Sensor data processing link failure monitoring method, device, medium, and vehicle

Abstract

The present application relates to the technical field of automatic driving, and particularly provides a sensor data processing link fault monitoring method, device, medium and vehicle, aiming to solve the problem of improving data processing link fault monitoring accuracy. To this end, the method provided by the present application comprises loading preset fault rules of each link link of the sensor data processing link, based on the preset fault rules of each link link, respectively matching the log information of each link link to judge whether each link link has a fault, and acquiring and storing the sensor data and / or log information when each link link has a fault. Through the above method, it can be judged in time and accurately which link links have faults, and the data when the link links have faults can be saved in time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a sensor data processing link fault monitoring method, device, medium and vehicle. BACKGROUND

[0002] When performing automatic driving control on a vehicle, an image acquisition device is usually used to acquire images around the vehicle, and then the images are input into task systems for performing different automatic driving tasks, so that different automatic driving tasks can be performed according to the images. For example, automatic driving tasks such as lane keeping, blind area detection and auxiliary parking can be performed according to the images. In actual application, the image processing link between the image acquisition device and each task system usually includes multiple link segments such as image exposure, image rendering, image encoding, image preprocessing (such as image cropping, scaling, distortion correction, etc.), and image transmission. Each link segment may fail. However, the current link fault monitoring method can only monitor whether the image processing link has an abnormality after the image processing in the rear end of the image processing link is completed by a technician according to the image processing result, and even if it is judged that an abnormality has occurred, it cannot be determined which link segment has failed. In addition, this monitoring method can only monitor the occurrence of a fault in the rear end after a period of time after the fault occurs. Since the image occupies a relatively large memory space, the historical image will be quickly overwritten by the new image. If the fault can only be monitored in the rear end after a period of time after the fault occurs, the image at the time of the fault occurrence is likely to have been overwritten, so that fault analysis cannot be performed according to the image at the time of the fault occurrence.

[0003] Therefore, there is a need in the art to develop a new technical solution to solve the above problems. SUMMARY

[0004] In order to overcome the above defects, the present application is proposed to provide a sensor data processing link fault monitoring method, device, medium and vehicle to solve or at least partially solve the technical problem of improving the accuracy of data processing link fault monitoring.

[0005] In a first aspect, a sensor data processing link fault monitoring method is provided, the method comprising:

[0006] loading preset fault rules of each link segment in the sensor data processing link;

[0007] based on the preset fault rules of each link segment, respectively performing fault matching on the log information of each link segment to determine whether a fault occurs in each link segment;

[0008] obtaining and storing sensor data and / or log information when a fault occurs in each link segment.

[0009] In one of the above technical solutions of the sensor data processing link fault monitoring method, the preset fault rules of each link segment are set by the following method:

[0010] Simulate the fault of each link segment respectively and obtain the fault log information of each link segment during the simulation process respectively;

[0011] According to the fault log information, the preset fault rules of each link segment are set respectively;

[0012] Among them, the preset fault rule is a single rule or a combination of multiple single rules indicating that the link segment has failed.

[0013] In one of the above technical solutions of the sensor data processing link fault monitoring method, after the step of "judging whether each link segment has failed", the method further comprises:

[0014] If at least one link segment has failed, output a prompt information and / or

[0015] Perform fault repair processing on the sensor data processing link to eliminate the failure of the at least one link segment.

[0016] In one of the above technical solutions of the sensor data processing link fault monitoring method, the step of "outputting a prompt information" specifically comprises:

[0017] Obtain the segment information and fault type of the link segment that has failed;

[0018] According to the segment information and the fault type, output a prompt information.

[0019] In one of the above technical solutions of the sensor data processing link fault monitoring method, the step of "judging whether each link segment has failed" specifically comprises:

[0020] According to the preset fault monitoring period, perform fault monitoring on the sensor data processing link;

[0021] Among them, at each fault monitoring, based on the preset fault rules of each link segment, the log information of each link segment is matched for fault to determine whether each link segment has failed.

[0022] In one of the above technical solutions of the sensor data processing link fault monitoring method, the step of "judging whether each link segment has failed" further comprises:

[0023] According to the preset fault monitoring period, perform fault monitoring on the sensor data processing link;

[0024] Wherein, at each time of fault monitoring, it is judged whether the monitoring times have reached a preset number threshold; if yes, the monitoring is stopped; if no, based on preset fault rules of each link link, the log information of each link link is matched for fault respectively to judge whether each link link has fault.

[0025] In one of the technical solutions of the above-mentioned fault monitoring method of the sensor data processing link, the method further comprises loading the preset fault rules and judging whether each link link has fault by the following way: in the application layer or the sensor driver layer of the system to which the sensor accesses,

[0026] loading the preset fault rules of each link link in the sensor data processing link, and based on the preset fault rules of each link link, matching the log information of each link link for fault respectively to judge whether each link link has fault;

[0027] Alternatively, the method further comprises loading the preset fault rules and judging whether each link link has fault by the following way: through the hardware device set between the sensor and the system to which the sensor accesses,

[0028] loading the preset fault rules of each link link in the sensor data processing link, and based on the preset fault rules of each link link, matching the log information of each link link for fault respectively to judge whether each link link has fault.

[0029] In one of the technical solutions of the above-mentioned fault monitoring method of the sensor data processing link, the step of "obtaining and storing the sensor data and / or the log information when each link link has fault" specifically comprises: obtaining and storing the sensor data and / or the log information in the system layer and the application layer of the system to which the sensor accesses.

[0030] In the second aspect, a computer device is provided, which comprises a processor and a storage device, the storage device is adapted to store a plurality of program codes, the program codes are adapted to be loaded and run by the processor to execute the method in any one of the technical solutions of the above-mentioned fault monitoring method of the sensor data processing link.

[0031] In the third aspect, a computer readable storage medium is provided, which has a plurality of program codes stored therein, the program codes are adapted to be loaded and run by a processor to execute the method in any one of the technical solutions of the above-mentioned fault monitoring method of the sensor data processing link.

[0032] In the fourth aspect, a vehicle is provided, which comprises the vehicle in the above-mentioned technical solution of the vehicle.

[0033] Scheme 1. A method for monitoring faults of a sensor data processing link, the method comprising:

[0034] loading preset fault rules for each link segment in the sensor data processing link;

[0035] based on the preset fault rules for each link segment, respectively performing fault matching on log information of each link segment to determine whether a fault occurs in each link segment;

[0036] acquiring and storing sensor data and / or log information when a fault occurs in each link segment.

[0037] Scheme 2. The method of scheme 1, wherein the preset fault rules for each link segment are set by the following method:

[0038] respectively simulating a fault occurring in each link segment and acquiring fault log information of each link segment during the simulation;

[0039] based on the fault log information, respectively setting the preset fault rules for each link segment;

[0040] wherein the preset fault rules are a single rule or a combination of multiple single rules indicating that a fault occurs in a link segment.

[0041] Scheme 3. The method of scheme 1, wherein after the step of determining whether a fault occurs in each link segment, the method further comprises:

[0042] if at least one link segment has a fault, outputting prompt information and / or

[0043] performing fault repair processing on the sensor data processing link to eliminate the fault occurring in the at least one link segment.

[0044] Scheme 4. The method of scheme 3, wherein the step of outputting prompt information specifically comprises:

[0045] acquiring segment information and a fault type of the link segment having a fault;

[0046] based on the segment information and the fault type, outputting prompt information.

[0047] Scheme 5. The method of scheme 1, wherein the step of determining whether a fault occurs in each link segment specifically comprises:

[0048] performing fault monitoring on the sensor data processing link according to a preset fault monitoring period;

[0049] Wherein, at each fault monitoring, based on the preset fault rules of each link section, the log information of each link section is matched with faults respectively to determine whether each link section has a fault.

[0050] Scheme 6. The method according to scheme 1, characterized in that the step of "determining whether each link section has a fault" further comprises:

[0051] According to the preset fault monitoring period, the sensor data processing link is monitored for faults;

[0052] Wherein, at each fault monitoring, it is determined whether the number of monitoring has reached the preset number threshold; if yes, the monitoring is stopped; if no, based on the preset fault rules of each link section, the log information of each link section is matched with faults respectively to determine whether each link section has a fault.

[0053] Scheme 7. The method according to any one of schemes 1 to 6, characterized in that,

[0054] The method further comprises loading the preset fault rules and determining whether each link section has a fault by the following way: in the application layer or the sensor driver layer of the system to which the sensor accesses,

[0055] Loading the preset fault rules of each link section in the sensor data processing link, and based on the preset fault rules of each link section, the log information of each link section is matched with faults respectively to determine whether each link section has a fault;

[0056] Alternatively, the method further comprises loading the preset fault rules and determining whether each link section has a fault by the following way: through the hardware device set between the sensor and the system to which the sensor accesses,

[0057] Loading the preset fault rules of each link section in the sensor data processing link, and based on the preset fault rules of each link section, the log information of each link section is matched with faults respectively to determine whether each link section has a fault.

[0058] Scheme 8. The method according to scheme 7, characterized in that the step of "obtaining and storing the sensor data and / or log information when each link section has a fault" specifically comprises:

[0059] In the system layer and the application layer of the system to which the sensor accesses, the sensor data and / or the log information are obtained and stored.

[0060] Scheme 9. A computer device comprising a processor and a storage device, the storage device being adapted to store a plurality of program codes, characterized in that the program codes are adapted to be loaded and run by the processor to execute the sensor data processing link fault monitoring method of any one of schemes 1 to 8.

[0061] Scheme 10. A computer readable storage medium, wherein a plurality of program codes are stored, characterized in that the program codes are adapted to be loaded and run by a processor to execute the sensor data processing link fault monitoring method of any one of schemes 1 to 8.

[0062] Scheme 11. A vehicle, characterized in that the vehicle comprises the computer device of scheme 9.

[0063] The above one or more technical solutions of the present application have at least one or more of the following beneficial effects:

[0064] In the technical solution of the sensor data processing link fault monitoring method provided by the present application, the preset fault rules of each link link of the sensor data processing link can be loaded, and based on the preset fault rules of each link link, the log information of each link link is matched for fault respectively to judge whether each link link has a fault. Through this step, it can be judged in time and accurately which link link has a fault when the sensor data processing link has a fault, which is beneficial to quickly positioning the fault position and solving the fault. In addition, the present application can also acquire and store the sensor data and / or log information when each link link has a fault. Through this step, the data when the link link has a fault can be saved in time, so that these data can be used for fault reproduction, accurate analysis of the fault cause and solution of the fault. BRIEF DESCRIPTION OF DRAWINGS

[0065] The disclosure of the present application will become more apparent with reference to the drawings. It is easy for those skilled in the art to understand that these drawings are only for illustrative purposes, and are not intended to limit the scope of protection of the present application. Among them:

[0066] Figure 1 is the main step flow diagram of the sensor data processing link fault monitoring method according to an embodiment of the present application;

[0067] Figure 2 is the main step flow diagram of the method for judging whether the link link has a fault according to an embodiment of the present application;

[0068] Figure 3 is the main step flow diagram of the method for judging whether the link link has a fault according to another embodiment of the present application;

[0069] Figure 4 is a main structure schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0070] Some embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art will understand that these embodiments are only used to explain the technical principles of the present application, and are not intended to limit the protection scope of the present application.

[0071] In the description of the present application, the "processor" can include hardware, software or a combination of both. The processor can be a central processor, a microprocessor, an image processor, a digital signal processor or any other suitable processor. The processor has data and / or signal processing functions. The processor can be implemented in software, hardware or a combination of both. The computer readable storage medium includes any suitable medium that can store program codes, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B or both A and B.

[0072] The related user personal information that may be involved in the embodiments of the present application is strictly in accordance with the requirements of laws and regulations, and follows the principles of legality, legitimacy and necessity, and is based on the reasonable purpose of the business scene, and processes the personal information of the user that is actively provided by the user in the process of using the product / service or generated due to the use of the product / service, and authorized by the user.

[0073] The user personal information processed by the applicant will be different for specific product / service scenarios, and should be based on the specific scene of the user using the product / service, which may involve the user's account information, device information, driving information, vehicle information or other related information. The applicant will treat the user's personal information with high diligence and obligation.

[0074] The applicant attaches great importance to the security of user personal information, and has taken security protection measures in accordance with industry standards, which are reasonable and feasible to protect the user's information and prevent unauthorized access, public disclosure, use, modification, damage or loss of personal information.

[0075] The following describes an embodiment of a sensor data processing link fault monitoring method.

[0076] Referring to the accompanying Figure 1 , Figure 1 is a main step flowchart of a sensor data processing link fault monitoring method according to an embodiment of the present application. As shown in Figure 1 , the fault monitoring method in the embodiment of the present application mainly includes the following steps S101 to S103.

[0077] Step S101: Load preset fault rules of each link element in the sensor data processing link. After the sensor is connected to the system (such as a vehicle control system), the preset fault rules can be loaded immediately after the system is started or after a preset time delay. The preset fault rules are pre-set rules for determining whether a fault occurs in a link element.

[0078] Step S102: Based on the preset fault rules of each link element, the log information of each link element is matched with the fault rules respectively to determine whether a fault occurs in each link element.

[0079] For each link element, if the log information of the current link element matches the fault rule of the current link element, it indicates that a fault occurs in the current link element. Further, according to the fault type corresponding to the fault rule, it can be determined which fault occurs in the current link element.

[0080] Step S103: Obtain and store the sensor data and / or log information when a fault occurs in each link element.

[0081] In some embodiments, in order to ensure the storage reliability of the sensor data and the log information, the sensor data and the log information can be stored in a non-volatile memory. Further, in order to reduce the data storage space, the sensor data and the log information can be packaged into a data packet first, and then the data packet is stored in the non-volatile memory.

[0082] In the method based on the above steps S101 to S103, through step S102, whether a fault occurs in each link element can be timely and accurately monitored in the process of performing the processing operation corresponding to each link element on the sensor data. Through step S103, the sensor data and the log information of the link element can be timely stored when a fault in the link element is monitored, which is helpful for fault analysis and solution based on the sensor data and the log information.

[0083] In one application scenario of implementing the above method, the sensor is a vehicle-mounted camera, and the sensor data processing link includes several link elements such as image cropping, scaling, and distortion correction. The image processed by the sensor data processing link is input to the automatic driving system of the vehicle, and the automatic driving system performs automatic driving tasks such as lane keeping, blind area detection, and auxiliary parking according to the received image. After the above processing link is started, the preset fault rules of the above link elements are loaded immediately, and then based on the preset fault rules of each link element, the log information of each link element is matched with the fault rules respectively to determine whether a fault occurs in each link element. If the log information of image cropping matches the corresponding fault rule, it indicates that a fault occurs in image cropping, and the image (i.e., the image being cropped when the fault occurs) and the log information when the fault occurs need to be obtained and stored.

[0084] The setting method of the preset fault rule in the embodiments of the present application is described below.

[0085] Specifically, in the embodiments of the present application, the fault of each link can be simulated respectively, and the fault log information of each link can be obtained in the simulation process. The fault log information refers to the log information generated when the link occurs fault. After obtaining the fault log information, the preset fault rule of each link is set according to the fault log information. The preset fault rule is a single rule or a combination of multiple single rules indicating that the link occurs fault.

[0086] When the preset fault rule is set as a single rule, the link can be determined to occur fault as long as it meets the single rule, which improves the efficiency of fault judgment. When the preset fault rule is set as a combination of multiple single rules, the link can be determined to occur fault only when it meets each single rule in the combination, which can significantly improve the accuracy of fault judgment.

[0087] The steps S101 to S103 of the above embodiments are described below respectively.

[0088] I. The step S101 is described.

[0089] In some embodiments of the above step S101, the system framework of the sensor access system can include a sensor driver layer, a system layer and an application layer. Under this framework, the preset fault rule can be loaded in the application layer or in the sensor driver layer. This way does not need to be modified in hardware, and the preset fault rule can be loaded after the sensor driver layer or the application layer is started, which improves the convenience of fault loading.

[0090] In some embodiments of the above step S101, the preset fault rule can be loaded in a soft and hard combined manner. Specifically, a hardware device capable of performing the operation corresponding to step S101 can be set between the sensor and the system to which the sensor accesses, such as between the vehicle-mounted camera and the vehicle-mounted processor of the automatic driving system. The preset fault rule is loaded by the hardware device when step S101 is performed. This way uses a separate hardware device for loading, which does not need to modify the sensor driver layer and the application layer, and can improve the reliability of fault rule loading.

[0091] II. The step S102 is described.

[0092] In some embodiments of the step S102, similar to the step S101, the log information of each link section can be matched with preset fault rules of the link section at the application layer or the sensor driver layer to determine whether a fault occurs in the link section. In addition, a hardware device capable of performing the operation of the step S102 can be arranged between the sensor and the system to which the sensor is connected, and the operation of the step S102 can be performed by the hardware device. In this way, the convenience or reliability of determining whether a fault occurs in the link section can be improved.

[0093] In some embodiments of the step S102, a non-terminable fault monitoring method or a terminable fault monitoring method can be used to monitor the fault to determine whether a fault occurs in the link section. The two monitoring methods are described as follows.

[0094] 1. Non-terminable fault monitoring method

[0095] In the embodiments of the present application, the fault monitoring can be performed in the following ways:

[0096] Specifically, a fault monitoring period can be set in advance, and the sensor data processing link is monitored according to the fault monitoring period. At each fault monitoring, the log information of each link section is matched with preset fault rules of the link section to determine whether a fault occurs in the link section. In this way, the fault monitoring can be repeatedly performed at intervals of the time corresponding to the fault monitoring period. In order to monitor whether a fault occurs in time, the fault monitoring period can be set to a small value, for example, the fault monitoring period can be greater than or equal to a period threshold; otherwise, the fault monitoring period can be set to a large value, for example, the fault monitoring period can be less than the period threshold. The value of the period threshold can be flexibly set by the person skilled in the art according to the actual needs, and the embodiments of the present application are not limited in this regard.

[0097] 2. Terminable fault monitoring method

[0098] In the embodiments of the present application, the terminable monitoring can be performed in the following ways:

[0099] Specifically, a fault monitoring cycle can be preset, and fault monitoring of the sensor data processing link can be performed according to this cycle. However, during each fault monitoring, it is first determined whether the number of monitoring attempts has reached a preset threshold; if so, monitoring stops; otherwise, based on the preset fault rules for each link, fault matching is performed on the log information of each link to determine whether a fault has occurred in each link. In this way, by setting the number of monitoring attempts, indefinite fault monitoring can be avoided, thereby reducing the consumption of computing resources. Those skilled in the art can flexibly set the value of the threshold according to actual needs, and the embodiments of the present invention do not impose specific limitations.

[0100] III. Explanation of step S103.

[0101] As described in steps S101 or S102 above, the system framework of the sensor access system can include a sensor driver layer, a system layer, and an application layer. Within this framework, when acquiring and storing data such as log information, sensor data and / or log information can be acquired and stored at both the system layer and the application layer. In this way, sensor data and log information from different data sources can be accurately acquired.

[0102] Furthermore, in the fault monitoring method according to an embodiment of the present invention, after determining whether each link has failed in step S102, fault repair processing can be performed based on the determination result. Specifically, if at least one link has failed, fault repair processing can be performed on the sensor data processing link to eliminate the fault in the at least one link. For example, the fault can be repaired by restarting the sensor data processing link. In addition, a prompt message can be output to remind the user to promptly detect the fault in the processing link. In some embodiments, when outputting the prompt message, the link information and fault type of the faulty link can be obtained, and the prompt message is output based on the link information and fault type. Different fault rules correspond one-to-one with different fault types, and the fault type corresponding to the fault rule can be obtained. Through the above method, it is possible to determine which link has failed based on the link information, and to determine the type of fault in this link based on the fault type.

[0103] The following is in conjunction with the appendix Figure 2 and attached Figure 3 This section explains the fault monitoring method when repairing faults by restarting the link. Figure 2 and Figure 3 The main steps of fault monitoring using non-termination and termination-enabled fault monitoring methods are illustrated respectively.

[0104] See appendix Figure 2The sensor data link can be monitored for faults through the following steps S201 to S206. Step S201: Power on the control system, i.e., restart the system. This system can be the sensor data processing link. Step S202: Start periodic timing. In this step, timing can be performed according to a preset fault monitoring period, and step S203 will be executed when the timing ends. For example, the fault monitoring period can be 5 minutes, then step S203 will be executed when the timing reaches 5 minutes. Step S203: Fault monitoring. In this step, preset fault rules can be loaded, and fault matching is performed on the log information of each link link based on the preset fault rules of each link link. Step S204: Determine if a fault has occurred. In this step, based on the results of the aforementioned fault matching, it can be determined whether a fault has occurred in each link link; if a fault has occurred, step S205 is executed; otherwise, return to step S201 to perform fault monitoring for the next cycle. Step S205: Collect and package data. In this step, for the faulty link, sensor data and log information at the time of the fault can be obtained, packaged into a data packet, and then stored. Step S206: Exit monitoring and preserve the fault scene. In this step, the fault scene can be preserved based on the previously stored sensor data and log information, eliminating the need to re-execute the sensor data processing link to reproduce the fault.

[0105] See appendix Figure 3 The sensor data link can be monitored for faults through the following steps S301 to S308. Step S301: Power on the control system, i.e., restart the system. This system can be the sensor data processing link. Step S302: Obtain the maximum number of monitoring attempts. A preset maximum number of monitoring attempts can be obtained directly, or a preset monitoring frequency can be obtained and the maximum number of monitoring attempts can be indirectly obtained based on that frequency. Step S303: Start the periodic timing. Step S304: Fault monitoring. Step S305: Determine if a fault has occurred. If a fault has occurred, proceed to step S306; otherwise, proceed to step S308. Step S306: Collect and package the data. Step S307: Exit monitoring, preserving the fault scene. Step S308: Check if the maximum number of fault monitoring attempts has been reached; if so, proceed to step S301; if not, proceed to step S303 to perform the next fault monitoring.

[0106] It should be noted that although the above embodiments describe the steps in a specific order, those skilled in the art can understand that in order to achieve the effect of the present application, the steps are not necessarily executed in such an order, and they can be executed simultaneously (in parallel) or in other orders. After these adjustments, the scheme belongs to an equivalent technical scheme described in the present application, and therefore will fall within the protection scope of the present application.

[0107] Those skilled in the art can understand that all or part of the processes in the method of the above embodiment of the present application can also be completed by a computer program instructing related hardware. The computer program can be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable storage medium can include any entity or device, medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code. It should be noted that the contents included in the computer readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable storage medium does not include electrical carrier signals and telecommunication signals.

[0108] Further, the present application also provides a computer device.

[0109] Referring to the accompanying Figure 4 , Figure 4 is the main structure schematic diagram of a computer device embodiment according to the present application. As shown in Figure 4 , the computer device in the embodiment of the present application mainly includes a storage device and a processor. The storage device can be configured to store the program of the fault monitoring method of the sensor data processing link, and the processor can be configured to execute the program in the storage device, which includes but is not limited to the program of the fault monitoring method described above. For the convenience of description, only the parts related to the embodiment of the present application are shown, and the specific technical details not disclosed are referred to the method part of the embodiment of the present application.

[0110] In an embodiment of the present application, the computer device can be a control device formed by various electronic devices. In some possible implementation manners, the computer device can include a plurality of storage devices and a plurality of processors. The program for implementing the fault monitoring method of the above method embodiment can be divided into a plurality of sub-programs, each of which can be loaded and run by a processor to implement different steps of the fault monitoring method of the above method embodiment. Specifically, each sub-program can be stored in a different storage device, and each processor can be configured to execute the program in one or more storage devices to jointly implement the fault monitoring method of the above method embodiment, that is, each processor implements different steps of the fault monitoring method of the above method embodiment to jointly implement the fault monitoring method of the above method embodiment.

[0111] The plurality of processors can be processors deployed on the same device, for example, the computer device can be a high-performance device composed of a plurality of processors, and the plurality of processors can be processors configured on the high-performance device. In addition, the plurality of processors can also be processors deployed on different devices, for example, the computer device can be a server cluster, and the plurality of processors can be processors on different servers in the server cluster.

[0112] Further, the present application also provides a computer readable storage medium.

[0113] In an embodiment of the computer readable storage medium according to the present application, the computer readable storage medium can be configured to store a program for implementing the fault monitoring method of the sensor data processing link according to the above method embodiment, which can be loaded and run by a processor to implement the above fault monitoring method. For the convenience of description, only the part related to the embodiment of the present application is shown, and the specific technical details not disclosed are referred to the method part of the embodiment of the present application. The computer readable storage medium can be a storage device formed by various electronic devices, and optionally, the computer readable storage medium in the embodiment of the present application is a non-transitory computer readable storage medium.

[0114] Further, the present application also provides a vehicle.

[0115] In an embodiment of the vehicle according to the present application, the vehicle can include the computer device according to the above computer device embodiment. In this embodiment, the vehicle can be an autonomous vehicle, an unmanned vehicle, etc. In addition, according to the type of power source, the vehicle in this embodiment can be a fuel vehicle, an electric vehicle, a hybrid vehicle using electric energy and fuel, or a vehicle using other new energy, etc.

[0116] The technical scheme of the present application has been described in combination with one embodiment shown in the drawings, but it is easily understood by those skilled in the art that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical scheme after the changes or replacements will fall within the protection scope of the present application.

Claims

1. A fault monitoring method for a sensor data processing link, characterized in that, The method includes: Load the preset fault rules of each link in the sensor data processing link; Based on the preset fault rules of each link, fault matching is performed on the log information of each link to determine whether a fault has occurred in each link. Acquire and store sensor data and / or log information when each link fails; in, The preset fault rules for each link are set in the following way: each link is simulated to fail and fault log information of each link is obtained during the simulation; based on the fault log information, preset fault rules for each link are set; the preset fault rules are a single rule or a combination of multiple single rules that indicate that a link has failed.

2. The method according to claim 1, characterized in that, After the step of "determining whether each link has failed", the method further includes: If at least one link fails, an alert message and / or will be output. The sensor data processing link is repaired to eliminate the fault that occurred in at least one link.

3. The method according to claim 2, characterized in that, The steps for "outputting a prompt message" specifically include: Obtain information about the faulty link and the fault type; Based on the process information and the fault type, output a prompt message.

4. The method according to claim 1, characterized in that, The specific steps for "determining whether each link has failed" include: The sensor data processing link is monitored for faults according to a preset fault monitoring cycle. In each fault monitoring, based on the preset fault rules of each link link, the log information of each link link is matched for faults to determine whether a fault has occurred in each link link.

5. The method according to claim 1, characterized in that, The steps for "determining whether each link has failed" also include: The sensor data processing link is monitored for faults according to a preset fault monitoring cycle. During each fault monitoring, it is determined whether the number of monitoring sessions has reached a preset threshold. If so, monitoring is stopped. If not, fault matching is performed on the log information of each link based on the preset fault rules of each link to determine whether a fault has occurred in each link.

6. The method according to any one of claims 1 to 5, characterized in that, The method also includes loading preset fault rules and determining whether a fault has occurred in each link by means of: in the application layer or sensor driver layer of the sensor access system. The preset fault rules of each link in the sensor data processing link are loaded, and the log information of each link is matched for faults based on the preset fault rules of each link to determine whether a fault has occurred in each link. or, The method also includes loading preset fault rules and determining whether each link has failed by means of hardware devices installed between the sensor and the system it is connected to. The preset fault rules of each link in the sensor data processing link are loaded, and the log information of each link is matched for faults based on the preset fault rules of each link to determine whether a fault has occurred in each link.

7. The method according to claim 6, characterized in that, The steps of "acquiring and storing sensor data and / or log information when each link fails" specifically include: The sensor data and / or log information are acquired and stored at the system layer and application layer of the sensor access system.

8. A computer device comprising a processor and a storage device, said storage device being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the fault monitoring method for the sensor data processing link according to any one of claims 1 to 7.

9. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the fault monitoring method for the sensor data processing link according to any one of claims 1 to 7.

10. A vehicle, characterized in that, The vehicle includes the computer equipment as described in claim 8.

Images