Seat adjustment method, electronic device, vehicle, storage medium and computer product

Abstract

The application discloses a seat adjustment method, an electronic device, a vehicle, a storage medium and a computer product, relates to the technical field of vehicles, and the seat adjustment method is applied to the electronic device, the electronic device comprises a wireless signal transmitting module, and specifically comprises the following steps: controlling the wireless signal transmitting module to emit a plurality of wireless detection signals to the cabin of the vehicle; generating a first target living body image containing a target occupant based on the plurality of wireless detection signals, and extracting first image features of the first target living body image; determining a first sitting posture type of the target occupant according to the first image features, and determining a target seat adjustment parameter according to the first sitting posture type; and adjusting a target seat where the target occupant is located according to the target seat adjustment parameter, so that the target seat enters a target seat state matched with the first sitting posture type. The application achieves the technical effect that the electronic device can accurately adjust the seat based on the sitting posture of the occupant.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a seat adjustment method, an electronic device, a vehicle, a storage medium and a computer program product. BACKGROUND

[0002] With the continuous development of the automobile industry, new energy vehicles have become the preferred means of transportation for more and more people in their daily travel.

[0003] In order to improve the experience of passengers as much as possible when riding new energy vehicles, technicians usually configure a camera device in the cabin, so as to detect the sitting posture of the passenger on the seat through the camera device, and adjust the seat according to the sitting posture, so that the seat can be more fitted to the sitting posture of the passenger.

[0004] However, since the camera device is easily affected by environmental light during the process of shooting the interior of the cabin, the image data obtained by the camera device is likely to be of low quality, which makes it difficult for the vehicle to accurately identify the sitting posture of the passenger, and thus reduces the accuracy of the vehicle in adjusting the seat. SUMMARY

[0005] The main purpose of the present application is to provide a seat adjustment method, an electronic device, a vehicle, a storage medium and a computer program product, which aims to solve the technical problem that the vehicle is difficult to accurately identify the sitting posture of the passenger in the related art.

[0006] To achieve the above-mentioned purpose, the present application provides a seat adjustment method, which is applied to an electronic device, the electronic device comprises a wireless signal emitting module, and the seat adjustment method comprises:

[0007] controlling the wireless signal emitting module to emit a plurality of wireless detection signals to the cabin of the vehicle;

[0008] generating a first target living body image containing a target passenger based on the plurality of wireless detection signals, and extracting a first image feature of the first target living body image;

[0009] determining a first sitting posture type of the target passenger according to the first image feature, and determining a target seat adjustment parameter according to the first sitting posture type;

[0010] adjusting a target seat where the target passenger is located according to the target seat adjustment parameter, so that the target seat enters a target seat state matched with the first sitting posture type.

[0011] In an embodiment, the step of determining a target seat adjustment parameter according to the first sitting posture type comprises:

[0012] determining a target seat corresponding to the target passenger, and detecting a current seat state of the target seat;

[0013] determining a target seat state according to the first sitting type, and determining a target seat adjustment parameter based on the current seat state and the target seat state.

[0014] In an embodiment, after the step of determining the target seat corresponding to the target passenger, the method further comprises:

[0015] detecting a door of the vehicle, and determining a first aisle size corresponding to the target seat when the door is detected to be in an open state;

[0016] determining a first seat position adjustment parameter according to the first aisle size and a preset target aisle size, and adjusting the target seat according to the first seat position adjustment parameter, so that an aisle size corresponding to the target seat is switched from the first aisle size to the target aisle size.

[0017] In an embodiment, after the step of adjusting the target seat in which the target passenger is located according to the target seat adjustment parameter, the method further comprises:

[0018] generating a second target living body image containing the target passenger based on a plurality of the wireless detection signals, and extracting a second image feature of the second target living body image;

[0019] determining a second sitting type corresponding to the target passenger according to the second image feature, and determining a function control instruction corresponding to the second sitting type, wherein the function control instruction is a control instruction for controlling a target function module configured in the vehicle and needed to be adjusted by the target passenger;

[0020] controlling the target function module according to the function control instruction, so that the target function module enters a function running state matched with the function control instruction.

[0021] In an embodiment, the step of determining the function control instruction corresponding to the second sitting type comprises:

[0022] determining a preset sitting type matched with the second sitting type;

[0023] determining a preset function instruction matched with the preset sitting type as the function control instruction corresponding to the second sitting type.

[0024] In an embodiment, the step of generating a first target living body image containing the target passenger based on a plurality of the wireless detection signals comprises:

[0025] detecting initial channel state information matched by each of the plurality of wireless detection signals, and performing cleaning processing on each of the initial channel state information to obtain complete channel state information;

[0026] screening each of the complete channel state information to determine target channel state information, and generating a first target living body image based on each of the target channel state information, wherein the target channel state information is channel state information corresponding to a wireless detection signal detecting a target passenger.

[0027] In an embodiment, the step of detecting initial channel state information matched by each of the plurality of wireless detection signals comprises:

[0028] detecting wireless reception signals matched by each of the plurality of wireless detection signals;

[0029] determining signal change ratios between each of the plurality of wireless detection signals and the matched wireless reception signals;

[0030] determining initial channel state information matched by each of the plurality of wireless detection signals based on each of the signal change ratios.

[0031] In an embodiment, the step of generating a first target living body image based on each of the target channel state information comprises:

[0032] extracting one-dimensional vector features contained in each of the target channel state information;

[0033] fusing each of the one-dimensional vector features to obtain two-dimensional vector features, and generating a first target living body image based on the two-dimensional vector features.

[0034] In addition, to achieve the above object, the present application further provides an electronic device, which comprises a wireless signal transmitting module, a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the seat adjustment method as described above.

[0035] In addition, to achieve the above object, the present application further provides a vehicle comprising the electronic device as described above.

[0036] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the seat adjustment method as described above.

[0037] In addition, to achieve the above object, the application further provides a computer program product, which comprises a computer program, and the computer program, when executed by a processor, implements the steps of the seat adjustment method as described above.

[0038] The seat adjustment method provided by the embodiments of the application is applied to an electronic device, and the electronic device comprises a wireless signal emitting module. The seat adjustment method comprises the following steps: controlling the wireless signal emitting module to emit a plurality of wireless detection signals to a cabin of a vehicle; generating a first target living body image containing a target occupant based on the plurality of wireless detection signals, and extracting a first image feature of the first target living body image; determining a first sitting posture type of the target occupant according to the first image feature, and determining a target seat adjustment parameter according to the first sitting posture type; and adjusting a target seat where the target occupant is located according to the target seat adjustment parameter, so that the target seat enters a target seat state matching the first sitting posture type.

[0039] In the embodiments, during the running of the electronic device, the electronic device first controls a wireless signal emitting module configured by the electronic device to emit a plurality of wireless detection signals to the cabin of the vehicle. Then, the electronic device generates a first target living body image containing a target occupant in the cabin based on the plurality of wireless detection signals, and extracts a first image feature contained in the first target living body image. Then, the electronic device determines a first sitting posture type of the target occupant in the target seat according to the first image feature, and determines a target seat adjustment parameter for adjusting the target seat according to the first sitting posture type. Finally, the electronic device adjusts the target seat according to the target seat adjustment parameter, so that the target seat enters a target seat state matching the first sitting posture type adopted by the target occupant.

[0040] In this way, the application solves the technical problem that the vehicle is difficult to accurately identify the sitting posture of the occupant in the related art. That is, the application can accurately identify the sitting posture type of the target occupant in the cabin of the vehicle by using the characteristic that the wireless detection signal will generate different channel state information when contacting a living body. Then, the seat adjustment parameter is determined according to the sitting posture type, so that the target seat is adjusted to the target seat state matching the sitting posture type according to the seat adjustment parameter. Thus, the situation that the camera device is difficult to accurately identify the sitting posture of the occupant due to the influence of the ambient light is avoided, and the technical effect that the electronic device can accurately adjust the seat based on the sitting posture of the occupant is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0041] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate one embodiment consistent with the application and, together with the description, serve to explain the principles of the application.

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings are provided only for purposes of illustration and are not intended to limit the present application.

[0043] Figure 1 The structural schematic diagram of the electronic device related to the seat adjustment method of one embodiment of the present application is shown in the following figure:

[0044] Figure 2 The flowchart provided by the seat adjustment method of one embodiment of the present application is shown in the following figure:

[0045] Figure 3 The first target living body image related to the seat adjustment method of one embodiment of the present application is shown in the following figure:

[0046] Figure 4 The schematic diagram of the brief flowchart of the seat adjustment method of the present application is shown in the following figure:

[0047] Figure 5 The module structure schematic diagram of the vehicle early warning device of the embodiment of the present application is shown in the following figure:

[0048] Figure 6 The device structure schematic diagram of the hardware running environment related to the seat adjustment method in the embodiment of the present application is shown in the following figure.

[0049] The purpose realization, functional features and advantages of the present application will be further explained with reference to the accompanying drawings in combination with the embodiments. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0051] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the accompanying drawings and specific embodiments.

[0052] In the present embodiment, for the convenience of description, please refer to Figure 1 , Figure 1 The structural schematic diagram of the electronic device related to the seat adjustment method of one embodiment of the present application is shown in the following figure: Figure 1As shown, the electronic device internally configured with a wireless signal transmission module, or the mobile terminal, data storage control terminal, PC and other terminals connected with the electronic control unit of the electronic device as the execution subject are described. Among them, the wireless signal transmission module includes TCAM (Telematics & Connectivity Antenna Module, intelligent antenna module) and DHU (Digital Cockpit Head Unit, digital cockpit unit) two parts, wherein the TCAM includes the first Wifi Service, Core Service, MCU (Microcontroller Unit, microcontroller unit), and the same, the DHU includes the second Wifi Service, QNX Service (QNX virtual machine), AndroidService (Android subsystem), Algorithm Service (data processing unit) and MCU.

[0053] Based on the above electronic device, the overall concept of the seat adjustment method of the present application is proposed.

[0054] With the continuous development of the automobile industry, new energy vehicles have become the preferred means of transportation for more and more people in their daily travel. In order to improve the experience of passengers as much as possible when riding new energy vehicles, technicians usually configure a camera device in the cabin, so as to detect the sitting posture of the passenger on the seat through the camera device, and adjust the seat according to the sitting posture, so that the seat can be more fitted with the sitting posture of the passenger. However, since the camera device is easily affected by the ambient light during the process of shooting the interior of the cabin, thus, it is easy to appear that the image data obtained by the camera device is of low quality, thereby causing the vehicle to be difficult to accurately identify the sitting posture of the passenger, and further causing the accuracy of the seat adjustment of the vehicle to be reduced.

[0055] In view of the above phenomenon, the seat adjustment method provided by the present application is applied to an electronic device, the electronic device includes a wireless signal transmission module, and the seat adjustment method includes: controlling the wireless signal transmission module to transmit a plurality of wireless detection signals to the cabin of a vehicle; generating a first target living body image containing a target passenger based on a plurality of wireless detection signals, and extracting a first image feature of the first target living body image; determining a first sitting posture type of the target passenger according to the first image feature, and determining a target seat adjustment parameter according to the first sitting posture type; adjusting a target seat where the target passenger is located according to the target seat adjustment parameter, so that the target seat enters a target seat state matched with the first sitting posture type.

[0056] Therefore, the application solves the technical problem that the vehicle cannot accurately identify the sitting posture of the occupant in the related art, that is, the application can accurately identify the sitting posture type of the target occupant in the vehicle cabin by using the characteristic that the wireless detection signal will generate different channel state information when it contacts a living body, so as to determine the seat adjustment parameter according to the sitting posture type, and adjust the target seat to the target seat state matched with the sitting posture type according to the seat adjustment parameter, thereby avoiding the situation that the camera device cannot accurately identify the sitting posture of the occupant due to the influence of the ambient light, and achieving the technical effect that the electronic device can accurately adjust the seat based on the sitting posture of the occupant.

[0057] Based on the overall concept of the seat adjustment method, the embodiment of the application provides a seat adjustment method, which refers to Figure 2 , Figure 2 FIG. 1 is a flowchart of a first embodiment of the seat adjustment method of the application.

[0058] In this embodiment, the seat adjustment method is applied to an electronic device, and the electronic device comprises a wireless signal emitting module. The seat adjustment method comprises steps S10-S40:

[0059] Step S10: controlling the wireless signal emitting module to emit a plurality of wireless detection signals to the cabin of the vehicle;

[0060] Step S20: generating a first target living body image containing a target occupant based on the plurality of wireless detection signals, and extracting a first image feature of the first target living body image;

[0061] It should be noted that the wireless detection signal can be a Wifi signal. In addition, the first target living body image is image data containing the living body detection target generated by the electronic device after detecting the living body detection target in the vehicle cabin through the Wifi signal. In addition, the first image feature is an image feature contained in the first target living body image, which can reflect the position, sitting posture and other information of the detected living body detection target. It can be understood that the living body detection target can be a target occupant detected in the cabin or entering the cabin through the door.

[0062] In the embodiment, the electronic device, when running, firstly calls the wireless signal transmitting module configured by itself to continuously transmit multiple wireless detection signals into the vehicle cabin, then the electronic device controls the wireless signal transmitting module to receive wireless reflection signals generated by the multiple wireless detection signals respectively, the wireless signal transmitting module further obtains multiple initial channel state information according to each wireless detection signal and each wireless reflection signal, and inputs the multiple initial channel state information into the data processing unit configured by itself, the data processing unit calls the preset convolutional neural network model to generate a first target living body image containing a target occupant existing in the vehicle cabin according to the received initial channel state information, the convolutional neural network model performs phase separation processing on the first target living body image to obtain multiple sub-living body images, and calls the encoder to perform encoding processing on the multiple sub-living body images to identify the convolutional feature weights corresponding to the multiple sub-living body images respectively, the convolutional neural network model further fuses the convolutional feature weights to obtain posture fusion data, performs inference merging operation on the posture fusion data, and performs sampling processing on the posture fusion data after inference merging to extract the first image feature.

[0063] Exemplarily, for example, the electronic device first controls the wireless transmission module configured by itself to control the TCAM in the wireless transmission module to start, so that the first Wifi Service in the TCAM transmits a plurality of first Wifi signals to the vehicle cabin, and the first Wifi Service further receives a first reflection signal generated by each of the plurality of first Wifi signals, so as to determine initial CSI (Channel State Information) data corresponding to each of the plurality of first Wifi signals according to each first reflection signal. The TCAM further inputs each of the obtained initial CSI data to the DHU in the wireless transmission module, so that each of the initial CSI data enters the data processing unit Algorithm Service configured in the DHU; at the same time, the electronic device controls the DHU in the wireless transmission module to start, so that the second Wifi Service in the DHU transmits a plurality of second Wifi signals to the vehicle cabin, and the second Wifi Service further receives a second reflection signal generated by each of the plurality of second Wifi signals, so as to determine initial CSI data corresponding to each of the plurality of second Wifi signals according to each second reflection signal. The DHU further inputs each of the obtained initial CSI data to the data processing unit Algorithm Service configured by itself, and the Algorithm Service inputs each of the CSI data to the preset RCNN (Regions with Convolutional Neural Networks) after obtaining each of the initial CSI data. The RCNN generates first target image data containing a target occupant located in the cabin based on each of the initial CSI data. The RCNN performs phase separation on the first target image data to obtain a plurality of sub-living body images, and calls an encoder to perform encoding processing on each of the plurality of sub-living body images to identify convolution feature weights corresponding to each of the plurality of sub-living body images. The RCNN further fuses each of the obtained convolution feature weights to obtain posture fusion preliminary data. The RCNN performs inference operation through 8-bit 3-channel RGB reshape to merge the posture fusion preliminary data into 24-bit data. The RCNN further performs upsampling encoding operation and downsampling decoding operation on the 24-bit data in sequence to output a 3-channel image. Finally, the 3-channel image is determined as image features corresponding to the first target living body image.

[0064] It should be noted that in the embodiment and another embodiment, before controlling the wireless transmission module, the electronic device can also control the QNX virtual machine (QNX Service) configured in the DHU to initialize, so as to start the second Wifi Service and the Android subsystem (Android Service) in the DHU through the QNX virtual machine, and the electronic device also controls the Socket communication between the TCAM and the DHU to determine that the TCAM can send the obtained initial CSI data to the Algorithm Service in the DHU.

[0065] In addition, in the embodiment and another embodiment, after controlling the TCAM to start, the electronic device also needs to control the Core Service configured in the TCAM and the QNX virtual machine configured in the DHU to detect the communication state, so as to initiate a re-communication request in time when the heartbeat communication between the TCAM and the DHU is interrupted.

[0066] In this way, the vehicle can identify the target occupant in the vehicle cabin through the multiple wireless detection signals and generate the first target living body image of the target occupant by calling the wireless transmission module to transmit multiple wireless detection signals to the cabin, so as to avoid the interference of ambient light when detecting the target occupant, and extract the first image feature reflecting the position and posture of the target occupant from the first target living body image, and then accurately identify the posture of the target occupant on the target seat.

[0067] In a feasible implementation manner, the step of generating the first target living body image containing the target occupant based on the multiple wireless detection signals can specifically include steps S201-S202.

[0068] Step S201: detecting the initial channel state information matched by each of the multiple wireless detection signals, and performing cleaning processing on each of the initial channel state information to obtain complete channel state information;

[0069] Step S202: screening each of the complete channel state information to determine target channel state information, and generating a first target living body image based on each of the target channel state information, wherein the target channel state information is the channel state information corresponding to the wireless detection signal of the target occupant.

[0070] It should be noted that the initial channel state information is CSI data that has not been screened and cleaned. In addition, the complete channel state information is CSI data that has been cleaned and filtered, and does not contain abnormal values. In addition, the target channel state information is CSI data corresponding to the Wifi signal of the living body detection target detected to exist around the vehicle. It can be understood that the CSI data is a series of complex decimal sequences, which can represent the signal wave ratio between the wireless detection signal and the corresponding wireless received signal.

[0071] In this embodiment, after the electronic device controls the wireless signal transmitting module to transmit a plurality of wireless detection signals to the vehicle cabin, the electronic device further controls the wireless signal transmitting module to receive a plurality of wireless reflection signals respectively generated by the plurality of wireless detection signals, and controls the wireless signal transmitting module to obtain a plurality of initial channel state information respectively matched with the plurality of wireless detection signals according to the received plurality of wireless detection signals and the plurality of wireless reflection signals. The electronic device further controls the wireless signal transmitting module to input each initial channel state information to the data processing unit arranged in the electronic device, so that the data processing unit reads the initial amplitude parameter and the initial phase parameter respectively contained in each initial channel state information. The data processing unit performs phase unfolding operation on the initial amplitude parameter and the initial phase parameter. The data processing unit further performs filtering elimination operation on the initial amplitude parameter and the initial phase parameter after phase unfolding, so as to eliminate abnormal values respectively contained in the initial amplitude parameter and the initial phase parameter, and obtain a plurality of target amplitude parameters and a plurality of target phase parameters. The data processing unit fuses each target amplitude parameter and the target phase parameter respectively matched with the target amplitude parameter, so as to obtain a plurality of complete channel state information not containing abnormal values. Then, the data processing unit reads the storage module arranged in the electronic device to obtain the standard channel state information corresponding to the wireless detection signal detecting the non-living body detection target. The data processing unit compares each complete channel state information obtained with the standard channel state information to obtain a plurality of comparison results. The data processing unit reads the plurality of comparison results to determine whether there is a target comparison result in which the complete channel state information and the standard channel state information are inconsistent. When it is determined that the target comparison result exists, the data processing unit determines the complete channel state information corresponding to the target comparison result as the target channel state information corresponding to the wireless detection signal detecting the target occupant. The data processing unit further calls the convolutional neural network to generate a first target living body image containing the target living body existing in the vehicle cabin based on the target channel state information.

[0072] For example, the electronic device controls the first Wifi Service to continuously transmit a plurality of first Wifi signals into the vehicle cabin, and controls the first Wifi Service to continuously receive a first reflection signal generated by each of the plurality of first Wifi signals, and determines initial CSI data matched with each of the plurality of first Wifi signals based on each first reflection signal and each first Wifi signal. Meanwhile, the electronic device controls the second Wifi Service to continuously transmit a plurality of second Wifi signals into the vehicle cabin, and controls the second Wifi Service to continuously receive a second reflection signal generated by each of the plurality of second Wifi signals, and determines initial CSI data matched with each of the plurality of second Wifi signals based on each second reflection signal and each second Wifi signal. The electronic device further controls the TCAM and the DHU to input the initial CSI data obtained by each of the TCAM and the DHU to the data processing unit Algorithm Service configured in the DHU. The Algorithm Service extracts initial amplitude parameters and initial phase parameters included in each of the initial CSI data, and performs phase unfolding processing on the initial amplitude parameters and the initial phase parameters, so that the unfolded amplitude curve and the unfolded phase curve are both restored to continuous curves. Meanwhile, the Algorithm Service performs median filtering and uniform filtering processing on the unfolded initial amplitude parameters and the unfolded initial phase parameters to eliminate abnormal values in the time and frequency domains of the unfolded initial amplitude parameters and the unfolded initial phase parameters, thereby obtaining target amplitude parameters and target phase parameters in which target abnormal values are eliminated. The Algorithm Service fuses each target amplitude parameter with a target phase parameter matched therewith, thereby obtaining complete CSI data in which abnormal values are not included. Then, the Algorithm Service reads a storage module configured in the electronic device to obtain a preset standard CSI data corresponding to a non-living detection target when a Wifi signal is detected. The Algorithm Service compares each complete CSI data with the standard CSI data to obtain a plurality of comparison results. The Algorithm Service determines target comparison results in which the comparison results included in the plurality of comparison results are inconsistent between the complete CSI data and the standard CSI data, and screens a plurality of Wifi signals based on the plurality of target comparison results, thereby determining a target Wifi signal corresponding to the target comparison result as a target Wifi signal detecting a target occupant, and determining complete CSI data corresponding to the target Wifi signal as target CSI data capable of generating a first target living body image including the target occupant.The Algorithm Service calls the RCNN configured by itself to generate a first target living body image containing a target passenger existing in the vehicle cabin based on the target CSI data of each target.

[0073] It should be noted that the initial CSI data has problems of random drift and inversion of amplitude and phase. Therefore, without denoising the initial CSI data, the abnormal values contained in the initial CSI data will have a certain impact on the final detection result. In addition, the amplitude and phase in the initial CSI data can be calculated, and during the calculation of the amplitude and phase, the phase and amplitude exceeding the preset function range will be folded, resulting in discontinuity of the phase and amplitude. Therefore, a phase unfolding operation is needed to restore each phase and amplitude to a continuous state. It can be understood that the specific calculation process of the phase unfolding operation is prior art, and therefore will not be described here. In addition, the specific process of median filtering and uniform filtering of the unfolded phase value and amplitude parameter by the Algorithm Service is prior art, and therefore will not be described here either.

[0074] Therefore, the vehicle can identify the target passenger located in the vehicle cabin through multiple wireless detection signals and generate a first target living body image of the target passenger by calling the wireless transmission module to transmit multiple wireless detection signals to the cabin, so as to avoid the interference of ambient light when detecting the target passenger. At the same time, the first image feature reflecting the position and posture of the target passenger is extracted from the first target living body image, so as to accurately identify the posture of the target passenger on the target seat.

[0075] In a feasible implementation, the step of detecting the initial channel state information matched by each of the multiple wireless detection signals in step S201 can specifically include steps S2011-S2013:

[0076] Step S2011: detecting a wireless reception signal matched by each of the multiple wireless detection signals;

[0077] Step S2012: determining a signal change ratio between each of the multiple wireless detection signals and the matched wireless reception signal;

[0078] Step S2013: determining the initial channel state information matched by each of the multiple wireless detection signals based on each of the signal change ratios.

[0079] In this embodiment, after the electronic device controls the wireless signal transmitting module to continuously transmit multiple wireless detection signals to the vehicle cabin, the electronic device further controls the wireless signal transmitting module to receive wireless reflection signals generated by the multiple wireless detection signals respectively, and then the wireless signal transmitting module compares the multiple wireless detection signals with the respective and matched wireless receiving signals, to determine the signal change ratios generated between the multiple wireless detection signals and the respective and matched wireless receiving signals, and finally the wireless signal transmitting module determines the signal change ratios corresponding to the multiple wireless detection signals respectively as the initial channel state information matched by the multiple wireless detection signals respectively, and inputs the initial channel state information to the data processing unit.

[0080] For example, after the electronic device controls the TCAM to transmit multiple first Wifi signals to the vehicle cabin through the first Wifi Service configured by the TCAM, the electronic device further controls the TCAM to receive first Wifi reflection signals formed by reflection of the multiple first Wifi signals respectively after contacting obstacles, and then the TCAM compares the multiple first Wifi signals with the respective and matched first Wifi reflection signals, to determine first signal wave ratios formed between the multiple first Wifi signals and the respective and matched first Wifi reflection signals, and finally the TCAM determines the first signal wave ratios corresponding to the multiple first Wifi signals respectively as the initial CSI data corresponding to the multiple first Wifi signals respectively.

[0081] Similarly, after the electronic device controls the DHU to transmit multiple second Wifi signals to the vehicle cabin through the second Wifi Service configured by the DHU, the electronic device further controls the DHU to receive second Wifi reflection signals formed by reflection of the multiple second Wifi signals respectively after contacting obstacles, and then the DHU compares the multiple second Wifi signals with the respective and matched second Wifi reflection signals, to determine second signal wave ratios formed between the multiple second Wifi signals and the respective and matched second Wifi reflection signals, and finally the TCAM determines the second signal wave ratios corresponding to the multiple second Wifi signals respectively as the second initial CSI data corresponding to the multiple second Wifi signals respectively, and the electronic device controls the TCAM and the DHU to input the collected initial CSI data to the data processing unit Algorithm Service configured in the DHU.

[0082] In this way, the electronic device can obtain the initial channel state information generated by the multiple wireless detection signals by calling the wireless transmitting module to transmit the multiple wireless detection signals to the vehicle cabin.

[0083] In a possible implementation, the step of “generating a first target living body image based on the target channel state information” in the step S202 can include steps S2021-S2022.

[0084] Step S2021: extracting one-dimensional vector features contained in each of the target channel state information;

[0085] Step S2022: fusing each of the one-dimensional vector features to obtain a two-dimensional vector feature, and generating a first target living body image based on the two-dimensional vector feature.

[0086] It should be noted that the one-dimensional vector feature is a latent space feature contained in the target channel state information, and the one-dimensional vector feature specifically includes an amplitude tensor and a phase tensor, wherein the size of each tensor is 150x3x3 (5 continuous samples, 30 frequencies, 3 transmitters and 3 receivers). In this way, RCNN (Regions with Convolutional Neural Networks, regional convolutional neural network) can extract the spatial features contained in the one-dimensional vector feature through the last two dimensions of each tensor.

[0087] In this embodiment, after determining the plurality of target channel state information, the data processing unit first inputs the plurality of target channel state information to the convolutional neural network model configured by itself, so as to call a plurality of encoders by the convolutional neural network model to extract one-dimensional feature vectors contained in each of the plurality of target channel state information. Then, the data processing unit fuses each one-dimensional feature vector to obtain a two-dimensional fusion feature, and converts the two-dimensional fusion feature into a feature map in a spatial domain. Furthermore, the data processing unit performs up-sampling processing on the converted two-dimensional feature map to obtain a first target living body image containing a target occupant.

[0088] For example, please refer to Figure 3 , Figure 3For the first target living body image of the embodiment of the seat adjustment method of the present application, after determining the plurality of target CSI data, the Algorithm Service first inputs the plurality of target CSI data to the RCNN configured by itself, so that the RCNN calls two different encoders to process each target CSI data to extract the amplitude tensor and the phase tensor corresponding to each target CSI data, each with a size of 150x3x3. The RCNN further determines the amplitude tensor and the phase tensor corresponding to each target CSI data as 1D features. Then, the RCNN extracts the spatial information contained in each 1D feature based on the last two dimensions (3 transmitters and 3 receivers) of each amplitude tensor and each phase tensor, and fuses each 1D feature according to the spatial information to obtain a fused 1D feature. The RCNN further reshapes the fused 1D feature into an initial 2D feature map with a size of 24x24, and extracts the spatial information contained in the initial 2D feature map through the two convolution blocks configured by itself to obtain a 2D feature vector with a spatial dimension of 6x6. Finally, the RCNN performs an upsampling operation on the 2D feature vector with a spatial dimension of 6x6 to adjust the 2D feature vector to a size of 3x720x1280 as shown in Figure 3

[0089] In this way, the electronic device can construct a target living body image containing the target occupant based on the screened target channel state information.

[0090] Step S30: determining a first sitting posture type of the target occupant according to the first image feature, and determining a target seat adjustment parameter according to the first sitting posture type;

[0091] Step S40: adjusting a target seat on which the target occupant is located according to the target seat adjustment parameter, so that the target seat enters a target seat state matching the first sitting posture type.

[0092] In this embodiment, after extracting the first image feature through the convolutional neural network model, the electronic device can further process the first image feature to determine the first sitting posture type of the target occupant on the target seat according to the first image feature, and determine the matching target seat adjustment parameter according to the first sitting posture type. Finally, the electronic device inputs the target seat adjustment parameter to the seat control module configured by itself, and adjusts the target seat according to the target seat adjustment parameter through the seat control module, so that the target seat switches from the preset first seat state to the target seat state matching the first sitting posture type.

[0093] ​Exemplarily, for example, after the Algorithm Service extracts the first image features through the RCNN, the Algorithm Service can further identify the first image features to determine the first sitting posture type adopted by the target passenger when sitting in the target seat. If the Algorithm Service detects that the first sitting posture type is the leg opening and closing type, the Algorithm Service determines that the target seat state matched with the leg opening and closing type is the leg rest opening state. The Algorithm Service determines the target seat adjustment parameter capable of controlling the leg rest on the target seat according to the target seat state. Finally, the Algorithm Service converts the target seat adjustment parameter into a CAN signal through the MCU connected with the DHU, and sends the CAN signal to the bidirectional motor configured for controlling the target seat through the BUS bus in the vehicle, so that the bidirectional motor controls the target seat according to the target seat adjustment parameter, so that the leg rest on the target seat enters the opening state.

[0094] Similarly, if the Algorithm Service detects that the first sitting posture type is the trunk tilting type according to the first image features, the Algorithm Service determines that the target seat state matched with the trunk tilting type is the backrest tilting state. The Algorithm Service determines the target seat adjustment parameter capable of controlling the backrest of the target seat according to the target seat state. Finally, the Algorithm Service converts the target seat adjustment parameter into a CAN signal through the MCU connected with the DHU, and sends the CAN signal to the bidirectional motor configured for controlling the target seat through the BUS bus in the vehicle, so that the bidirectional motor controls the target seat according to the target seat adjustment parameter, so that the backrest on the target seat enters the tilting state.

[0095] It should be noted that in the present embodiment and another embodiment, if the data processing unit detects that the target passenger adopts multiple first sitting posture types (for example, in the leg opening and closing state and the trunk tilting type at the same time), the data processing unit can determine the target seat adjustment parameter for adjusting the leg rest and the backrest on the target seat at the same time, and send the target seat adjustment parameter to the seat control module. The seat control module adjusts the target seat according to the target seat adjustment parameter, so that the backrest of the target seat enters the tilting state, and the leg rest of the target seat enters the opening state. It can be understood that the present application does not limit the number of modules of the target seat which can be adjusted by the generated target seat adjustment parameter.

[0096] In this way, the electronic device can recognize the sitting posture type of the user on the target seat by processing the first image features, and can determine the target seat state that is most matched with the sitting posture type, so as to generate the seat adjustment parameter according to the target seat state, and then adjust the target seat according to the seat adjustment parameter, so as to switch the target seat to the target seat state.

[0097] In an available implementation, the step of "determining the target seat adjustment parameter according to the first sitting posture type" in the step S30 can specifically include steps S301-S302:

[0098] Step S301: determining the target seat corresponding to the target occupant, and detecting the current seat state of the target seat;

[0099] Step S302: determining the target seat state according to the first sitting posture type, and determining the target seat adjustment parameter based on the current seat state and the target seat state.

[0100] In the embodiment, after the first image features are extracted, the data processing unit can first read the seat pressure sensors arranged on each seat in the vehicle, and determine the target seat where the target occupant is located according to the seat sensors in each seat. At the same time, the data processing unit detects the target seat to determine the current seat state of the target seat. Then, the data processing unit queries the preset seat adjustment table, and determines the target seat state matched with the first sitting posture type according to the seat adjustment table. The data processing unit further determines the target seat adjustment parameter that can switch the target seat from the current seat state to the target seat state according to the target seat state and the current seat state.

[0101] Exemplarily, for example, after extracting the first image feature, the Algorithm Service can also first detect each seat arranged in the vehicle, so as to determine the target seat where the target occupant is located in each seat through the seat pressure sensor arranged in each seat according to each seat posture, and detect that the current seat state of the target seat is the leg rest retracted state. Then, the Algorithm Service determines that the first seat posture type adopted by the target occupant when sitting in the target seat is the leg opening and closing type according to the first image feature. The Algorithm Service reads the storage module mentioned above to obtain the seat adjustment table containing a plurality of preset seat posture types and a plurality of preset seat state matched with each preset seat posture type. The Algorithm Service queries the seat adjustment table based on the leg opening and closing type, so as to compare the leg opening and closing type with the plurality of preset seat posture types respectively, so as to determine the target preset seat posture type matched with the leg opening and closing type in the plurality of preset seat posture types, and determine the preset seat state matched with the target preset seat posture type as the target seat state matched with the leg opening and closing type. Finally, the Algorithm Service determines the target seat adjustment parameter capable of switching the leg rest on the target seat from the leg rest retracted state to the leg rest opened state in the case of detecting that the target seat state is the leg rest opened state. The Algorithm Service converts the target seat adjustment into a CAN signal through the MCU connected with the DHU, and sends the CAN signal to the bidirectional motor arranged in the vehicle for controlling the target seat through the BUS bus in the vehicle, so as to control the target seat according to the target seat adjustment parameter through the bidirectional motor, so as to make the leg rest on the target seat enter the leg rest opened state.

[0102] Similarly, when the Algorithm Service determines, according to the first image feature, that the first sitting posture type assumed by the target occupant when sitting in the target seat is a torso inclination type, the Algorithm Service queries the seat adjustment table based on the torso inclination type to compare the torso inclination type with the plurality of preset sitting posture types, respectively, so as to determine a target preset sitting posture type matching the torso inclination type from the plurality of preset sitting posture types, and determine a preset seat state matching the target preset sitting posture type as a target seat state matching the torso inclination type. Finally, when the Algorithm Service detects that the target seat state is a backrest inclination state, the Algorithm Service determines a target seat adjustment parameter capable of adjusting the backrest of the target seat to the backrest inclination state. The Algorithm Service converts the target seat adjustment into a CAN signal through the MCU connected to the DHU, and sends the CAN signal to the bidirectional motor configured to control the target seat through the BUS in the vehicle, so that the bidirectional motor controls the target seat according to the target seat adjustment parameter, thereby enabling the backrest of the target seat to enter the backrest inclination state.

[0103] In addition, in the present embodiment and another embodiment, after extracting the first image feature and identifying the first sitting posture type according to the first image feature, if it is detected that the first sitting posture type is a leg opening type, the Algorithm Service can also identify a leg opening parameter corresponding to the target occupant according to the first image feature. The Algorithm Service then queries a leg rest adjustment table containing a plurality of preset leg opening parameters and a plurality of preset leg rest angle parameters each matching a preset leg opening parameter based on the leg opening parameter, so as to determine a target preset leg rest angle parameter matching the leg opening parameter. The Algorithm Service thereby generates a target seat adjustment parameter based on the initial leg rest angle parameter contained in the current seat state and the target preset leg rest angle parameter, and sends the target seat adjustment parameter to the bidirectional motor, which adjusts the target leg rest to the target leg rest angle according to the target seat adjustment parameter, so that the legs of the target occupant are placed on the leg rest at a more comfortable angle, further improving the riding experience of the occupant.

[0104] Similarly, if the Algorithm Service detects that the first sitting posture type is a torso leaning type, it can also identify the target passenger's torso leaning angle according to the first image features, and then determine the matching target seat backrest angle according to the torso leaning angle. The Algorithm Service identifies the initial seat backrest angle of the target seat, and generates a target seat adjustment parameter according to the initial seat backrest angle and the target seat backrest angle. Then the target seat adjustment is sent to the bidirectional motor, which adjusts the seat backrest to the target seat backrest angle according to the target seat adjustment parameter, so that the target passenger's torso can be comfortably leaned against the seat backrest, further improving the passenger's riding experience.

[0105] It can be understood that the Algorithm Service can also integrate the obtained target backrest adjustment parameter and the above target seat adjustment parameter to obtain a target seat adjustment parameter, so that the bidirectional motor adjusts the seat backrest and the leg rest simultaneously based on the target seat adjustment parameter. In addition, the Algorithm Service can also calculate other adjustment parameters such as armrest, seat height, position, etc. based on the first image features, and integrate the adjustment parameters to make more comprehensive adjustments to the seat.

[0106] In this embodiment, the electronic device, when running, first calls the wireless signal transmitting module configured by itself to continuously transmit multiple wireless detection signals into the vehicle cabin, then the electronic device controls the wireless signal transmitting module to receive the wireless reflection signals generated by the multiple wireless detection signals respectively, and the wireless signal transmitting module further obtains multiple initial channel state information according to each wireless detection signal and each wireless reflection signal, and inputs the multiple initial channel state information into the data processing unit configured by itself, and the data processing unit calls the preset convolutional neural network model to generate a first target living body image containing the target occupant existing in the vehicle cabin according to the received initial channel state information, the convolutional neural network model performs phase separation processing on the first target living body image to obtain multiple sub-living body images, and calls the encoder to perform encoding processing on the multiple sub-living body images to identify the convolutional feature weight corresponding to each sub-living body image, and the convolutional neural network model further fuses each convolutional feature weight to obtain pose fusion data, performs inference merging operation on the pose fusion data, and performs sampling processing on the inference merged pose fusion data to extract the first image feature, and then the electronic device processes the first image feature to determine the first sitting posture type of the target occupant on the target seat according to the first image feature, and determines the matching target seat adjustment parameter according to the first sitting posture type, and finally the electronic device inputs the target seat adjustment parameter into the seat control module configured by itself, and the seat control module adjusts the target seat according to the target seat adjustment parameter to switch the target seat from the preset first seat state to the target seat state matched with the first sitting posture type.

[0107] Thus, the present application solves the technical problem that the vehicle is difficult to accurately identify the sitting posture of the occupant in the related art, that is, the present application utilizes the characteristic that the wireless detection signal will generate different channel state information when contacting the living body, can accurately identify the sitting posture type of the target occupant in the vehicle cabin, so as to determine the seat adjustment parameter according to the sitting posture type, and adjust the target seat to the target seat state matched with the sitting posture type according to the seat adjustment parameter, avoiding the case that the camera is difficult to accurately identify the sitting posture of the occupant due to the influence of environmental light, and achieving the technical effect that the electronic device can accurately adjust the seat based on the sitting posture of the occupant.

[0108] Based on the first embodiment of the present application, the second embodiment of the present application is proposed, and the same or similar contents as the above embodiments can be referred to the above introduction, and will not be described in detail. On this basis, after the step of "determining the target seat corresponding to the target occupant" in the above step S301, the seat adjustment method of the present application can further include steps A10-A20:

[0109] Step A10: detecting a door of the vehicle, and determining a first aisle size corresponding to the target seat when the door is detected to be in an open state;

[0110] Step A20: determining a first seat position adjustment parameter according to the first aisle size and a preset target aisle size, and adjusting the target seat according to the first seat position adjustment parameter, so as to switch the aisle size corresponding to the target seat from the first aisle size to the target aisle size.

[0111] It should be noted that the first aisle size is the width of the aisle generated between the front side edge of the target seat in the initial position and the obstacle in front of the target seat. The obstacle in front of the target seat can be the rear side edge of the seat back of the front seat corresponding to the target seat, or the rear side edge of the front console corresponding to the target seat. In addition, the target aisle size is a preset aisle size that can allow the target occupant to pass through smoothly. It can be understood that the specific value of the target aisle size can be set by the technician according to the requirements, and the present application does not limit this.

[0112] In the embodiment, after the data processing unit identifies the target seat where the target occupant is located, the data processing unit can further detect the door, so as to determine a first aisle size corresponding to the aisle where the target seat is located when the door is detected to be in an open state. Then, the data processing unit reads the storage module to obtain a preset target aisle size, and determines a first seat position adjustment parameter for adjusting the seat position according to the first aisle size and the target aisle size. The data processing unit further transmits the first seat position adjustment parameter to the seat control module, and the seat control module adjusts the position of the seat according to the first seat position adjustment parameter, so as to switch the aisle size corresponding to the seat from the first aisle size to the target aisle size.

[0113] Exemplarily, for example, after identifying the target seat where the target passenger is located, the Algorithm Service can further detect the vehicle door, so that in the case that the vehicle door is detected to be in the open state, the Algorithm Service reads the storage module to obtain the initial position information of the target seat, and determines the first passage size of the front aisle corresponding to the target seat according to the initial position information. Then, the Algorithm Service reads the storage module to obtain the preset target passage size for enabling the target passenger to smoothly pass through the aisle, and determines the first seat position adjustment parameter corresponding to the target seat according to the first passage size and the target passage size. The Algorithm Service converts the first seat position adjustment parameter into a CAN signal through the MCU connected with the DHU, and sends the CAN signal to the bidirectional motor configured for controlling the target seat through the BUS bus in the vehicle, so that the bidirectional motor controls the target seat according to the first seat position adjustment parameter, thereby moving the target seat to the rear of the vehicle until the size of the aisle in front of the target seat reaches the target passage size, so that the target passenger can smoothly enter the vehicle and reach the target seat;

[0114] It should be noted that in the present embodiment and another embodiment, after the Algorithm Service controls the target seat to move backward, the Algorithm Service can further detect the vehicle door, so that in the case that the vehicle door is detected to be in the closed state, the second seat position adjustment parameter for moving the seat to the initial position is generated based on the first seat position adjustment parameter, and the second seat position adjustment parameter is converted into a CAN signal through the MCU connected with the DHU, and the CAN signal is sent to the bidirectional motor configured for controlling the target seat through the BUS bus in the vehicle, so that the bidirectional motor controls the target seat according to the second seat position adjustment parameter, so that the target seat moves to the front of the vehicle, and the passage size of the aisle in front of the target seat recovers from the target passage size to the first passage size, so that after the target passenger sits down, the seat moves to the original position.

[0115] In this way, the electronic device can control the seat to move backward to vacate enough space for the target passenger to enter the cabin when the vehicle door is open, and then control the seat to move forward to restore the aisle to the initial passage size after detecting that the vehicle door is closed, thereby further enhancing the passenger's riding experience.

[0116] Based on the first embodiment and / or the second embodiment of the present application, the third embodiment of the present application is proposed. In the third embodiment of the present application, the same or similar contents as the above embodiments can be referred to the above description, and will not be described hereinafter. On this basis, after the step S40, the seat adjusting method of the present application can further include steps B10-B30:

[0117] Step B10: generating a second target living body image containing the target occupant based on a plurality of wireless detection signals, and extracting a second image feature of the second target living body image;

[0118] Step B20: determining a second sitting posture type corresponding to the target occupant according to the second image feature, and determining a function control instruction corresponding to the second sitting posture type, wherein the function control instruction is a control instruction for controlling a target function module configured in the vehicle and needed to be adjusted by the target occupant;

[0119] Step B30: controlling the target function module according to the function control instruction, so as to make the target function module enter a function running state matched with the function control instruction.

[0120] In this embodiment, after the seat control module completes the adjustment of the target seat, the electronic device can also call the wireless signal emitting module to continuously emit a plurality of wireless detection signals into the vehicle cabin, and determine a plurality of initial channel state information through the plurality of wireless detection signals and the respective corresponding wireless reflection signals. The electronic device inputs the plurality of initial channel state information to the data processing unit, and the data processing unit calls the convolutional neural network model to generate a second target living body image containing the target occupant based on the plurality of initial channel state information, and processes the second target living body image to extract a second image feature contained in the second target living body image. Then, the data processing unit determines a second sitting posture type adopted by the target occupant on the target seat according to the second image feature, and determines a function control instruction matched with the second sitting posture type for controlling a target function module needed to be adjusted by the target occupant. Finally, the electronic device controls the target function module according to the function control instruction, so as to make the target function module enter a running state matched with the function control instruction.

[0121] Exemplarily, for example, after adjusting the target seat to the target seat state, the electronic device can also continue to control the wireless transmitting module to control the TCAM and the DHU in the wireless transmitting module to respectively transmit a plurality of wireless wifi signals into the cabin and receive a plurality of reflected signals of the plurality of wireless wifi signals, and then determine a plurality of second initial CSI data according to the plurality of wireless wifi signals and the plurality of reflected signals. The electronic device inputs the plurality of second initial CSI data into the data processing unit Algorithm Service, and the Algorithm Service inputs the plurality of second initial CSI data into the RCNN configured by the electronic device, and the RCNN generates a second target living body image containing the target passenger sitting on the target seat based on the plurality of second initial CSI data. The RCNN further performs feature processing operation on the second target living body image to extract a second image feature. Then, the Algorithm Service determines a second sitting posture type of the target passenger on the target seat based on the second image, and determines that the target function module that needs to be adjusted by the target passenger is the loudspeaker / air conditioner / seat heating function according to the second sitting posture type. Finally, the Algorithm Service converts the function control instruction into a CAN signal through the MCU connected with the DHU, and sends the CAN signal to the function control module configured in the vehicle through the BUS in the vehicle, so that the function control module adjusts the loudspeaker / air conditioner / seat heating function in the cabin according to the function control instruction, so that the loudspeaker / air conditioner / seat heating function enters the running mode matched with the function control instruction.

[0122] In this way, the electronic device can determine the function control instruction that needs to be executed by the target passenger by detecting the sitting posture type of the target passenger, and then directly control the corresponding target function module without additional operation of the target passenger, thereby further improving the riding experience of the passenger.

[0123] In a possible implementation, the step of "determining the function control instruction corresponding to the second sitting posture type" in step B20 can specifically include steps B201-B203:

[0124] Step B201: determining a preset sitting posture type matched with the second sitting posture type.

[0125] Step B202: determining a preset function instruction matched with the preset sitting posture type as the function control instruction corresponding to the second sitting posture type.

[0126] In this embodiment, after the data processing unit identifies the second sitting posture type according to the second image feature, the data processing unit can further read the storage module to obtain a plurality of preset sitting posture types, and the data processing unit filters the plurality of preset sitting postures based on the second sitting posture type to determine a preset sitting posture type that matches the second sitting posture type. Finally, the data processing unit determines the preset function instruction corresponding to the preset sitting posture type that matches the second sitting posture type as the function control instruction to be used by the target passenger.

[0127] For example, after the Algorithm Service identifies that the second sitting posture type of the target passenger in the target seat is a single-hand lifting / double-hand lifting action according to the second image feature, the Algorithm Service can further read the storage module to obtain an instruction mapping table containing a plurality of preset sitting posture types and a plurality of preset function instructions respectively matched with the plurality of preset sitting posture types. The Algorithm Service queries the instruction mapping table based on the second sitting posture type to compare the second sitting posture type with the plurality of preset sitting posture types contained in the instruction mapping table, thereby determining a preset sitting posture type that matches the second sitting posture type from the plurality of preset sitting posture types. Finally, if the Algorithm Service determines that the preset function instruction matched with the second sitting posture type in the instruction mapping table is a seat heating instruction, the Algorithm Service determines the seat heating instruction as the function control instruction to be used by the target passenger.

[0128] Similarly, if the Algorithm Service determines that the preset function instruction matched with the second sitting posture type in the instruction mapping table is an air conditioner heating instruction, the Algorithm Service determines the air conditioner heating instruction as the function control instruction to be used by the target passenger. It can be understood that the mapping relationship between the plurality of preset sitting posture types and the respective preset function instructions can be set by the technician according to the actual needs, and the present application does not limit this.

[0129] In this way, the electronic device can determine the function control instruction to be performed by the target passenger by detecting the sitting posture type of the target passenger, and directly control the corresponding function module without additional operation of the target passenger, thereby further improving the riding experience of the passenger.

[0130] For example, in order to assist in understanding the implementation process of the seat adjustment method obtained by combining the above embodiments, please refer to Figure 4 , Figure 4 for a brief flowchart of the seat adjustment method of the present application. Specifically:

[0131] In the embodiment, the electronic device starts the TCAM and the DHU configured by itself at runtime, and detects whether the TCAM and the DHU can normally communicate by the Core Service in the TCAM. When the Core Service detects that the TCAM and the DHU normally communicate, the electronic device controls the first Wifi Service in the TCAM to emit a plurality of first Wifi signals into the vehicle cabin, and controls the first Wifi Service to receive first Wifi reflection signals respectively generated by the first Wifi signals. The first Wifi Service generates a plurality of first initial CSI data according to the first Wifi signals and the first Wifi reflection signals, and the TCAM further sends the generated first initial CSI data to the data processing unit in the DHU.

[0132] Meanwhile, the electronic device controls the second Wifi Service in the DHU to emit a plurality of second Wifi signals into the vehicle cabin, and controls the second Wifi Service to receive second Wifi reflection signals respectively generated by the second Wifi signals. The second Wifi Service generates a plurality of second initial CSI data according to the second Wifi signals and the second Wifi reflection signals, and the DHU further sends the generated second CSI data to the data processing unit.

[0133] Then, the data processing unit performs noise reduction processing on the obtained first initial CSI data and second initial CSI data to obtain a plurality of complete CSI data. At this time, the data processing unit reads the storage module in the electronic device to obtain preset CSI data corresponding to the Wifi signals when detecting the non-living body detection target, and compares each complete CSI data with each preset CSI data to obtain a plurality of comparison results. The data processing unit determines the target CSI data corresponding to the Wifi signal detecting the living body detection target in each complete CSI data based on the plurality of comparison results.

[0134] Afterwards, the data processing unit inputs each target CSI data into a preset convolutional neural network model, extracts one-dimensional feature vectors contained in each target CSI data by the convolutional neural network model, and fuses each one-dimensional feature vector to generate a first target living body image containing a target occupant in the cabin. The convolutional neural network model further extracts first image features of the first target living body image, and uploads the first image features to the data processing unit. The data processing unit matches the first image features with preset human body features, and further identifies seat pressure sensors arranged on each seat in the vehicle to determine a target seat where the target occupant is located and a current seat state of the target seat when it is determined that the image features and the human body features match. Meanwhile, the data processing unit determines a first sitting posture type of the target occupant on the target seat according to the first image features, and queries a preset seat adjustment table to determine a target seat state matching the first sitting posture type. The data processing unit further generates a target seat adjustment parameter according to the current seat state and the target seat state, and then sends the target seat adjustment parameter to a seat control module arranged in the vehicle. The seat control module adjusts the target seat according to the target seat adjustment parameter to switch the target seat from the current seat state to the target seat state.

[0135] After detecting that the target seat is switched from the current seat state to the target seat state, the electronic device further calls the wireless signal emitting module to continuously emit a plurality of wireless detection signals into the vehicle cabin, and generates a second target living body image containing the target occupant by the plurality of wireless detection signals and respective corresponding wireless reflection signals. The data processing unit extracts second image features from the second target living body image, and determines a second sitting posture type of the target occupant on the target seat according to the second image features. Finally, the data processing unit queries an instruction mapping table based on the second sitting posture type to determine a function control instruction matching the second sitting posture type. Finally, the electronic device controls a target function module that needs to be adjusted by the target occupant according to the function control instruction to make the target function module enter an operating state matching the function control instruction.

[0136] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the seat adjustment method of the present application. More forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0137] The present application also provides a seat adjustment device, please refer to Figure 5 , the seat adjustment device is applied to an electronic device, the electronic device contains a wireless signal emitting module, and the device comprises:

[0138] a signal detection module 10, configured to control the wireless signal transmission module to transmit a plurality of wireless detection signals to the vehicle cabin;

[0139] a feature extraction module 20 for generating a first target living body image including a target occupant based on the plurality of wireless detection signals, and extracting a first image feature of the first target living body image;

[0140] a parameter recognition module 30 for determining a first sitting posture type of the target occupant according to the first image feature, and determining a target seat adjustment parameter according to the first sitting posture type;

[0141] The seat adjustment module 40 is configured to adjust the target seat where the target occupant is located according to the target seat adjustment parameters, so that the target seat enters a target seat state that matches the first sitting posture type.

[0142] In a feasible implementation manner, the parameter identification module 30 is further configured to:

[0143] Determining a target seat corresponding to the target occupant and detecting a current seat state of the target seat;

[0144] A target seat state is determined according to the first sitting posture type, and a target seat adjustment parameter is determined based on the current seat state and the target seat state.

[0145] In a feasible implementation manner, the parameter identification module 30 is further configured to:

[0146] detecting a door of the vehicle, and determining a first channel size corresponding to the target seat when detecting that the door is in an open state;

[0147] A first seat position adjustment parameter is determined based on the first channel size and a preset target channel size, and the target seat is adjusted according to the first seat position adjustment parameter so that the channel size corresponding to the target seat is switched from the first channel size to the target channel size.

[0148] In a feasible embodiment, the seat adjustment module 40 is further configured to:

[0149] generating a second target living body image including the target occupant based on the plurality of wireless detection signals, and extracting a second image feature of the second target living body image;

[0150] determine a second sitting posture type corresponding to the target passenger according to the second image feature, and determine a function control instruction corresponding to the second sitting posture type, wherein the function control instruction is a control instruction for controlling a target function module configured in the vehicle and needed to be adjusted by the target passenger;

[0151] control the target function module according to the function control instruction, so that the target function module enters a function running state matched with the function control instruction.

[0152] In an available implementation, the seat adjustment module 40 is further configured to:

[0153] determine a preset sitting posture type matched with the second sitting posture type;

[0154] determine a preset function instruction matched with the preset sitting posture type as the function control instruction corresponding to the second sitting posture type.

[0155] In an available implementation, the feature extraction module 20 is further configured to:

[0156] detect initial channel state information matched with each of the wireless detection signals, and perform cleaning processing on each of the initial channel state information to obtain complete channel state information;

[0157] perform screening on each of the complete channel state information to determine target channel state information, and generate a first target living body image based on each of the target channel state information, wherein the target channel state information is channel state information corresponding to a wireless detection signal of a target passenger.

[0158] In an available implementation, the feature extraction module 20 is further configured to:

[0159] detect wireless receiving signals matched with each of the wireless detection signals;

[0160] determine signal change ratios between each of the wireless detection signals and the matched wireless receiving signals;

[0161] determine initial channel state information matched with each of the wireless detection signals based on each of the signal change ratios.

[0162] In an available implementation, the feature extraction module 20 is further configured to:

[0163] extract one-dimensional vector features contained in each of the target channel state information;

[0164] The one-dimensional vector features are fused to obtain a two-dimensional vector feature, and a first target living body image is generated based on the two-dimensional vector feature.

[0165] The seat adjustment device provided in the present application adopts the seat adjustment method in the above embodiments, and can solve the technical problem that the vehicle cannot accurately identify the sitting posture of the occupant in the related art. Compared with the prior art, the seat adjustment device provided in the present application has the same beneficial effects as the seat adjustment method provided in the above embodiments, and other technical features in the seat adjustment device are the same as the features disclosed in the above embodiments, which will not be described herein.

[0166] The present application provides an electronic device, which comprises at least one processor and a memory connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the seat adjustment method in the above embodiment one.

[0167] Reference will be made to the following Figure 6 which shows a structural schematic diagram of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application can include but is not limited to an electronic device internally configured with a wireless signal transmitting module, or a mobile terminal connected with an electronic control unit matched with the electronic device, a data storage control terminal, a PC terminal, etc. Figure 6 The electronic device shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0168] As Figure 6As shown, the electronic device can include a processing apparatus 1001 (for example, a central processor, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage apparatus 1003 into a random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for operation of the electronic device are also stored. The processing apparatus 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input apparatus 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output apparatus 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; the storage apparatus 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication apparatus 1009. The communication apparatus 1009 can allow the electronic device to perform wireless or wired communication with other devices to exchange data. Although the electronic device having various systems is shown in the figure, it should be understood that all the shown systems are not required to be implemented or possessed. More or less systems can be alternatively implemented or possessed.

[0169] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program codes for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication apparatus, or installed from the storage apparatus 1003, or installed from the ROM 1002. When the computer program is executed by the processing apparatus 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are performed.

[0170] The electronic device provided in the present application adopts the seat adjustment method in the above-mentioned embodiments, and can solve the technical problem that the vehicle is difficult to accurately identify the sitting posture of the occupant in the related art. Compared with the prior art, the electronic device provided in the present application has the same beneficial effects as the seat adjustment method provided in the above-mentioned embodiments, and other technical features in the electronic device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0171] It should be understood that various aspects of the disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any appropriate manner in any one or more embodiments or examples.

[0172] The above description is merely illustrative of the application and is not intended to limit the scope of the application. Any variations and modifications that can be made by any person skilled in the art within the spirit and scope of the application are intended to be encompassed by the application. Therefore, the scope of the application should be determined by the scope of the claims.

[0173] The application provides a vehicle having the electronic device described above, which is used to execute the seat adjustment method in the above embodiments.

[0174] The application provides a computer readable storage medium having computer readable program instructions (i.e. computer programs) stored thereon, which are used to execute the seat adjustment method in the above embodiments.

[0175] The computer readable storage medium provided by the application may, for example, be a U disk, but is not limited to an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system or device, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electric connection having one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), an optical fiber, a portable compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination of the above. In the present embodiment, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer readable storage medium can be transmitted by any appropriate medium, including but not limited to an electric wire, an optical cable, an RF (Radio Frequency), etc., or any appropriate combination of the above.

[0176] The above computer readable storage medium can be contained in the electronic device; or can exist separately without being assembled into the electronic device.

[0177] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by an electronic device, the electronic device: controls the wireless signal transmission module to transmit multiple wireless detection signals to the vehicle cabin; generates a first target living image containing a target occupant based on multiple wireless detection signals, and extracts a first image feature of the first target living image; determines a first sitting posture type of the target occupant according to the first image feature, and determines a target seat adjustment parameter according to the first sitting posture type; adjusts the target seat where the target occupant is located according to the target seat adjustment parameter, so that the target seat enters a target seat state that matches the first sitting posture type.

[0178] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0179] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0180] The modules described in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the names of the modules do not constitute a limitation on the modules themselves.

[0181] The computer readable storage medium provided in the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the seat adjustment method described above, and can solve the technical problem that a vehicle is difficult to accurately identify the sitting posture of an occupant in the related art. Compared with the prior art, the computer readable storage medium provided in the present application has the same beneficial effects as the seat adjustment method provided in the above embodiments, and will not be described here.

[0182] The present application also provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the seat adjustment method as described above.

[0183] The computer program product provided in the present application can solve the technical problem that a vehicle is difficult to accurately identify the sitting posture of an occupant in the related art. Compared with the prior art, the computer program product provided in the present application has the same beneficial effects as the seat adjustment method provided in the above embodiments, and will not be described here.

[0184] The above only describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields based on the technical concept of the present application, and the content of the present application specification and drawings are included in the patent protection scope of the present application.

Claims

1. A seat adjustment method, characterized in that: The seat adjustment method is applied to an electronic device, wherein the electronic device includes a wireless signal transmission module, and the seat adjustment method includes: Controlling the wireless signal transmitting module to transmit a plurality of wireless detection signals to the cabin of the vehicle; generating a first target living body image including a target occupant based on the plurality of wireless detection signals, and extracting a first image feature of the first target living body image; determining a first sitting posture type of the target occupant according to the first image feature, and determining a target seat adjustment parameter according to the first sitting posture type; adjusting the target seat where the target occupant is located according to the target seat adjustment parameter so that the target seat enters a target seat state that matches the first sitting posture type; The step of generating a first target living body image including a target occupant based on the plurality of wireless detection signals comprises: detecting initial channel state information respectively matched by the plurality of wireless detection signals, and performing cleaning processing on each of the initial channel state information to obtain each complete channel state information; Filtering each of the complete channel state information to determine target channel state information, and generating a first target living body image based on each of the target channel state information, wherein the target channel state information is channel state information corresponding to a wireless detection signal detecting a target occupant; The step of detecting initial channel state information that matches each of the plurality of wireless detection signals includes: detecting wireless receiving signals that are matched with each of the plurality of wireless detection signals; determining a signal change ratio between each of the plurality of wireless detection signals and a matching wireless reception signal; Based on each of the signal change ratios, initial channel state information that matches each of the plurality of wireless detection signals is determined.

2. The seat adjustment method according to claim 1, wherein: The step of determining target seat adjustment parameters according to the first sitting posture type includes: Determining a target seat corresponding to the target occupant and detecting a current seat state of the target seat; A target seat state is determined according to the first sitting posture type, and a target seat adjustment parameter is determined based on the current seat state and the target seat state.

3. The seat adjustment method according to claim 2, wherein: After the step of determining the target seat corresponding to the target occupant, the method further includes: detecting a door of the vehicle, and determining a first channel size corresponding to the target seat when detecting that the door is in an open state; A first seat position adjustment parameter is determined based on the first channel size and a preset target channel size, and the target seat is adjusted according to the first seat position adjustment parameter so that the channel size corresponding to the target seat is switched from the first channel size to the target channel size.

4. The seat adjustment method according to claim 1, wherein: After the step of adjusting the target seat where the target occupant is located according to the target seat adjustment parameters, the method further includes: generating a second target living body image including the target occupant based on the plurality of wireless detection signals, and extracting a second image feature of the second target living body image; determining a second sitting posture type corresponding to the target occupant based on the second image feature, and determining a function control instruction corresponding to the second sitting posture type, wherein the function control instruction is a control instruction for controlling a target function module configured in the vehicle and required to be adjusted by the target occupant; The target functional module is controlled according to the functional control instruction, so that the target functional module enters a functional operation state matching the functional control instruction.

5. The seat adjustment method according to claim 4, wherein: The step of determining the function control instruction corresponding to the second sitting posture type includes: determining a preset sitting posture type that matches the second sitting posture type; The preset function instruction that matches the preset sitting posture type is determined as the function control instruction corresponding to the second sitting posture type.

6. The seat adjustment method according to claim 4, wherein: The step of generating a first target living body image based on each target channel state information includes: Extracting a one-dimensional vector feature contained in each of the target channel state information; The one-dimensional vector features are fused to obtain two-dimensional vector features, and a first target living body image is generated based on the two-dimensional vector features.

7. An electronic device, characterized in that: The device includes: a wireless signal transmission module, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the seat adjustment method according to any one of claims 1 to 6.

8. A vehicle, characterized in that: The vehicle includes the electronic device according to claim 7.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the seat adjustment method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, which implements the steps of the seat adjustment method according to any one of claims 1 to 6 when executed by a processor.

Images