Seat control method and device of vehicle, storage medium and vehicle

Abstract

This invention relates to the field of vehicle control technology, specifically disclosing a vehicle seat control method and device, a storage medium, and a vehicle. The vehicle seat control method includes: acquiring music signals, speed signals, acceleration signals, and body pressure distribution signals of the vehicle; determining the current state information of the vehicle based on the music signals, speed signals, acceleration signals, and body pressure distribution signals; determining the seat's action commands based on the current state information using a preset learning algorithm; controlling the seat according to the action commands; acquiring the reward value corresponding to the seat after executing the action command and the next state information of the vehicle; updating the preset learning algorithm based on the current state information, action commands, reward value, and next state information to improve the accuracy of action command determination. This enables personalized massage operations controlled by the seat in conjunction with music signals, achieving linkage with the vehicle and possessing self-learning capabilities, thereby improving the comfort and entertainment of the seat.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and more particularly to a vehicle seat control method and device, storage medium, and vehicle. Background Technology

[0002] With the increasing popularity of intelligent vehicles, the requirements for vehicle intelligence and personalization are getting higher and higher. As an important component that integrates functionality, safety, comfort and aesthetics, car seats have attracted the attention of major OEMs and consumers. Among them, the comfort of massage in the seat is also one of the key points.

[0003] In related technologies, seat massage is generally replaced by fixed modes, and has poor correlation with the whole vehicle. The modes are also relatively monotonous and boring, and it does not have a self-learning function, making it difficult to meet the user's needs. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in related technologies. Therefore, the first objective of this invention is to propose a vehicle seat control method that can combine music signals to control the seat for personalized massage operations, achieve linkage with the vehicle, and has a self-learning function, thereby improving the comfort and entertainment of the seat.

[0005] A second objective of this invention is to provide a computer-readable storage medium.

[0006] The third objective of this invention is to provide a vehicle seat control device.

[0007] The fourth objective of this invention is to provide a vehicle.

[0008] To achieve the above objectives, a first aspect of the present invention provides a vehicle seat control method, the method comprising: S10: acquiring music signals, speed signals, acceleration signals, and body pressure distribution signals of the vehicle; S20: determining the current state information of the vehicle based on the music signals, speed signals, acceleration signals, and body pressure distribution signals; S30: determining the action command of the seat based on the current state information using a preset learning algorithm; S40: controlling the seat according to the action command; S50: acquiring the reward value corresponding to the seat after executing the action command and the next state information of the vehicle; S60: updating the preset learning algorithm according to the current state information, the action command, the reward value, and the next state information to improve the determination accuracy of the action command.

[0009] In the vehicle seat control method of this invention, the vehicle's music signal, speed signal, acceleration signal, and seat body pressure distribution signal are first acquired. Then, the vehicle's current state information is determined based on the acquired signals. Next, a preset learning algorithm is used to determine the seat's action command based on the current state information, and the seat is controlled to execute the action command. After the seat executes the action command, a reward value and the vehicle's next state information are acquired. The preset learning algorithm is then updated based on the current state information, action command, reward value, and next state information to determine more accurate action commands in the future. This embodiment can combine music signals to control the seat for personalized massage operations, achieve linkage with the vehicle, and has a self-learning function, which can improve the seat's comfort and entertainment value.

[0010] In some embodiments of the present invention, determining the current state information of the vehicle based on the music signal, the speed signal, the acceleration signal, and the body pressure distribution signal includes: S201: performing analog-to-digital conversion and signal segmentation on the music signal to obtain discrete drum beat signals; S202: using a Butterworth filter to filter the discrete drum beat signals to extract drum beat features, wherein the drum beat features include at least one of low-frequency drum beat features, mid-frequency drum beat features, and high-frequency drum beat features; S203: determining the current state information of the vehicle based on the drum beat features, the speed signal, the acceleration signal, and the body pressure distribution signal to improve the accuracy of the determination of the action command.

[0011] In some embodiments of the present invention, obtaining the reward value corresponding to the seat after executing the action command includes: S301: obtaining the comfort data of the seat after executing the action command; S302: querying a preset data table based on the comfort data to determine the reward value, wherein the preset data table includes the correspondence between the reward value and the comfort data.

[0012] In some embodiments of the present invention, the backrest and / or seat cushion of the seat are provided with multiple massage points, and each massage point is provided with a vibrator, an air bag and a pressure sensor, wherein the distance between the pressure sensor and the air bag and the vibrator is greater than or equal to a preset distance.

[0013] In some embodiments of the present invention, the action command includes the vibration frequency of the oscillator and the inflation amount of the air bag.

[0014] In some embodiments of the present invention, the preset learning algorithm is a Q-learning algorithm. The preset learning algorithm is used to determine the action command of the seat based on the current state information, including: selecting the action command with the largest cumulative reward expectation value from the Q table according to the current state information, wherein the Q table records the cumulative reward expectation value of executing each action command under each state information.

[0015] In some embodiments of the present invention, updating the preset learning algorithm based on the current state information, the action instruction, the reward value, and the next state information includes updating the Q-table based on the current state information, the action instruction, the reward value, and the next state information.

[0016] To achieve the above objectives, a second aspect of the present invention provides a computer-readable storage medium storing a vehicle seat control program thereon, wherein when the vehicle seat control program is executed by a processor, the vehicle seat control method described in any of the above embodiments is implemented.

[0017] The computer-readable storage medium of this invention, through a processor executing a vehicle seat control program stored thereon, can control the seat to perform personalized massage operations in conjunction with music signals, achieve linkage with the vehicle, and has a self-learning function, which can improve the comfort and entertainment of the seat.

[0018] To achieve the above objectives, a third aspect of the present invention provides a vehicle seat control device, the device comprising: an acquisition module for acquiring music signals, speed signals, acceleration signals, and body pressure distribution signals of the vehicle; a determination module for determining the current state information of the vehicle based on the music signals, speed signals, acceleration signals, and body pressure distribution signals, and determining the action command of the seat based on the current state information using a preset learning algorithm; a control module for controlling the seat according to the action command; the acquisition module further comprising acquiring a reward value corresponding to the seat after executing the action command and the next state information of the vehicle; and an update module for updating the preset learning algorithm based on the current state information, the action command, the reward value, and the next state information to improve the determination accuracy of the action command.

[0019] The vehicle seat control device of this invention includes an acquisition module, a determination module, a control module, and an update module. The acquisition module first acquires the vehicle's music signal, speed signal, acceleration signal, and seat pressure distribution signal. Then, the determination module determines the vehicle's current state information based on the acquired signals. Next, it uses a preset learning algorithm to determine the seat's action commands based on the current state information. The control module then controls the seat to execute the action commands. After the seat executes the action commands, the acquisition module acquires a reward value and the vehicle's next state information. The update module then updates the preset learning algorithm based on the current state information, action commands, reward value, and next state information to determine more accurate action commands in the future. This embodiment can control the seat for personalized massage operations in conjunction with music signals, achieve linkage with the vehicle, and has a self-learning function, thereby improving the seat's comfort and entertainment value.

[0020] To achieve the above objectives, a fourth aspect of the present invention provides a vehicle that includes the seat control device of the vehicle described above.

[0021] The vehicle of this invention, through the seat control device of the vehicle described in the above embodiment, can control the seat to perform personalized massage operations in conjunction with music signals, link with the vehicle, and has a self-learning function, which can improve the comfort and entertainment of the seat.

[0022] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0023] Figure 1 This is a flowchart of a vehicle seat control method according to one embodiment of the present invention; Figure 2 This is a flowchart of a vehicle seat control method in another embodiment of the present invention; Figure 3 This is a flowchart of a vehicle seat control method in another embodiment of the present invention; Figure 4 This is a schematic diagram of the massage points of the seat in one embodiment of the present invention; Figure 5 This is a block diagram of the vehicle seat control device in an embodiment of the present invention; Figure 6 This is a vehicle block diagram according to an embodiment of the present invention.

[0024] Reference numerals: 10-Pressure sensor; 20-Massage point; 500-Vehicle seat control device; 501-Acquisition module; 502-Determination module; 503-Control module; 504-Update module; 600-Vehicle. Detailed Implementation

[0025] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0026] The following description, with reference to the accompanying drawings, describes a vehicle seat control method and apparatus, a storage medium, and a vehicle according to embodiments of the present invention.

[0027] Figure 1 This is a flowchart of a vehicle seat control method according to one embodiment of the present invention.

[0028] S10: Acquire the vehicle's music signal, speed signal, acceleration signal, and seat pressure distribution signal.

[0029] Specifically, the music signal in this embodiment can be music played by the in-vehicle multimedia system or music played by the driver and passengers through a personal terminal device, including but not limited to mobile phones, tablets, and watches. It should be noted that the music signal from the vehicle can be collected by a sound sensor; if it's music played by the in-vehicle multimedia system, it can also be obtained directly from the in-vehicle entertainment system. Speed ​​and acceleration signals can be obtained directly from the speed and acceleration sensors via the vehicle's infotainment system, specifically through a CAN bus. Multiple pressure sensors can be distributed on the vehicle seats to collect the body pressure distribution signals. This means that the seats have multiple massage points, each with a corresponding pressure sensor, allowing the acquisition of the pressure value for each massage point. It should be noted that in this embodiment, each signal can be configured with a corresponding acquisition period; for example, the sampling frequency of each sensor can be set to 50 Hz, 100 Hz, etc.

[0030] S20: Determine the vehicle's current status information based on music signals, speed signals, acceleration signals, and body pressure distribution signals.

[0031] Specifically, this embodiment can determine the current state information in several ways. For example, a mapping table can be set up. After acquiring the music signal, speed signal, acceleration signal, and body pressure distribution signal, these signals can be input into the mapping table to query and determine the corresponding state information as the vehicle's current state information. Alternatively, in other instances, the music signal, speed signal, acceleration signal, and body pressure distribution signal can be fused. For example, weights can be assigned to these signals, and they can be fused according to the weights to obtain a fusion vector. The corresponding vehicle state information can then be determined based on this fusion vector to ascertain the vehicle's current state information. A mapping table or calculation function can also be set up between the fusion vector and the state information.

[0032] In some embodiments of the present invention, determining the current state information of the vehicle based on music signals, speed signals, acceleration signals, and body pressure distribution signals includes: S201: Perform analog-to-digital conversion and signal segmentation on the music signal to obtain discrete drum beat signals.

[0033] S202: A Butterworth filter is used to filter the discrete drum beat signal to extract the drum beat features of the discrete drum beat signal. The drum beat features include at least one of low-frequency drum beat features, mid-frequency drum beat features, and high-frequency drum beat features.

[0034] S203: Determine the vehicle's current state information based on drumbeat characteristics, speed signals, acceleration signals, and body pressure distribution signals.

[0035] Specifically, the vehicle's amplifier module can output an analog music signal xana(t). The ADC (Analogue-to-Digital Conversion) pin of the seat controller can receive this analog music signal xana(t) and convert it into a digital music signal x[n]. The sampling rate of the ADC pin can be 21.1kHz, so x[n] = xana(n / 21100), n = 0, 1, 2, ... To meet real-time requirements, the signal can be segmented according to hardware timer interrupts, taking the latest 512 sampling points as a frame each time to obtain discrete drum beat signals. A fourth-order Butterworth filter can be used, with specific design parameters extracting the cutoff frequency of 150 Hz as low-frequency drum beat features, 150-400 Hz as mid-frequency drum beat features, and above 400 Hz as high-frequency drum beat features. After extracting the drum beat features, the current state information of the vehicle can be determined based on the drum beat features, speed signal, acceleration signal, and body pressure distribution signal. The specific determination method can be found in the description of the above embodiment. Understandably, extracting the drum beat features from the music signal allows the subsequent control of the massage chair to incorporate these features, thus increasing the entertainment value.

[0036] S30: Determine the seat's motion command based on the current state information using a preset learning algorithm.

[0037] Specifically, the preset learning algorithm in this embodiment can be of various types, such as value-based, policy-based, and actor-critic. After determining the current state information of the vehicle, the preset learning algorithm can be used to process the current state information in order to determine the action command of the seat.

[0038] In one embodiment, taking the Q-learning algorithm (value-based) as the preset learning algorithm as an example, the preset learning algorithm is used to determine the action command of the seat based on the current state information, including: selecting the action command with the largest cumulative reward expectation value from the Q table according to the current state information, wherein the Q table records the cumulative reward expectation value of executing each action command under each state information.

[0039] Specifically, the strategy employed in the Q-learning algorithm can be an ε-greedy strategy, where ε is the exploration rate, with an initial value greater than or equal to 0.5. As the number of decision steps increases, ε can decay to a minimum value, which can be set to no higher than 0.05. In this embodiment, a uniformly random number within the interval [0, 1] is first generated. If this uniformly random number is less than the exploration rate ε, an action instruction corresponding to the current state information can be randomly selected uniformly from the Q-table. If the uniformly random number is greater than or equal to the exploration rate ε, the action instruction with the largest expected cumulative reward value corresponding to the current state information can be selected from the action instruction space.

[0040] S40: Controls the seat according to action commands.

[0041] Specifically, after determining the action command, the seat can be controlled according to the action command. In this embodiment, the seat back and / or cushion are provided with multiple massage points 20, and each massage point 20 is provided with a vibrator, an air bag, and a pressure sensor 10. The action command includes the vibration frequency of the vibrator and the inflation amount of the air bag. More specifically, the solenoid valve of the corresponding air bag can be driven by PWM (Pulse-Width Modulation) to continuously inflate the air bag according to the target pressure and the inflation amount ratio; at the same time, the motor of the corresponding vibrator is driven to vibrate according to the vibration frequency, which continues for the entire decision cycle. For example, if the decision cycle is 200 milliseconds, then it lasts for 200 milliseconds. It should be noted that in this embodiment, the distance between the pressure sensor 10 and the air bag and the vibrator is greater than or equal to a preset distance. Optionally, the preset distance can be 5 mm to prevent the vibrator and the air bag from affecting the pressure signal collected by the pressure sensor 10 when working. Figure 4 As shown.

[0042] S50: Obtain the reward value corresponding to the seat after executing the action command and the next state information of the vehicle.

[0043] Specifically, the reward value in this embodiment can be related to changes in body pressure distribution. Therefore, after the seat completes the action command, the body pressure distribution signal of the seat can be collected again. Then, the newly collected body pressure distribution signal is subtracted from the previously collected body pressure distribution signal to obtain the change in body pressure distribution. The reward value is then calculated based on the change in body pressure distribution. Specifically, the change in body pressure distribution can be multiplied by a preset coefficient, and the resulting value is used as the reward value. In addition, the determination of the next state information can be performed in accordance with the method for determining the current state information in the above embodiment, and will not be repeated here.

[0044] In some embodiments of the present invention, such as Figure 3 As shown, the reward value obtained after the seat completes the action command includes: S301: Acquire comfort data of the seat after the action command has been executed.

[0045] S302: Determine the reward value by querying a preset data table based on the comfort data, wherein the preset data table includes the correspondence between the reward value and the comfort data.

[0046] Specifically, during the vehicle development phase, multiple testers of varying heights and weights can be selected to conduct calibration tests in a static environment with a real vehicle. More than ten different types of music, such as rock, pop, and classical, can be played. After each state information-action command combination is executed, a comfort score is given to determine comfort data, and a reward value is assigned to obtain a preset data table. Subsequently, after the seat executes the action command, comfort data is acquired, and the reward value is determined by querying the preset data table based on this data. Optionally, if the comfort data differs significantly from the calibrated comfort data in the preset data table by more than a preset range, the reward value is smaller; the reward value can be negative.

[0047] S60: Update the preset learning algorithm based on the current state information, action command, reward value and next state information to improve the accuracy of the action command determination.

[0048] Specifically, after determining the reward value and the next state information, the preset learning algorithm can be updated based on the current state information, action command, reward value, and next state information, thereby improving the action command subsequently determined by the preset learning algorithm based on the current state information. More specifically, in some embodiments, updating the preset learning algorithm based on the current state information, action command, reward value, and next state information includes updating the Q-table based on the current state information, action command, reward value, and next state information.

[0049] Specifically, the Q-table includes a mapping between state information and multiple action instructions. After each action is executed and the reward and next state information are collected, the Q-table can be updated online with a delay time set to no more than 10 milliseconds. This can be achieved using the formula: Q(st,at)←Q(st,at)+α[rt+γmaxQ(st+1,a′)] Q(st,at)], where Q(st,at) can represent the cumulative expected value of the action instruction at corresponding to the current state information st, rt can represent the reward value, maxQ(st+1,a′) can represent the action instruction a′ with the highest cumulative expected value corresponding to the next state information st+1, α and γ are preset parameters, where α represents the learning rate, which can be 0.1, and γ represents the discount factor, which can be 0.9.

[0050] In summary, the vehicle seat control program in this embodiment of the invention can combine music signals to control the seat to perform personalized massage operations, link with the vehicle, and has a self-learning function, which can improve the comfort and entertainment of the seat.

[0051] Furthermore, the present invention proposes a computer-readable storage medium storing a vehicle seat control program thereon, wherein when the vehicle seat control program is executed by a processor, the vehicle seat control method of any of the above embodiments is implemented.

[0052] The computer-readable storage medium of this invention, through a processor executing a vehicle seat control program stored thereon, can control the seat to perform personalized massage operations in conjunction with music signals, achieve linkage with the vehicle, and has a self-learning function, which can improve the comfort and entertainment of the seat.

[0053] Figure 5 This is a block diagram of the vehicle seat control device in an embodiment of the present invention.

[0054] Furthermore, such as Figure 5 As shown, the present invention proposes a vehicle seat control device 500, which includes an acquisition module 501, a determination module 502, a control module 503 and an update module 504.

[0055] The acquisition module 501 is used to acquire the vehicle's music signal, speed signal, acceleration signal, and seat pressure distribution signal; the determination module 502 is used to determine the vehicle's current state information based on the music signal, speed signal, acceleration signal, and body pressure distribution signal, and to determine the seat's action command based on the current state information using a preset learning algorithm; the control module 503 is used to control the seat according to the action command; the acquisition module 501 is also used to acquire the reward value corresponding to the seat after executing the action command and the vehicle's next state information; the update module 504 is used to update the preset learning algorithm based on the current state information, action command, reward value, and next state information to improve the accuracy of the action command determination.

[0056] In some embodiments of the present invention, the determining module 502 is further configured to: perform analog-to-digital conversion and signal segmentation on the music signal to obtain discrete drum beat signals; use a Butterworth filter to filter the discrete drum beat signals to extract drum beat features of the discrete drum beat signals, the drum beat features including at least one of low-frequency drum beat features, mid-frequency drum beat features and high-frequency drum beat features; determine the current state information of the vehicle based on the drum beat features, speed signal, acceleration signal and body pressure distribution signal to improve the accuracy of action command determination.

[0057] In some embodiments of the present invention, the acquisition module 501 is further configured to: acquire comfort data of the seat after executing the action command; query a preset data table based on the comfort data to determine a reward value, wherein the preset data table includes the correspondence between the reward value and the comfort data.

[0058] In some embodiments of the present invention, the backrest and / or seat cushion of the seat are provided with a plurality of massage points 20, and each massage point 20 is provided with a vibrator, an air bag and a pressure sensor 10, wherein the distance between the pressure sensor 10 and the air bag and the vibrator is greater than or equal to a preset distance.

[0059] In some embodiments of the present invention, the action command includes the vibration frequency of the oscillator and the inflation amount of the air bag.

[0060] In some embodiments of the present invention, the preset learning algorithm is the Q-learning algorithm, and the determining module 502 is further configured to: select the action instruction with the largest cumulative reward expectation value from the Q table according to the current state information, wherein the Q table records the cumulative reward expectation value of executing each action instruction under each state information.

[0061] In some embodiments of the present invention, the update module 504 is further configured to update the Q table based on the current state information, action instructions, reward value and next state information.

[0062] It should be noted that the specific implementation of the vehicle seat control device in the embodiments of the present invention can be found in the specific implementation of the vehicle seat control method in the above embodiments. To avoid redundancy, it will not be described again here.

[0063] In summary, the vehicle seat control device in this embodiment of the invention can combine music signals to control the seat to perform personalized massage operations, link with the vehicle, and has a self-learning function, which can improve the comfort and entertainment of the seat.

[0064] Figure 6 This is a vehicle block diagram according to an embodiment of the present invention.

[0065] Furthermore, such as Figure 6 As shown, the present invention proposes a vehicle 600, which includes the seat control device 500 of the vehicle in the above embodiment.

[0066] The vehicle of this invention, through the seat control device of the vehicle described in the above embodiment, can control the seat to perform personalized massage operations in conjunction with music signals, link with the vehicle, and has a self-learning function, which can improve the comfort and entertainment of the seat.

[0067] Furthermore, other components and functions of the vehicle in the embodiments of the present invention are known to those skilled in the art, and will not be described in detail here to reduce redundancy.

[0068] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0069] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0070] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0071] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0072] Furthermore, the terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying relative importance, or implicitly specifying the number of technical features indicated in this embodiment. Therefore, features defined with terms such as "first" and "second" in the embodiments of this invention can explicitly or implicitly indicate that the embodiment includes at least one of those features. In the description of this invention, the word "multiple" means at least two or more, such as two, three, four, etc., unless otherwise explicitly specified in the embodiments.

[0073] In this invention, unless otherwise explicitly specified or limited in the embodiments, the terms "installation," "connection," "joining," and "fixing" appearing in the embodiments should be interpreted broadly. For example, a connection can be a fixed connection, a detachable connection, or an integral part; it can also be a mechanical connection, an electrical connection, etc. Of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components, or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific implementation.

[0074] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0075] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A seat control method of a vehicle, characterized by, The method includes: S10: Acquire the music signal, speed signal, acceleration signal and body pressure distribution signal of the vehicle and the seat; S20: Determine the current state information of the vehicle based on the music signal, the speed signal, the acceleration signal, and the body pressure distribution signal; S30: Based on the current state information, a preset learning algorithm is used to determine the action command of the seat; S40: Control the seat according to the action command; S50: Obtain the reward value corresponding to the seat after executing the action command and the next state information of the vehicle; S60: Update the preset learning algorithm based on the current state information, the action command, the reward value, and the next state information to improve the accuracy of the action command determination.

2. The vehicle seat control method according to claim 1, characterized in that, The current state information of the vehicle is determined based on the music signal, the speed signal, the acceleration signal, and the body pressure distribution signal, including: S201: Perform analog-to-digital conversion and signal segmentation on the music signal to obtain discrete drum beat signals; S202: The discrete drum beat signal is filtered using a Butterworth filter to extract the drum beat features of the discrete drum beat signal, wherein the drum beat features include at least one of low-frequency drum beat features, mid-frequency drum beat features, and high-frequency drum beat features; S203: Determine the current state information of the vehicle based on the drumbeat characteristics, the speed signal, the acceleration signal, and the body pressure distribution signal.

3. The vehicle seat control method according to claim 1, characterized in that, Obtain the reward value corresponding to the seat after executing the action command, including: S301: Obtain comfort data of the seat after executing the action command; S302: Query a preset data table based on the comfort data to determine the reward value, wherein the preset data table includes the correspondence between the reward value and the comfort data.

4. The vehicle seat control method according to claim 1, characterized in that, The backrest and / or seat cushion of the seat are provided with multiple massage points (20), and each massage point (20) is provided with a vibrator, an air bag and a pressure sensor (10), wherein the distance between the pressure sensor (10) and the air bag and the vibrator is greater than or equal to a preset distance.

5. The vehicle seat control method according to claim 4, characterized in that, The action command includes the vibration frequency of the oscillator and the inflation amount of the air bag.

6. The vehicle seat control method according to claim 1, characterized in that, The preset learning algorithm is the Q-learning algorithm. Based on the current state information, the preset learning algorithm is used to determine the action commands of the seat, including: Based on the current state information, the action instruction with the largest cumulative reward expectation value is selected from the Q table, wherein the Q table records the cumulative reward expectation value of executing each action instruction under each state information.

7. The vehicle seat control method according to claim 6, characterized in that, The preset learning algorithm is updated based on the current state information, the action instruction, the reward value, and the next state information, including: The Q table is updated based on the current state information, the action instruction, the reward value, and the next state information.

8. A computer-readable storage medium, characterized in that, It stores a vehicle seat control program, which, when executed by a processor, implements the vehicle seat control method according to any one of claims 1-7.

9. A vehicle seat control device (500), characterized in that, The device (500) includes: The acquisition module (501) is used to acquire the music signal, speed signal, acceleration signal and body pressure distribution signal of the vehicle and the seat. The determining module (502) is used to determine the current state information of the vehicle based on the music signal, the speed signal, the acceleration signal and the body pressure distribution signal, and to determine the action command of the seat based on the current state information using a preset learning algorithm; The control module (503) is used to control the seat according to the action command; The acquisition module (501) is also used to acquire the reward value corresponding to the seat after executing the action command and the next state information of the vehicle; The update module (504) is used to update the preset learning algorithm according to the current state information, the action instruction, the reward value and the next state information, so as to improve the determination accuracy of the action instruction.

10. A vehicle (600), characterized in that, Includes the seat control device (500) of the vehicle as described in claim 9.

Images