Vehicle suspension control method and device, computer equipment and storage medium

Abstract

The invention relates to a vehicle suspension control method and device, computer equipment and a storage medium. The method comprises the steps that an interaction mode is obtained; obtaining interaction data corresponding to the interaction mode according to an interaction module corresponding to the interaction mode, and determining a suspension control instruction according to the interaction data; according to the suspension control instruction, the height of a vehicle suspension is adjusted; by means of the method, the problem that in the prior art, the suspension adjusting mode is single can be solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a vehicle suspension control method, device, computer equipment, and storage medium. Background Art

[0002] With the development of intelligent automobile chassis, the suspension height can be adjusted in specific situations to meet requirements such as off-road passability. However, user control is limited to a single interaction method, such as using the central control screen for operation, which cannot meet the needs and preferences of different users, limiting the user's interactive experience and operational convenience. Summary of the Invention

[0003] Based on this, a vehicle suspension control method, device, computer equipment and storage medium are provided to improve the problem of single suspension adjustment method in the prior art.

[0004] In one aspect, a vehicle suspension control method is provided, comprising:

[0005] Get the interaction mode;

[0006] acquiring, according to an interaction module corresponding to the interaction mode, interaction data corresponding to the interaction mode, and determining a suspension control instruction according to the interaction data;

[0007] The vehicle suspension height is adjusted according to the suspension control instruction.

[0008] In one embodiment, determining the suspension control instruction according to the interaction data includes:

[0009] In the case where the interaction mode is gesture interaction, determining a target image containing a hand as the interaction data, so as to obtain a gesture category according to the target image; or

[0010] In the case where the interaction mode is gesture interaction, determining a target image containing a body gesture as the interaction data, so as to obtain a human gesture category based on the target image; or

[0011] In a case where the interaction mode is key point interaction, determining a target image including hand and / or body posture as the interaction data, so as to obtain a key point posture category based on the target image;

[0012] The suspension control instruction is determined according to the gesture category, the human body posture category or the key point posture category.

[0013] In one embodiment, acquiring the interaction mode according to the interaction module corresponding to the interaction mode includes:

[0014] Receive a mode selection instruction from a user and obtain a target location of the user, wherein the target location includes inside or outside the vehicle;

[0015] In response to the user's mode selection instruction and according to the user's target position, the interaction mode is determined.

[0016] In one embodiment, after obtaining the interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode, the method further includes:

[0017] configuring a state machine model, wherein the state machine model determines a target state of suspension control according to the interaction data;

[0018] executing the suspension control instructions allowed under the target state according to the target state;

[0019] Wherein, when the target position is switched, the state machine model inherits the target state.

[0020] In one embodiment, after determining the interaction mode, the method further includes:

[0021] According to the target position, the external vehicle feedback component or the internal vehicle feedback component corresponding to the interactive mode is called to provide information feedback, wherein the external vehicle feedback component includes a wiper, and the internal vehicle feedback component includes a central control screen.

[0022] In one embodiment, before adjusting the vehicle suspension height according to the suspension control instruction, the method further includes:

[0023] In the event that the suspension control command recognition fails, the interactive mode is switched according to a preset conversion sequence.

[0024] In one embodiment, after obtaining the interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode, the method further includes:

[0025] Uploading the interaction data to the cloud for data enhancement in the cloud to obtain pre-processed data;

[0026] The pre-processed data is received, and a suspension control instruction is determined based on the pre-processed data.

[0027] In another aspect, a vehicle suspension control device is provided, the device comprising:

[0028] A first acquisition module is used to acquire an interaction mode;

[0029] A second acquisition module is used to acquire interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode;

[0030] an identification module, configured to determine a suspension control instruction based on the interaction data;

[0031] The execution module is used to adjust the vehicle suspension height according to the suspension control instruction.

[0032] In another aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method is implemented when the processor executes the computer program.

[0033] A computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0034] The above-mentioned vehicle suspension control method, device, computer equipment and storage medium first obtain the interaction mode, obtain the interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode, and then identify and determine the suspension control instructions, thereby adjusting the vehicle suspension height. By providing users with multiple modes to choose from, users can operate flexibly. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 1 is a flow chart of a vehicle suspension control method according to an embodiment;

[0036] Figure 2 is a structural block diagram of a vehicle suspension control device according to one embodiment;

[0037] Figure 3 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0039] In one embodiment, a vehicle suspension control method is as follows: Figure 1 As shown, the following steps are included:

[0040] Step 110: Obtain the interaction mode.

[0041] During actual implementation, the vehicle can authenticate the driver and passengers in a variety of ways. For example, when a person approaches the vehicle and activates and unlocks the car through a mobile phone application, the ID (Identity Document) of the interactive object is confirmed; or the person confirms the interactive identity through the large screen inside the car; the person whose identity is confirmed is the user in this implementation.

[0042] Users can choose to activate the interaction mode of suspension interaction through their mobile phones or the large screen inside the car. Based on the interaction module configured in the vehicle, the available interaction modes may include gesture interaction mode, posture interaction mode, key point recognition interaction mode, voice interaction mode, etc. On the other hand, in combination with other interaction tools, such as the central control large screen, mobile phone terminals, etc., it can also include central control interaction or mobile phone interaction.

[0043] Step 120: Acquire interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode.

[0044] Different interaction modes correspond to different interaction modules. For example, the voice interaction mode corresponds to the voice interaction module, which exemplarily includes functional units such as voice acquisition, speech recognition (ASR), and natural language processing (NLP); the gesture interaction mode corresponds to the gesture interaction module, which exemplarily includes functional units such as gesture acquisition and gesture recognition.

[0045] The interaction modules associated with different modes are predefined and are called accordingly in response to the user's mode selection instruction.

[0046] In another embodiment, the interaction mode inside and outside the vehicle can correspond to different interaction modules. During actual implementation, the vehicle receives the user's mode selection instruction and obtains the user's target position, responds to the user's mode selection instruction, and determines the interaction mode based on the user's target position.

[0047] Exemplarily, the vehicle can obtain mode selection instructions through a mobile phone, a central control screen, or the user's voice commands. When the vehicle recognizes that the user is outside the vehicle and the user selects one of the modes such as gesture interaction mode, posture interaction mode, key point recognition interaction mode, and voice interaction mode, the vehicle accordingly determines that the interaction mode to be executed is the gesture interaction mode outside the vehicle, the posture interaction mode outside the vehicle, the key point recognition interaction mode outside the vehicle, or the voice interaction mode outside the vehicle; when the user is inside the vehicle and the user selects one of the modes such as gesture interaction mode, posture interaction mode, key point recognition interaction mode, and voice interaction mode, the vehicle determines that the interaction mode to be executed is the gesture interaction mode inside the vehicle, the posture interaction mode inside the vehicle, the key point recognition interaction mode inside the vehicle, the voice interaction mode inside the vehicle, etc.

[0048] After the vehicle determines the interaction mode, it calls the interaction module inside the vehicle corresponding to the interaction mode, or the interaction module outside the vehicle corresponding to the interaction mode to obtain the interaction data; for example, the gesture interaction mode outside the vehicle, the posture interaction mode outside the vehicle, and the key point recognition interaction mode outside the vehicle correspond to calling the camera outside the vehicle; the voice interaction mode outside the vehicle corresponds to calling the microphone outside the vehicle; the gesture interaction mode inside the vehicle, the posture interaction mode inside the vehicle, and the key point recognition interaction mode inside the vehicle correspond to calling the camera inside the vehicle; the voice interaction mode inside the vehicle corresponds to calling the microphone inside the vehicle.

[0049] The user's target location can be obtained based on different means, including but not limited to sensor sensing technology and image processing technology to identify the user's location.

[0050] In some embodiments, the interaction module includes an acquisition component for the vehicle to obtain user data (such as a microphone for voice interaction, a camera for gesture interaction, etc.), and also includes a feedback component for the vehicle to feed back information to the user. For example, after determining the interaction mode, the external feedback component or the internal feedback component corresponding to the interaction mode is called according to the target location to provide information feedback. When the user is outside the vehicle, the wiper is used as the external feedback component, and a variety of interaction modes are provided to the user on the mobile phone. At this time, the user manually selects. When the user selects a certain interaction mode, the vehicle shakes the wiper once to inform the user that the startup has been successful. When the user is inside the vehicle, the central control screen can be used as the internal feedback component.

[0051] According to the user's target location, the appropriate external vehicle feedback component or internal vehicle feedback component is adaptively selected to flexibly meet the user's interaction needs.

[0052] Step 130: Determine suspension control instructions based on the interaction data.

[0053] For example, in voice interaction mode, the interaction data is voice interaction data. The vehicle uses an audio capture device such as a microphone inside or outside the vehicle to capture voice. The voice recognition algorithm identifies the user's timbre, and the user's voice is used as the interaction object. Speech recognition is first performed, converting the user's voice commands into text for computer processing and understanding. The recognized text is then deeply analyzed to understand the user's intentions and needs. This includes semantic extraction, contextual interaction, information source search, and dialogue management, thereby identifying suspension control commands such as "start suspension interaction" and "pause adjustment."

[0054] In another possible implementation, when the interaction mode is a gesture interaction mode, a posture interaction mode, or a key point interaction mode, a target image of the user is acquired and used as interaction data, thereby determining a suspension control instruction based on the target image.

[0055] Exemplarily, in gesture interaction mode, the interaction data is gesture interaction data, such as obtaining a target image containing the user's hand as interaction data, performing image recognition on the target image containing the hand, and detecting defined gesture categories through target detection or image classification technologies. For example, there are predefined thumbs-up gestures, fist gestures, OK gestures, etc. Different gesture categories correspond to different suspension control instructions.

[0056] For example, in gesture interaction mode, the interaction data is gesture interaction data. For example, a target image containing a body posture is obtained as interaction data, and the target image containing the body posture is input into a pre-established gesture recognition model to obtain the user's human posture category. Different human posture categories correspond to different suspension control instructions. The gesture recognition model can accurately determine the position and movement of each human joint in a video composed of a target image or a target image sequence, and perform human skeleton extraction and action recognition. First, human skeleton extraction uses video or depth data to capture human movements. Then, image processing algorithms such as skeleton extraction algorithms, color segmentation, and background subtraction are used to extract human skeleton information from the image, including human key points and edges connecting key points. Second, action recognition uses machine learning or deep learning algorithms to recognize the extracted human skeleton information. Deep learning technologies such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory networks (LSTMs) are typically used.

[0057] For example, in the key point interaction mode, the interaction data can be a target image including the user's hand. A pre-trained deep learning model such as a convolutional neural network (CNN) or a recurrent neural network (RNN) is used to recognize the key points of the hand, detect the key point positions of the hand (such as fingers, palms, etc.), and then infer the hand posture information as the key point posture category based on the spatial relationship of these key points.

[0058] In the key point interaction mode, the interaction data can also be a target image including the user's body posture. A pre-trained deep learning model is used to identify human key points, detect the key point positions of the human body, such as the head, shoulders, wrists, knees, etc. from the image or video, and predict the position of each key point of the human body through regression or classification. The posture information of the human body, that is, the relative position and angle relationship between the various joints of the human body, is estimated as the key point posture category. Different key point posture categories correspond to different suspension control instructions.

[0059] It can be understood that, in the key point interaction mode, hand key point recognition and human key point recognition can be selected based on the parts contained in the acquired target image; or in some embodiments, in the key point interaction mode, human key point recognition and hand key point recognition can be performed simultaneously, and the final executed suspension control instruction can be judged based on the normalized confidence level.

[0060] In the above process, the suspension control instruction is determined according to the recognized gesture category, human posture category or key point posture category.

[0061] Exemplarily, the suspension control instructions include initialization instructions, height increase instructions, height decrease instructions, pause adjustment instructions, reset instructions, exit instructions, etc. Different gesture categories, human posture categories, key point posture categories, and voice instructions are pre-configured for each suspension control instruction.

[0062] Step 140: Adjust the vehicle suspension height according to the suspension control instruction.

[0063] For smart chassis, it is common to use an adjustable suspension system. Examples of adjustable suspension systems include air suspension, which uses an air compressor to generate compressed air and adjusts the ground clearance of the car chassis through the compressed air; and hydraulic suspension, which changes the height of the car body by adjusting the amount of hydraulic oil.

[0064] Taking the gesture interaction mode as an example, in one embodiment, the gesture categories include dynamic gestures and static gestures. When the user makes a static gesture of "OK", the chassis suspension is initialized, the height of the center point of the OK gesture is identified, the height of the center point of the OK gesture is used as the reference height, and the suspension is adjusted to the initial height preset by the system. The user then adjusts the suspension height up and down through the gesture category. For example, if the gesture category is a dynamic gesture of the hand moving upward from the reference height, it is considered that the user has issued a suspension increase instruction, and the intelligent chassis can adjust the vehicle suspension height. The specific value of the increase can be determined based on the pixel height of the dynamic gesture moving in the image. Generally, a mapping relationship between pixel height and suspension adjustment height is pre-established, and the specific value of the increase is determined from the mapping relationship. When the gesture category is identified as a static gesture of making a fist, the suspension adjustment is paused; when the static gesture of "thumbs-up" is identified, the suspension is reset, and the function ends and exits.

[0065] During the gesture interaction process of the above process, the vehicle suspension is initialized according to the initialization gesture, including determining the reference height according to the height of the initialization gesture, and determining the height change of the vehicle suspension according to the height change of the dynamic gesture relative to the reference height, thereby meeting the suspension adjustment needs of users of different heights.

[0066] In some possible embodiments, the vehicle suspension is initialized according to the initialization posture (human body posture or key point posture), including determining a reference height based on the height of the initialization posture, and determining the height change of the vehicle suspension based on the height change of the dynamic posture (human body dynamic posture or key point dynamic posture) relative to the reference height.

[0067] Through the above-mentioned vehicle suspension control method, users can choose the interaction mode that suits their current needs. The vehicle calls the corresponding interaction module according to the interaction mode, obtains the user's interaction data, identifies the interaction data, and determines the user's expected suspension control instructions, thereby adjusting the vehicle suspension height according to the suspension control instructions. Human-vehicle interaction is no longer limited to a single method, providing users with a flexible chassis interaction experience.

[0068] In some cases, human-vehicle interaction may fail. For example, gesture recognition may fail due to poor or changing lighting, camera distance, or background clutter. Voice interaction may also fail due to noise. To address the situation where suspension control command recognition fails, some possible embodiments provide a preset transition sequence for the interaction mode. After the user selects the initial interaction mode, if recognition fails, the preset transition sequence is used to switch.

[0069] For example, if the user selects gesture interaction mode and the suspension control command recognition fails, the system will automatically switch in the order of gesture interaction mode-posture interaction mode-key point recognition interaction mode-voice interaction mode, reducing the user's resetting process.

[0070] In some embodiments, to address data security and limited computing power of vehicle terminals, cloud services are provided to assist in identifying suspension control commands. Exemplarily, the process includes:

[0071] After obtaining the interaction data corresponding to the interaction mode, the vehicle terminal uploads the interaction data to the cloud for the cloud to perform data enhancement to obtain pre-processed data; the vehicle terminal then receives the pre-processed data and determines the suspension control instructions based on the pre-processed data.

[0072] In the aforementioned multiple interaction modes, the recognition processing of target images (gesture interaction, posture interaction, key point recognition interaction) and voice (voice interaction) enhances robustness in complex and changing environments, and uniquely processes image noise and voice noise. The data enhancement process at least includes noise processing, as exemplified below:

[0073] Speech noise processing:

[0074] Whether the user is inside or outside the vehicle, there will be interference from voice noise. To eliminate noise and filter out clear speech, the received speech is extracted from the spectral features. To protect the user's timbre privacy, the speech is encoded through a transformer and uploaded to the cloud. The spectrum is then modeled using a large cloud model to restore the clear speech signal. The cloud model also separates the user's speech from the background sound, retaining the target speech signal. Key commands in the user's speech (such as "start suspension interaction" and "pause adjustment") are used as model targets, and the corresponding targets are enhanced. After filtering and cleaning in the cloud, the signal is transmitted back to the vehicle terminal for speech recognition.

[0075] Image noise processing:

[0076] To protect user privacy, real-time image data is encoded using the Swin transformer and uploaded to the cloud for gradual denoising and restoration. In scenes with insufficient lighting or complex backgrounds, gesture or body posture features are automatically enhanced. To combat lighting changes, the cloud-based large model models local and global image features to enhance the recognition of gesture and body key points. To adapt to dynamic backgrounds, the large model's semantic understanding capabilities, combined with semantic segmentation technology, segment and filter dynamic backgrounds (such as pedestrians, trees, and vehicles) in the image, retaining only the user's relevant actions and features. To address occlusion recovery, when gestures or body postures are partially occluded, the cloud-based large model is used for posture completion, recovering missing key points through prior knowledge and contextual inference.

[0077] By uploading data to the cloud for processing, the computing power requirements for vehicle terminals are effectively reduced, and recognition accuracy can also be improved.

[0078] The vehicle suspension control method provided in this application can facilitate users to adjust the suspension both inside and outside the vehicle. In some possible embodiments, a unified connection is established for in-vehicle and out-vehicle recognition, ensuring consistency of data in multiple interaction modes when switching between the two scenes. For example:

[0079] Unification of interactive objects:

[0080] After the user confirms their interaction identity through the mobile app or the in-car large screen, the interaction object ID remains consistent on the edge device and in the cloud when the data inside and outside the car are linked, ensuring that the system recognizes the same user. Whether switching from inside the car to outside or back to inside, the interaction object remains unchanged.

[0081] Identify logical connections:

[0082] After obtaining the interaction data corresponding to the interaction mode, the vehicle terminal configures a state machine model. The state machine model determines the target state of the suspension control based on the interaction data; based on the target state, the suspension control instructions allowed under the target state are executed; among them, when the target position is switched, the state machine model inherits the target state.

[0083] The explanation is as follows: The state machine model is a model used to describe the different states of a system or object under different conditions and the way they convert to each other. In one implementation of this embodiment, a state machine model is designed for state migration, and the interaction process inside and outside the car is abstracted into a series of states (such as initialization, interacting, paused, and exited), and state transition rules are defined. For example: after the suspension is adjusted to a certain height through gestures outside the car, the target state switches to "interacting"; after the user enters the car, the system detects identity consistency and directly continues the "interacting" state. Then, for the real-time synchronization mechanism, edge-cloud collaboration is used to synchronize the data and status inside and outside the car in real time: when adjustments are made outside the car, the vehicle posture and suspension height are displayed through a mobile phone application or the large screen of the car; when adjustments continue to be made inside the car, the real-time data outside the car is directly inherited to avoid user resetting.

[0084] It can be understood that in the initialization state, the vehicle runs and executes the initialization instructions; in the interactive state, the vehicle can run the suspension control instructions expected by the user; in the paused state, the vehicle does not adjust the suspension height, but keeps calling the interactive module, and identifies the user's interaction data in real time, waiting for the user to issue an instruction to continue adjustment; in the exit state, the vehicle no longer adjusts the suspension height or calls the interactive module.

[0085] The following exemplifies the control process of the vehicle suspension control method provided by this application inside and outside the vehicle:

[0086] When the user approaches the vehicle, they activate and unlock the car through the mobile app, and choose to start the chassis suspension interaction mode outside or inside the car through the mobile phone or the large screen inside the car. At this time, the ID of the interaction object has been confirmed, and then the chassis interaction is carried out:

[0087] 1. When selecting the interaction mode outside the vehicle:

[0088] 1.1. When the vehicle's external suspension interaction mode is enabled, the user is provided with four interaction modes to choose from on the mobile phone. The user must manually select one.

[0089] 1.2. When the user selects gesture interaction mode, the car's windshield wiper shakes once to notify the user that the interaction has been successfully initiated. The car's cameras then activate, capturing real-time footage of pedestrians ahead. The gesture recognition algorithm detects the user's hands and identifies the gesture type. When the user makes an "OK" gesture, the chassis suspension is initialized. The user can then adjust the suspension height up or down using gestures, or perform a "dance" with the vehicle. If a fist gesture is recognized, suspension adjustments are paused. If a thumbs-up gesture is recognized, the suspension resets, the function ends, and the user exits, successfully completing the gesture interaction. If gesture recognition fails due to factors such as dim lighting, varying camera distance, or background clutter, the car's windshield wiper shakes twice to notify the user that the mode has failed. The user can then manually select a different recognition mode or end the function. After 10 seconds, the system automatically switches to the next recognition mode, cycling through gesture interaction mode, posture interaction mode, key point recognition interaction mode, and voice interaction mode. The user can manually end the function.

[0090] 1.3. When the user manually selects gesture interaction mode, the car's computer notifies the user of successful activation by shaking the windshield wipers once. The car's cameras activate real-time video of the user in front of it, and the human gesture recognition algorithm detects the user and identifies the gesture type. When the user's arms are extended, the chassis suspension is initialized. The user then extends their arms and swings them left and right, and the chassis suspension adjusts height accordingly, or the vehicle and the user dance together. When the user's hands are extended forward, suspension adjustments are paused. When the user's bowing gesture is recognized, the suspension resets, the function ends, and the gesture interaction mode is successfully completed. Similarly, if the gesture interaction mode fails due to complex and changing external conditions, the car's computer notifies the user by shaking the windshield wipers twice. The user can manually select the next recognition mode or wait 10 seconds for the system to automatically switch to the next recognition mode.

[0091] 1.4. When the user selects the key point recognition interaction mode, the car computer will also inform the user that the startup has been successful by shaking the wiper once. The car computer camera will start to shoot the pedestrians in front in real time, and the hand and 21 key points of the hand will be detected through the key point recognition algorithm. When the OK gesture is recognized in a key point manner, the chassis suspension is initialized, and then the user can adjust the suspension height by interacting with the hand up and down, or dance with the car. When a fist is recognized in a key point manner, the suspension interaction is suspended; when the key point recognizes that the user makes a heart gesture, the suspension is reset, the function ends and exits, and the key point recognition interaction mode is successfully completed. Similarly, when the external environment changes, hand occlusion, etc. cause the recognition to fail, the car computer will inform the user that this mode recognition failed by shaking the wiper twice. The user can switch to the next interaction mode manually or automatically.

[0092] 1.5. When the user selects voice interaction mode, the car computer also notifies the user of successful activation by shaking the windshield wipers once. The car computer's audio reception is enabled to receive the user's voice in real time. When the user speaks a predefined phrase, the voice recognition algorithm identifies the user's voice and uses the voice owner as the interaction object. When the user speaks the phrase "start suspension interaction", the chassis suspension is initialized, and the user then uses voice to switch to the car computer to adjust the suspension. When the user speaks the phrase "pause suspension adjustment", the suspension adjustment is paused. When the user speaks phrases such as praise, the suspension resets, and the function ends and exits, successfully completing the voice interaction mode. If the voice recognition interaction fails due to factors such as outdoor noise or murmurs, the car computer notifies the user that the recognition mode has failed by shaking the windshield wipers twice. The user can also manually or automatically switch to the next interaction mode.

[0093] 2. When selecting the suspension interaction mode in the car:

[0094] 2.1. When selecting the in-car suspension interaction mode, the user is presented with four interactive modes to choose from on the central control screen or mobile app. The user manually selects the mode, and the interior ambient lighting turns on. The car's head unit plays interesting background music, and the ambient lighting also animates to the music. The central control screen displays the entire vehicle in 3D, allowing the user to see the vehicle's real-time posture.

[0095] 2.2. When the user selects gesture interaction mode, the voice assistant informs the user that this recognition mode has been successfully activated. The camera at the front of the vehicle in the cabin starts real-time recording, and the gesture recognition algorithm detects the user's hand and gesture type. When the user makes an OK gesture, the chassis suspension is initialized. The initial suspension height position corresponds to the height of the OK gesture center point. The user then adjusts the suspension height up or down through gestures, and the user can watch the dynamic adjustment of the 3D vehicle on the large screen. When a fist is recognized, the suspension adjustment is paused; when a thumbs-up gesture is recognized, the suspension is reset, the voice assistant expresses praise to the user, and the function ends and exits. If gesture recognition fails due to factors such as long-term occlusion or darkness in the cabin, the voice assistant informs the user of the failed interaction mode. The user can choose another interaction mode or the vehicle computer will automatically adjust to the next interaction mode. The user can manually choose to end this function.

[0096] 2.3. When the user selects gesture interaction mode, the voice assistant informs the user that this mode has been successfully activated. The camera at the front of the vehicle in the cabin starts real-time recording, and the human gesture recognition algorithm is used to detect the scene in the same way as the scene outside the vehicle. After initialization, the suspension is dynamically adjusted based on the human gesture category, and the vehicle's posture is displayed on the large screen of the vehicle in 3D. This mode is suitable for fun interactions with children or interactions in scenes with ample rear space, and can meet the needs of upper body gesture recognition in the cabin. If recognition fails due to factors such as long-term occlusion or lighting changes, the voice assistant will inform the user that this mode has failed, and the user can manually or the vehicle computer can automatically adjust to the next interaction mode to continue interaction.

[0097] 2.4. When the user selects the keypoint recognition interaction mode, the voice assistant informs the user that this mode has been successfully activated. The front camera in the cabin starts real-time recording, and the human keypoint recognition algorithm detects the hands and hand keypoints. The interaction method is the same as outside the vehicle. If the environment causes recognition failure, the user can adjust to another recognition mode or automatically adjust.

[0098] 2.5. When the user selects voice interaction mode, the voice assistant informs the user that this mode has been successfully activated. The in-cabin voice recognition module activates and uses the voice recognition algorithm to identify the user's voice. Similar to external interaction, the user's voice is used as the interaction object to interact with the suspension. Similarly, the user can select other interaction modes as desired.

[0099] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0100] In one embodiment, Figure 2 As shown, a vehicle suspension control device is provided, comprising: a first acquisition module 210, a second acquisition module 220, an identification module 230 and a row module, wherein:

[0101] A first acquisition module 210 is used to acquire an interaction mode;

[0102] A second acquisition module 220 is configured to acquire interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode;

[0103] an identification module 230 for determining suspension control instructions based on the interaction data;

[0104] The execution module 240 is used to adjust the vehicle suspension height according to the suspension control instruction.

[0105] The vehicle suspension control device provided in this application provides users with a variety of modes to choose from, making it convenient for users to operate flexibly.

[0106] In one embodiment, when the interaction mode is gesture interaction, the second acquisition module 220 determines a target image containing a hand as interaction data, and the recognition module 230 obtains a gesture category based on the target image; or

[0107] In the case where the interaction mode is gesture interaction, the second acquisition module 220 determines a target image containing a body gesture as interaction data, and the recognition module 230 obtains a human gesture category based on the target image; or

[0108] In the case where the interaction mode is key point interaction, the second acquisition module 220 determines a target image containing hand and / or body gestures as interaction data, and the recognition module 230 obtains a key point gesture category based on the target image;

[0109] The recognition module 230 determines the suspension control instruction according to the gesture category, the human body posture category or the key point posture category.

[0110] In one embodiment, the second acquisition module 220 acquires the user's target location, which includes inside or outside the vehicle; the first acquisition module 210 receives the user's mode selection instruction, and in response to the user's mode selection instruction, determines the interaction mode according to the target location, and the second acquisition module 220 calls the corresponding interaction module inside or outside the vehicle to obtain interaction data corresponding to the interaction mode.

[0111] In one embodiment, a state management module is further included, which is used to configure a state machine model. The state machine model determines the target state of the suspension control based on the interaction data; executes the suspension control instructions allowed in the target state based on the target state; wherein, when the target position is switched, the state machine model inherits the target state.

[0112] In one embodiment, the second acquisition module 220 calls the external vehicle feedback component or the internal vehicle feedback component corresponding to the interaction mode to provide information feedback according to the target position, wherein the external vehicle feedback component includes a wiper and the internal vehicle feedback component includes a central control screen.

[0113] In one embodiment, when the suspension control instruction recognition fails, the first acquisition module 210 switches the interaction mode according to a preset conversion sequence.

[0114] In one embodiment, the second acquisition module 220 uploads the interaction data to the cloud for data enhancement in the cloud to obtain pre-processed data. The recognition module 230 receives the pre-processed data and determines the suspension control instruction according to the pre-processed data.

[0115] The specific definitions of the vehicle suspension control device can be found in the definitions of the vehicle suspension control method above and will not be repeated here. Each module in the aforementioned vehicle suspension control device may be implemented in whole or in part via software, hardware, or a combination thereof. Each of these modules may be embedded in or independent of a processor in a computer device in hardware form, or may be stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0116] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a vehicle suspension control method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0117] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0118] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed:

[0119] Get the interaction mode;

[0120] Acquire interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode, and determine the suspension control instruction according to the interaction data;

[0121] Adjust the vehicle suspension height according to the suspension control instructions.

[0122] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0123] In the case where the interaction mode is gesture interaction, a target image containing a hand is determined as interaction data to obtain a gesture category according to the target image; or

[0124] In the case where the interaction mode is gesture interaction, a target image containing a body gesture is determined as interaction data to obtain a human body gesture category based on the target image; or

[0125] In the case where the interaction mode is key point interaction, determining a target image including hand and / or body posture as interaction data, so as to obtain a key point posture category according to the target image;

[0126] Suspension control instructions are determined according to the hand gesture category, the human body posture category or the key point posture category.

[0127] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0128] Receive the user's mode selection command and obtain the user's target location, which may be inside or outside the vehicle;

[0129] In response to the user's mode selection instruction and according to the user's target position, the interaction mode is determined.

[0130] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0131] Configure a state machine model, which determines the target state of the suspension control based on the interaction data;

[0132] According to the target state, executing the suspension control instructions allowed in the target state;

[0133] Among them, when the target position is switched, the state machine model inherits the target state.

[0134] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0135] According to the target position, the external vehicle feedback component or the internal vehicle feedback component corresponding to the interactive mode is called to provide information feedback, wherein the external vehicle feedback component includes the wiper, and the internal vehicle feedback component includes the central control screen.

[0136] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0137] In the event that the suspension control command recognition fails, the interaction mode is switched according to the preset conversion sequence.

[0138] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0139] Upload the interaction data to the cloud so that the cloud can perform data enhancement to obtain pre-processed data;

[0140] The pre-processed data is received and a suspension control instruction is determined based on the pre-processed data.

[0141] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0142] Get the interaction mode;

[0143] Acquire interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode, and determine the suspension control instruction according to the interaction data;

[0144] Adjust the vehicle suspension height according to the suspension control instructions.

[0145] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0146] In the case where the interaction mode is gesture interaction, a target image containing a hand is determined as interaction data to obtain a gesture category according to the target image; or

[0147] In the case where the interaction mode is gesture interaction, a target image containing a body gesture is determined as interaction data to obtain a human body gesture category based on the target image; or

[0148] In the case where the interaction mode is key point interaction, determining a target image including hand and / or body posture as interaction data, so as to obtain a key point posture category according to the target image;

[0149] Suspension control instructions are determined according to the hand gesture category, the human body posture category or the key point posture category.

[0150] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0151] Receive the user's mode selection command and obtain the user's target location, which may be inside or outside the vehicle;

[0152] In response to the user's mode selection instruction and according to the user's target position, the interaction mode is determined.

[0153] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0154] Configure a state machine model, which determines the target state of the suspension control based on the interaction data;

[0155] According to the target state, executing the suspension control instructions allowed in the target state;

[0156] Among them, when the target position is switched, the state machine model inherits the target state.

[0157] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0158] According to the target position, the external vehicle feedback component or the internal vehicle feedback component corresponding to the interactive mode is called to provide information feedback, wherein the external vehicle feedback component includes the wiper, and the internal vehicle feedback component includes the central control screen.

[0159] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0160] In the event that the suspension control command recognition fails, the interaction mode is switched according to the preset conversion sequence.

[0161] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0162] Upload the interactive data to the cloud for data enhancement and pre-processing; receive the pre-processed data and determine the suspension control instructions based on the pre-processed data.

[0163] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0164] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0165] The above embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A vehicle suspension control method, characterized in that: include: Get the interaction mode; Acquire interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode, and determine the suspension control instruction according to the interaction data; The vehicle suspension height is adjusted according to the suspension control instruction.

2. The vehicle suspension control method according to claim 1, characterized in that: Determining the suspension control instruction according to the interaction data includes: In the case where the interaction mode is gesture interaction, determining a target image including a hand as the interaction data, so as to obtain a gesture category according to the target image; or, In the case where the interaction mode is gesture interaction, determining a target image containing a body gesture as the interaction data, so as to obtain a human body gesture category according to the target image; or In the case where the interaction mode is key point interaction, determining a target image including hand and / or body posture as the interaction data, so as to obtain a key point posture category according to the target image; The suspension control instruction is determined according to the gesture category, the human body posture category or the key point posture category.

3. The vehicle suspension control method according to claim 1, characterized in that: The acquisition interaction mode includes: Receive a mode selection instruction from a user and obtain a target location of the user, wherein the target location includes inside or outside the vehicle; In response to the mode selection instruction of the user and according to the target position of the user, an interaction mode is determined.

4. The vehicle suspension control method according to claim 3, characterized in that: After acquiring the interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode, the method further includes: configuring a state machine model, wherein the state machine model determines a target state of suspension control according to the interaction data; According to the target state, executing the suspension control instruction allowed under the target state; Wherein, when the target position is switched, the state machine model inherits the target state.

5. The vehicle suspension control method according to claim 3, characterized in that: After determining the interaction mode, the method further includes: According to the target position, the external vehicle feedback component or the internal vehicle feedback component corresponding to the interactive mode is called to perform information feedback, wherein the external vehicle feedback component includes a wiper, and the internal vehicle feedback component includes a central control large screen.

6. The vehicle suspension control method according to claim 1, characterized in that: Before adjusting the vehicle suspension height according to the suspension control instruction, the method further includes: In the case where the suspension control command recognition fails, the interactive mode is switched according to a preset conversion sequence.

7. The vehicle suspension control method according to claim 1, characterized in that: After acquiring the interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode, the method further includes: Uploading the interaction data to the cloud so that the cloud can perform data enhancement to obtain pre-processed data; The preprocessed data is received, and a suspension control instruction is determined according to the preprocessed data.

8. A vehicle suspension control device, characterized in that: The device comprises: A first acquisition module is used to acquire an interaction mode; A second acquisition module, used to acquire interaction data corresponding to the interaction mode according to the interaction module corresponding to the interaction mode; an identification module, used to determine a suspension control instruction according to the interaction data; The execution module is used to adjust the vehicle suspension height according to the suspension control instruction.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images