A method, apparatus, and medium for opening a tailgate of a vehicle

Abstract

The application discloses a method and device for opening a tail door of a vehicle and a medium, and belongs to the technical field of artificial intelligence. A processor needs to establish a kicking action capacitance value model in advance according to the change characteristics of historical capacitance values. The historical capacitance values are capacitance values corresponding to a kicking action for opening the tail door of the vehicle, and the change characteristics of the capacitance values represent a change process of the capacitance values corresponding to the kicking action. A capacitance sensor is arranged at the tail of the vehicle to detect the capacitance value between the sensor and the ground. The processor receives a current capacitance value detected by the capacitance sensor, and then processes the current capacitance value by using the kicking action capacitance value model. If the change characteristics of the current capacitance value within a period of time represent that the kicking action for opening the tail door of the vehicle occurs, the tail door of the vehicle is opened. The present scheme monitors a complete set of kicking actions, and is more reliable than the way of opening the tail door after the capacitance value reaches a threshold in the prior scheme, and the misjudgment situation caused by the interference of the capacitance signal does not occur.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a method and device for opening a tail door of a vehicle and a medium. BACKGROUND

[0002] The trunk of a vehicle is often used to place various larger items. Under normal circumstances, the tail door of the vehicle can be manually opened when placing items. However, when the target object is carrying something or holding a child, it is inconvenient to manually open the tail door. In this case, other methods can be used. For example, a common method for opening an electric tail door is to use a capacitive sensor to open the electric tail door of the vehicle by kicking. This allows the target object to open the trunk by sensing with the foot without moving the hand. Therefore, this way of opening the trunk is very convenient. It not only solves the problems of safety, hygiene, inconvenience and the like encountered by people in various scenarios of opening and closing the tail door, but also meets the requirements of people for safe, convenient and intelligent vehicle use. Specifically, an induction antenna is installed at the rear bumper of the vehicle to detect the capacitance value of the induction antenna relative to the ground. When the foot moves between the antenna and the ground, the capacitance value changes. When the change in the capacitance value reaches a threshold value, the vehicle is driven to open the tail door.

[0003] However, the current solution only determines whether the capacitance value reaches the threshold value. When the capacitance signal is disturbed, the tail door may be mistakenly opened, resulting in low accuracy of opening the tail door.

[0004] Therefore, how to improve the accuracy of opening the tail door of the vehicle is a problem to be solved by those skilled in the art. SUMMARY

[0005] The purpose of the present application is to provide a method and device for opening a tail door of a vehicle and a medium to improve the accuracy of opening the tail door of the vehicle.

[0006] To solve the above technical problems, the present application provides a method for opening a tail door of a vehicle, comprising:

[0007] receiving a current capacitance value detected by a capacitive sensor, wherein the capacitive sensor is arranged at the tail of the vehicle to detect the capacitance value between itself and the ground;

[0008] processing the current capacitance value using a kicking action capacitance value model, wherein the kicking action capacitance value model is established according to the change characteristics of historical capacitance values, and the historical capacitance values are the capacitance values corresponding to the kicking action for opening the tail door of the vehicle;

[0009] if the change characteristics of the current capacitance value within a period of time represent a kicking action for opening the tail door of the vehicle, then opening the tail door of the vehicle.

[0010] Preferably, the establishing the kick action capacitance value model according to the historical capacitance values comprises:

[0011] establishing a data set of the historical capacitance values;

[0012] reconstructing the data set to divide the data set into a training set and a validation set;

[0013] inputting the training set and the validation set into a recurrent neural network for training to obtain the kick action capacitance value model.

[0014] Preferably, a network structure of the recurrent neural network is a full connection layer + a GRU layer + a full connection layer; and the inputting the training set and the validation set into the recurrent neural network for training to obtain the kick action capacitance value model comprises:

[0015] inputting the training set and the validation set into the recurrent neural network to adjust training parameters and a loss function of the recurrent neural network.

[0016] Preferably, the reconstructing the data set to divide the data set into the training set and the validation set comprises:

[0017] performing a regularization processing on the data set;

[0018] dividing the data set after the regularization processing into the training set and the validation set.

[0019] Preferably, after the establishing the kick action capacitance value model, the method further comprises:

[0020] processing, by using the kick action capacitance value model, capacitance values in a period of time corresponding to a kick action of opening the tail door of the automobile, and obtaining an opening result of the tail door of the automobile;

[0021] optimizing the kick action capacitance value model according to the opening result.

[0022] Preferably, the historical capacitance values are capacitance values in a period of time corresponding to a kick action of opening the tail door of the automobile, which are detected by the capacitance sensor.

[0023] Preferably, after the opening the tail door of the automobile, the method further comprises:

[0024] if the capacitance value detected by the capacitance sensor represents that a kick action of closing the tail door of the automobile occurs, closing the tail door of the automobile.

[0025] To solve the above technical problem, the application further provides a device for opening a tail door of an automobile, comprising:

[0026] receive a current capacitance value detected by a capacitance sensor, wherein the capacitance sensor is arranged at a tail of the vehicle to detect a capacitance value between the vehicle and the ground;

[0027] process the current capacitance value by using a kick action capacitance value model, wherein the kick action capacitance value model is established according to a change feature of historical capacitance values corresponding to the kick action of opening the tail door of the vehicle;

[0028] open the tail door of the vehicle if the change feature of the current capacitance value within a period of time indicates that the kick action of opening the tail door of the vehicle occurs.

[0029] To solve the above technical problem, the application further provides a device for opening a tail door of a vehicle, comprising: a memory for storing a computer program;

[0030] a processor for implementing the steps of the method for opening the tail door of the vehicle when executing the computer program.

[0031] To solve the above technical problem, the application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method for opening the tail door of the vehicle.

[0032] The method for opening the tail door of the vehicle provided by the application requires that the processor establishes a kick action capacitance value model in advance according to a change feature of historical capacitance values corresponding to the kick action of opening the tail door of the vehicle, and the change feature of the capacitance value represents a change process of the capacitance value corresponding to the kick action. The capacitance sensor is arranged at the tail of the vehicle to detect the capacitance value between the vehicle and the ground. The processor receives a current capacitance value detected by the capacitance sensor, and then processes the current capacitance value by using the kick action capacitance value model. If the change feature of the current capacitance value within a period of time indicates that the kick action of opening the tail door of the vehicle occurs, the tail door of the vehicle is opened. The method provided by the application trains a model by using historical capacitance values corresponding to the kick action of opening the tail door of the vehicle, and then determines whether to open the tail door according to the model. The present solution monitors a complete set of kick actions, which is more reliable than the current solution of opening the tail door after simply determining that the capacitance value reaches a threshold, and does not cause misjudgment when the capacitance signal is disturbed.

[0033] The application further provides a device for opening a tail door of a vehicle and a computer readable storage medium, which correspond to the above method and have the same beneficial effects as the above method. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to illustrate the embodiments of the present application more clearly, the drawings required in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some of the embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0035] Figure 1 A flowchart of a method for opening a tail door of a vehicle according to an embodiment of the present application;

[0036] Figure 2 A structural diagram of a device for opening a tail door of a vehicle according to an embodiment of the present application;

[0037] Figure 3 A structural diagram of a device for opening a tail door of a vehicle according to another embodiment of the present application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort belong to the protection scope of the present application.

[0039] The core of the present application is to provide a method, device and medium for opening a tail door of a vehicle, so as to improve the accuracy of opening the tail door of the vehicle.

[0040] In order to make the persons skilled in the art better understand the present application, the present application will be further described in detail in the following with reference to the drawings and specific embodiments.

[0041] The present application is applied in the scenario of opening a tail door of a vehicle. Generally, an inductive antenna is installed at the rear bumper of the vehicle, which is used to detect the capacitance value of the inductive antenna relative to the ground. The type of the device for detecting the capacitance value can be arbitrarily selected, and the specific installation position is not limited. Here, the inductive antenna is taken as an example for description. When the foot moves between the inductive antenna and the ground, the capacitance value changes. The processor receives the capacitance value collected by the inductive antenna, and then controls the opening operation of the tail door according to the change of the capacitance value. At present, the tail door is opened after it is determined that the capacitance value reaches a threshold value. If the capacitance signal is disturbed at a certain moment, and the signal noise pollution is serious, the tail door of the vehicle may be opened by mistake, that is, the accuracy of the current scheme is not high. In order to solve the above technical problem, the present application provides a method for opening a tail door of a vehicle. The present scheme relates to the field of artificial intelligence technology, and more specifically, relates to a detection method for electric tail door kick sensing opening based on a recurrent neural network. Figure 1A flow chart of a method for opening a tail door of a vehicle is provided in the embodiments of the present application. As shown in the figure, the method comprises the following steps:

[0042] S10: receiving a current capacitance value detected by the capacitance sensor.

[0043] The capacitance sensor is arranged at the tail of the vehicle to detect the capacitance value between itself and the ground. As mentioned above, the capacitance sensor can be an induction antenna, and the number thereof can be determined according to actual conditions. In order to more accurately detect the kicking action, a plurality of capacitance sensors can be arranged at the tail of the vehicle. In addition, in order to ensure that the action is a human action and not a change in the capacitance value caused by other objects, an infrared sensor can be used in cooperation with the capacitance sensor. The detection time of the capacitance sensor is not required. Generally, the detection function of the capacitance sensor is started when the vehicle is completely stationary and locked, or the capacitance sensor is always detected, but the processor does not control the tail door. Because the change characteristics of the capacitance value need to be obtained, a plurality of capacitance values need to be obtained, that is, the process of detecting the current capacitance value by the capacitance sensor and the process of receiving the current capacitance value by the processor can be considered as continuous.

[0044] S11: processing the current capacitance value by using a kicking action capacitance value model.

[0045] The kick action capacitance value model is established according to the change characteristics of historical capacitance values, and the historical capacitance values are the capacitance values corresponding to the kick action for opening the tail door of the automobile. The historical capacitance values can be capacitance value data collected by the sensor of the automobile. The change characteristics of the capacitance values corresponding to a complete kick action are recorded, and a kick action capacitance value model capable of controlling the kick action for opening the tail door is trained according to the change characteristics. The kick action capacitance value model can effectively determine whether a kick action exists, thereby determining whether the tail door should be opened. The steps for constructing the kick action capacitance value model are as follows: 1. Construct a database, specifically, collect a data set D1 of the capacitance values corresponding to the kick action within a certain period of time through the capacitance sensor. 2. Preprocess the data in the data set, reconstruct the data set, label the data set, and divide the data set D1 into a training set and a validation set according to a ratio of 7:3. The data set D1 of multiple kick actions within a certain period of time can also be subjected to a regularization operation, and then the regularized data set is labeled according to whether there is a kick action. The labels include 0 and 1, 0 representing no kick action at this moment, and 1 representing a kick action at this moment. 3. Train a recurrent neural network model for controlling the kick action for opening the electric tail door. The training set and the validation set are input into the recurrent neural network for training. The process of training the recurrent neural network is as follows: first, design the network structure of the recurrent neural network model, which can be a fully connected layer + a GRU layer + a fully connected layer; then input the labeled training set and the validation set into the network for training, and take the accuracy of the kick action for opening the tail door as an indicator; through a large number of experiments, adjust the training parameters, loss function, etc., and finally train a model with the best performance in all aspects, which can fully control the kick action for opening the electric tail door. 4. Verify the opening effect of the kick action capacitance value model on the actual kick action for opening the electric tail door. Specifically, verify the effectiveness of the above model on the test set, apply the trained model to the test set, and finally perform a kick action to actually detect the effect of the model. Alternatively, the network architecture is composed of a sequence input layer, a fully connected layer, a GRU layer, and a fully connected layer. The sequence input layer specifies that the input data dimension is 14 and the output feature dimension is 2. The number of hidden units of the GRU layer is 12, and the feature dimension of the fully connected layer is 12. The training parameters are set as follows: the solver is set to Adam, the maximum number of iterations is set to 500, and the learning rate is set to 0.001. The method for training the model in this example is only one of the embodiments of the present application, and does not limit other schemes of the present application. The loss function is used to adjust and update the weight parameters and the offset parameters, complete learning, determine the parameters of the GRU model, and improve the accuracy of the model.

[0046] S12: Determine whether the change characteristics of the current capacitance value within a period of time represent a kick action for opening the tail door of the automobile. If so, proceed to step S13.

[0047] S13: Open the tail door of the automobile.

[0048] The current capacitance value collected by the capacitance sensor is processed by the trained model. If the change feature of the current capacitance value in a period of time represents that the kick action of opening the tail door of the automobile occurs, the motor is driven to open the tail door of the automobile. In fact, the change feature of the capacitance value is the change of the capacitance value in this period of time. The processor continuously receives the capacitance value detected by the capacitance sensor, and can determine whether the kick action of opening the tail door of the automobile occurs according to the change of the plurality of capacitance values in a period of time. In addition, after the tail door of the automobile is opened, the capacitance value can be continuously detected. If the capacitance value at this time represents that the kick action of closing the tail door of the automobile occurs, the motor is continuously driven to close the tail door of the automobile.

[0049] The method for opening the tail door of the automobile provided in the embodiment of the application needs to establish the kick action capacitance value model in advance according to the change feature of the historical capacitance value. The historical capacitance value is the capacitance value corresponding to the kick action of opening the tail door of the automobile, and the change feature of the capacitance value represents the change process of the capacitance value corresponding to the kick action. The capacitance sensor is arranged at the tail of the automobile to detect the capacitance value between itself and the ground. The processor receives the current capacitance value detected by the capacitance sensor, and then processes the current capacitance value by using the kick action capacitance value model. If the change feature of the current capacitance value in a period of time represents that the kick action of opening the tail door of the automobile occurs, the tail door of the automobile is opened. The method provided in the embodiment of the application trains the model by using the historical capacitance value corresponding to the kick action of opening the tail door of the automobile, and then determines whether the tail door is opened according to the model. The present scheme monitors a complete set of kick actions, and is more reliable than the current scheme in which the tail door is opened after the capacitance value reaches a threshold. The present scheme will not misjudge when the capacitance signal is disturbed.

[0050] The embodiment of the application provides a specific scheme for establishing a kick action capacitance value model. The method for establishing the kick action capacitance value model according to the historical capacitance value includes: establishing a data set of the historical capacitance value; reconstructing the data set to divide the data set into a training set and a verification set; and inputting the training set and the verification set into a recurrent neural network for training to obtain the kick action capacitance value model. In addition, the network structure of the recurrent neural network can be set as a fully connected layer + a GRU layer + a fully connected layer. The method for inputting the training set and the verification set into the recurrent neural network for training to obtain the kick action capacitance value model includes: inputting the training set and the verification set into the recurrent neural network to adjust the training parameters and the loss function of the recurrent neural network. The method provided in the embodiment can obtain a model with better effect. The method for reconstructing the data set to divide the data set into the training set and the verification set includes: performing regularization processing on the data set; and dividing the data set after the regularization processing into the training set and the verification set. When the training data is not enough, overfitting often occurs. Regularization is to introduce additional information into the original model at this time, so as to prevent overfitting and improve the generalization performance of the model.

[0051] The effect of the theoretically derived foot kicking action capacitance value model in actual application is not necessarily very ideal, and in the above embodiment, after the foot kicking action capacitance value model is established, the method further includes: using the foot kicking action capacitance value model to process the capacitance values in a period of time corresponding to the foot kicking action of opening the tail door of the automobile, and obtaining an opening result of the tail door of the automobile; and optimizing the foot kicking action capacitance value model according to the opening result. The method provided in the embodiment of the application optimizes the foot kicking action capacitance value model through actual conditions, thereby ensuring the accuracy of the foot kicking action capacitance value model in actual application.

[0052] After the tail door of the automobile is opened, the article is placed or taken out, and then the tail door of the automobile needs to be closed. Therefore, as an optional solution, after the tail door of the automobile is opened, the method further includes: if the capacitance value detected by the capacitance sensor represents that a foot kicking action of closing the tail door of the automobile occurs, the tail door of the automobile is closed. Here, the capacitance value representing that the foot kicking action of closing the tail door of the automobile occurs can be the capacitance value in a period of time detected, and the way of opening the tail door of the automobile is the same as in the present application. A model for closing the tail door of the automobile is trained, and the capacitance value collected by the capacitance sensor is processed through the model. The tail door of the automobile can also be simply closed after the capacitance value reaches a threshold. Here, the way of determining whether the tail door of the automobile is closed is not limited.

[0053] In the above embodiment, the method of opening the tail door of the automobile is described in detail, and the present application further provides an embodiment of a device for opening the tail door of the automobile. It should be noted that the embodiment of the device part is described from two angles, one is based on the functional module, and the other is based on the hardware.

[0054] Based on the functional module, the embodiment provides a device for opening the tail door of the automobile, Figure 2 The structural diagram of the device for opening the tail door of the automobile provided in the embodiment of the present application is shown in Figure 2 The device includes:

[0055] The receiving module 10 is configured to receive a current capacitance value detected by a capacitance sensor, wherein the capacitance sensor is arranged at the tail of the automobile to detect the capacitance value between itself and the ground;

[0056] The processing module 11 is configured to process the current capacitance value by using a foot kicking action capacitance value model, wherein the foot kicking action capacitance value model is established according to the change characteristics of historical capacitance values, and the historical capacitance values are capacitance values corresponding to the foot kicking action of opening the tail door of the automobile;

[0057] The opening module 12 is configured to open the tail door of the automobile if the change characteristics of the current capacitance value in a period of time represent that the foot kicking action of opening the tail door of the automobile occurs.

[0058] Since the embodiments of the device part correspond to the embodiments of the method part, the embodiments of the device part are described in the description of the embodiments of the method part, and will not be described here.

[0059] The device for opening the tail door of the automobile provided in the embodiment corresponds to the method described above, and thus has the same beneficial effects as the method.

[0060] From the perspective of hardware, the embodiment provides another device for opening the tail door of the automobile, Figure 3 The structural diagram of the device for opening the tail door of the automobile provided in another embodiment of the present application is shown in Figure 3 The device for opening the tail door of the automobile includes a memory 20 for storing a computer program.

[0061] A processor 21 is configured to execute the computer program to implement the steps of the method for opening the tail door of the automobile mentioned in the above embodiments.

[0062] The processor 21 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one of a hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 21 can also include a main processor and a coprocessor. The main processor is a processor for processing data in a wake-up state, also known as a central processing unit (CPU). The coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 can be integrated with a graphics processor (GPU) that is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 can also include an artificial intelligence (AI) processor for processing machine learning-related computing operations.

[0063] The memory 20 can include one or more computer-readable storage media. The memory 20 can also include high-speed random access memory and non-volatile, computer-readable storage media such as one or more magnetic disk storage devices, flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, wherein the computer program is loaded and executed by the processor 21 and can implement the related steps of the method for opening the tail door of the vehicle disclosed in any of the preceding embodiments. In addition, the resources stored in the memory 20 can also include an operating system 202 and data 203, etc., and the storage mode can be temporary storage or permanent storage. The operating system 202 can include Windows, Unix, Linux, etc. The data 203 can include but is not limited to data related to the method for opening the tail door of the vehicle, etc.

[0064] In some embodiments, the device for opening the tail door of the vehicle can further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0065] Those skilled in the art can understand that the structure shown in the figure does not constitute a limitation on the device for opening the tail door of the vehicle, and can include more or fewer components than those shown in the figure.

[0066] The device for opening the tail door of the vehicle provided by the embodiments of the present application includes a memory and a processor, and the processor can implement the following method when executing the program stored in the memory: the method for opening the tail door of the vehicle.

[0067] The device for opening the tail door of the vehicle provided by the embodiments of the present application corresponds to the above method, and therefore has the same beneficial effects as the above method.

[0068] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, and the computer program is executed by the processor to implement the steps as described in the above method embodiment.

[0069] It can be understood that if the method in the above embodiment is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and performs all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0070] The computer readable storage medium provided by the embodiment has the same beneficial effects as the above method.

[0071] The method, device and medium for opening the tail door of the automobile are described in detail above. The embodiments in the specification are described in a progressive manner, and each embodiment mainly describes the differences from other embodiments. The same or similar parts of each embodiment can be referred to. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the related parts are described in the method part. It should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, the present application can be improved and modified, and these improvements and modifications also fall within the protection scope of the claims of the present application.

[0072] It should be further noted that in the specification, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or equipment including the above element.

Claims

1. A method of opening a tailgate of a vehicle, characterized by, The method comprises: receiving a current capacitance value detected by a capacitance sensor, wherein the capacitance sensor is arranged at the tail of the automobile to detect the capacitance value between itself and the ground; processing the current capacitance value by using a foot-kicking action capacitance value model, wherein the foot-kicking action capacitance value model is established according to the change characteristics of historical capacitance values corresponding to the foot-kicking action of opening the tail door of the automobile; if the change characteristics of the current capacitance value within a period of time represent that the foot-kicking action of opening the tail door of the automobile has occurred, then opening the tail door of the automobile; establishing the foot-kicking action capacitance value model according to the historical capacitance values comprises: establishing a data set of the historical capacitance values; reconstructing the data set to divide the data set into a training set and a verification set; inputting the training set and the verification set into a recurrent neural network for training to obtain the foot-kicking action capacitance value model; the network structure of the recurrent neural network is a fully connected layer + a GRU layer + a fully connected layer; the inputting of the training set and the verification set into the recurrent neural network for training to obtain the foot-kicking action capacitance value model comprises: inputting the training set and the verification set into the recurrent neural network to adjust the training parameters and the loss function of the recurrent neural network; the reconstruction of the data set to divide the data set into the training set and the verification set comprises: performing regularization processing on the data set; dividing the data set after the regularization processing into the training set and the verification set; after the establishment of the foot-kicking action capacitance value model, further comprising: processing the capacitance value within a period of time corresponding to the foot-kicking action of opening the tail door of the automobile by using the foot-kicking action capacitance value model, and obtaining the opening result of the tail door of the automobile; optimizing the foot-kicking action capacitance value model according to the opening result.

2. The method of opening a tailgate of a vehicle according to claim 1, wherein, The historical capacitance values are the capacitance values within a period of time corresponding to the foot-kicking action of opening the tail door of the automobile detected by the capacitance sensor.

3. The method of opening a tailgate of a vehicle of claim 1, wherein, after the opening of the tail door of the automobile, further comprising: if the capacitance value detected by the capacitance sensor represents that the foot-kicking action of closing the tail door of the automobile has occurred, then closing the tail door of the automobile.

4. A device for opening a tailgate of a vehicle, characterized in that The method comprises: a receiving module configured to receive a current capacitance value detected by a capacitance sensor, wherein the capacitance sensor is arranged at the tail of the automobile to detect the capacitance value between itself and the ground; a processing module configured to process the current capacitance value by using a foot-kicking action capacitance value model, wherein the foot-kicking action capacitance value model is established according to the change characteristics of historical capacitance values corresponding to the foot-kicking action of opening the tail door of the automobile; an opening module configured to open the tail door of the automobile if the change characteristics of the current capacitance value within a period of time represent that the foot-kicking action of opening the tail door of the automobile has occurred; establishing the foot-kicking action capacitance value model according to the historical capacitance values comprises: establishing a data set of the historical capacitance values; reconstructing the data set to divide the data set into a training set and a verification set; inputting the training set and the verification set into a recurrent neural network for training to obtain the foot-kicking action capacitance value model; The network structure of the recurrent neural network is full connection layer+GRU layer+full connection layer; the inputting the training set and the verification set into the recurrent neural network for training to obtain the kick action capacitance value model comprises: inputting the training set and the verification set into the recurrent neural network to adjust the training parameters and the loss function of the recurrent neural network; the reconstruction of the data set to divide the data set into a training set and a verification set comprises: normalizing the data set; dividing the data set after the normalization into the training set and the verification set; is also used for: adopting the kick action capacitance value model to process the capacitance value in a period of time corresponding to the kick action of opening the automobile tail door, and obtaining the opening result of the automobile tail door; optimizing the kick action capacitance value model according to the opening result.

5. A device for opening a tailgate of a vehicle, characterized in that comprising a memory for storing a computer program; a processor for executing the computer program to realize the steps of the method for opening the automobile tail door according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer program is stored on the computer readable storage medium, and the computer program is executed by the processor to realize the steps of the method for opening the automobile tail door according to any one of claims 1 to 3.

Images