A vehicle intelligent fault-tolerant optimization method and system based on a preset time

Abstract

The application relates to a vehicle intelligent fault-tolerant optimization method and system based on a preset time. The method comprises the following steps: acquiring an environment parameter, inputting the environment parameter into a local model preset at a vehicle end to obtain a first control instruction generated by the vehicle end model; uploading the environment parameter to a cloud end, so that the cloud end inputs the environment parameter into a cloud end model preset at the cloud end and acquires a second control instruction; waiting for and acquiring a receiving time stamp of complete received environment parameters fed back by the cloud end, judging whether a time corresponding to the receiving time stamp is greater than a time corresponding to a time stamp of the uploaded environment parameter or not; if yes, the priority of the second driving instruction fed back by the cloud end is lowered; acquiring a third control instruction acquired by in-vehicle hardware; comparing the priorities of the first control instruction, the second control instruction and the third control instruction, and acquiring the one with the highest priority as an actual control instruction and outputting.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle automatic control, in particular to a vehicle intelligent fault-tolerant optimization method and system based on preset time, computer equipment, storage medium and computer program product. BACKGROUND

[0002] With the rapid development of new energy vehicles towards intelligence, more comprehensive assisted driving and automatic driving technologies, and steady progress towards unmanned driving, as the number of input sources that can control vehicles gradually increases, how to coordinate the input instructions of the input sources to ensure the smooth and safe driving of the vehicle has become a hot issue of concern in the industry.

[0003] The invention patent with publication number CN120161852A discloses an automatic driving system based on 5G Internet of Things, which includes an image acquisition device, a cloud server platform and a general control center. The image acquisition device includes sensor devices such as laser radar cameras, which are used to acquire road images. The cloud server platform is used to process image information and perform intelligent identification to obtain road recognition results. The general control center makes decision control on the driving behavior of the automatic driving vehicle according to the data processing results. Through the image processing technology of the cloud server platform, the collected road condition information, especially the potholed road and the icy road, is intelligently identified, and the automatic driving is decided according to the road conditions. The method disclosed in the present application can accurately identify potholed roads and speed control on icy roads, realize accurate control of automatic driving vehicles in complex road conditions, and improve the identification accuracy and unmanned driving control accuracy of poor road conditions.

[0004] However, this system relies on real-time data interaction between the vehicle and the cloud, and when the communication is disturbed by environmental factors, the vehicle will be in a dangerous state that is difficult to respond to unexpected situations. Therefore, there is an urgent need for a vehicle control method that can optimize the coordination relationship between multiple control sources and perform fault-tolerant control on the vehicle to meet the demand for unmanned driving in areas with poor signal quality. SUMMARY

[0005] Therefore, it is necessary to provide a vehicle intelligent fault-tolerant optimization method, device, computer equipment, computer readable storage medium and computer program product based on preset time, which can reduce the communication quality requirement between the vehicle and the cloud.

[0006] In a first aspect, the present application provides a vehicle intelligent fault-tolerant optimization method based on preset time, which comprises:

[0007] Obtaining an environment parameter and inputting the environment parameter into a local model preset on the vehicle end to obtain a first control instruction generated by a vehicle end model;

[0008] uploading the environmental parameter to the cloud to make the cloud input the environmental parameter into a cloud model preset in the cloud and acquire a second control instruction;

[0009] waiting for and acquiring a receiving time stamp of the cloud feedback of the complete receiving environmental parameter, judging whether a time corresponding to the receiving time stamp is greater than a time corresponding to the uploading environmental parameter time stamp by a preset time threshold value;

[0010] if yes, then down-regulating the priority of the second driving instruction of the cloud feedback;

[0011] if no, then up-regulating the priority of the second driving instruction of the cloud feedback;

[0012] acquiring a third control instruction acquired by the in-vehicle hardware;

[0013] comparing the priorities of the first control instruction, the second control instruction and the third control instruction, and acquiring the one with the highest priority as the actual control instruction and outputting.

[0014] In one of the embodiments, the specific steps of waiting for and acquiring the environmental parameter complete receiving time stamp of the cloud feedback, and judging whether the complete receiving time stamp corresponding event is greater than the uploading environmental parameter time stamp event by a preset time threshold value include:

[0015] acquiring a sending time stamp when the environmental parameter is uploaded to the cloud, the sending time stamp being at least accurate to the microsecond level;

[0016] waiting for and acquiring a receiving time stamp, the receiving time stamp being at least accurate to the microsecond level;

[0017] calculating a time stamp difference value of the sending time stamp and the receiving time stamp, and judging whether the time stamp difference value is greater than a preset time threshold value;

[0018] if yes, then down-regulating the priority of the second driving instruction;

[0019] if no, then up-regulating the priority of the second driving instruction.

[0020] In one of the embodiments, the receiving time stamp is the time when the cloud acquires the complete environmental parameter, and the determination method of the receiving time includes:

[0021] the cloud records the time stamp information of receiving the environmental parameter;

[0022] verifying the completeness of the environmental parameter, if the environmental parameter passes the completeness verification, then taking the time stamp information as the receiving time and sending to the vehicle end.

[0023] In one of the embodiments, the priority levels are all represented by numerical values, and the larger the numerical value representing the priority level, the higher the priority level. The first control instruction, the second control instruction, and the third control instruction are all preset with priority levels. The priority level of the first control instruction is set to 3, the priority level of the second control instruction is set to 4, and the priority level of the third control instruction is set to 1. The specific steps of down-regulating the priority of the second driving instruction include:

[0024] determining whether the current priority level of the second driving instruction is less than 3;

[0025] if yes, keeping the priority level of the second control instruction unchanged;

[0026] if no, halving the priority of the second control instruction;

[0027] The specific steps of up-regulating the priority of the second driving instruction include:

[0028] determining whether the current priority level of the second driving instruction is greater than 3;

[0029] if yes, keeping the priority level of the second control instruction unchanged;

[0030] if no, doubling the priority of the second control instruction.

[0031] In one of the embodiments, the specific steps of comparing the priorities of the first control instruction, the second control instruction, and the third control instruction, and obtaining the one with the highest priority as the actual control instruction and outputting include:

[0032] determining whether the specific instruction content of the first control instruction and the second control instruction at the current time matches;

[0033] if yes, taking the first control instruction as the actual control instruction and outputting;

[0034] if no, reading the priorities of the first control instruction, the second control instruction, and the third control instruction, and obtaining the one with the largest priority value as the actual control instruction and outputting.

[0035] In one of the embodiments, the vehicle intelligent fault-tolerant optimization method based on the preset time further includes: waiting for and obtaining the execution result of the actual control instruction, and determining whether an accident occurs;

[0036] if no, determining whether the actual control instruction is the first control instruction;

[0037] if no, taking the actual control instruction and the environmental parameter as a training positive sample, and inputting the training positive sample into the cloud model to complete the cloud model training.

[0038] In a second aspect, the application further provides a vehicle intelligent fault-tolerant optimization system based on a preset time, which comprises:

[0039] An environmental parameter acquisition module comprising an image sensor and a millimeter wave radar, configured to collect environmental parameters;

[0040] A vehicle-end control module configured to store and run a local model to generate a first control instruction according to the environmental parameters;

[0041] A cloud-end control module configured to store and run a cloud-end model to generate a second control instruction according to the environmental parameters;

[0042] A communication module arranged in the vehicle-end control module and the cloud-end control module to realize data and information exchange between the vehicle-end control module and the cloud-end control module;

[0043] A hardware control module configured to generate a third control instruction according to specific behaviors of the driver in manipulating the hardware in the vehicle;

[0044] An instruction fusion module configured to compare the priority of the first control instruction, the second control instruction and the third control instruction, and obtain the one with the highest priority as the actual control instruction and output it.

[0045] In a third aspect, the application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor realizes the following steps when executing the computer program:

[0046] Acquiring environmental parameters and inputting the environmental parameters into a local model preset in the vehicle-end to obtain a first control instruction generated by the vehicle-end model;

[0047] Uploading the environmental parameters to the cloud-end to make the cloud-end input the environmental parameters into a cloud-end model preset in the cloud-end and obtain a second control instruction;

[0048] Waiting for and acquiring a receiving time stamp of the complete receiving environmental parameters fed back by the cloud-end, and judging whether the time corresponding to the receiving time stamp is greater than the time corresponding to the time stamp of the uploaded environmental parameters by a preset time threshold;

[0049] If yes, the priority of the second driving instruction fed back by the cloud-end is lowered;

[0050] If no, the priority of the second driving instruction fed back by the cloud-end is raised;

[0051] Acquiring a third control instruction obtained by the hardware in the vehicle;

[0052] Comparing the priority of the first control instruction, the second control instruction and the third control instruction, and obtaining the one with the highest priority as the actual control instruction and outputting it;

[0053] Wait for and obtain the execution results of the actual control commands to determine whether an accident has occurred;

[0054] If not, then determine whether the actual control instruction is the first control instruction;

[0055] If not, the actual control commands and environmental parameters will be used as positive training samples, and the positive training samples will be input into the cloud model to complete the cloud model training.

[0056] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0057] Obtain environmental parameters and input them into the local model preset on the vehicle to obtain the first control command generated by the vehicle model;

[0058] Upload environmental parameters to the cloud so that the cloud can input the environmental parameters into the cloud model preset in the cloud and obtain the second control command;

[0059] Wait for and obtain the receiving timestamp of the complete receiving environment parameters from the cloud, and determine whether the time corresponding to the receiving timestamp and the time corresponding to the uploading environment parameters timestamp are greater than a preset time threshold.

[0060] If so, then lower the priority of the second driving command fed back from the cloud;

[0061] If not, then increase the priority of the second driving command fed back from the cloud;

[0062] Acquire third control commands obtained from the vehicle's hardware;

[0063] Compare the priorities of the first control instruction, the second control instruction, and the third control instruction, and select the one with the highest priority as the actual control instruction and output it.

[0064] Wait for and obtain the execution results of the actual control commands to determine whether an accident has occurred;

[0065] If not, then determine whether the actual control instruction is the first control instruction;

[0066] If not, the actual control commands and environmental parameters will be used as positive training samples, and the positive training samples will be input into the cloud model to complete the cloud model training.

[0067] Fifthly, this application also provides a computer program product comprising a computer program that, when executed by a processor, performs the following steps:

[0068] obtaining an environment parameter, and inputting the environment parameter into a local model preset at a vehicle end to obtain a first control instruction generated by the vehicle end model;

[0069] uploading the environment parameter to a cloud end to make the cloud end input the environment parameter into a cloud end model preset at the cloud end and obtain a second control instruction;

[0070] waiting for and obtaining a receiving time stamp of a complete receiving environment parameter fed back by the cloud end, and judging whether a time corresponding to the receiving time stamp is greater than a time corresponding to a time stamp of uploading the environment parameter by a preset time threshold;

[0071] if yes, then down-regulating a priority of the second driving instruction fed back by the cloud end;

[0072] if no, then up-regulating the priority of the second driving instruction fed back by the cloud end;

[0073] obtaining a third control instruction obtained by a hardware in the vehicle;

[0074] comparing priorities of the first control instruction, the second control instruction and the third control instruction, and obtaining a highest one as an actual control instruction and outputting;

[0075] waiting for and obtaining an execution result of the actual control instruction, and judging whether an accident occurs;

[0076] if no, then judging whether the actual control instruction is the first control instruction;

[0077] if no, then taking the actual control instruction and the environment parameter as a training positive sample, and inputting the training positive sample into the cloud end model to complete cloud end model training.

[0078] The above-mentioned vehicle intelligent fault-tolerant optimization method, system, computer device, storage medium and computer program product based on a preset time, through setting an instruction fusion module, selectively receive the first control instruction, the second control instruction and the third control instruction obtained in an actual scene, when the communication signal is blocked, the priority of the second control instruction is reduced, so that the vehicle relies on the first control instruction or the third control instruction generated by the local end to realize smooth running, thereby reducing the requirement of the automatic driving vehicle on the signal condition in the driving environment. BRIEF DESCRIPTION OF DRAWINGS

[0079] Figure 1 it is a structure topology diagram of the vehicle intelligent fault-tolerant optimization system based on a preset time in one embodiment;

[0080] Figure 2 it is a system structure diagram of the vehicle intelligent fault-tolerant optimization system based on a preset time in one embodiment;

[0081] Figure 3A flowchart of a preset time-based vehicle intelligent fault-tolerant optimization method in an embodiment;

[0082] Figure 4 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0083] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0084] In one embodiment, as shown in Figure 1 a preset time-based vehicle intelligent fault-tolerant optimization system is provided, which comprises a hardware control module, an environment parameter acquisition module, a vehicle end control module, a cloud end control module, a communication module, a hardware control module and an instruction fusion module, wherein:

[0085] The environment parameter acquisition module is configured to collect environment parameters, specifically, various sensors for collecting road surface environment and / or map data, for example, the environment parameter acquisition module includes but is not limited to image sensors and millimeter wave radars;

[0086] The vehicle end control module is configured to store and run a local model to generate a first control instruction according to the environment parameters. Specifically, the vehicle end control module can include a local intelligent driving chip installed at the vehicle end, a peripheral circuit and a local model installed thereon, which is used to generate a local intelligent driving instruction, i.e. the first control instruction, according to the environment parameters;

[0087] The cloud end control module is configured to store and run a cloud model to generate a second control instruction according to the environment parameters. Specifically, the cloud end control module can include a cloud server computing unit, a processor and a server, and a cloud model installed thereon. The cloud model is more complex than the local model, and the second control instruction generated by the cloud model contains more predictions of road conditions and their coping strategies than the first control instruction. In terms of time dimension, the time length of the second control instruction is longer than that of the first control instruction;

[0088] The communication module is arranged between the vehicle end control module and the cloud end control module to realize data and information exchange between the vehicle end control module and the cloud end control module. Specifically, the communication module in the present embodiment adopts 5G or other low-latency wireless communication protocols;

[0089] a hardware control module configured to generate a third control instruction according to a specific behavior of the in-vehicle hardware manipulated by the passenger, wherein the in-vehicle hardware includes, but is not limited to, a steering wheel, a brake pedal, an accelerator pedal, a gear lever, and other hardware devices for the driver to control the driving state of the vehicle;

[0090] an instruction fusion module configured to compare the priorities of the first control instruction, the second control instruction, and the third control instruction, and obtain the one with the highest priority as the actual control instruction and output the same.

[0091] In the embodiment, the steering wheel, the brake pedal, the accelerator pedal, the gear lever, and other hardware devices included in the hardware control module are decoupled from the corresponding steering, braking, power, and other systems, and are connected through the instruction fusion module, that is, in the process of the vehicle, if the intelligent driving or the unmanned driving mode is started, the driving state of the vehicle is controlled by the selective execution of the first control instruction, the second control instruction, and the third control instruction by the instruction fusion module, so as to realize the automatic driving or the co-driving of the vehicle by the passenger; when the human driving mode is started, the instruction fusion module mainly executes the third control instruction, the vehicle end obtains the environmental parameters of the road environment through the environmental parameter acquisition module, so as to determine whether a sudden event occurs in the driving process, and outputs the first control instruction to successfully trigger the AEB, the ABS, and other functions when the sudden event occurs, so as to ensure the safety of the driving of the vehicle.

[0092] Based on the same inventive concept, the embodiment of the present application also provides a preset time-based vehicle intelligent fault-tolerant optimization method for realizing the above-mentioned preset time-based vehicle intelligent fault-tolerant optimization system. The implementation scheme for solving the problem provided by the method is similar to the implementation scheme described in the above method, so the specific limitations in one or more preset time-based vehicle intelligent fault-tolerant optimization method embodiments provided below can refer to the limitations of the preset time-based vehicle intelligent fault-tolerant optimization system in the above text, which will not be repeated here.

[0093] In one embodiment, as shown in Figure 2 a preset time-based vehicle intelligent fault-tolerant optimization method is provided, including the following steps:

[0094] Step S100: obtaining an environmental parameter and inputting the environmental parameter into a local model preset at the vehicle end to obtain a first control instruction generated by the vehicle end model.

[0095] The environmental parameters are multi-type environmental information obtained by the environmental parameter obtaining module, including but not limited to road condition image data obtained by an image sensor, environmental point cloud data obtained by a millimeter wave radar, vehicle distance or distance data obtained by an ultrasonic sensor and / or an infrared sensor, position information obtained by a GPS module or a Beidou positioning module, and map data, etc. Part or all of the above environmental parameters are input into the vehicle-end model to obtain the first control instruction. The first control instruction is generated by the vehicle-end local model in real time and output to the instruction fusion module.

[0096] Step S200: uploading the environmental parameters to the cloud end, so that the cloud end inputs the environmental parameters into the cloud-end model preset in the cloud end and obtains the second control instruction.

[0097] The second control instruction contains more predictions of road conditions and their coping strategies than the first control instruction. In terms of time dimension, the time length of the second control instruction is longer than that of the first control instruction. In a preferred embodiment, the times of the two generated second control instructions have overlapping parts. When the communication signal is blocked during the vehicle driving process, the previous second control instruction is used as the current reference second control instruction. If the communication signal is not blocked and the new second control instruction is successfully received by the instruction fusion module, the newly received second control instruction is used as the current reference second control instruction.

[0098] Step S300: waiting for and obtaining the receiving time stamp of the complete received environmental parameters fed back by the cloud end, and judging whether the time corresponding to the receiving time stamp is greater than the time corresponding to the uploading time stamp of the environmental parameters by a preset time threshold.

[0099] The preset time threshold is a basis for judging whether the communication between the cloud end and the vehicle end is smooth or the delay is too large. In a specific embodiment, the specific steps of step S300 include:

[0100] Step S310: obtaining the sending time stamp when the environmental parameters are uploaded to the cloud end, and the sending time stamp is at least accurate to the microsecond level.

[0101] Step S320: waiting for and obtaining the receiving time stamp, and the receiving time stamp is at least accurate to the microsecond level.

[0102] The receiving time stamp is the time when the cloud end obtains the complete environmental parameters, and the determination method of the receiving time includes:

[0103] Step S321: the cloud end records the time stamp information of receiving the environmental parameters;

[0104] Step S322: verifying the integrity of the environmental parameter, if the environmental parameter passes the integrity verification, the timestamp information is taken as the receiving time and sent to the vehicle end.

[0105] Through steps S321 and S322, the timestamp information of the received environmental parameter is stored first, and then its integrity is verified. When the data integrity verification passes, the temporarily stored timestamp information is taken as the receiving information. Since the time occupied by the data integrity verification is not included, a more accurate data transmission time can be calculated.

[0106] Step S330: calculating the timestamp difference between the sending timestamp and the receiving timestamp, and determining whether the timestamp difference is greater than a preset time threshold.

[0107] Step S410: if yes, then down-regulating the priority of the second driving instruction fed back by the cloud;

[0108] Step S420: if no, then up-regulating the priority of the second driving instruction fed back by the cloud.

[0109] In one of the embodiments, the priority levels are all represented by numerical values, and the greater the numerical value representing the priority level, the higher the priority level. The first control instruction, the second control instruction, and the third control instruction are all preset with priority levels. The priority level of the first control instruction is set to 3, the priority level of the second control instruction is set to 4, and the priority level of the third control instruction is set to 1. The specific steps of step S410 include:

[0110] Step S411: determining whether the current priority level of the second driving instruction is less than 3;

[0111] Step S412: if yes, then keeping the priority level of the second control instruction unchanged;

[0112] Step S413: if no, then halving the priority of the second control instruction.

[0113] Similarly, the specific steps of step S420 include:

[0114] Step S421: determining whether the current priority level of the second driving instruction is greater than 3;

[0115] Step S422: if yes, then keeping the priority level of the second control instruction unchanged;

[0116] Step S423: if no, then doubling the priority of the second control instruction.

[0117] The purpose of setting the first control instruction, the second control instruction, and the third control instruction as above is that, during the driving of the vehicle, both the vehicle end control module and the hardware control module have the ability to make decisions on the real-time road conditions to generate corresponding first control instructions and third control instructions, but the delivery of the second control instruction of the cloud end control module is affected by many factors such as whether the communication signal is stable, whether the cloud computing power can generate the second control instruction in time, and the like, thereby affecting the timeliness of the second control instruction, so it is necessary to flexibly adjust the execution priority of the second control instruction during driving according to the actual situation to ensure the safety of the vehicle during driving. It is also because of the need to adjust the priority of the second control instruction in real time that the values of the first control instruction and the third control instruction are set as quantities, and the second control instruction is set as a variable, so that the size value relationship among the first control instruction, the second control instruction, and the third control instruction can be adjusted through simple mathematical operations. The specific priority values given in this embodiment, such as 1, 2, 3, 4, etc., are only used to clearly show the meaning of step S410 and step S420, and do not limit the protection scope of the present application.

[0118] Step S500: acquiring a third control instruction obtained by a hardware in the vehicle.

[0119] The third control instruction is a third control instruction generated by a specific behavior of the driver through the hardware in the vehicle, and the hardware in the vehicle includes but is not limited to a steering wheel, a brake pedal, an accelerator pedal, a gear lever, and other hardware devices for the driver to control the driving state of the vehicle. The corresponding third control instruction is corresponding to the behavior of the driver such as stepping on or releasing the brake pedal, the accelerator pedal, or rotating the steering wheel, and the third control instruction is an instruction for controlling the acceleration of the vehicle, the deceleration of the vehicle, and the rotation of the steering wheel of the vehicle. The difference between the third control instruction and the first control instruction and the second control instruction is that the first control instruction and the second control instruction are control commands generated by the automatic driving model for controlling the vehicle to be executed at a specific time in the next period of time, which has a certain prediction or pre-input property, but the third control instruction is an immediate instruction, that is, the instruction fusion module receives the third control instruction corresponding to the driving of the driver after the driver actively controls the vehicle.

[0120] Step S600: comparing the priorities of the first control instruction, the second control instruction, and the third control instruction, and acquiring the one with the highest priority as the actual control instruction and outputting.

[0121] The specific steps of step S600 include:

[0122] Step S610: determining whether the specific instruction content of the first control instruction and the second control instruction at the current time matches.

[0123] Step S620: If yes, the first control instruction is output as the actual control instruction.

[0124] Step S630: If no, the priority of the first control instruction, the second control instruction and the third control instruction is read, and the control instruction with the maximum priority value is obtained as the actual control instruction and output.

[0125] Step S700: Wait for and obtain the execution result of the actual control instruction, and determine whether an accident occurs.

[0126] Step S810: If no, determine whether the actual control instruction is the first control instruction.

[0127] Step S820: If no, the actual control instruction and the environmental parameter are taken as a training positive sample, and the training positive sample is input to the cloud model to complete cloud model training.

[0128] Through steps S700-S820, the correct decision made by the vehicle-side control module can be summarized and output to the cloud for iteration of the cloud model, so as to complete the reinforcement training of the model and realize the function of self-iteration of the cloud model.

[0129] However, it should be additionally noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0130] In another optional embodiment, the user can select an automatic driving mode (or a man-vehicle co-driving mode) or a driver active driving mode when starting the vehicle or driving the vehicle. When the automatic driving mode (or the man-vehicle co-driving mode) is started, the vehicle performs steps S100-S820 to realize man-vehicle co-driving. When the driver active driving mode is started, the vehicle side stops sending sensor data to the cloud, but the vehicle side still obtains sensor and map data in real time, but only outputs a second control instruction for responding to an emergency situation when an emergency situation occurs (such as a front vehicle deceleration or parking on a highway, or a pedestrian appears at a road intersection when driving to the intersection), and the instruction fusion module executes the second control instruction preferentially after receiving the second control instruction because the preset priority of the second control instruction is higher than the preset priority of the third control instruction, thereby ensuring that the AEB function is successfully triggered, so as to respond to the emergency situation.

[0131] It should be understood that although the steps in the flowcharts related to the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts related to the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be alternately or alternately executed with at least part of other steps or steps or stages in other steps.

[0132] The modules in the vehicle intelligent fault-tolerant optimization system based on the preset time described above can be implemented wholly or partially by software, hardware and combinations thereof. The modules described above can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above modules.

[0133] In one embodiment, a computer device, which can be a terminal, can have an internal structure diagram as shown in Figure 4 The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by 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 operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with external terminals in wired or wireless mode. Wireless mode can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement a vehicle intelligent fault-tolerant optimization method based on a preset time. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a button, trackball or touchpad externally connected to the computer device, etc.

[0134] Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0135] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0136] Step S100: obtaining an environment parameter, and inputting the environment parameter into a local model preset at a vehicle end to obtain a first control instruction generated by the vehicle end model;

[0137] Step S200: uploading the environment parameter to a cloud end to make the cloud end input the environment parameter into a cloud end model preset at the cloud end and obtain a second control instruction;

[0138] Step S300: waiting for and obtaining a receiving timestamp of the complete received environment parameter fed back by the cloud end, and judging whether a time corresponding to the receiving timestamp is greater than a time corresponding to a time stamp of the uploaded environment parameter by a preset time threshold;

[0139] Step S410: if yes, then down-regulating a priority of the second driving instruction fed back by the cloud end;

[0140] Step S420: if no, then up-regulating the priority of the second driving instruction fed back by the cloud end;

[0141] Step S500: obtaining a third control instruction obtained by a hardware in the vehicle;

[0142] Step S600: comparing priorities of the first control instruction, the second control instruction and the third control instruction, and obtaining the one with the highest priority as an actual control instruction and outputting;

[0143] Step S700: waiting for and obtaining an execution result of the actual control instruction, and judging whether an accident occurs;

[0144] Step S810: if no, then judging whether the actual control instruction is the first control instruction;

[0145] Step S820: if no, then taking the actual control instruction and the environment parameter as a training positive sample, and inputting the training positive sample into the cloud end model to complete training of the cloud end model.

[0146] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program is executed by a processor to implement the following steps:

[0147] Step S100: obtaining an environment parameter, and inputting the environment parameter into a local model preset at a vehicle end to obtain a first control instruction generated by the vehicle end model;

[0148] Step S200: uploading the environment parameter to a cloud end to make the cloud end input the environment parameter into a cloud end model preset at the cloud end and obtain a second control instruction;

[0149] Step S300: waiting for and obtaining the receiving timestamp of the complete receiving environment parameter fed back by the cloud, and judging whether the time corresponding to the receiving timestamp is greater than the time corresponding to the uploading environment parameter timestamp by a preset time threshold;

[0150] Step S410: if yes, then down-regulating the priority of the second driving instruction fed back by the cloud;

[0151] Step S420: if no, then up-regulating the priority of the second driving instruction fed back by the cloud;

[0152] Step S500: obtaining the third control instruction acquired by the in-vehicle hardware;

[0153] Step S600: comparing the priorities of the first control instruction, the second control instruction and the third control instruction, and obtaining the one with the highest priority as the actual control instruction and outputting;

[0154] Step S700: waiting for and obtaining the execution result of the actual control instruction, and judging whether an accident occurs;

[0155] Step S810: if no, then judging whether the actual control instruction is the first control instruction;

[0156] Step S820: if no, then taking the actual control instruction and the environment parameter as a training positive sample, and inputting the training positive sample into the cloud model to complete the cloud model training.

[0157] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the following steps:

[0158] Step S100: obtaining an environment parameter, and inputting the environment parameter into a local model preset at a vehicle end to obtain a first control instruction generated by a vehicle end model;

[0159] Step S200: uploading the environment parameter to the cloud, so that the cloud inputs the environment parameter into a cloud model preset at the cloud and obtains a second control instruction;

[0160] Step S300: waiting for and obtaining the receiving timestamp of the complete receiving environment parameter fed back by the cloud, and judging whether the time corresponding to the receiving timestamp is greater than the time corresponding to the uploading environment parameter timestamp by a preset time threshold;

[0161] Step S410: if yes, then down-regulating the priority of the second driving instruction fed back by the cloud;

[0162] Step S420: if no, then up-regulating the priority of the second driving instruction fed back by the cloud;

[0163] Step S500: acquiring a third control instruction representing a third control instruction acquired by in-vehicle hardware;

[0164] Step S600: comparing the priorities of the first control instruction, the second control instruction and the third control instruction, and acquiring the one with the highest priority as an actual control instruction and outputting;

[0165] Step S700: waiting for and acquiring an execution result of the actual control instruction, and judging whether an accident occurs;

[0166] Step S810: if not, judging whether the actual control instruction is the first control instruction;

[0167] Step S820: if not, taking the actual control instruction and the environmental parameter as a training positive sample, inputting the training positive sample to the cloud model to complete cloud model training.

[0168] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0169] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0170] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A vehicle intelligent fault-tolerant optimization method based on a preset time, characterized by, The method comprises the following steps: acquiring an environment parameter and inputting the environment parameter into a local model preset at a vehicle end to obtain a first control instruction generated by the vehicle end model; uploading the environment parameter to a cloud end to make the cloud end input the environment parameter into a cloud end model preset at the cloud end and acquire a second control instruction; waiting for and acquiring a receiving time stamp of the cloud end feedback of the complete received environment parameter, and judging whether a time corresponding to the receiving time stamp is greater than a time corresponding to a time stamp of uploading the environment parameter by a preset time threshold; if yes, down-regulating a priority of the second driving instruction of the cloud end feedback; if no, up-regulating the priority of the second driving instruction of the cloud end feedback; acquiring a third control instruction acquired by a hardware in the vehicle; comparing priorities of the first control instruction, the second control instruction and the third control instruction, and acquiring a highest one as an actual control instruction and outputting.

2. The pre-set time based intelligent fault tolerant optimization method for vehicles as claimed in claim 1 wherein, The specific steps of waiting for and acquiring the receiving time stamp of the cloud end feedback of the complete received environment parameter, and judging whether a time corresponding to the receiving time stamp is greater than a time corresponding to a time stamp of uploading the environment parameter by a preset time threshold comprise: acquiring a sending time stamp when the environment parameter is uploaded to the cloud end, the sending time stamp being at least accurate to a microsecond level; waiting for and acquiring the receiving time stamp, the receiving time stamp being at least accurate to a microsecond level; calculating a time stamp difference value of the sending time stamp and the receiving time stamp, and judging whether the time stamp difference value is greater than the preset time threshold; if yes, down-regulating the priority of the second driving instruction; if no, up-regulating the priority of the second driving instruction. 3.The preset time based vehicle intelligent fault-tolerant optimization method according to claim 2, characterized in that, The receiving time stamp is a time when the cloud end acquires the complete environment parameter, and the determination manner of the receiving time comprises: the cloud end records time stamp information of receiving the environment parameter; verifying completeness of the environment parameter, if the environment parameter passes the completeness verification, the time stamp information is taken as the receiving time, and is sent to the vehicle end. 4.The preset time based vehicle intelligent fault-tolerant optimization method according to claim 2, characterized in that, The priority levels are all represented by numerical values, the greater the numerical value representing the priority level is, the higher the priority level is, the first control instruction, the second control instruction and the third control instruction are all preset with priority levels, the priority level of the first control instruction is set to 3, the priority of the second control instruction is set to 4, and the priority of the third control instruction is set to 1, the specific steps of down-regulating the priority of the second driving instruction comprise: judging whether a current priority instruction of the second driving instruction is less than 3; if yes, keeping the priority level of the second control instruction unchanged; if no, halving the priority of the second control instruction; The specific steps of up-regulating the priority of the second driving instruction comprise: judging whether a current priority instruction of the second driving instruction is greater than 3; if yes, keeping the priority level of the second control instruction unchanged; if no, doubling the priority of the second control instruction.

5. The preset time based vehicle intelligent fault tolerant optimization method according to claim 3, wherein, The specific steps of comparing the priorities of the first control instruction, the second control instruction and the third control instruction, and acquiring a highest one as an actual control instruction and outputting comprise: determining whether the specific instruction content of the first control instruction and the second control instruction at the current time matches; if yes, taking the first control instruction as the actual control instruction and outputting; if no, reading the priority of the first control instruction, the second control instruction and the third control instruction, and taking the control instruction with the maximum priority value as the actual control instruction and outputting. 6.The preset time based intelligent fault-tolerant optimization method for vehicles according to any one of claims 1-5, characterized in that Further comprising: waiting for and obtaining the execution result of the actual control instruction, and determining whether an accident occurs; if no, determining whether the actual control instruction is the first control instruction; if no, taking the actual control instruction and the environmental parameter as a training positive sample, inputting the training positive sample into a cloud model, so as to complete the cloud model training. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the method in any one of claims 1 to 6.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 6.

9. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 6.

Images