to the current value of each pressure sensor, and obtain the first pressure parameter corresponding to each pressure sensor according to the ratio of the pressure value of each pressure sensor to the total pressure value.

[0025] With the above technical solution, the pressure sensors are arranged in series or in parallel, and the ratio of the obtained voltage value to the total voltage value is used as the first pressure parameter, or the voltage value is calculated based on the obtained current value, and the ratio of the voltage value to the total voltage value is used as the first pressure parameter. In this way, the proportion of the gravity distribution of the human body on each pressure sensor can be obtained simply and quickly, and then the inflation amount of the airbag at each part can be adjusted, making the seat adjustment more precise and accurate.

[0026] In a second aspect, an adjustment system for a vehicle seat provided by an embodiment of the present application includes a sensor and a controller. The sensor is used to collect at least one pressure value or at least one current value and send the pressure value or the current value to the controller. The controller is used to, when it is determined that there is a user on the vehicle seat, determine the corresponding first pressure parameter according to the pressure value or the current value, determine the first weight parameter corresponding to each first pressure parameter, determine at least one first inflation parameter according to the first pressure parameter, the first weight parameter and a neural network model, and perform an adjustment operation on the airbag corresponding to each first inflation parameter arranged in the vehicle seat according to each first inflation parameter to complete the adjustment of the vehicle seat. The adjustment operation includes one of an inflation operation, a deflation operation, and no operation. The first pressure parameter is the pressure parameter of the user on the vehicle seat.

[0027] The adjustment system of the vehicle seat provided by this application includes a module for executing the adjustment method of the vehicle seat provided in the above first aspect, and thus can also achieve the beneficial effects (or advantages) of the adjustment method of the vehicle seat provided in the first aspect.

[0028] In a third aspect, an embodiment of this application provides a computer-readable storage medium. Computer-executable instructions are stored in the computer-readable storage medium. When the computer-executable instructions are executed by an electronic device, they are used to implement the adjustment method of the vehicle seat provided in the implementation manner of the above first aspect.

[0029] It can be understood that for the beneficial effects of the above second aspect to the third aspect, reference can also be made to the relevant descriptions in the above first aspect, which will not be elaborated here.

[0030] The adjustment method of the vehicle seat provided by the implementation manner of this application determines at least one pressure parameter of the vehicle seat by the user and the corresponding first weight parameter, obtains at least one first inflation parameter according to the first pressure parameter, the first weight parameter and the neural network model, and performs adjustment operations such as inflation operation, deflation operation and no operation on the airbags corresponding to the respective first inflation parameters arranged in the vehicle seat according to the first inflation parameter, so as to complete the adjustment of the vehicle seat. In this way, the vehicle seat can be adjusted correspondingly based on the pressure applied by the user to the vehicle seat, so that the adjusted seat fits the human body better, can better meet the user's usage requirements for the vehicle seat, and moreover, there is no need for the user to manually adjust, and automatic adjustment can still be achieved according to the pressure of the user on the vehicle seat during driving, improving the user experience.

[0031] Further, after the first adjustment is completed, the second pressure parameter will be collected again, the first mean square deviation of the first pressure parameter and the second mean square deviation of the second pressure parameter will be calculated, and then subsequent secondary adjustments will be performed according to the magnitude relationship between the first pressure mean square deviation and the second pressure mean square deviation until the pressure mean square deviation corresponding to the latest collected pressure parameter converges to zero, and then the adjustment is considered appropriate. In this way, multiple adjustments can be made for the user, and for different users, the inflation parameters obtained by the seat adjustment are different, making the seat adjustment fit the user better, the user feels more comfortable using the seat, and the user experience is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic flowchart of the adjustment method of the vehicle seat provided by the implementation manner of this application;

[0033] Figure 2 It is a schematic distribution diagram of the gravity sensors provided by the implementation manner of this application;

[0034] Figure 3 It is a schematic structural diagram of the gravity sensors provided by the implementation manner of this application;

[0035] Figure 4 Schematic flowchart of another method for adjusting a vehicle seat provided by an implementation manner of the present application;

[0036] Figure 5 Schematic flowchart of another method for adjusting a vehicle seat provided by an implementation manner of the present application;

[0037] Figure 6 Schematic structural diagram of a vehicle seat adjustment system provided by an implementation manner of the present application;

[0038] Figure 7 Schematic structural diagram of another vehicle seat adjustment system provided by an implementation manner of the present application. Specific implementation manners

[0039] The following specific embodiments illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Although the description of the present application will be introduced in conjunction with preferred embodiments, this does not mean that the features of this invention are limited to this implementation manner. On the contrary, the purpose of introducing the invention in conjunction with the implementation manner is to cover other alternatives or modifications that may be extended based on the claims of the present application. In order to provide a deep understanding of the present application, many specific details will be included in the following description. The present application can also be implemented without these details. In addition, in order to avoid confusing or obscuring the key points of the present application, some specific details will be omitted in the description. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0040] Terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0041] The technical solutions of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts fall within the scope of protection of the present application.

[0042] As described above, the method for adjusting a seat provided by the prior art has the problem that the types of seat adjustment are limited and cannot meet the seat adjustment needs of different users.

[0043] With the popularization of, for example, family cars and the iteration of products, more and more manufacturers have defined new scenario functions in the seat, among which there is the function of the car seat fitting the human body to meet the comfort requirements of users during vehicle use, especially during long-distance driving.

[0044] For example, many vehicle brands have added comfort features such as zero-gravity seats and functions such as back massages for seats. However, these functions all have limitations. Take the zero-gravity seat as an example. The zero-gravity seat is a comfort cockpit scenario. The specific way to implement its functions is that after one-key start is triggered, the seat cushion rises, the backrest reclines, and the leg rest lifts. The problem is that it cannot be applied to the driver's seat and can only be used in non-driver areas such as the passenger seat and the rear row. And during driving, when the backrest reclines, the restraint and protection functions of the seat belt on the human body will fail, lacking in safety and being relatively unsafe to use during driving. Also, its comfort function cannot be dynamically adjusted according to the human body posture. Therefore, a new seat adjustment method that can follow the human body posture to provide sufficient support for the human body is needed.

[0045] For functions such as back / waist massages for seats, only some fixed-mode back / waist massages are provided. Since such comfort functions of massages have only a fixed inflation volume, the stroke of functions such as massages is fixed and cannot provide personalized human comfort support for passengers of different body types and sitting postures.

[0046] Based on this, a seat adjustment method for a vehicle seat that can automatically adjust the seat surface according to the driver's body posture and can improve the user's physical comfort under the premise of ensuring driving safety is emerging.

[0047] The implementation method of the present application provides an adjustment method for a vehicle seat, which is executed by a vehicle or a cloud server. When it is determined that there is a user on the vehicle seat, a first pressure parameter of the user on the vehicle seat is determined, a first inflation parameter is obtained based on the first pressure parameter, and corresponding adjustment operations are performed on the airbags provided in the vehicle seat according to the first inflation parameter, so as to perform inflation operations, deflation operations, and no operations on the airbags, etc., to complete the adjustment of the vehicle seat, making the current seat posture more in line with the user's needs and enabling the user to experience the seat more comfortably.

[0048] The vehicle seat adjustment method provided by the implementation method of the present application, taking the vehicle as an example, see Figure 1 , specifically includes the following steps.

[0049] S110, when it is determined that there is a user on the vehicle seat, determine at least one first pressure parameter and the first weight parameter corresponding to each first pressure parameter, where the first pressure parameter is the pressure parameter of the user on the vehicle seat.

[0050] In an implementation manner of the present application, the first pressure parameter is obtained by corresponding processing based on the voltage value or current value collected by at least one gravity sensor provided in the vehicle seat. And the number of first pressure parameters is the same as the number of gravity sensors. The number of first weight parameters is the same as the number of first pressure parameters.

[0051] Exemplarily, such as Figure 2 shown, at least one microgravity sensor (as an example of a gravity sensor) for collecting human postures is arranged at the seat cushion and / or the backrest position. For example, a total of 16 microgravity sensors are arranged in different areas of the seat cushion and / or the backrest. When the microgravity sensors detect a pressure change, it is considered that there is a user on the vehicle seat, and then the first pressure parameter is collected.

[0052] Of course, in another implementation manner of the present application, it may also be that an in-vehicle camera monitors that a passenger (i.e., a user) is sitting on the seat, and then triggers the microgravity sensors to collect the first pressure parameter. Of course, other methods can also be used to monitor whether there is a user on the vehicle seat. The implementation manners of the present application are only for illustrative purposes.

[0053] Furthermore, although the pressure distribution test of the prior art can be applied to implement this function, the amount of data in the pressure distribution cloud map is too large, and the bandwidth of the in-vehicle CANFD bus cannot meet the bandwidth requirements of this amount of data, which will cause time delays in the calculation of the micro control unit (MCU) and communication time delays, making the adaptive function respond slowly and unable to fit the human body in real time. Therefore, in the implementation manner of the present application, an algorithm for data analysis and processing is redesigned to implement the recognition of the human sitting posture of the adaptive seat.

[0054] In one implementation manner of the present application, the 16 microgravity sensors can be connected in series or in parallel.

[0055] Among them, if the gravity sensors are connected in series, the voltage values of the gravity sensors are determined, and the first pressure parameter corresponding to each gravity sensor is obtained according to the ratio of the voltage value of each gravity sensor to the total voltage value.

[0056] Exemplarily, if connected in series, when the microgravity sensor is pressed, its resistance value will change. By detecting the partial pressure value (i.e., voltage value) of each microgravity sensor, the pressure on each microgravity sensor is calculated, and the resistance value of the electronic control unit (ECU) at the end of the sensor is made much smaller than the resistance values of each microgravity sensor, so that the ratio of the partial pressure value of each microgravity sensor to the total pressure value can directly represent the proportion of the pressure-bearing area of each microgravity sensor in the human body gravity.

[0057] That is, the ratio of the pressure value collected by the microgravity sensor to the total voltage value of all microgravity sensors is used as the ratio of the gravity in the area of the microgravity sensor in the human body gravity (i.e., the first pressure parameter).

[0058] Further, if the pressure sensors are connected in parallel, determine the current values of the pressure sensors, determine the pressure values and the total pressure value of the pressure sensors according to the current values of the pressure sensors, obtain the first pressure parameter corresponding to each pressure sensor according to the ratio of the pressure value of each pressure sensor to the total pressure value, and then calculate the overall sitting posture of the human body according to the first pressure parameter.

[0059] Exemplarily, if data is collected in parallel, calculate the voltage values of the microgravity sensors according to the shunt values (i.e., current values) of the currents of the microgravity sensors and the resistance values of the microgravity sensors, and then calculate the ratio of the voltage values of the microgravity sensors to the total voltage value as the gravity ratio (i.e., the first pressure parameter) of the human body gravity in the area of the microgravity sensor, and then calculate the overall sitting posture of the human body according to the first pressure parameter.

[0060] In an implementation manner of the present application, as Figure 3 shown, the microgravity sensor is intended to use the FT-4x00 sensor of Qrovo, which is composed of a layer of surface structure connected to a layer of rubber sandwich, a piezoresistor (FT-4x00) and a microprocessor base (PCB). The rubber sandwich is connected to the surface structure under the seat cover by hot melt adhesive to absorb manufacturing tolerances. The resistance value of the piezoresistor changes under pressure. After the microprocessor collects its partial voltage or current, it sends the data to the seat controller. The seat controller performs operations according to the obtained data to obtain the first inflation parameter and sends an inflation and deflation instruction to the airbag.

[0061] Among them, the seat controller can be a massage controller for inflating the airbag.

[0062] S120. Determine at least one first inflation parameter according to the first pressure parameter, the first weight parameter, and the neural network model.

[0063] In the implementation manner of the present application, input the matrix formed by the first pressure parameter and the matrix formed by the first weight parameter into a convolutional neural network model (as an example of the neural network model) to obtain the matrix corresponding to the first inflation parameter. Among them, the number of the first inflation parameters is the same as the number of airbags provided in the vehicle seat.

[0064] That is, in the present application, the number of the first pressure parameters and the number of the first weight parameters specified in the neural network model also specify the number of the output first inflation parameters.

[0065] Exemplarily, to determine at least one first inflation parameter according to the first pressure parameter, the first weight parameter, and the neural network model, the first inflation parameter can be obtained in the following manner:

[0066]

[0067] Among them, b ij is the first inflation parameter, 1 ≤ i ≤ n, 1 ≤ j ≤ n, b ij ∈ [0, 1], and n * n corresponds to the number of airbags.

[0068] σ is a preset activation function.

[0069] a km is the first pressure parameter, 1 ≤ k ≤ i, 1 ≤ m ≤ i, and i * i corresponds to the number of the first pressure parameters (i.e., the number of gravity sensors).

[0070] x km is the first weight parameter, 1 ≤ k ≤ i, 1 ≤ m ≤ i, i * i corresponds to the number of the first weight parameters, and |W| = 1.

[0071] Exemplarily, taking the example of obtaining 16 first pressure parameters according to 16 microgravity sensors, the matrix obtained according to the 16 first pressure parameters is as follows:

[0072]

[0073] Among them, a 11 , a 12 , a 13 , a 14 , a 21 , a 22 , a 23 , a 24 , a 31 , a 32 , a 33 , a 34 , a 41 , a 42 , a 42 , a 43 , a 44 are the first pressure parameters.

[0074] Let the weight function be where |W| = 1. In this way, the normalization processing of the final first inflation parameter can be realized based on the weight function. Among them, x 11 , x 12 , x 13 , x 14 , x 21 , x 22 , x 23 , x 24 , x 31 , x 32, x 33 , x 34 , x 41 , x 42 , x 43 , x 44 is the first weight parameter.

[0075] In the implementation manner of the present application, the weight function is recursively obtained according to the real vehicle calibration, which is a function pre-based on the real vehicle calibration and preset in the vehicle controller.

[0076] Furthermore, the first layer of recursive transmission is performed in the manner of a single-layer convolutional neural network model, and the matrix modulus value of the first pressure parameter is divided to obtain the first inflation parameter.

[0077] For example, according to the formula to obtain a 3*3 matrix. Wherein, σ is the activation function, σ = [c1 c2 c3 c4 c5 c6], which is a 1*6 matrix, |σ| = 1, and b1, b2, b3, b4, b5, b6, b7, b8, b9 are the first inflation parameters.

[0078] In this way, the calculation result H1 of the single-layer convolutional neural network model transmission is obtained, which is a 3*3 matrix, and since it has been normalized, b1~b9 are all values with a value range belonging to [0, 1].

[0079] S130, adjust the airbag corresponding to the first inflation parameter set in the vehicle seat according to each first inflation parameter to complete the adjustment of the vehicle seat. The adjustment operation includes one of inflation operation, deflation operation, and no operation.

[0080] In an implementation manner of the present application, the corresponding adjustment gear is first determined according to the calculated first inflation parameter, and then the airbag set in the vehicle seat is inflated and deflated correspondingly according to the adjustment gear.

[0081] Among them, if the first inflation parameter is in [0 - 0.2], it is determined that the adjustment gear of the airbag corresponding to the first inflation parameter set in the vehicle seat is the first adjustment gear.

[0082] If the first inflation parameter is in [0.2 - 0.4], it is determined that the adjustment gear of the airbag corresponding to the first inflation parameter set in the vehicle seat is the second adjustment gear.

[0083] In this application, if the adjustment gear is the first adjustment gear and the second adjustment gear, the corresponding airbag is inflated. Exemplarily, if the calculated result of the first inflation parameter is any value in [0 - 0.2] or [0.2 - 0.4], it indicates that the supporting force is weak at this time, so inflation operation needs to be appropriately performed.

[0084] That is, if the first inflation parameter is greater than or equal to 0 (as an example of the first inflation threshold) and less than or equal to 0.4 (as an example of the second inflation threshold), the airbag corresponding to the first inflation parameter set in the vehicle seat is inflated according to the first inflation parameter.

[0085] Further, if the first inflation parameter is in [0.4 - 0.6], it is determined that the adjustment gear of the airbag corresponding to the first inflation parameter set in the vehicle seat is the third adjustment gear.

[0086] In this application, if the adjustment gear is the third adjustment gear, no operation is performed on the corresponding airbag.

[0087] That is, if the first inflation parameter is greater than 0.4 and less than or equal to 0.6 (as an example of the third inflation threshold), no operation is performed on the airbag corresponding to the first inflation parameter set in the vehicle seat.

[0088] Exemplarily, if the calculated result of the first inflation parameter is any value in [0.4 - 0.6], it indicates that the support at this position is appropriate, so no inflation or deflation operation is required.

[0089] If the first inflation parameter is in [0.6 - 0.8], it is determined that the adjustment gear of the airbag corresponding to the first inflation parameter set in the vehicle seat is the fourth adjustment gear.

[0090] If the first inflation parameter is in [0.8 - 1], it is determined that the adjustment gear of the airbag corresponding to the first inflation parameter set in the vehicle seat is the fifth adjustment gear.

[0091] In this application, if the adjustment gear is the fourth adjustment gear and the fifth adjustment gear, the corresponding airbag is deflated.

[0092] Exemplarily, if the calculated result of the first inflation parameter is any value in [0.6 - 0.8] or [0.8 - 1.0], it indicates that the supporting force is too strong at this time, so deflation operation needs to be appropriately performed.

[0093] That is, if the first inflation parameter is greater than 0.6 and less than or equal to 1 (as an example of the fourth inflation threshold), the airbag corresponding to the first inflation parameter set in the vehicle seat is deflated according to the first inflation parameter.

[0094] It should be noted that the smaller the value, the larger the inflation volume required for inflation. The larger the value, the larger the deflation volume required for deflation. After calculating the inflation parameters of the airbags at multiple positions, the airbags are inflated, deflated, or no operation is performed according to the inflation parameters of each airbag. That is, when calculating based on a single-layer convolutional neural network, the position of the first inflation parameter in the matrix corresponds to the airbag.

[0095] In this application, the first inflation parameter is also the inflation volume corresponding to the airbag. Taking 9 first inflation parameters as an example, the values of the 9 first inflation parameters correspond to the inflation volumes of the airbags at 9 positions. These 9 values are also the corresponding values of the inflation volumes of the airbags. Only a 5-digit hexadecimal signal needs to be output to describe the inflation volume value of this airbag. If the current inflation volume of the airbag is greater than the calculated first inflation parameter, a deflation operation is required. If the current inflation volume is less than the calculated first inflation parameter, an inflation operation is required. If the current inflation volume is equal to the calculated first inflation parameter, no operation is required, and the current inflation volume can be maintained.

[0096] Furthermore, as Figure 4 shown, the method for adjusting a vehicle seat provided by the implementation manner of this application further includes the following steps.

[0097] S140, determine the first mean square error according to at least one first pressure parameter.

[0098] Exemplarily, the first mean square error is obtained according to the following formula:

[0099]

[0100] where is the average value obtained based on each first pressure parameter.

[0101] Of course, the first mean square error can also be calculated according to .

[0102] It should be noted that step S140 can be executed after step S110 and before step S120, or can also be executed after step S130.

[0103] S150, when it is determined that the vehicle seat has completed adjustment, determine at least one second pressure parameter.

[0104] Exemplarily, after the first inflation volume adjustment is completed, a microgravity sensor is used to collect body pressure data again (that is, the second pressure parameter), and its collection method is the same as the collection method of the first pressure parameter, which will not be elaborated here.

[0105] 16 second pressure parameters are collected and form a matrix as follows:

[0106]

[0107] Among them, a' 11 , a' 12 , a' 13 , a' 14 , a' 21 , a' 22 , a' 23 , a' 24 , a' 31 , a' 32 , a' 33 , a' 34 , a' 41 , a' 42 , a' 43 , a' 44 are the second pressure parameters collected.

[0108] S160. Determine the second mean square deviation according to at least one second pressure parameter.

[0109] Exemplarily, the second mean square deviation of the following formula.

[0110]

[0111] Among them, is the average value obtained based on each second pressure parameter.

[0112] Of course, the first mean square deviation can also be calculated according to calculate the first mean square deviation.

[0113] S170. In the case where it is determined that the second mean square deviation does not converge to zero, perform corresponding processing according to the first mean square deviation and the second mean square deviation.

[0114] Exemplarily, use the Cauchy convergence criterion (that is, the Cauchy limit existence criterion) and other methods to determine whether the second mean square deviation converges to zero. If it does not converge to zero, perform corresponding processing according to the first mean square deviation and the second mean square deviation.

[0115] In the implementation mode of the present application, performing corresponding processing according to the first mean square deviation and the second mean square deviation includes, in the case where it is determined that the first mean square deviation is less than the second mean square deviation, adjusting each first weight parameter to obtain a second weight parameter, determining at least one second inflation parameter according to the second pressure parameter, the second weight parameter, and the neural network model, and performing an adjustment operation on the airbag corresponding to the second inflation parameter provided in the vehicle seat according to each second inflation parameter to complete the adjustment of the vehicle seat.

[0116] Exemplarily, compare the magnitudes of S1 (that is, the first mean square deviation) and S2 (that is, the second mean square deviation). If S1 < S2, then for the first weight parameter x in the weight function w kmAdjustments are made to obtain a second weight parameter, and then a second weight function w1 is obtained to determine a new second inflation parameter according to the second weight parameter and the second pressure parameter, and then the corresponding airbag is adjusted according to the second inflation parameter.

[0117] In the implementation manner of this application, adjusting each first weight parameter to obtain a second weight parameter includes determining a corresponding first average pressure parameter according to at least one first pressure parameter, determining a first squared value of the difference between the first average pressure parameter and the first pressure parameter according to the first pressure parameter and the first average pressure parameter, and adjusting the weight parameter related to the first pressure parameter in the first weight parameter to obtain the second weight parameter when the first squared value is greater than a preset first threshold.

[0118] Exemplarily, after determining the first average pressure parameter the first squared value is determined according to the square of the difference between the first average pressure parameter and the first pressure parameter Taking the first threshold μ, if at this time, then select this a′ ij position, select the weight function x corresponding to a′ in the first weight function ij and adjust x ij as well as the weight parameters adjacent to x ij to obtain the second weight parameter x′ ij . ij .

[0119] For example, when the value is greater than the threshold, then adjust the weight parameters of the weight function adjacent to it to x′ 22 , x′ 23 , x′ 24 , x′ 32 , x′ 33 , x′ 34 , x′ 42 , x′ 43 , x′ 44 (as multiple examples of the second weight parameter), and obtain the weight function as

[0120]

[0121] In the implementation manner of this application, in the matrix calculation process, the weight parameters having a calculation process with the first pressure parameter are considered as the weight parameters related to the first pressure parameter.

[0122] In the implementation manner of the present application, adjusting the weight parameter related to the first pressure parameter in the first weight parameter includes, when the first average pressure parameter is greater than the first pressure parameter, determining a first adjustment parameter according to the first squared value, so as to increase the weight parameter related to the first pressure parameter in the first weight parameter according to the first adjustment parameter, and obtaining a second weight parameter.

[0123] Exemplarily, adjust its weight according to the positive and negative of, if it indicates that the force here is too small, then increase x ij and the values of its adjacent weight factors (that is, weight parameters). And, determine how much to increase according to the value of, for example, the corresponding first adjustment parameter can be determined according to the value of, the existing x ij plus the first adjustment parameter is used as the second adjustment parameter x' ij .

[0124] It should be noted that the corresponding relationship between the value of and the first adjustment parameter can be obtained through physical calibration, and the implementation manner of the present application forms the corresponding relationship between the value of and the first adjustment parameter into a table and stores it in the vehicle controller.

[0125] When the first average pressure parameter is less than the first pressure parameter, determine a second adjustment parameter according to the first squared value, so as to decrease the weight parameter related to the first pressure parameter in the first weight parameter according to the second adjustment parameter, and obtain a second weight parameter.

[0126] Exemplarily, if it indicates that the force here is too large, then decrease x ij and the values of its adjacent weight factors (that is, weight parameters). And, determine how much to decrease according to the value of, for example, the corresponding second adjustment parameter can be determined according to the value of, the existing x ij minus the second adjustment parameter is used as the second adjustment parameter x' ij .

[0127] It should be noted that the corresponding relationship between the value of and the first adjustment parameter can be obtained through physical calibration, and the implementation manner of the present application forms the corresponding relationship between the value of and the first adjustment parameter into a table and stores it in the vehicle controller.

[0128] In the present application, for as many pressure parameters as there are, the weight parameters need to be adjusted the same number of times. Therefore, a weight parameter may be involved in multiple adjustments, and the last adjustment shall prevail according to the adjustment order.

[0129] Further, when the first squared value is less than or equal to a preset first threshold, the weight parameter in the first weight parameter related to the first pressure parameter is not adjusted, and the first weight parameter is used as the second weight parameter.

[0130] Exemplarily, if at this time, it indicates that the value of the first weight parameter is appropriate. Therefore, it is not necessary to adjust the weight parameter related to the first pressure parameter, and the first weight parameter is directly used as the second weight parameter to form a new weight function matrix based on the second weight parameter:

[0131]

[0132] Among them, the size of the first threshold can be specifically set according to the actual situation.

[0133] Further, after obtaining the second weight parameter, the matrix formed by the second pressure parameter and the matrix formed by the second weight parameter are input into the single-layer convolutional neural network model, and the second inflation parameter is output. Then, according to the second inflation parameter, the airbag corresponding to each second inflation parameter set in the vehicle seat is adjusted to complete the secondary adjustment of the vehicle seat, and the pressure parameter is re-collected, and the mean square error is recalculated until the calculated mean square error converges to 0 to complete the adjustment. If it has not converged to 0, either the weight parameter is adjusted based on the foregoing method, and the new inflation parameter is calculated according to the newly collected pressure parameter and the new weight parameter, or the new inflation parameter is calculated according to the newly collected pressure parameter and the weight parameter calculated last time.

[0134] The process of adjusting the airbag using the second inflation parameter is the same as the process of adjusting the airbag using the first inflation parameter, and will not be elaborated here.

[0135] Further, when it is determined that the first mean square error is greater than or equal to the second mean square error, at least one third inflation parameter is determined according to the second pressure parameter, the first weight parameter and the neural network model, and the airbag corresponding to the third inflation parameter set in the vehicle seat is adjusted according to the third inflation parameter to complete the adjustment of the vehicle seat.

[0136] Exemplarily, if it is determined that the first mean square error is greater than or equal to the second mean square error, it indicates that the mean square error is gradually converging, indicating that the preset first weight parameter is appropriate. Therefore, the matrix generated by the collected second pressure parameter and the matrix generated by the first weight parameter are input into the single-layer convolutional neural network model to obtain the third inflation parameter, and the airbag corresponding to the third inflation parameter set in the vehicle seat is adjusted according to the third inflation parameter to complete the adjustment of the vehicle seat.

[0137] The process of adjusting the airbag using the third inflation parameter is the same as the process of adjusting the airbag using the first inflation parameter, and will not be elaborated here.

[0138] S180. When it is determined that the second mean square error converges to zero, the adjustment of the vehicle seat is ended.

[0139] Exemplarily, if it is determined that the second mean square error has converged to 0, this indicates that the airbag inflation volume is appropriate at this time. It is only necessary to maintain the existing inflation volume, and there is no need to adjust the vehicle seat anymore. Therefore, the adjustment of the vehicle seat is ended until the microgravity sensor collects the change in pressure again.

[0140] When it is determined that there is a user on the vehicle seat, at least one pressure parameter of the user on the vehicle seat and the corresponding first weight parameter are determined. At least one first inflation parameter is obtained according to the first pressure parameter, the first weight parameter and the neural network model. Adjustment operations such as inflation operation, deflation operation and no operation are performed on each airbag corresponding to each first inflation parameter arranged in the vehicle seat according to the first inflation parameter, so as to complete the adjustment of the vehicle seat. In this way, the vehicle seat can be adjusted correspondingly based on the pressure applied by the user to the vehicle seat, so that the adjusted seat fits the human body better and can better meet the user's needs for using the vehicle seat. Moreover, there is no need for the user to manually adjust, which improves the user experience.

[0141] Further, in an implementation manner of the present application, after the first adjustment is completed, the second pressure parameter will be collected again, the mean square error of the first pressure parameter and the second pressure parameter will be calculated, and then subsequent secondary adjustment, tertiary adjustment, etc. will be performed according to the magnitude relationship between the first pressure mean square error and the second pressure mean square error, until the pressure mean square error corresponding to the latest collected pressure parameter converges to zero, and then the adjustment is considered appropriate. In this way, multiple adjustments can be made for the user, and for different users, the inflation parameters obtained by the seat adjustment are different, so that the seat adjustment can fit the user better, the user is more comfortable using the seat, and the user experience is improved.

[0142] In another implementation manner of the present application, as Figure 5 shown, the method for adjusting the vehicle seat provided by the implementation manner of the present application further includes the following steps.

[0143] S210. The adaptive mode is started.

[0144] Exemplarily, after it is determined that the seat adaptive mode is started and it is determined that there is a user on the current vehicle seat, the collection of the first pressure parameter is started.

[0145] S220. The microgravity sensor detects the body pressure.

[0146] Exemplarily, a micro-gravity sensor is used to obtain the pressure of the human body on each micro-gravity sensor (i.e., the first pressure parameter).

[0147] S230, single-layer convolutional neural network model transfer.

[0148] Exemplarily, the first pressure parameter and a preset first weight parameter are input into a single-layer convolutional neural network model to obtain a first inflation parameter.

[0149] S240, the controller drives the air valve and air pump to perform inflation and deflation operations according to the first inflation parameter.

[0150] S250, the micro-gravity sensor detects the body pressure again to obtain a second pressure parameter.

[0151] S260, determine whether the mean square error (i.e., the second mean square error) corresponding to the second pressure parameter collected by the pressure sensor (i.e., the micro-gravity sensor) converges to 0. If so, execute step S270; if not, execute step S280.

[0152] S270, determine that the inflation and deflation are ended, and the airbag maintains the current inflation amount until the pressure value (i.e., the detection value) detected by the micro-gravity sensor changes again.

[0153] S280, determine whether the mean square error corresponding to the second pressure parameter collected by the pressure sensor decreases after the single-layer convolutional neural network transfers and adjusts the inflation amount of the airbag. If so, execute step S230; if not, execute step S290.

[0154] S290, adjust the weight function w, and execute step S230.

[0155] In the implementation manner of this application, after the adaptive mode is started, the micro-gravity sensor detects the body pressure to obtain the first pressure parameter, performs single-layer convolutional neural network model transfer to obtain the first inflation parameter, the controller drives the air valve and air pump to perform inflation and deflation operations according to the first inflation parameter, the micro-gravity sensor detects the body pressure again to obtain the second pressure parameter, and determines whether the second mean square error corresponding to the second pressure parameter converges to 0. If so, end the inflation and deflation, and the inflation amount of the airbag remains the current inflation amount until the micro-gravity sensor detects that the pressure value changes again and the seat adjustment is restarted. If not, determine whether the second mean square error of the second pressure parameter collected again by the micro-gravity sensor is less than the first mean square error of the first inflation parameter (i.e., whether it decreases) after the single-layer convolutional neural network model transfers and the controller adjusts the inflation amount of the airbag. If so, perform single-layer convolutional neural network model transfer again based on the second pressure parameter and the first weight parameter; if not, adjust the weight parameter in the weight function to obtain the second weight parameter, and perform single-layer convolutional neural network model transfer according to the second pressure parameter and the second weight parameter.

[0156] The adjustment method of the vehicle seat provided by the implementation mode of the present application is also a method for adjusting the seat based on solving the adaptive seat human sitting posture algorithm by a single-layer convolutional neural network. Through the pressure sensors at the seat cushion acquisition end, the human posture is calculated by a software algorithm to obtain a calculation result (i.e., the inflation parameter). According to the calculation result, the air valve under the cushion is driven to inflate the seat cushion airbag, so that the seat cushion fits the human body and optimizes the comfort. In this way, by arranging airbags in the seat cushion, when it is necessary to adjust the softness and hardness of the seat, the air valve inflates and deflates the airbag so that its softness and hardness can be adjusted. That is, by calculating the pressure of the human body in each area of the seat cushion, the human sitting posture information is extracted, and then according to the human sitting posture measured by the pressure sensor, appropriate inflation amounts are respectively filled into the airbags arranged in different areas of the seat cushion. The inflation amounts of the airbags in each area of the seat cushion change the contact surface to wrap the human body as the human posture changes, so that the softness and hardness of the seat cushion and the contact surface fit the human body, providing better support and improving comfort.

[0157] Furthermore, a neural network model is used to predict the inflation amount, which can detect the motion state during the human driving process, learn the most comfortable postures and sitting posture habits of the human body, and the calculated inflation parameters can be used for comfort optimization.

[0158] Furthermore, due to the limitation of the vehicle computer communication bandwidth, the pressure distribution cloud map is not applicable to this scenario, and since the controller applied to the seat belongs to the slave node of the CAN bus, the total data size transmitted is limited, and only the signal with the data volume processed and compressed can be used as the logical criterion for driving the airbag to work. Using the algorithm model provided by the present application (i.e., the single-layer convolutional neural network model), the body pressure data (i.e., the first pressure parameter) can be compressed, and after collecting the human body pressure data, it can be compressed and output a 5-bit hexadecimal signal to describe the human body pressure information (i.e., the first inflation parameter) and adjust the airbag inflation amount according to the corresponding sitting posture. Its data volume meets the communication bandwidth limitation of CANFD to ensure that the function can be implemented under the hardware conditions of the existing seat controller and the vehicle communication bandwidth.

[0159] Moreover, the controller will iterate with the change of the human body pressure, adjust the weight function transmitted by the convolutional neural network, and adjust to the state that fits the human body most as the human posture changes.

[0160] In the implementation mode of the present application, when the user sits on the seat, the pressure values at each position are detected by the pressure sensors, and after being transmitted by a single-layer convolutional neural network by the controller, the airbag inflation value is output for inflation and deflation operations. According to the inflation and deflation results, the software will calculate and iterate the weight function of the neural network until the root mean square value (i.e., the mean square error) of the pressure values detected by each sensor converges to 0. At this time, the support force of the human body surface is evenly pressured and the comfort is optimized. When the human posture changes, the software will still adjust the airbag inflation amount according to the body pressure change so that the seat cushion fits the human body surface again.

[0161] Furthermore, the vehicle seat adjustment method provided by the implementation manner of the present application can also be applied to a cloud server. The cloud server receives the voltage value or current value sent by the microgravity sensor set in the vehicle seat, calculates the first pressure parameter, determines the first inflation parameter according to the first pressure parameter, the first weight parameter, and the neural network model, and sends the first inflation parameter to the vehicle seat controller. The vehicle seat controller adjusts the airbag corresponding to the first inflation parameter set in the vehicle seat according to each first inflation parameter to complete the adjustment of the vehicle seat. The adjustment operation includes one of inflation operation, deflation operation, and no operation.

[0162] The implementation manner of the present application, as Figure 6 shown, also discloses a vehicle seat adjustment system, including a sensor and a controller.

[0163] The sensor is used to collect at least one pressure value or at least one current value, and send the pressure value or current value to the controller.

[0164] The controller is used to, when it is determined that there is a user in the vehicle seat, determine at least one corresponding first pressure parameter according to the pressure value or current value, determine the first weight parameter corresponding to each first pressure parameter, determine at least one first inflation parameter according to the first pressure parameter, the first weight parameter, and the neural network, determine the adjustment gear of each airbag corresponding to each first inflation parameter set in the vehicle seat according to each first inflation parameter, and perform an adjustment operation on the corresponding airbag according to the adjustment gear to complete the adjustment of the vehicle seat. The adjustment operation includes one of inflation operation, deflation operation, and no operation, where the first pressure parameter is the pressure parameter of the user on the vehicle seat.

[0165] In the implementation manner of the present application, the vehicle seat adjustment system is also the hardware device for executing the vehicle seat adjustment method. Among them, the sensor can be the aforementioned microgravity sensor. Of course, the sensor can also be other sensors for collecting pressure information. The controller can specifically be a micro control unit MCU for controlling the vehicle seat. Of course, the controller can also be other in-vehicle terminals, vehicle total controllers, etc.

[0166] Furthermore, as Figure 7As shown, the overall circuit of the control system is as shown in the figure. When the microcontroller unit (MCU) receives the in-vehicle signal, the MCU calculates the pressure parameter based on the voltage value or current value sent by the sensors, calculates the nine inflation parameters (i.e., values) representing the human body posture signs based on the pressure parameter, controls the opening and closing of the air valve and drives the air pump to work via the MCU. The inflation amount of each airbag is inflated in five gears according to the calculation results of b1 - b9, so as to make the seat cushion / backrest fit the human body position and surface and coincide with the human body to optimize the support effect.

[0167] In the implementation manner of this application, the microcontroller unit is connected to the DC - DC converter (DCDC), low - dropout linear regulator (LDO), controller area network (CAN), and air pump drive (PUMP Drive). Among them, the DC - DC converter (DCDC) and low - dropout linear regulator (LDO) are respectively connected to the power supply (VCC) and ground wire (GND), the controller area network (CAN) and air pump drive (PUMP Drive) are respectively connected to the ground wire (GND). The microcontroller unit communicates with the vehicle using the controller area network, obtains the calculated inflation parameters based on the DC - DC converter, and controls the air pump drive to inflate and deflate the airbag.

[0168] The embodiment of this application also provides a chip for operation instructions, and this chip is used to execute the technical solution of the vehicle seat adjustment method in the above - mentioned embodiment.

[0169] The embodiment of this application also provides a computer - readable storage medium, and computer instructions are stored in this computer - readable storage medium. When these computer instructions run on a computer, the computer is made to execute the technical solution of the vehicle seat adjustment method in the above - mentioned embodiment.

[0170] In some possible implementation manners, each aspect of the method provided in this application can also be implemented in the form of a program product, which includes program code. When the program product runs on a computer device, the program code is used to make the computer device execute the steps in the method according to various exemplary implementation manners of this application described above in this specification. For example, the computer device can execute the vehicle seat adjustment method recorded in the embodiment of this application.

[0171] The program product may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0172] The implementation manner of the present application further provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when the at least one processor executes the computer program, the technical solution of the adjustment method of the vehicle seat in the foregoing embodiments can be implemented.

[0173] Although the present application has been illustrated and described by referring to some preferred embodiments of the present application, those of ordinary skill in the art should understand that the above content is a further detailed description of the present application in combination with specific embodiments, and it cannot be determined that the specific implementation of the present application is only limited to these descriptions. Those skilled in the art can make various changes in form and details, including making several simple deductions or substitutions, without departing from the spirit and scope of the present application.

Claims

1. A method for adjusting a vehicle seat, characterized in that, The method includes: When it is determined that there is a user on the vehicle seat, determining at least one first pressure parameter and a first weight parameter corresponding to each of the first pressure parameters, where the first pressure parameter is the pressure parameter of the user on the vehicle seat; Determining at least one first inflation parameter according to the first pressure parameter, the first weight parameter and a neural network model; Performing an adjustment operation on an airbag corresponding to the first inflation parameter arranged in the vehicle seat according to each of the first inflation parameters to complete the adjustment of the vehicle seat, where the adjustment operation includes one of an inflation operation, a deflation operation and no operation.

2. The adjustment method of the vehicle seat according to claim 1, characterized in that, The method further includes: Determining a first mean square error according to the at least one first pressure parameter; When it is determined that the adjustment of the vehicle seat is completed, determining at least one second pressure parameter; Determining a second mean square error according to the at least one second pressure parameter; When it is determined that the second mean square error does not converge to zero, performing corresponding processing according to the first mean square error and the second mean square error; When it is determined that the second mean square error converges to zero, ending the adjustment of the vehicle seat.

3. The adjustment method of the vehicle seat according to claim 2, characterized in that, Performing corresponding processing according to the first mean square error and the second mean square error includes: When it is determined that the first mean square error is less than the second mean square error, adjusting the first weight parameter to obtain a second weight parameter, determining at least one second inflation parameter according to the second pressure parameter, the second weight parameter and the neural network model, and performing an adjustment operation on an airbag corresponding to the second inflation parameter arranged in the vehicle seat according to each of the second inflation parameters to complete the adjustment of the vehicle seat; When it is determined that the first mean square error is greater than or equal to the second mean square error, determining at least one third inflation parameter according to the second pressure parameter, the first weight parameter and the neural network model, and performing an adjustment operation on an airbag corresponding to the third inflation parameter arranged in the vehicle seat according to the third inflation parameter to complete the adjustment of the vehicle seat.

4. The adjustment method of the vehicle seat according to claim 3, characterized in that, Adjusting the first weight parameter to obtain a second weight parameter includes: Determining a corresponding first average pressure parameter according to the at least one first pressure parameter; Determining a first squared value of the difference between the first average pressure parameter and the first pressure parameter according to the first pressure parameter and the first average pressure parameter; When the first squared value is greater than a preset first threshold, adjusting the weight parameter related to the first pressure parameter in the first weight parameter to obtain the second weight parameter; When the first squared value is less than or equal to the preset first threshold, not adjusting the weight parameter related to the first pressure parameter in the first weight parameter, and using the first weight parameter as the second weight parameter.

5. The adjustment method of the vehicle seat according to claim 4, characterized in that, Adjusting the weight parameter related to the first pressure parameter in the first weight parameter includes: When the first average pressure parameter is greater than the first pressure parameter, a first adjustment parameter is determined according to the first squared value, so as to increase the weight parameter related to the first pressure parameter in the first weight parameter according to the first adjustment parameter to obtain the second weight parameter; When the first average pressure parameter is less than the first pressure parameter, a second adjustment parameter is determined according to the first squared value, so as to decrease the weight parameter related to the first pressure parameter in the first weight parameter according to the second adjustment parameter to obtain the second weight parameter.

6. The adjustment method of the vehicle seat according to any one of claims 1-5, characterized in that, At least one first inflation parameter is determined according to the first pressure parameter, the first weight parameter and a neural network model, including obtaining the first inflation parameter by the following method: Among them, b ij is the first inflation parameter, 1 ≤ i ≤ n, 1 ≤ j ≤ n, b ij ∈ [0, 1], n * n corresponds to the number of the airbags, and σ is a preset activation function. a km is the first pressure parameter, where 1 ≤ k ≤ i, 1 ≤ m ≤ i, and i * i corresponds to the number of the first pressure parameters x km is the first weight parameter, where 1 ≤ k ≤ i, 1 ≤ m ≤ i, and i * i corresponds to the number of the first weight parameters, and |W| = 1 7. The adjustment method of the vehicle seat according to any one of claims 1-5, characterized in that, Adjustment operations are performed on the airbags corresponding to the first inflation parameters arranged in the vehicle seat according to the first inflation parameters, including: If the first inflation parameter is greater than or equal to a first inflation threshold and less than or equal to a second inflation threshold, inflation operations are performed on the airbag corresponding to the first inflation parameter arranged in the vehicle seat according to the first inflation parameter; If the first inflation parameter is greater than the second inflation threshold and less than or equal to a third inflation threshold, no operation is performed on the airbag corresponding to the first inflation parameter arranged in the vehicle seat; If the first inflation parameter is greater than the third inflation threshold and less than or equal to a fourth inflation threshold, deflation operations are performed on the airbag corresponding to the first inflation parameter arranged in the vehicle seat according to the first inflation parameter.

8. The adjustment method of the vehicle seat according to any one of claims 1-5, characterized in that, The first pressure parameter is obtained by correspondingly processing at least one voltage value or current value collected by at least one pressure sensor arranged in the vehicle seat.

9. The adjustment method of the vehicle seat according to claim 8, characterized in that, The first pressure parameter is obtained by the following method: If the pressure sensors are connected in series, the voltage values and the total voltage value of the pressure sensors are determined, and the first pressure parameter corresponding to each pressure sensor is obtained according to the ratio of the voltage value of each pressure sensor to the total voltage value; If the pressure sensors are connected in parallel, the current values of the pressure sensors are determined, the pressure values and the total pressure value of the pressure sensors are determined according to the current values of the pressure sensors, and the first pressure parameter corresponding to each pressure sensor is obtained according to the ratio of the pressure value of each pressure sensor to the total pressure value.

10. An adjustment system for a vehicle seat, characterized in that, Including a sensor and a controller, where The sensor is used to collect at least one pressure value or at least one current value and send the pressure value or the current value to the controller; The controller is configured to, when it is determined that there is a user on the vehicle seat, determine a corresponding first pressure parameter according to the pressure value or the current value, determine a first weight parameter corresponding to each of the first pressure parameters, determine at least one first inflation parameter according to the first pressure parameter, the first weight parameter, and a neural network model, and perform an adjustment operation on the airbag corresponding to each of the first inflation parameters provided in the vehicle seat according to each of the first inflation parameters, so as to complete the adjustment of the vehicle seat, where the adjustment operation includes one of an inflation operation, a deflation operation, and no operation, and the first pressure parameter is the pressure parameter of the user on the vehicle seat.

Images