Seat trunk angle and backrest angle mutual calculation method and device, electronic equipment and medium

Abstract

The invention relates to the technical field of computer systems based on specific calculation models, in particular to a seat trunk angle and backrest angle mutual calculation method and device, electronic equipment and a medium, and the method comprises the steps: obtaining flexible three coordinates of a vehicle seat, and constructing a current seat coordinate system of the vehicle seat based on the flexible three coordinates; the adjusting range of the vehicle seat is obtained, the adjusting range is divided according to preset conditions, and backrest mark point coordinates of the multiple segmentation units are obtained; and measuring an angle value of an HPM trunk angle corresponding to the backrest angle in each segmentation unit, and training the bidirectional neural network by using the backrest angle and the corresponding angle value to obtain a mutual calculation model of the trunk angle and the backrest angle of the vehicle seat. Therefore, the technical problems of complicated operation, poor accuracy, low working efficiency and the like due to the fact that a large amount of data changes exist in the collision test and the trunk angle needs to be measured repeatedly by using the HPM in the related technology are solved.

Description

Technical Field

[0001] The present application relates to the technical field of computer systems based on specific calculation models, and in particular to a method, device, electronic equipment and medium for calculating the mutual calculation of a seat trunk angle and a backrest angle. Background Art

[0002] In automobile collision tests, the dummy's torso angle is one of the important parameters of the dummy's posture and is directly related to the damage results of the dummy's head, neck, chest and other parts. However, due to deficiencies in material properties and production experience, seat products inevitably deviate from their original design values. Therefore, in automobile collision tests, HPM (Human Position Measurement System) is often used to measure the actual torso angle of the seat for dummy posture positioning.

[0003] However, the above operation has the following defects: 1. The actual trunk angle of the seat can only be measured by HPM. Once the seat back changes, the trunk angle can only be measured again by HPM, which is cumbersome. 2. When the actual load of the seat is different from the weight of HPM, for example, a test dummy with a different body shape from HPM is used to collect injury data, and the dummy's ability to press the backrest is different from that of HPM, then the actual trunk angle of the seat is different from the trunk angle measured by the previous HPM, and the accuracy is poor. 3. As the requirements of drivers and passengers for seat comfort increase, more and more drivers and passengers will choose to lie down at a large angle to ride in the car. Accordingly, in the collision test, it is required to use HPM to repeatedly measure the trunk angle of the seat back at any position within its angle variation range, and each measurement needs to be installed according to the procedure and the left and right H-point errors of HPM are measured multiple times. After determining that the error accuracy meets the requirements, the trunk angle at this time can be measured, which is inefficient.

[0004] In summary, in the related art, measuring the torso angle through HPM has technical problems such as cumbersome operation, poor accuracy, and low work efficiency, which need to be improved. Summary of the invention

[0005] The present application provides a method, device, electronic device and medium for calculating the trunk angle and backrest angle of a seat, so as to solve technical problems in related technologies, such as the need to repeatedly measure the trunk angle using HPM due to a large amount of data changes in collision tests, which results in cumbersome operation, poor accuracy and low work efficiency.

[0006] The first aspect of the present application provides a method for mutual calculation of seat trunk angle and backrest angle, which is applied to the model building stage, wherein the method includes the following steps: obtaining the flexible three-coordinates of the vehicle seat, and constructing the current seat coordinate system of the vehicle seat based on the flexible three-coordinates; obtaining the adjustment range of the vehicle seat, and dividing the adjustment range according to preset conditions to obtain the backrest marking point coordinates of multiple segmentation units; measuring the angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit, and using the backrest angle and the corresponding angle value to train a bidirectional neural network to obtain a mutual calculation model of the trunk angle and backrest angle of the vehicle seat.

[0007] Optionally, in one embodiment of the present application, the flexible three-coordinate acquisition of the vehicle seat and the construction of the current seat coordinate system of the vehicle seat based on the flexible three-coordinate construction include: when the vehicle seat is fixed on a target fixed plane, measuring the flexible three-coordinate values ​​of any two symmetrical points on the seat cushion surface and the backrest surface of the vehicle seat; adjusting the fixed plane or the seat base of the vehicle seat based on the flexible three-coordinate values ​​until the symmetrical points on the seat cushion surface and the backrest surface are at the same height in the plumb direction; using the flexible three-coordinate values ​​for positioning to determine the origin of the current seat coordinate system, and starting from the origin, with the horizontal direction of the seat back pointing to the seat cushion as the positive direction of the horizontal axis, the direction from the right side of the seat to the left side as the positive direction of the longitudinal axis, and the direction from the seat cushion to the headrest as the positive direction of the vertical axis.

[0008] Optionally, in one embodiment of the present application, the measuring of the angle value of the HPM torso angle corresponding to the backrest angle in each segmentation unit includes: adjusting the backrest of the vehicle seat to the angle corresponding to any segmentation unit, and obtaining any marking point of the backrest; using flexible three-coordinate measurement to determine whether the left and right H-point difference of the vehicle seat is less than a preset threshold; if the left and right H-point difference is less than the preset threshold, using a preset HPM device to measure the HPM torso angle of the vehicle seat, measuring the position of any marking point, and determining whether the position of any marking point satisfies a preset error condition, otherwise, readjusting the position of the preset HPM device until the left and right H-point difference is greater than or equal to the preset threshold; if the position of any marking point satisfies the preset error condition, obtaining the angle value, and adjusting the backrest to the next segmentation unit, measuring the angle value of the next segmentation unit, until the backrest is adjusted to the upper limit of the adjustment range.

[0009] Optionally, in one embodiment of the present application, the use of the backrest angle and the corresponding angle value to train a bidirectional neural network to obtain a mutual calculation model of the torso angle and the backrest angle of the vehicle seat includes: taking the angle value as the input value of the bidirectional neural network to obtain the corresponding backrest angle as the label value of the network output value; training the bidirectional neural network based on the label value and the angle value to obtain a forward calculation model.

[0010] Optionally, in one embodiment of the present application, the use of the backrest angle and the corresponding angle value to train a bidirectional neural network to obtain a mutual calculation model of the torso angle and the backrest angle of the vehicle seat includes: reversely transforming the relationship between adjacent neurons of the bidirectional neural network and the corresponding weights and biases to obtain an inverse problem neural network; solving the corresponding weights and biases in the neural network from the output layer to the input layer to obtain a reverse calculation model, wherein the input value of the reverse calculation model is the backrest angle, and the output value is the corresponding torso angle; based on the forward calculation model and the reverse calculation model, the mutual calculation model is obtained.

[0011] A second aspect of the present application provides a method for mutual calculation of a seat torso angle and a backrest angle, which is applied to a model use stage, wherein the method comprises the following steps: receiving a backrest angle of a target vehicle seat or a torso angle of a target vehicle seat; inputting the backrest angle into a pre-built mutual calculation model to obtain the torso angle of the target vehicle seat, or inputting the torso angle into the mutual calculation model to obtain the backrest angle of the target vehicle seat, wherein the mutual calculation model is obtained by training a bidirectional neural network.

[0012] The third aspect of the present application provides a device for calculating the trunk angle and backrest angle of a seat, which is applied to the model building stage, wherein the device includes: a first acquisition module, used to acquire the flexible three-coordinates of a vehicle seat, and construct a current seat coordinate system of the vehicle seat based on the flexible three-coordinates; a second acquisition module, used to acquire the adjustment range of the vehicle seat, and divide the adjustment range according to preset conditions to obtain the backrest marker point coordinates of multiple segmentation units; a training module, used to measure the angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit, and use the backrest angle and the corresponding angle value to train a bidirectional neural network to obtain a mutual calculation model of the trunk angle and backrest angle of the vehicle seat.

[0013] Optionally, in one embodiment of the present application, the first acquisition module includes: a first measuring unit, used to measure the flexible three-coordinate values ​​of any two symmetrical points on the seat cushion surface and the backrest surface of the vehicle seat when the vehicle seat is fixed on a target fixed plane; a first adjustment unit, used to adjust the fixed plane or the seat base of the vehicle seat based on the flexible three-coordinate values ​​until the heights of the symmetrical points on the seat cushion surface and the backrest surface are consistent in the plumb direction; a determination unit, used to use the flexible three-coordinate values ​​for positioning, determine the origin of the current seat coordinate system, and starting from the origin, with the horizontal direction of the seat back pointing to the seat cushion as the positive direction of the horizontal axis, the direction from the right side of the seat to the left side as the positive direction of the longitudinal axis, and the direction from the seat cushion to the headrest as the positive direction of the vertical axis.

[0014] Optionally, in one embodiment of the present application, the training module includes: a second adjustment unit, used to adjust the backrest of the vehicle seat to an angle corresponding to any segmentation unit, and obtain any marking point of the backrest; a second measurement unit, used to use flexible three-coordinate measurement to determine whether the left and right H-point difference of the vehicle seat is less than a preset threshold; a third measurement unit, used to use a preset HPM device to measure the HPM torso angle of the vehicle seat, measure the position of any marking point, and determine whether the position of any marking point meets a preset error condition when the left and right H-point difference is less than the preset threshold, otherwise, readjust the position of the preset HPM device until the left and right H-point difference is greater than or equal to the preset threshold; a fourth strategy unit, used to obtain the angle value when the position of any marking point meets the preset error condition, and adjust the backrest to the next segmentation unit, measure the angle value of the next segmentation unit, until the backrest is adjusted to the upper limit of the adjustment range.

[0015] Optionally, in one embodiment of the present application, the training module includes: a first calculation unit, used to take the angle value as the input value of the bidirectional neural network to obtain the corresponding backrest angle as the label value of the network output value; a training unit, used to train the bidirectional neural network based on the label value and the angle value to obtain a forward calculation model.

[0016] Optionally, in one embodiment of the present application, the training module includes: a transformation unit, used to reversely transform the relationship between adjacent neurons and corresponding weights and biases of the bidirectional neural network to obtain an inverse problem neural network; a second calculation unit, used to solve the corresponding weights and biases in the neural network from the output layer to the input layer to obtain a reverse calculation model, wherein the input value of the reverse calculation model is the backrest angle, and the output value is the corresponding torso angle; an acquisition unit, used to obtain the mutual calculation model based on the forward calculation model and the reverse calculation model.

[0017] The fourth aspect of the present application provides a mutual calculation device for the torso angle and backrest angle of a seat, which is applied to the model use stage, wherein the device includes: a receiving module, used to receive the backrest angle of a target vehicle seat or the torso angle of a target vehicle seat; a calculation module, used to input the backrest angle into a pre-built mutual calculation model to obtain the torso angle of the target vehicle seat, or, input the torso angle into the mutual calculation model to obtain the backrest angle of the target vehicle seat, wherein the mutual calculation model is obtained by training a bidirectional neural network.

[0018] The fifth aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for calculating the seat trunk angle and backrest angle as described in the above embodiment.

[0019] A sixth aspect of the present application provides a computer-readable storage medium storing computer instructions for causing the computer to execute the method for calculating the seat trunk angle and backrest angle as described in the above embodiments.

[0020] The seventh aspect of the present application provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned method for calculating the seat trunk angle and backrest angle.

[0021] The embodiment of the present application can construct the current seat coordinate system of the vehicle seat according to the flexible three-coordinate system of the vehicle seat, obtain the adjustment range of the vehicle seat, and divide the adjustment range according to the preset conditions to obtain the coordinates of the backrest mark points of multiple segmentation units, and then measure the angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit, so as to train the bidirectional neural network with the backrest angle and the corresponding angle value, and obtain the mutual calculation model of the trunk angle and the backrest angle of the vehicle seat, so as to overcome the cumbersome operation of only measuring the actual trunk angle corresponding to all the backrest angles of the seat through HPM in the lying state at a large angle. When the backrest angle changes, the corresponding trunk angle value can be directly calculated through the conversion relationship between the backrest angle and the trunk angle, without having to measure by installing the HPM equipment, which simplifies the solution method and improves the measurement efficiency and the accuracy of the measurement results. Therefore, the technical problems in the related art that the HPM needs to be used to repeatedly measure the trunk angle due to a large number of data changes in the collision test, which is cumbersome, inaccurate, and has low work efficiency are solved.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flowchart of a method for calculating a seat trunk angle and a seat back angle according to an embodiment of the present application;

[0025] Figure 2 A schematic diagram of a current seat coordinate system of a vehicle seat provided according to an embodiment of the present application;

[0026] Figure 3 A schematic diagram of the division principle of the adjustable range of a seat back provided according to an embodiment of the present application;

[0027] Figure 4 A schematic diagram of a torso angle measurement process of a segmentation unit according to an embodiment of the present application;

[0028] Figure 5 A schematic diagram of a bidirectional neural network structure provided according to an embodiment of the present application;

[0029] Figure 6 A flowchart of a method for calculating a seat trunk angle and a seat back angle according to an embodiment of the present application;

[0030] Figure 7 It is a structural schematic diagram of a device for calculating the seat trunk angle and backrest angle according to an embodiment of the present application;

[0031] Figure 8 A flowchart of another method for calculating the seat trunk angle and backrest angle according to an embodiment of the present application;

[0032] Fig. 9 It is a structural schematic diagram of another device for calculating the trunk angle and backrest angle of a seat provided according to an embodiment of the present application;

[0033] Fig.10 It is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0035] The following describes the mutual calculation method, device, electronic device and medium of the seat trunk angle and backrest angle according to the embodiment of the present application with reference to the accompanying drawings. In view of the technical problems that, in the related technologies mentioned in the above background technology, there are a large number of data changes in the collision test, and the torso angle needs to be repeatedly measured using HPM, which is cumbersome, inaccurate, and inefficient, the present application provides a method for calculating the torso angle and backrest angle of a seat. In this method, the current seat coordinate system of the vehicle seat can be constructed according to the flexible three-coordinate system of the vehicle seat, the adjustment range of the vehicle seat can be obtained, and the adjustment range can be divided according to preset conditions to obtain the coordinates of the backrest marking points of multiple segmentation units, and then the angle value of the HPM torso angle corresponding to the backrest angle in each segmentation unit is measured, so as to train a bidirectional neural network using the backrest angle and the corresponding angle value to obtain a mutual calculation model of the torso angle and the backrest angle of the vehicle seat, thereby overcoming the cumbersome operation of only being able to measure the actual torso angle corresponding to all the backrest angles of the seat through HPM in a large-angle lying state. When the backrest angle changes, the corresponding torso angle value can be directly calculated through the conversion relationship between the backrest angle and the torso angle, without having to install the HPM equipment for measurement, thereby simplifying the solution method and improving the measurement efficiency and the accuracy of the measurement results. This solves the technical problems in the related art, such as the need to use HPM to repeatedly measure the torso angle due to a large number of data changes in the collision test, which results in cumbersome operation, poor accuracy and low work efficiency.

[0036] Specifically, Figure 1 A schematic flow chart of a method for calculating the seat trunk angle and backrest angle provided in an embodiment of the present application.

[0037] like Figure 1 As shown, the mutual calculation method of the seat trunk angle and the backrest angle is applied in the model building stage, wherein the method comprises the following steps:

[0038] In step S101 , the flexible three-coordinates of the vehicle seat are acquired, and a current seat coordinate system of the vehicle seat is constructed based on the flexible three-coordinates.

[0039] In the actual implementation process, the embodiment of the present application can use a flexible three-dimensional coordinate measuring machine to obtain the flexible three-dimensional coordinates of the vehicle seat, and then construct the current seat coordinate system of the vehicle seat.

[0040] Among them, the flexible three-dimensional measuring machine can perform high-precision three-dimensional measurement and is suitable for the inspection of complex parts and large-size workpieces.

[0041] Optionally, in one embodiment of the present application, the flexible three-coordinates of the vehicle seat are obtained, and the current seat coordinate system of the vehicle seat is constructed based on the flexible three-coordinates, including: when the vehicle seat is fixed on a target fixed plane, measuring the flexible three-coordinate values ​​of any two symmetrical points on the seat cushion surface and the backrest surface of the vehicle seat; adjusting the fixed plane or seat base of the vehicle seat based on the flexible three-coordinate values ​​until the symmetrical points on the seat cushion surface and the backrest surface are at the same height in the plumb direction; using the flexible three-coordinate values ​​for positioning, determining the origin of the current seat coordinate system, and starting from the origin, with the horizontal direction of the seat back pointing to the seat cushion as the positive direction of the horizontal axis, the direction from the right side of the seat to the left side as the positive direction of the vertical axis, and the direction from the seat cushion to the headrest as the positive direction of the vertical axis.

[0042] Furthermore, combined with Figure 2 As shown, the present embodiment of the present application may include the following steps when constructing the current seat coordinate system:

[0043] Step S1: Fix the vehicle seat on a flat ground (target fixed plane), use a flexible three-coordinate device to measure the coordinate values ​​of any two symmetrical points on the seat cushion surface and the backrest surface, and compare whether the coordinate values ​​of the symmetrical points in the plumb direction are within the error range. If the error is exceeded, it is necessary to adjust the seat fixing plane or seat base until the heights of the symmetrical points on the seat cushion surface and the backrest surface in the plumb direction are consistent.

[0044] Step S2: removing the outer enclosure of the seat back's rotating shaft to expose the seat back's rotating shaft.

[0045] Step S3: Mark multiple marking points on the metal structures on the left and right sides of the seat bottom for establishing the seat coordinate system and restoring the coordinate system after the seat is moved.

[0046] Step S4: Define that when the driver and passenger are sitting in the seat forward, that is, when looking from the seat back to the seat cushion, the left side of the driver and passenger is recorded as the left side of the seat, and the right side of the driver and passenger is recorded as the right side of the seat. Use flexible three-coordinate positioning to locate the center of the left and right rotation axes of the backrest, and select the midpoint of the line connecting the centers of the circles as the origin of the seat coordinate system. Starting from the origin, the horizontal direction of the seat back pointing to the seat cushion is the positive direction of the X-axis; starting from the origin, on the line connecting the centers of the left and right rotation axes, the direction from the right side of the seat to the left side is the positive direction of the Y-axis; starting from the origin, perpendicular to the X-axis and Y-axis, the direction from the seat cushion to the headrest is the positive direction of the Z-axis.

[0047] Step S5: Use the flexible three-coordinate system to record and construct the current seat coordinate system, and record the coordinates of the restored marking points for restoring the coordinate system after the seat moves.

[0048] In step S102, the adjustment range of the vehicle seat is obtained, and the adjustment range is divided according to preset conditions to obtain the coordinates of the backrest marking points of multiple segmentation units.

[0049] As a possible way to achieve this, combining Figure 3 As shown, the embodiment of the present application may include the following steps when dividing the segmentation unit:

[0050] Step S1: Select a fixed point on the seat back as the marking point. You can select the headrest rod position or a point on the seat back. Select a flat area on the back as the backrest angle measurement area. Figure 3 (a) shown.

[0051] Step S2: Adjust the seat back to the front, that is, adjust the seat back to the front position of its variable range in the positive direction of the X axis, and use the flexible three-dimensional coordinate system to measure the coordinates of the back mark point, which is recorded as "backrest 0 degree position". And reset the inclinometer value in the angle measurement area. Figure 3 (b) as shown.

[0052] Step S3: Adjust the seat back to the last position, that is, adjust the back to the negative direction of the X-axis to the last position of its variable range, that is, adjust it to the maximum range, use the flexible three-dimensional coordinate measurement to measure the coordinates of the backrest mark point, and use the inclinometer in the angle measurement area to measure the backrest angle at this time, which is α degrees. Then the backrest position is recorded as "backrest α degree position". Figure 3 (c) as shown.

[0053] Step S4: Segment the seat back angle from "backrest 0 degree position" to "backrest α degree position" with β degree as segmentation interval, and obtain (α-0) / β units. The density of the segmented units is adjusted by the size of β.

[0054] Step S5: Adjust the seat back from the "backrest 0 degree position" to the negative direction of the X axis by β degrees. The adjustment angle is measured by an inclinometer in the angle measurement area. Use the flexible three-dimensional coordinate system to measure the coordinates of the backrest mark point at this time, which is recorded as the "backrest β degree position". Figure 3 (d)

[0055] Step S6: Adjust the seat back from the "backrest β degree position" to the negative direction of the X axis by β degrees. The adjustment angle is measured by the inclinometer in the angle measurement area. Use the flexible three-dimensional coordinate system to measure the coordinates of the backrest mark point at this time, which is recorded as "backrest 2*β degree position".

[0056] Step S7: Record the coordinates of the backrest marking point at each segmentation unit position from the "backrest 0 degree position" to the "backrest α degree position".

[0057] In step S103, the angle value of the HPM torso angle corresponding to the backrest angle in each segmentation unit is measured, and the backrest angle and the corresponding angle value are used to train a bidirectional neural network to obtain a mutual calculation model of the torso angle and the backrest angle of the vehicle seat.

[0058] In some embodiments, the HPM device can be used to measure the angle value of the torso angle corresponding to the backrest angle in each segmentation unit, so that the bidirectional neural network can be trained using multiple sets of backrest angles and angle values ​​to obtain a mutual calculation model of the torso angle and backrest angle of the vehicle seat, so that when one of the torso angle and backrest angle is input, the corresponding value can be obtained.

[0059] Optionally, in one embodiment of the present application, the angle value of the HPM torso angle corresponding to the backrest angle in each segmentation unit is measured, including: adjusting the backrest of the vehicle seat to the angle corresponding to any segmentation unit, and obtaining any marking point of the backrest; using flexible three-coordinate measurement to determine whether the left and right H-point difference of the vehicle seat is less than a preset threshold; if the left and right H-point difference is less than the preset threshold, using a preset HPM device to measure the HPM torso angle of the vehicle seat, measuring the position of any marking point, and determining whether the position of any marking point meets a preset error condition, otherwise, readjusting the position of the preset HPM device until the left and right H-point difference is greater than or equal to the preset threshold; if the position of any marking point meets the preset error condition, the angle value is obtained, and the backrest is adjusted to the next segmentation unit, and the angle value of the next segmentation unit is measured until the backrest is adjusted to the upper limit of the adjustment range.

[0060] Among them, combined Figure 4 As shown, the embodiment of the present application may include the following steps when measuring the angle value of the segmentation unit:

[0061] Step S1: Adjust the seat back to the "backrest 0 degree position". According to the installation requirements of the HPM, accurately install the HPM on the seat, and use the flexible three-coordinate measurement to restore the mark point of the seat coordinate system to ensure that the installation of the HPM does not affect the accuracy of the seat coordinate system. Use the flexible three-coordinate measurement to measure the left and right H points of the HPM. When the error of the left and right H points is within the allowable range, measure and record the torso angle of the HPM at this time. If it is not within the allowable range, readjust the HPM. Otherwise, use the flexible three-coordinate measurement to measure and record the coordinates of the backrest mark point, which is recorded as the "loaded 0 degree position".

[0062] Step S2: Remove the HPM equipment, wait for 30 minutes, and after the seat rebounds, adjust the seat back to the "backrest β degree position". The adjustment process is completed by measuring the backrest mark point to the coordinate position corresponding to the "backrest β degree position" through flexible three-coordinate measurement. Before adjustment, the coordinate system position should be restored through the restoration mark point of the seat coordinate system to ensure that the previous HPM removal process does not affect the accuracy of the seat coordinate system.

[0063] Step S3: Use the flexible three-dimensional coordinate measurement to measure the left and right H points of the HPM. When the error between the left and right H points is within the allowable range, measure and record the torso angle of the HPM at this time. Use the flexible three-dimensional coordinate measurement to measure and record the coordinates of the backrest mark point, which is recorded as the "loaded β position".

[0064] Step S4: Record the angle value of the HPM torso angle at each segmentation unit position from the "backrest 0 degree position" to the "backrest α degree position".

[0065] Optionally, in one embodiment of the present application, a bidirectional neural network is trained using a backrest angle and a corresponding angle value to obtain a mutual calculation model of the torso angle and the backrest angle of the vehicle seat, including: using the angle value as the input value of the bidirectional neural network to obtain the corresponding backrest angle as the label value of the network output value; training the bidirectional neural network based on the label value and the angle value to obtain a forward calculation model.

[0066] In the actual implementation process, the embodiments of the present application can use Figure 5 The bidirectional neural network shown in Figure 1 obtains the forward computation model.

[0067] The bidirectional neural network is divided into an input layer, an intermediate layer, and an output layer. The intermediate layer is composed of one or more layers of neurons. All neurons in the entire bidirectional neural network are in the form of full connections. The number of neurons in all layers of the network is set to be the same.

[0068] In the embodiment of the present application, the obtained (α-0) / β torso angles can be used as input values ​​and input from the input layer of the network; the obtained (α-0) / β backrest angles can be used as label values ​​of the network output values. The relationship between the i-th neuron in the l-th layer and the (l-1)-th layer neurons and their corresponding weights and biases.

[0069]

[0070] Among them, “→” represents the solution process of the bidirectional neural network from the input layer to the output layer, N l represents the number of neurons in the lth layer, represents the weight of the i-th neuron in the l-th layer and the j-th neuron in the (l-1)-th layer, b represents the bias value, represents the activation function of the ith neuron in the lth layer.

[0071] Formula (2) is expressed in the form of matrix and vector as shown in formula (3):

[0072]

[0073] At this time, the embodiment of the present application can use the collected trunk angle and backrest angle data sets to train the neural network. The data set is divided into a training set, a test set, and a validation set according to a certain ratio. First, after the network is trained with the training set, the loss value of the network is tested with the test set. If the output backrest angle loss value meets the accuracy requirement, the network is verified with the validation set. If the verified loss value meets the accuracy requirement, the network parameters at this time are saved to obtain a forward calculation model, which can be used in the scenario of knowing the trunk angle and solving the backrest angle.

[0074] Optionally, in one embodiment of the present application, a bidirectional neural network is trained using a backrest angle and corresponding angle values ​​to obtain a mutual calculation model of the torso angle and the backrest angle of the vehicle seat, including: reversely transforming the relationship between adjacent neurons of the bidirectional neural network and the corresponding weights and biases to obtain an inverse problem neural network; solving the corresponding weights and biases in the neural network from the output layer to the input layer to obtain a reverse calculation model, wherein the input value of the reverse calculation model is the backrest angle, and the output value is the corresponding torso angle; based on the forward calculation model and the reverse calculation model, a mutual calculation model is obtained.

[0075] Furthermore, the embodiment of the present application can obtain a corresponding reverse calculation model through the trained neural network, that is, the forward calculation model, wherein the embodiment of the present application can achieve the solution from the backrest angle to the trunk angle through the inverse solution method. Formula (2) is expressed in the form of matrix and vector as shown in Formula (4):

[0076]

[0077] Among them, R l is the diagonal matrix of the activation function, as shown in formula (5), and the elements on the diagonal represent the activation function of each layer. The activation function should be a reversible function.

[0078]

[0079] The weight matrix is ​​shown in formula (6):

[0080]

[0081] Based on formula (4), the explicit expression of the corresponding inverse problem neural network is shown in formula (7).

[0082]

[0083] Among them, a 2 represents the Tikhonov regularization parameter, I α represents the identity matrix corresponding to the regularization parameter. The regularization parameter should be determined based on the measured noise level of the measurable output or the noise level added to the calculated response.

[0084] Therefore, the expressions of weights and biases in the neural network solved from the output layer to the input layer can be expressed as shown in equations (8) and (9):

[0085]

[0086] Through equations (8) and (9), equation (7) can be expressed as equation (10):

[0087]

[0088] Where “←” represents the neural network that is solved from the output layer to the input layer. Formula (10) can be expressed in the form of formula (11).

[0089]

[0090] In the embodiment of the present application, the backrest angle can be input as an input into formula (11) for reverse solution, that is, a reverse calculation model can be obtained, and finally the angle value of the torso angle can be obtained, thereby realizing the solution of the backrest angle to the torso angle.

[0091] By combining the forward calculation model and the reverse calculation model, the embodiment of the present application can obtain a mutual calculation model.

[0092] In summary, the working principle of the embodiment of the present application can be as follows: Figure 6 As shown, in the actual implementation process, the embodiment of the present application can fix the seat and establish the coordinate system; divide the adjustable range of the seat backrest, and record the coordinates of the marking points of the split unit backrest; install and measure the split unit HPM; and establish a mutual calculation model of the trunk angle and the seat backrest angle based on a bidirectional neural network. That is, the bidirectional neural network established is trained and verified by the collected trunk angle and backrest angle data. The trained bidirectional neural network can not only realize the calculation of the trunk angle to the backrest angle, but also realize the calculation of the backrest angle to the trunk angle through the inverse solution method. It makes up for the deficiency that the trunk angle can only be measured by HPM. When the backrest angle changes, the corresponding trunk angle value can be directly calculated by the neural network without having to measure by installing the HPM equipment, which simplifies the solution method. The complex conversion relationship between the backrest angle and the trunk angle is realized, and the trunk angle value of the driver and passenger in the lying state can be calculated, providing a data basis for occupant protection.

[0093] According to the mutual calculation method of the seat trunk angle and backrest angle proposed in the embodiment of the present application, the current seat coordinate system of the vehicle seat can be constructed according to the flexible three-coordinate system of the vehicle seat, the adjustment range of the vehicle seat can be obtained, and the adjustment range can be divided according to the preset conditions to obtain the coordinates of the backrest mark points of multiple segmentation units, and then the angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit can be measured, so as to train the bidirectional neural network with the backrest angle and the corresponding angle value, and obtain the mutual calculation model of the trunk angle and backrest angle of the vehicle seat, so as to overcome the cumbersome operation of only measuring the actual trunk angle corresponding to all the backrest angles of the seat through HPM in the lying state at a large angle. When the backrest angle changes, the corresponding trunk angle value can be directly calculated through the conversion relationship between the backrest angle and the trunk angle, without having to measure by installing the HPM equipment, which simplifies the solution method and improves the measurement efficiency and the accuracy of the measurement results. Therefore, the technical problems in the related art that the HPM needs to be used to repeatedly measure the trunk angle due to a large number of data changes in the collision test, which is cumbersome, inaccurate, and has low work efficiency are solved.

[0094] Next, a device for calculating the seat trunk angle and backrest angle according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0095] Figure 7 It is a block diagram of a device for calculating the seat trunk angle and backrest angle according to an embodiment of the present application.

[0096] like Figure 7 As shown, the seat trunk angle and backrest angle mutual calculation device 10 is applied to the model building stage, wherein the device 10 includes: a first acquisition module 101, a second acquisition module 102 and a training module 103.

[0097] Specifically, the first acquisition module 101 is used to acquire the flexible three-coordinates of the vehicle seat and construct a current seat coordinate system of the vehicle seat based on the flexible three-coordinates.

[0098] The second acquisition module 102 is used to acquire the adjustment range of the vehicle seat and divide the adjustment range according to preset conditions to obtain the coordinates of the backrest marking points of multiple segmentation units.

[0099] The training module 103 is used to measure the angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit, and use the backrest angle and the corresponding angle value to train a bidirectional neural network to obtain a mutual calculation model of the trunk angle and the backrest angle of the vehicle seat.

[0100] Optionally, in an embodiment of the present application, the first acquisition module 101 includes: a first measuring unit, a first adjusting unit and a determining unit.

[0101] Wherein, the first measuring unit is used to measure the flexible three-coordinate values ​​of any two symmetrical points on the cushion surface and the backrest surface of the vehicle seat when the vehicle seat is fixed on the target fixed plane.

[0102] The first adjustment unit is used to adjust the fixed plane or the seat base of the vehicle seat based on the flexible three-coordinate values ​​until the symmetrical points of the seat cushion surface and the backrest surface have the same height in the plumb direction.

[0103] The determination unit is used to use the flexible three-coordinate values ​​for positioning to determine the origin of the current seat coordinate system, and starting from the origin, the horizontal direction of the seat back pointing to the seat cushion is the positive direction of the horizontal axis, the direction from the right side of the seat to the left side is the positive direction of the vertical axis, and the direction from the seat cushion to the headrest is the positive direction of the vertical axis.

[0104] Optionally, in one embodiment of the present application, the training module 103 includes: a second adjustment unit, a second measurement unit, a third measurement unit and a fourth strategy unit.

[0105] Among them, the second adjustment unit is used to adjust the backrest of the vehicle seat to an angle corresponding to any segmentation unit and obtain any marking point of the backrest.

[0106] The second measuring unit is used to measure the left and right H point difference of the vehicle seat by using flexible three-coordinate measurement to see whether it is less than a preset threshold.

[0107] The third measurement unit is used to measure the HPM torso angle of the vehicle seat using a preset HPM device when the left and right H-point difference is less than a preset threshold, measure the position of any marking point, and determine whether the position of any marking point meets a preset error condition. Otherwise, readjust the position of the preset HPM device until the left and right H-point difference is greater than or equal to the preset threshold.

[0108] The fourth strategy unit is used to obtain the angle value when any mark point position meets the preset error condition, and adjust the backrest to the next segmentation unit, and measure the angle value of the next segmentation unit until the backrest is adjusted to the upper limit of the adjustment range.

[0109] Optionally, in one embodiment of the present application, the training module 103 includes: a first computing unit and a training unit.

[0110] Among them, the first calculation unit is used to use the angle value as the input value of the bidirectional neural network to obtain the corresponding backrest angle as the label value of the network output value.

[0111] The training unit is used to train the bidirectional neural network based on the label value and the angle value to obtain a forward calculation model.

[0112] Optionally, in one embodiment of the present application, the training module 103 includes: a conversion unit, a second calculation unit and an acquisition unit.

[0113] Among them, the conversion unit is used to reversely transform the relationship between adjacent neurons and corresponding weights and biases of the bidirectional neural network to obtain an inverse problem neural network.

[0114] The second calculation unit is used to solve the corresponding weights and biases in the neural network from the output layer to the input layer to obtain a reverse calculation model, wherein the input value of the reverse calculation model is the backrest angle, and the output value is the corresponding trunk angle.

[0115] The acquisition unit is used to obtain the mutual calculation model based on the forward calculation model and the reverse calculation model.

[0116] It should be noted that the above explanation of the embodiment of the method for mutual calculation of the seat trunk angle and the backrest angle is also applicable to the device for mutual calculation of the seat trunk angle and the backrest angle of this embodiment, and will not be repeated here.

[0117] According to the mutual calculation device of the seat trunk angle and backrest angle proposed in the embodiment of the present application, the current seat coordinate system of the vehicle seat can be constructed according to the flexible three-coordinate system of the vehicle seat, the adjustment range of the vehicle seat can be obtained, and the adjustment range can be divided according to the preset conditions to obtain the coordinates of the backrest mark points of multiple segmentation units, and then the angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit can be measured, so as to train the bidirectional neural network with the backrest angle and the corresponding angle value, and obtain the mutual calculation model of the trunk angle and backrest angle of the vehicle seat, so as to overcome the cumbersome operation of only measuring the actual trunk angle corresponding to all the backrest angles of the seat through HPM in the lying state at a large angle. When the backrest angle changes, the corresponding trunk angle value can be directly calculated through the conversion relationship between the backrest angle and the trunk angle, without having to measure by installing the HPM equipment, which simplifies the solution method and improves the measurement efficiency and the accuracy of the measurement results. Therefore, the technical problems in the related art that the HPM needs to be used to repeatedly measure the trunk angle due to a large number of data changes in the collision test, which is cumbersome, inaccurate, and has low work efficiency are solved.

[0118] The above is a description of the embodiment of the present application at the model building stage. The following is a description of the embodiment of the present application at the model usage stage.

[0119] Specifically, Figure 8 A schematic flow chart of a method for calculating the seat trunk angle and backrest angle provided in an embodiment of the present application.

[0120] like Figure 8 As shown, the mutual calculation method of the seat trunk angle and the backrest angle is applied to the model use stage, wherein the method comprises the following steps:

[0121] In step S801 , a backrest angle of a target vehicle seat or a torso angle of a target vehicle seat is received.

[0122] In step S802, the backrest angle is input into a pre-built mutual calculation model to obtain the trunk angle of the target vehicle seat, or the trunk angle is input into the mutual calculation model to obtain the backrest angle of the target vehicle seat, wherein the mutual calculation model is obtained by training a bidirectional neural network.

[0123] According to the mutual calculation method of the seat trunk angle and backrest angle proposed in the embodiment of the present application, the current seat coordinate system of the vehicle seat can be constructed according to the flexible three-coordinate system of the vehicle seat, the adjustment range of the vehicle seat can be obtained, and the adjustment range can be divided according to the preset conditions to obtain the coordinates of the backrest mark points of multiple segmentation units, and then the angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit can be measured, so as to train the bidirectional neural network with the backrest angle and the corresponding angle value, and obtain the mutual calculation model of the trunk angle and backrest angle of the vehicle seat, so as to overcome the cumbersome operation of only measuring the actual trunk angle corresponding to all the backrest angles of the seat through HPM in the lying state at a large angle. When the backrest angle changes, the corresponding trunk angle value can be directly calculated through the conversion relationship between the backrest angle and the trunk angle, without having to measure by installing the HPM equipment, which simplifies the solution method and improves the measurement efficiency and the accuracy of the measurement results. Therefore, the technical problems in the related art that the HPM needs to be used to repeatedly measure the trunk angle due to a large number of data changes in the collision test, which is cumbersome, inaccurate, and has low work efficiency are solved.

[0124] Next, a device for calculating the seat trunk angle and backrest angle according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0125] Fig. 9 It is a block diagram of a device for calculating the seat trunk angle and backrest angle according to an embodiment of the present application.

[0126] like Fig. 9 As shown, the seat trunk angle and backrest angle mutual calculation device 20 is applied in the model use stage, wherein the device 20 includes: a receiving module 201 and a calculation module 202.

[0127] Specifically, the receiving module 201 is used to receive the backrest angle of the target vehicle seat or the torso angle of the target vehicle seat.

[0128] The calculation module 202 is used to input the backrest angle into a pre-built mutual calculation model to obtain the trunk angle of the target vehicle seat, or to input the trunk angle into the mutual calculation model to obtain the backrest angle of the target vehicle seat, wherein the mutual calculation model is obtained by training a bidirectional neural network.

[0129] It should be noted that the above explanation of the embodiment of the method for mutual calculation of the seat trunk angle and the backrest angle is also applicable to the device for mutual calculation of the seat trunk angle and the backrest angle of this embodiment, and will not be repeated here.

[0130] According to the mutual calculation device of the seat trunk angle and backrest angle proposed in the embodiment of the present application, the current seat coordinate system of the vehicle seat can be constructed according to the flexible three-coordinate system of the vehicle seat, the adjustment range of the vehicle seat can be obtained, and the adjustment range can be divided according to the preset conditions to obtain the coordinates of the backrest mark points of multiple segmentation units, and then the angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit can be measured, so as to train the bidirectional neural network with the backrest angle and the corresponding angle value, and obtain the mutual calculation model of the trunk angle and backrest angle of the vehicle seat, so as to overcome the cumbersome operation of only measuring the actual trunk angle corresponding to all the backrest angles of the seat through HPM in the lying state at a large angle. When the backrest angle changes, the corresponding trunk angle value can be directly calculated through the conversion relationship between the backrest angle and the trunk angle, without having to measure by installing the HPM equipment, which simplifies the solution method and improves the measurement efficiency and the accuracy of the measurement results. Therefore, the technical problems in the related art that the HPM needs to be used to repeatedly measure the trunk angle due to a large number of data changes in the collision test, which is cumbersome, inaccurate, and has low work efficiency are solved.

[0131] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0132] A memory 1001 , a processor 1002 , and a computer program stored in the memory 1001 and executable on the processor 1002 .

[0133] When the processor 1002 executes the program, the mutual calculation method of the seat trunk angle and the backrest angle provided in the above embodiment is implemented.

[0134] Furthermore, the electronic device further comprises:

[0135] The communication interface 1003 is used for communication between the memory 1001 and the processor 1002 .

[0136] The memory 1001 is used to store computer programs that can be executed on the processor 1002 .

[0137] The memory 1001 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0138] If the memory 1001, the processor 1002 and the communication interface 1003 are implemented independently, the communication interface 1003, the memory 1001 and the processor 1002 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0139] Optionally, in a specific implementation, if the memory 1001, the processor 1002 and the communication interface 1003 are integrated on a chip, the memory 1001, the processor 1002 and the communication interface 1003 can communicate with each other through an internal interface.

[0140] The processor 1002 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0141] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned method for calculating the seat trunk angle and the backrest angle is implemented.

[0142] The embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for calculating the seat trunk angle and backrest angle provided in the embodiment of the present application.

[0143] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0144] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0145] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0146] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0147] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0148] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0149] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0150] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for calculating the seat trunk angle and backrest angle, characterized in that: Applied to the model building stage, wherein the method comprises the following steps: Acquire the flexible three-coordinates of the vehicle seat, and construct a current seat coordinate system of the vehicle seat based on the flexible three-coordinates; Acquiring an adjustment range of the vehicle seat, and dividing the adjustment range according to preset conditions to obtain the coordinates of the backrest marking points of a plurality of segmentation units; The angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit is measured, and the backrest angle and the corresponding angle value are used to train a bidirectional neural network to obtain a mutual calculation model of the trunk angle and the backrest angle of the vehicle seat.

2. The method according to claim 1, characterized in that: The step of acquiring the flexible three-coordinates of the vehicle seat and constructing a current seat coordinate system of the vehicle seat based on the flexible three-coordinates includes: When the vehicle seat is fixed on a target fixed plane, measuring the flexible three-coordinate values ​​of any two symmetrical points on the seat cushion surface and the backrest surface of the vehicle seat; Adjusting the fixed plane or the seat base of the vehicle seat based on the flexible three-coordinate values ​​until the symmetric points of the seat cushion surface and the backrest surface have the same height in the plumb direction; The flexible three-coordinate values ​​are used for positioning to determine the origin of the current seat coordinate system, and starting from the origin, the horizontal direction of the seat back pointing to the seat cushion is the positive direction of the horizontal axis, the direction from the right side of the seat to the left side is the positive direction of the vertical axis, and the direction from the seat cushion to the headrest is the positive direction of the vertical axis.

3. The method according to claim 1, characterized in that The measuring of the angle value of the HPM torso angle corresponding to the backrest angle in each segmented unit includes: Adjusting the backrest of the vehicle seat to an angle corresponding to any segmentation unit, and obtaining any marking point of the backrest; Using flexible three-coordinate measurement to determine whether the left and right H-point difference of the vehicle seat is less than a preset threshold; If the left and right H-point difference is less than the preset threshold, the HPM torso angle of the vehicle seat is measured by using a preset HPM device, the position of any of the marking points is measured, and it is determined whether the position of any of the marking points meets a preset error condition; otherwise, the position of the preset HPM device is readjusted until the left and right H-point difference is greater than or equal to the preset threshold; If the position of any of the marking points satisfies the preset error condition, the angle value is obtained, and the backrest is adjusted to the next segmentation unit, and the angle value of the next segmentation unit is measured until the backrest is adjusted to the upper limit of the adjustment range.

4. The method according to claim 1, characterized in that: The method of using the backrest angle and the corresponding angle value to train a bidirectional neural network to obtain a mutual calculation model of the torso angle and the backrest angle of the vehicle seat includes: Using the angle value as the input value of the bidirectional neural network, obtaining the corresponding backrest angle as the label value of the network output value; The bidirectional neural network is trained based on the label value and the angle value to obtain a forward calculation model.

5. The method according to claim 4, characterized in that The method of using the backrest angle and the corresponding angle value to train a bidirectional neural network to obtain a mutual calculation model of the torso angle and the backrest angle of the vehicle seat includes: Reversely transform the relationship between adjacent neurons and corresponding weights and biases of the bidirectional neural network to obtain an inverse problem neural network; Solving the corresponding weights and biases in the neural network from the output layer to the input layer to obtain a reverse calculation model, wherein the input value of the reverse calculation model is the backrest angle, and the output value is the corresponding torso angle; Based on the forward calculation model and the reverse calculation model, the mutual calculation model is obtained.

6. A method for calculating the seat trunk angle and backrest angle, characterized in that: Applied to the model use phase, wherein the method comprises the following steps: receiving a backrest angle of a target vehicle seat or a torso angle of a target vehicle seat; The backrest angle is input into a pre-built mutual calculation model to obtain the trunk angle of the target vehicle seat, or the trunk angle is input into the mutual calculation model to obtain the backrest angle of the target vehicle seat, wherein the mutual calculation model is obtained by bidirectional neural network training.

7. A device for calculating the seat trunk angle and backrest angle, characterized in that: Applied to the model building stage, wherein the device comprises: A first acquisition module, used for acquiring flexible three-coordinates of a vehicle seat, and constructing a current seat coordinate system of the vehicle seat based on the flexible three-coordinates; A second acquisition module is used to acquire the adjustment range of the vehicle seat and divide the adjustment range according to a preset condition to obtain the coordinates of the backrest marking points of multiple segmentation units; The training module is used to measure the angle value of the HPM trunk angle corresponding to the backrest angle in each segmentation unit, and use the backrest angle and the corresponding angle value to train a bidirectional neural network to obtain a mutual calculation model of the trunk angle and backrest angle of the vehicle seat.

8. A device for calculating the seat trunk angle and backrest angle, characterized in that: Applied to the model use stage, wherein the device comprises: A receiving module, used for receiving a backrest angle of a target vehicle seat or a torso angle of a target vehicle seat; A calculation module is used to input the backrest angle into a pre-built mutual calculation model to obtain the trunk angle of the target vehicle seat, or to input the trunk angle into the mutual calculation model to obtain the backrest angle of the target vehicle seat, wherein the mutual calculation model is obtained by training a bidirectional neural network.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for calculating the seat trunk angle and backrest angle as described in any one of claims 1-5 or 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the mutual calculation method of the seat trunk angle and the backrest angle as described in any one of claims 1-5 or 6.

Images