Data processing model, control method and device of vehicle and readable storage medium

Abstract

The application discloses a data processing model, a control method and device of a vehicle and a readable storage medium, and relates to the technical field of vehicles. The data processing model of the vehicle comprises a reflex arc layer, the reflex arc layer is used for receiving environmental data of an area where the vehicle is located and determining threat feature data in the environmental data during automatic parking of the vehicle; a consciousness layer connected with the reflex arc layer, the consciousness layer is used for determining a communication health degree of the vehicle according to the threat feature data; and a decision layer connected with the consciousness layer, the decision layer is used for determining a communication control instruction of the vehicle according to the communication health degree and the threat feature data. The application improves the data processing accuracy of the data processing model.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a vehicle data processing model, control method, device, and readable storage medium. Background Technology

[0002] Currently, autonomous driving systems for vehicles have extremely high requirements for real-time and reliable communication, needing to ensure low-latency transmission of control commands and perception data in complex environments (such as signal interference in parking garages and sensor noise spikes caused by heavy rain). Traditional communication middleware mostly adopts a "store-and-forward" data processing model, which is only responsible for data distribution and cannot perceive changes in the external environment or its own communication status. This leads to delayed response to threat events and easy paralysis when the link fails, making it difficult to meet the "safety first" survivability requirements of autonomous driving. Therefore, existing vehicle data processing models suffer from technical problems such as poor data processing accuracy. Summary of the Invention

[0003] This application provides a vehicle data processing model, control method, device, and readable storage medium to solve technical problems such as poor data processing accuracy in the prior art.

[0004] A first aspect of this application provides a vehicle data processing model, the data processing model comprising: The reflective arc layer is used to receive environmental data of the area where the vehicle is located and to identify threat characteristics in the environmental data during the automatic parking process. The awareness layer, which connects to the reflex arc layer, is used to determine the communication health of a vehicle based on threat signature data. The decision-making layer, which connects to the awareness layer, is used to determine the vehicle's communication control commands based on communication health and threat characteristic data.

[0005] The vehicle data processing model in this embodiment implements a three-layer data processing architecture: "reflex arc layer – awareness layer – decision layer." Specifically, the reflex arc layer improves data processing speed and accuracy, and can identify threat characteristic data in the environmental data, ensuring the accuracy and timeliness of the threat characteristic data. The awareness layer can determine the vehicle's communication health in real time based on the threat characteristic data, ensuring the real-time and accurate monitoring of the vehicle. The decision layer can determine the vehicle's communication control commands based on the communication health and threat characteristic data. Through the fusion processing of communication health and threat characteristic data, the timeliness and accuracy of the communication control commands are ensured.

[0006] In summary, the data processing model in this embodiment improves the accuracy and efficiency of data processing by adopting a three-layer structure of "reflex arc layer - consciousness layer - decision layer". Furthermore, the communication control commands generated based on the data processing model adjust the vehicle, improving the stability and safety of the vehicle during automatic parking.

[0007] A second aspect of this application provides a vehicle control device, the method comprising: During the automatic parking process, environmental data of the area where the vehicle is located is acquired. Environmental data is input into the data processing model to obtain communication control commands output by the data processing model, wherein the data processing model is the data processing model in any of the above embodiments; The vehicle's communication system is controlled based on communication control commands.

[0008] A third aspect of this application provides a vehicle control device, the device comprising: The acquisition unit is used to acquire environmental data of the area where the vehicle is located during the automatic parking process. The processing unit is used to input environmental data into the data processing model to obtain communication control commands output by the data processing model, wherein the data processing model is the data processing model in any of the above embodiments; The control unit is used to control the vehicle's communication system based on communication control commands.

[0009] A fourth aspect of this application provides another vehicle control device, including a processor and a memory. The memory stores a computer program that, when executed by the processor, implements the steps of the vehicle control method as described in any of the above embodiments. Therefore, this vehicle control device possesses all the beneficial effects of the vehicle control method in any of the above embodiments, which will not be elaborated further here.

[0010] A fifth aspect of this application provides a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the vehicle control method as described in any of the above embodiments. Therefore, this readable storage medium possesses all the beneficial effects of the vehicle control method in any of the above embodiments, which will not be elaborated further here. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of the structure of the vehicle data processing model provided in the embodiments of this application; Figure 2 A schematic diagram of the preprocessing module provided in an embodiment of this application; Figure 3 A schematic diagram of the feature extraction model provided in the embodiments of this application; Figure 4 A schematic diagram of the consciousness layer provided in the embodiments of this application; Figure 5 A schematic diagram of the decision layer provided in the embodiments of this application; Figure 6 A flowchart of a vehicle control method provided in an embodiment of this application; Figure 7 Functional block diagram of the vehicle control device provided in the embodiments of this application; Figure 8 This is a structural block diagram of a vehicle control device provided in an embodiment of this application. Detailed Implementation

[0013] To better understand the technical solutions provided in the embodiments of this specification, the technical solutions of the embodiments of this specification will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0014] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The term "two or more" includes two or more cases.

[0015] In some embodiments, such as Figure 1 As shown, an embodiment of this application provides a vehicle data processing model 100, which includes: The reflective arc layer 101 is used to receive environmental data of the area where the vehicle is located and to determine threat feature data in the environmental data during the automatic parking process. Consciousness layer 102 is connected to reflex arc layer 101. Consciousness layer 102 is used to determine the communication health of the vehicle based on threat characteristic data. The decision layer 103 is connected to the awareness layer 102. The decision layer 103 is used to determine the vehicle's communication control commands based on communication health and threat characteristic data.

[0016] In this embodiment, a vehicle data processing model 100 is proposed. The data processing model 100 is used to generate communication control instructions for the vehicle, wherein the communication control instructions are control instructions for adjusting the vehicle's communication strategy.

[0017] For example, the autonomous driving system of a vehicle has extremely high requirements for real-time and reliability of communication. It needs to ensure low-latency transmission of control commands and perception data in complex environments (such as signal interference in underground parking lots, and the impact of severe weather such as rainstorms). The data processing model 100 generates communication control commands based on the impact of complex environments, which can ensure the real-time and reliability of vehicle communication.

[0018] The vehicle's data processing model 100 includes a reflex arc layer 101, a consciousness layer 102, and a decision-making layer 103.

[0019] The input end of the consciousness layer 102 is connected to the output end of the reflex arc layer 101, and the input end of the decision layer 103 is connected to the output end of the consciousness layer 102.

[0020] For example, the vehicle is equipped with sensors, and the data collected by the sensors is input through the input terminal of the reflective arc layer 101.

[0021] For example, the output of the decision layer 103 is used to output communication control commands.

[0022] The reflective arc layer 101 is used to receive environmental data of the area where the vehicle is located and to determine the threat feature data in the environmental data. The environmental data is the specific data of the area where the vehicle is located, and the threat feature data is the feature data in the environmental data that poses a threat to the vehicle.

[0023] For example, environmental data may specifically include: Meteorological parameters include ambient temperature, humidity, wind speed, wind direction, atmospheric pressure, precipitation, and visibility. This data is provided by the vehicle-mounted environmental monitoring weather station and is used to issue warnings for dangerous weather conditions such as icing, fog, and heavy rain, automatically adjusting the air conditioning to dehumidify, reminding drivers to slow down, or adjusting routes.

[0024] Air quality: Monitors the concentration of pollutants such as PM2.5, PM10, nitrogen oxides, sulfur oxides, volatile organic compounds (VOCs) and ozone. Some high-end models can automatically switch between internal and external circulation modes in conjunction with the air conditioning system to ensure air quality inside the vehicle.

[0025] Road and traffic conditions: Using cameras, millimeter-wave radar, and lidar, it identifies lane lines, traffic signs, traffic lights, vehicles ahead, pedestrians, bicycles, construction cones, obstacles, etc., and calculates the distance and relative speed to the vehicle in front to determine whether the traffic is congested, slow-moving, or smooth.

[0026] Road conditions: Some systems can sense the dryness or wetness of the road surface, water accumulation, ice, or snow, providing key inputs for ESP (Electronic Stability Program) and AEB (Automatic Emergency Braking).

[0027] The aforementioned environmental data is jointly collected by vehicle-mounted sensors (cameras, radar, weather sensors) and roadside sensing devices (traffic radar, weather stations, cameras), and then processed by vehicle-side fusion.

[0028] The awareness layer 102 is used to determine the communication health of a vehicle based on threat characteristic data, where the communication health is a numerical value representing the vehicle's communication status.

[0029] For example, threat signature data can specifically be obstacle features in environmental data.

[0030] For example, threat signature data can be specifically severe weather features in environmental data.

[0031] For example, threat signature data can be specifically spatial constraint features in environmental data.

[0032] For example, the communication health score can be a value between 0 and 1. A higher communication health score indicates that the vehicle's communication status is more normal and stable, while a lower communication health score indicates that the vehicle's communication status is more abnormal.

[0033] For example, vehicle communication health refers to the stability, reliability, and performance of the in-vehicle communication system in complex environments, and is a core indicator of the operational safety and functional realization of intelligent connected vehicles. Its evaluation is based on multi-dimensional communication quality parameters, combined with industry standards and manufacturer technical practices, forming a systematic evaluation system.

[0034] The decision layer 103 is used to determine the vehicle's communication control commands based on communication health and threat signature data.

[0035] For example, when a vehicle encounters a road obstacle, the vehicle's communication state is readjusted based on communication control commands. This ensures the reliability of the vehicle's communication while the vehicle avoids the obstacle, thereby guaranteeing the safety of automatic parking.

[0036] For example, when a vehicle encounters heavy rain, the vehicle's communication resources are allocated based on communication control commands to ensure that the processing flow and data communication flow can be maintained simultaneously during heavy rain, thereby ensuring the safety of automatic parking.

[0037] For example, the data processing model 100 of this embodiment implements a three-layer architecture of "reflex arc layer 101 - consciousness layer 102 - decision layer 103", and performs functional visualization and mathematical modeling for each layer.

[0038] For example, the reflex arc layer 101, by mimicking the reflex arc of the biological spinal cord "sensory neuron-interneuron-motor neuron", achieves a millisecond-level closed loop for determining threat triggers based on raw data, bypassing complex calculations and improving the data processing efficiency of the reflex arc layer 101.

[0039] For example, the consciousness layer 102 mimics the "self-awareness" of a biological brain, monitors external environmental threats and internal communication health in real time, and forms the system's "cognitive state".

[0040] For example, the decision-making layer 103 mimics the "decision-control" of the biological nerve center, and dynamically adjusts the communication strategy according to the cognitive state of the consciousness layer 102 to ensure survivability under extreme conditions.

[0041] The vehicle data processing model 100 in this embodiment implements a three-layer data processing architecture: "reflex arc layer 101 – awareness layer 102 – decision layer 103". Specifically, the reflex arc layer 101 improves data processing speed and accuracy, and can identify threat characteristic data in environmental data, ensuring the accuracy and timeliness of the threat characteristic data. The awareness layer 102 can determine the vehicle's communication health in real time based on the threat characteristic data, ensuring the real-time and accurate monitoring of the vehicle. The decision layer 103 can determine the vehicle's communication control commands based on the communication health and threat characteristic data. Through the fusion processing of the communication health and threat characteristic data, the timeliness and accuracy of the communication control commands are ensured.

[0042] In summary, the data processing model 100 of this embodiment improves the accuracy and efficiency of data processing by adopting a three-layer structure of "reflex arc layer 101 - consciousness layer 102 - decision layer 103". Furthermore, adjusting the vehicle based on the communication control commands generated by the data processing model 100 improves the stability and safety of the vehicle during automatic parking.

[0043] In some embodiments, the present application provides a vehicle data processing model 100, wherein the reflection arc layer 101 includes a preprocessing module and a feature extraction model; The preprocessing module is used to sample and process environmental data to obtain sampled data from the environmental data, and to denoise the sampled data to obtain valid data from the sampled data. Feature extraction models are used to extract features from valid data to obtain threat feature data and determine the threat confidence corresponding to the threat feature data.

[0044] In this embodiment, the reflection arc layer 101 includes a preprocessing module and a feature extraction model, wherein the preprocessing module is a module that preprocesses environmental data, and the feature extraction model is a module that extracts threat feature data.

[0045] For example, the output of the preprocessing module is connected to the input of the feature extraction model.

[0046] For example, the processing flow of the preprocessing module is as follows: Figure 2 As shown.

[0047] The input to the preprocessing module is the raw sensor data stream (taking commonly used sensors in autonomous driving as an example), including: Ultrasonic echo: Time-series signal (sampling rate fs = 100 kHz, representing the raw fluctuations in the distance to the obstacle). Camera data: pixel matrix (H / W is resolution, 3 is RGB channels).

[0048] The preprocessing module is used to sample and process environmental data to obtain sampled data from the environmental data, where the sampled data is the data after sampling the environmental data.

[0049] For example, downsampling: reduces the amount of data while preserving key features. For ultrasonic echoes, the average is taken for every N=10 sampling points: ; Where, x u Let k be a time series signal, where k represents the kth sampled data and i represents the i-th sample point.

[0050] The preprocessing module is used to denoise the sampled data to obtain the valid data in the sampled data. The valid data refers to the effective data in the sampled data.

[0051] For example, noise reduction: For camera data, use mean filtering to eliminate random noise (window size 3×3): ; Where i and j represent pixel positions in the image, I c This is valid data.

[0052] The feature extraction model is used to extract features from valid data to obtain threat feature data and determine the threat confidence level corresponding to the threat feature data, where the threat confidence level is the confidence level of the threat feature data.

[0053] For example, feature extraction models such as Figure 3 As shown.

[0054] For example, for ultrasonic echoes: the input to the feature extraction model is the downsampled echo sequence, and the model structure is as follows: Conv1D(32,kernel=5)→ReLU→MaxPool(2)→Conv1D(64,kernel=3)→ReLU→GlobalAvgPool→Dense(1,sigmoid) The output of the feature extraction model is the confidence level c of the threat feature (c∈[0,1]), which represents the probability of a "high-threat event" (such as a rapidly approaching object).

[0055] Triggering condition: When the confidence level exceeds the threshold θ1=0.8, output a low-latency communication trigger command (such as "High Threat Event - Ultrasonic Wave"): ; Where Trigger is the low-latency communication trigger command, c is the threat confidence level, and θ1 is the confidence threshold.

[0056] For example, in the functional verification of the reflective arc layer 101, the scenario is as follows: an ultrasonic wave detects an obstacle approaching at 5 m / s (the echo intensity increases sharply by 20% within 3 ms), the model outputs c=0.9, and a command is triggered. The delay is ≤5 ms, which is much faster than the traditional 50 ms process of "calculating distance → judging threat".

[0057] In some embodiments, this application provides a vehicle data processing model 100, whereby the awareness layer 102 is used to: determine the environmental threat level corresponding to the vehicle based on threat characteristic data and threat confidence. Determine the health of communications based on the level of environmental threats.

[0058] In this embodiment, the awareness layer 102 is used to determine the environmental threat level corresponding to the vehicle based on threat feature data and threat confidence, wherein the environmental threat level is a level representing the threat in the environment.

[0059] The awareness layer 102 is also used to determine the health of communications based on the level of environmental threats.

[0060] For example, the structure of consciousness layer 102 is as follows Figure 4 As shown.

[0061] For example, the inputs and core components of consciousness layer 102: Input: Threat characteristics of the reflection arc layer 101 (confidence level c); Status information for each module: planning module task progress p (∈[0,1], 1 indicates task completion), control module execution delay d (∈[0,100]ms).

[0062] Core component: Metacognitive supervisor, which uses fuzzy logic + graph neural network to achieve multi-source information fusion.

[0063] For example, the external environmental threat assessment of awareness layer 102: Define the environmental threat level T: Calculated by weighting the threat characteristics and task urgency. ; in,- =0.5 (threat feature weight) =0.3 (Task progress: the slower the progress, the higher the threat). =0.2 (execution delay: the greater the delay, the higher the threat); -T∈[0,1], T>0.7 indicates "high threat" (such as passing on a narrow road + approaching obstacles).

[0064] For example, an internal communication health assessment of consciousness layer 102: Constructing a communication resource graph: Abstracting communication links into a graph G=(V,E) (V is a node: sensor / computing unit; E is a link: Ethernet / CAN).

[0065] Define link health Based on packet loss rate and bandwidth utilization Calculated using exponentially weighted moving average (EWMA): ; For example, the system communication health H of awareness layer 102 is: a weighted average of all links (weights are based on link importance). ): ; Where H∈[0,1], H<0.6 indicates “low communication health”.

[0066] For example, the self-cognition conclusion of the consciousness layer 102 is output by the metacognitive supervisor as a fuzzy cognitive state, such as "high threat level (T=0.8), medium communication health (H=0.7)", providing a "global perspective" for the decision layer 103.

[0067] In some embodiments of this application, a vehicle data processing model 100 is provided, wherein a decision layer 103 is used to: determine the vehicle's communication mode, communication link, and resource allocation scheme based on communication health and threat characteristic data; Based on the communication mode, communication link, and resource allocation ratio, determine the communication control commands.

[0068] In this embodiment, the decision layer 103 is used to determine the vehicle's communication mode, communication link, and resource allocation scheme based on communication health and threat characteristic data. The communication mode represents the vehicle's data transmission method, the communication link represents the vehicle's data transmission path, and the resource allocation scheme is the allocation scheme for the vehicle's processing resources.

[0069] The decision layer 103 is also used to determine communication control commands based on the communication mode, communication link, and resource allocation ratio.

[0070] For example, the structure of decision layer 103 is as follows: Figure 5 As shown.

[0071] In some embodiments, this application provides a vehicle data processing model 100, whereby a decision layer 103 is used to: determine a communication pattern based on communication health and threat characteristic data; Determine the communication link based on the communication health status; Determine the resource allocation ratio based on threat characteristic data.

[0072] In this embodiment, the decision layer 103 is further configured to: determine the communication pattern based on communication health and threat characteristic data; Determine the communication link based on the communication health status; Determine the resource allocation ratio based on threat characteristic data.

[0073] For example, the inputs and core components of decision layer 103 are: Input: Cognitive status of consciousness layer 102 (threat level T, communication health H).

[0074] Core component: Dynamic policy engine, which uses a rule engine and reinforcement learning to optimize policies.

[0075] For example, the mode switching of decision layer 103: normal → critical.

[0076] Rule: When the threat level or communication health exceeds the threshold, switch the communication mode: if the threat level is greater than the threshold or the communication health is less than the threshold, the communication mode is critical mode; otherwise, the communication mode is normal mode.

[0077] The emergency mode is as follows: The planning module sends semantic instructions (such as EMERGENCY_STOP) instead of complete waypoints; The control module calculates instructions locally (e.g., upon receiving a STOP signal, it directly outputs a braking signal).

[0078] For example, topology reconfiguration of decision layer 103: faulty link replacement Triggering condition: When the health of a link e0 is less than 0.5 (e.g., Camera-SoC Ethernet interruption).

[0079] Path planning: Use a preset algorithm to find alternative paths. The path cost is defined as the reciprocal of the link health (links with higher health are preferred). ; For example: the original path "Camera→SoC→MCU" is interrupted, and the path "Camera→Ultrasonic Sensor→CAN→MCU" is reconstructed to bypass the faulty node.

[0080] For example, resource allocation at decision level 103: Threat tasks prioritized: Strategy: Allocate bandwidth / computing resources according to task priority, with high-threat tasks preempting resources from low-threat tasks.

[0081] Priority calculation: Task priority Pt is positively correlated with threat level T: Pt = T × P base , where P base Prioritize tasks Bandwidth allocation: High-threat tasks consume bandwidth (Bt): ; For example, total bandwidth B total =100Mbps, collision avoidance task P=0.9, surround view rendering P=0.3, then the collision avoidance task is allocated 75Mbps and the surround view rendering is allocated 25Mbps.

[0082] In some embodiments, such as Figure 6 As shown, an embodiment of this application provides a vehicle control method, including: Step S601: During the automatic parking process, acquire environmental data of the area where the vehicle is located. Step S602: Input environmental data into data processing model 100 to obtain communication control commands output by data processing model 100; Step S603: Control the vehicle's communication system based on communication control commands.

[0083] In this embodiment, a vehicle control method is proposed, which acquires environmental data of the area where the vehicle is located during the automatic parking process.

[0084] The data processing model 100 is acquired, and environmental data is input into the data processing model 100 to obtain the communication control commands output by the data processing model 100.

[0085] The data processing model 100 is the data processing model 100 in any of the above embodiments.

[0086] The vehicle's communication system is controlled based on communication control commands.

[0087] For example, the vehicle's communication system is one of the core technologies for realizing intelligent driving, vehicle networking, and smart transportation. It not only connects various electronic control units in the vehicle, but also enables efficient information interaction between vehicles, between vehicles and roads, and between vehicles and the cloud, thereby improving driving safety, traffic efficiency, and driving experience.

[0088] The vehicle control method in this embodiment generates communication control commands through the data processing model 100, ensuring the accuracy of the communication control commands. Based on the communication control commands, the vehicle's communication system is controlled, ensuring the vehicle's operational stability and safety.

[0089] In some embodiments, this application provides a vehicle control method, the vehicle including an ultrasonic sensor and a camera, for acquiring environmental data of the area where the vehicle is located, including: Control ultrasonic sensors and cameras to collect environmental data of the area where the vehicle is located.

[0090] In this embodiment, the vehicle includes an ultrasonic sensor and a camera, and the ultrasonic sensor and camera are controlled to collect environmental data of the area where the vehicle is located.

[0091] For example, ultrasonic sensors calculate the distance to obstacles by emitting high-frequency sound waves and receiving their reflected echoes, using the time difference. They are widely used in scenarios such as reversing radar, automatic parking assistance, and low-speed emergency braking.

[0092] For example, cameras, acting as the "eyes" of an autonomous driving system, are primarily responsible for capturing image information around the vehicle and identifying key targets such as lane lines, traffic signs, pedestrians, and other vehicles. Depending on their structure and purpose, they can be categorized into monocular, binocular, surround-view, and infrared cameras.

[0093] In some embodiments, such as Figure 7 As shown, an embodiment of this application provides a vehicle control device 700, including: The acquisition unit 702 is used to acquire environmental data of the area where the vehicle is located during the automatic parking process. The processing unit 704 is used to input environmental data into the data processing model in order to obtain communication control commands output by the data processing model 100; Control unit 706 is used to control the vehicle's communication system based on communication control commands.

[0094] In this embodiment, the vehicle control device 700 generates communication control commands through a data processing model, ensuring the accuracy of the communication control commands. Based on the communication control commands, it controls the vehicle's communication system, ensuring the vehicle's operational stability and safety.

[0095] In some embodiments of this application, a vehicle control device 700 is provided, wherein the control unit 706 is further configured to: Control ultrasonic sensors and cameras to collect environmental data of the area where the vehicle is located.

[0096] In some embodiments, such as Figure 8 As shown, a vehicle control device 800 is proposed. The vehicle control device 800 includes a processor 802 and a memory 804. The memory 804 stores a computer program, which, when executed by the processor 802, implements the steps of the vehicle control method as described in any of the above embodiments. Therefore, the vehicle control device 800 possesses all the beneficial effects of the vehicle control method in any of the above embodiments, which will not be elaborated further here.

[0097] In some embodiments, a readable storage medium is provided having a program stored thereon, which, when executed by a processor, implements the steps of the vehicle control method as described in any of the above embodiments, and thus has all the beneficial technical effects of the vehicle control method described in any of the above embodiments.

[0098] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0099] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0100] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0101] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0102] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0103] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to execute a process of a vehicle control method.

[0104] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0105] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0106] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0107] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0108] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0109] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0110] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0111] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this specification.

[0112] Obviously, those skilled in the art can make various modifications and variations to this specification without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims and their equivalents, this specification is also intended to include such modifications and variations.

Claims

1. A vehicle data processing model, characterized in that, The data processing model includes: The reflective arc layer is used to receive environmental data of the area where the vehicle is located during the automatic parking process and to determine threat feature data in the environmental data. A consciousness layer, which is connected to the reflex arc layer, is used to determine the communication health of the vehicle based on the threat characteristic data; The decision layer is connected to the awareness layer and is used to determine the communication control commands of the vehicle based on the communication health status and the threat characteristic data.

2. The data processing model according to claim 1, characterized in that, The reflection arc layer includes a preprocessing module and a feature extraction model; The preprocessing module is used to sample the environmental data to obtain sampled data from the environmental data, and to denoise the sampled data to obtain valid data from the sampled data. The feature extraction model is used to perform feature extraction processing on the effective data to obtain the threat feature data and determine the threat confidence level corresponding to the threat feature data.

3. The data processing model according to claim 2, characterized in that, The awareness layer is used to: determine the environmental threat level corresponding to the vehicle based on the threat feature data and the threat confidence level; The communication health is determined based on the environmental threat level.

4. The data processing model according to any one of claims 1 to 3, characterized in that, The decision-making layer is used to: determine the vehicle's communication mode, communication link, and resource allocation scheme based on the communication health status and the threat characteristic data; The communication control command is determined based on the communication mode, the communication link, and the resource allocation ratio.

5. The data processing model according to claim 4, characterized in that, The decision-making layer is used to: determine the communication pattern based on the communication health status and the threat characteristic data; The communication link is determined based on the communication health status; The resource allocation ratio is determined based on the threat characteristic data.

6. A method for controlling a vehicle, characterized in that, The method includes: During the automatic parking process, environmental data of the area where the vehicle is located is acquired. The environmental data is input into the data processing model to obtain the communication control command output by the data processing model, wherein the data processing model is the data processing model according to any one of claims 1 to 5; The communication system of the vehicle is controlled based on the communication control commands.

7. The data processing model according to claim 6, characterized in that, The vehicle includes ultrasonic sensors and a camera. Acquiring environmental data of the area where the vehicle is located includes: The ultrasonic sensor and the camera are controlled to collect environmental data of the area where the vehicle is located.

8. A vehicle control device, characterized in that, The device includes: The acquisition unit is used to acquire environmental data of the area where the vehicle is located during the automatic parking process. A processing unit is configured to input the environmental data into a data processing model to obtain communication control commands output by the data processing model, wherein the data processing model is the data processing model according to any one of claims 1 to 5; A control unit for controlling the vehicle's communication system based on the communication control commands.

9. A vehicle control device, characterized in that, include: processor; A memory that stores programs or instructions, wherein the processor, when executing the programs or instructions in the memory, implements the steps of the vehicle control method as described in claim 6 or 7.

10. A readable storage medium, characterized in that, A program or instructions are stored on a readable storage medium, which, when executed by a processor, implement the steps of the vehicle control method as described in claim 6 or 7.

Images