Monitoring Device Fault Detection Method, Electronic Device, and Computer-Readable Storage Medium

Abstract

The present application discloses a method for detecting faults of monitoring devices, an electronic device, and a computer-readable storage medium. The method includes: obtaining current cycle data of multiple monitoring devices; where at least one preset target is collected in the current cycle data; determining false shooting detection results of each monitoring device for the preset target based on the current cycle data of each monitoring device; and determining an estimated moving speed of the preset target between at least some of the monitoring devices based on the real-time position information and the current cycle data of each monitoring device; taking the monitoring device with an estimated moving speed exceeding the speed threshold as a monitoring device to be tested, determining a test moving speed of the preset target between the monitoring device to be tested and the reference monitoring devices within its preset range, and obtaining a speed detection result of the monitoring device to be tested based on the test moving speed; determining a fault detection result based on the false shooting detection result and the speed detection result. The above solution can improve the efficiency and accuracy of fault detection.

Description

Technical Field

[0001] This application relates to the technical field of fault detection, and particularly to a method for detecting faults of monitoring devices, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the continuous popularization of monitoring devices, the fault detection work of monitoring devices has received increasing attention. Conventional fault detection work is carried out by technicians regularly, or it can only be determined that the monitoring device has failed after there is no monitoring data for a long time. Such a detection method consumes a high labor cost, and the accuracy and efficiency of fault detection are relatively low. In view of this, how to improve the efficiency and accuracy of fault detection has become an urgent problem to be solved. Summary of the Invention

[0003] The main technical problem to be solved by this application is to provide a method for detecting faults of monitoring devices, an electronic device, and a computer-readable storage medium, which can improve the efficiency and accuracy of fault detection.

[0004] To solve the above technical problem, in the first aspect of this application, a method for detecting faults of monitoring devices is provided, including: obtaining current cycle data of multiple monitoring devices; where the current cycle data collects at least one preset target; based on the current cycle data of each monitoring device, determining the false shooting detection results of each monitoring device for the preset target; and, based on the real-time position information and current cycle data of each monitoring device, determining the estimated moving speed of the preset target between at least some of the monitoring devices; using the monitoring device with the estimated moving speed exceeding the speed threshold as the monitoring device to be tested, determining the inspection moving speed of the preset target between the monitoring device to be tested and the reference monitoring devices within its preset range, and obtaining the speed detection result of the monitoring device to be tested based on the inspection moving speed; based on the false shooting detection results and speed detection results of each monitoring device, determining the fault detection results of each monitoring device.

[0005] To solve the above technical problem, in the second aspect of this application, an electronic device is provided. The electronic device includes: a memory and a processor coupled to each other, where the memory stores program data, and the processor calls the program data to execute the method described in the first aspect above.

[0006] To solve the above technical problem, in the third aspect of this application, a computer-readable storage medium is provided, on which program data is stored, and the program data, when executed by a processor, implements the method described in the first aspect above.

[0007] In the above solution, current cycle data collected by multiple monitoring devices is obtained. At least one preset target is collected in the current cycle data. Based on the current cycle data of each monitoring device, misdetection results when each monitoring device captures the preset target are determined. Based on the real-time position information of each monitoring device and the current cycle data of each monitoring device, the estimated moving speed of the preset target between at least some of the monitoring devices is determined. When the estimated moving speed exceeds the speed threshold, all the monitoring devices corresponding to the exceeded speed threshold of the estimated moving speed are used as the monitoring devices to be tested. The moving speed of the preset target between the monitoring devices to be tested and the reference monitoring devices within their preset ranges is tested to obtain the tested moving speed. The speed detection result of the monitoring devices to be tested is determined based on the tested moving speed. The accuracy of the speed detection result is improved through secondary verification. Based on the misdetection results and speed detection results of each monitoring device, the fault detection results of each monitoring device are determined. Therefore, when the misdetection result and / or speed detection result corresponding to a monitoring device is abnormal, it can be determined that the fault detection result of the corresponding monitoring device is a fault, improving the efficiency and accuracy of fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0009] Figure 1 is a flowchart of an implementation manner of the monitoring device fault detection method of the present application;

[0010] Figure 2 is Figure 1 a flowchart of an implementation manner corresponding to step S103 in;

[0011] Figure 3 is Figure 2 an application scenario diagram of an implementation manner corresponding to step S203 in;

[0012] Figure 4 is a structural diagram of an implementation manner of an electronic device of the present application;

[0013] Figure 5 is a structural diagram of an implementation manner of a computer-readable storage medium of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0015] The terms "system" and "network" are often used interchangeably herein. The term "and / or" in this article only describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the preceding and following associated objects. In addition, "multiple" in this article means two or more than two.

[0016] If the technical solution of the present application involves personal information, before the product applying the technical solution of the present application processes personal information, it has clearly informed the personal information processing rules and obtained the autonomous consent of the individual. If the technical solution of the present application involves sensitive personal information, before the product applying the technical solution of the present application processes sensitive personal information, it has obtained the individual's separate consent and at the same time meets the requirements of "express consent". For example, at a personal information collection device such as a camera, a clear and prominent sign is set to inform that the personal information collection range has been entered and personal information will be collected. If an individual voluntarily enters the collection range, it is regarded as consenting to the collection of their personal information; or on the device for processing personal information, when the personal information processing rules are informed by obvious signs / information, personal authorization is obtained through pop-up information or asking the individual to upload their personal information by themselves, etc.; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0017] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of an implementation manner of the method for detecting faults of monitoring devices in the present application. The method includes:

[0018] S101: Obtain the current cycle data of multiple monitoring devices, where at least one preset target is collected in the current cycle data.

[0019] Specifically, there are multiple monitoring devices corresponding to a monitoring area. Obtain the current cycle data collected by the multiple monitoring devices. Among them, at least one preset target corresponds to the current cycle data collected by at least some of the monitoring devices, and the current cycle data corresponds to a cycle time period.

[0020] In an application mode, video data uploaded in real time by multiple monitoring devices is obtained, and the video data within a periodic time period before the current time node is used as the current periodic data, and a preset target in the current periodic data is determined.

[0021] In another application mode, video data uploaded by multiple monitoring devices to a cloud platform is obtained, and the video data corresponding to the same periodic time period of each monitoring device is extracted from the cloud platform as the current periodic data, and a preset target in the current periodic data is determined.

[0022] In a specific application scenario, the periodic time period corresponding to the current periodic data is 24 hours, and the preset target is a vehicle or a pedestrian. In other specific application scenarios, the periodic time period and the preset target can be freely set and defined, and the present application does not make specific restrictions thereon.

[0023] S102: Based on the current periodic data of each monitoring device, determine the false capture detection results of each monitoring device for the preset target, and based on the real-time position information and the current periodic data of each monitoring device, determine the estimated moving speed of the preset target between at least some of the monitoring devices.

[0024] Specifically, the preset target collected based on the current periodic data of each monitoring device is verified to determine the false capture detection results of each monitoring device for the preset target.

[0025] In an application mode, the preset target collected in the current periodic data of the monitoring device is verified, and the preset target is matched with the targets in the database. When no matching result can be obtained for the preset target in the database, it is determined that the false capture detection result of the monitoring device for the preset target is a false capture, where the database includes multiple targets of the same type as the preset target.

[0026] In another application mode, the preset target collected in the current periodic data of the monitoring device is verified to determine whether the preset target belongs to the basic type of the preset target. When the preset target does not belong to the basic type, it is determined that the false capture detection result of the monitoring device for the preset target is a false capture.

[0027] Further, based on the real-time position information of each monitoring device and the time nodes when each monitoring device captures the preset target, among the monitoring devices passed by the preset target, the estimated moving speed of the preset target between any two monitoring devices is determined, so as to obtain the estimated moving speed of the preset target between at least some of the monitoring devices in the monitoring area.

[0028] In one application mode, obtain the real-time location information of each monitoring device, determine the time nodes when the monitoring device captures a preset target. Among the monitoring devices that capture the same preset target, determine the time difference between different time nodes of the preset target based on the sequence of the time nodes, and determine the distance between two monitoring devices based on the real-time location information. Thus, based on the ratio of the distance to the time difference, obtain the estimated moving speed of the preset target between the two monitoring devices.

[0029] In another application mode, obtain the real-time location information of each monitoring device, determine the movement trajectory of the preset target captured by the monitoring device. In the movement trajectory corresponding to the preset target, obtain the distance between two monitoring devices based on the location information between the two monitoring devices, and determine the time difference when the preset target passes through the two monitoring devices based on the time nodes when the two monitoring devices capture the preset target. Thus, based on the ratio of the distance to the time difference, obtain the estimated moving speed of the preset target between the two monitoring devices.

[0030] Optionally, the estimated moving speed between two monitoring devices includes the moving speed of the preset target between any two monitoring devices, where preferably it is the moving speed between two adjacent monitoring devices.

[0031] In an application scenario, the preset target is a vehicle. Determine whether it is the same vehicle based on the license plate on the vehicle. Determine the time difference based on the time nodes when the same vehicle is captured by two adjacent monitoring devices. Convert the distance between the two adjacent monitoring devices based on the location information of the two adjacent monitoring devices. Thus, based on the ratio of the distance to the time difference, obtain the estimated moving speed of each vehicle between the adjacent monitoring devices.

[0032] In another specific application scenario, the preset target is a pedestrian. Determine whether it is the same pedestrian based on the face recognition result of the pedestrian. Determine the time difference based on the time nodes when the same pedestrian is captured by two adjacent monitoring devices. Convert the distance between the two adjacent monitoring devices based on the location information of the two adjacent monitoring devices. Thus, based on the ratio of the distance to the time difference, obtain the estimated moving speed of each pedestrian between the adjacent monitoring devices.

[0033] S103: Regard the monitoring device whose estimated moving speed exceeds the speed threshold as the monitoring device to be tested, determine the inspection moving speed of the preset target between the monitoring device to be tested and the reference monitoring devices within its preset range, and obtain the speed detection result of the monitoring device to be tested based on the inspection moving speed.

[0034] Specifically, when the estimated moving speed of the preset target between two monitoring devices exceeds the speed threshold, both corresponding monitoring devices are regarded as the monitoring devices to be tested. That is to say, when the estimated moving speed of the preset target between two monitoring devices exceeds the speed threshold, the two corresponding monitoring devices are regarded as the monitoring devices that may be abnormal and are marked as the monitoring devices to be tested.

[0035] Further, based on the real-time position information of the monitoring devices to be tested and the reference monitoring devices within the preset range of the monitoring devices to be tested and the currently collected cycle data, the moving speed of the preset target between the monitoring devices to be tested and the reference monitoring devices is rechecked to obtain the checked moving speed, so as to determine the speed detection result of the monitoring devices to be tested based on the checked moving speed, improving the accuracy of the speed detection result. Among them, the reference monitoring devices do not include the monitoring devices to be tested.

[0036] In one application mode, obtain the real-time position information of the monitoring devices to be tested and each reference monitoring device, determine the time nodes when the reference monitoring devices collect the preset target, determine the time difference between the preset target at different time nodes based on the sequence of the time nodes, and determine the distance between the monitoring devices to be tested and the reference monitoring devices based on the real-time position information, so as to obtain the checked moving speed of the preset target between the monitoring devices to be tested and at least some of the reference monitoring devices based on the ratio of the distance and the time difference.

[0037] In another application mode, obtain the real-time position information of the monitoring devices to be tested and each reference monitoring device, determine the checked movement trajectory of the preset target between the monitoring devices to be tested and the reference monitoring devices. In the checked movement trajectory corresponding to the preset target, based on the position information between the two monitoring devices, obtain the distance between the monitoring devices to be tested and the reference monitoring devices, and determine the time difference when the preset target passes through the monitoring devices to be tested and the reference monitoring devices based on the time nodes when the monitoring devices to be tested and the reference monitoring devices collect the preset target, so as to obtain the estimated moving speed of the preset target between the monitoring devices to be tested and at least some of the reference monitoring devices based on the ratio of the distance and the time difference.

[0038] S104: Determine the fault detection results of each monitoring device based on the false shooting detection results and speed detection results of each monitoring device.

[0039] Specifically, when the false shooting detection result and / or speed detection result of any monitoring device is abnormal, the corresponding fault detection result of the corresponding monitoring device is that there is a fault. Therefore, when the false shooting detection result and / or speed detection result of the monitoring device is abnormal, the fault detection result of the corresponding monitoring device can be determined to be that there is a fault, so as to determine the fault detection results of each monitoring device and improve the efficiency of fault detection.

[0040] In the above solution, the current cycle data collected by multiple monitoring devices is obtained. At least one preset target is collected in the current cycle data. Based on the current cycle data of each monitoring device, the misdetection results when each monitoring device captures the preset target are determined. Based on the real-time position information of each monitoring device and the current cycle data of each monitoring device, the estimated moving speed of the preset target between at least some of the monitoring devices is determined. When the estimated moving speed exceeds the speed threshold, all the monitoring devices with the corresponding estimated moving speed exceeding the speed threshold are regarded as the monitoring devices to be tested. The moving speed of the preset target between the monitoring devices to be tested and the reference monitoring devices within their preset ranges is verified to obtain the verified moving speed. The speed detection result of the monitoring device to be tested is determined based on the verified moving speed. The accuracy of the speed detection result is improved through secondary verification. Based on the misdetection results and speed detection results of each monitoring device, the fault detection results of each monitoring device are determined. Therefore, when the misdetection result and / or speed detection result corresponding to a monitoring device is abnormal, it can be determined that the fault detection result of the corresponding monitoring device is a fault, improving the efficiency and accuracy of fault detection.

[0041] In some embodiments, determining the estimated moving speed of the preset target between at least some of the monitoring devices based on the real-time position information and current cycle data of each monitoring device includes: determining the moving trajectory of each preset target based on the current cycle data of each monitoring device; for each preset target, among the monitoring devices corresponding to the moving trajectory of the preset target, based on the real-time position information of the monitoring device and the time node when the monitoring device captures the preset target, determining the estimated moving speed of the preset target between two adjacent monitoring devices; traversing all preset targets to determine the estimated moving speed of the preset target between at least some of the monitoring devices.

[0042] Specifically, when multiple preset targets are collected in the monitoring area, based on the current cycle data collected by each monitoring device, the moving trajectory of each preset target is determined, and the following steps are performed on a single preset target, including: among all the monitoring devices corresponding to the moving trajectory of the preset target, based on the real-time position information of the monitoring device, determining two adjacent monitoring devices in the moving trajectory, determining the distance between the two adjacent monitoring devices based on the real-time position information of the two adjacent monitoring devices, determining the time difference between the two adjacent monitoring devices capturing the same preset target based on the current cycle data collected by the two adjacent monitoring devices, and thus determining the estimated moving speed of the preset target between the two adjacent monitoring devices based on the distance and the time difference.

[0043] Further, all the preset targets and their corresponding moving trajectories are traversed to determine the estimated moving speed of the preset target between at least some of the monitoring devices.

[0044] It can be understood that when the distance between monitoring devices is relatively long, due to the possible large changes in the moving path of the preset target, there may be a situation where the total distance of the moving path is much greater than the straight-line distance between the monitoring devices. Therefore, when estimating the moving speed corresponding to the moving speed between two adjacent monitoring devices, the accuracy of the estimated moving speed can be effectively improved.

[0045] In a specific application scenario, the real-time position information includes the longitude and latitude coordinates obtained based on map navigation called by the call interface of the monitoring device, so as to determine the distance between the monitoring devices based on the longitude and latitude coordinates.

[0046] In some embodiments, please refer to Figure 2 , Figure 2 is Figure 1 a schematic flowchart of an embodiment corresponding to step S103 in

[0047] S201: Determine the first quantity of the preset target collected between the monitoring device to be measured and the reference monitoring device.

[0048] Specifically, count the first quantity of the preset target collected between the monitoring device to be measured and each reference monitoring device.

[0049] In an application scenario, when any monitoring device collects a new preset target different from the archived preset target, set an identification number for the new preset target, archive the new preset target and its corresponding identification number, and take the number of times the identification number appears between the monitoring device to be measured and each reference monitoring device as the first quantity. Among them, in the current cycle data collected by the monitoring device to be measured and the reference monitoring device, when the same preset target appears multiple times between the monitoring device to be measured and the reference monitoring device, the corresponding number of times is included in the first quantity.

[0050] In a specific application scenario, the preset target is a vehicle, set an identification number for the preset target based on the vehicle number, count the number of times the identification number corresponding to the vehicle appears between the monitoring device to be measured and each reference monitoring device, so as to determine the first quantity of the preset target collected between the monitoring device to be measured and the reference monitoring device.

[0051] In another specific application scenario, the preset target is a pedestrian, set the same identification number for the same pedestrian appearing in different monitoring devices based on the face recognition result of the pedestrian, count the number of times the identification number corresponding to the pedestrian appears between the monitoring device to be measured and each reference monitoring device, so as to determine the first quantity of the preset target collected between the monitoring device to be measured and the reference monitoring device.

[0052] S202: Determine the inspection moving speed of each preset target between the monitoring device to be tested and the reference monitoring device based on the real-time position information of the monitoring device to be tested and the reference monitoring device, and the time nodes when the monitoring device to be tested and the reference monitoring device collect the preset target.

[0053] Specifically, based on the real-time position information of the monitoring device to be tested and the reference monitoring device, determine the distance between the monitoring device to be tested and the reference monitoring device. Based on the time nodes when the monitoring device to be tested and the reference monitoring device collect the same preset target, determine the time difference for collecting each preset target. Then, by calculating the ratio of the distance to the time difference, determine the inspection moving speed of each preset target between the monitoring device to be tested and the reference monitoring device.

[0054] S203: Determine the second quantity of inspection moving speeds that exceed the speed threshold among the first quantity of inspection moving speeds.

[0055] Specifically, among the inspection moving speeds corresponding to the first quantity of preset targets, compare the inspection moving speed with the speed threshold, and determine that the number of times the inspection moving speed exceeds the speed threshold is the second quantity.

[0056] In an application scenario, please refer to Figure 3 , Figure 3 is Figure 2 a schematic diagram of an application scenario of an embodiment corresponding to step S203 in Figure 3 wherein, both the monitoring device to be tested and the reference monitoring device correspond to device identifiers. When there is a monitoring device with an estimated moving speed exceeding the speed threshold, then at least two corresponding monitoring devices to be tested

[0057] merely exemplarily shows two monitoring devices to be tested in

[0058] but it is not the basis for limiting that there are only two monitoring devices to be tested.

[0059] S204: Traverse all reference monitoring devices within the preset range, and determine the speed detection result of the monitoring device to be tested based on the first quantity and the second quantity respectively corresponding between the monitoring device to be tested and each reference monitoring device.

[0059] Specifically, all monitoring devices within the preset range of the monitoring device to be tested are traversed. According to the respectively corresponding first quantity and second quantity between the monitoring device to be tested and each reference device, the abnormal movement speed between the monitoring device to be tested and the reference monitoring device is reconfirmed, so as to determine the speed detection result of the monitoring device to be tested, thereby improving the accuracy of the speed detection result.

[0060] In an application scenario, determining the speed detection result of the monitoring device to be tested based on the respectively corresponding first quantity and second quantity between the monitoring device to be tested and each reference monitoring device includes: in response to both the first quantity and the second quantity corresponding between the monitoring device to be tested and at least one reference monitoring device exceeding the number threshold, determining that the speed detection result of the monitoring device to be tested is abnormal; wherein, the number threshold is directly proportional to the sum of the number of the monitoring device to be tested and all its corresponding reference monitoring devices.

[0061] Specifically, when both the first quantity and the second quantity corresponding between the monitoring device to be tested and at least one reference monitoring device exceed the number threshold, the speed detection result of the corresponding monitoring device to be tested is set as abnormal, and the number threshold is directly proportional to the sum of the number of the monitoring device to be tested and all its corresponding reference monitoring devices.

[0062] In an application scenario, please refer to again Figure 3 , the number threshold is twice the sum of the monitoring device to be tested and the reference monitoring device, corresponding Figure 3 In the above, for the monitoring device to be tested with the device identifier 3310240500, and the monitoring device to be tested with the device identifier 3302145654, the corresponding number thresholds are both 8. Between the monitoring device to be tested with the device identifier 3310240500 and the reference monitoring device with the device identifier 3365452556, the first quantity is 91 and the second quantity is 9, both exceeding the number threshold, then it is determined that the speed detection result of the monitoring device to be tested with the device identifier 3310240500 is abnormal. While between the monitoring device to be tested with the device identifier 3302145654 and the reference monitoring device with the device identifier 3652414102, the first quantity is 12 and the second quantity is 1, and the second quantity does not exceed the number threshold, then the abnormal result less than the number threshold is considered a discrete value, which may be an accidental error caused by target recognition error rather than speed abnormality. Furthermore, by comparing both the first quantity and the second quantity with the number threshold, the speed detection result is determined, improving the accuracy and stability of speed detection and reducing the influence of discrete values.

[0063] It should be noted that the number threshold can be freely set in different application scenarios, and the present application does not make specific settings for this.

[0064] In some embodiments, determining false capture detection results of each monitoring device for a preset target based on the current cycle data of each monitoring device includes: extracting the preset target from the current cycle data of each monitoring device, matching the extracted preset target with the targets in the database to obtain a matching result; and verifying the extracted preset target to obtain a verification result; wherein the database includes multiple targets of the same type as the preset target; determining the false capture detection results of each monitoring device for the preset target based on the matching result and the number of times the verification result is abnormal.

[0065] Specifically, extract the preset target from the current cycle data collected by each monitoring device, and remove duplicates for the same preset target to obtain the preset target extracted from each monitoring device.

[0066] Furthermore, match the extracted preset target with the targets in the database to determine whether the captured preset target can be successfully matched with the targets in the database to obtain a matching result, verify the preset target extracted from each monitoring device to determine whether the preset target can be recognized as a normal preset target to obtain a verification result. When the number of times the matching result and the verification result are abnormal exceeds the abnormal number threshold, it is determined that the false capture detection result of the corresponding monitoring device is abnormal. The false capture detection result is determined through two verification methods, and the number of times the matching result and the verification result are abnormal is combined during the determination, thereby reducing the influence of discrete values and improving the stability and accuracy of the false capture detection result.

[0067] In a specific application scenario, the preset target is a vehicle, and the database is a national vehicle database. Compare the license plate of the vehicle with the license plates in the national vehicle database. If there is no data for the identified license plate in the national vehicle database, the matching result is abnormal, otherwise it is normal. If the captured license plate is determined not to be a normal license plate after function verification, the verification result is abnormal, otherwise it is normal. When the matching result or the verification result is abnormal, the number of abnormal times is incremented by one. If the number of abnormal times of the preset target in the current cycle data collected by any monitoring device exceeds the abnormal number threshold, it is determined that the false capture detection result of the corresponding monitoring device is abnormal, otherwise it is normal.

[0068] Optionally, when the extracted license plate is an out-of-town license plate and has not appeared in the historical cycle data before the current cycle, that is, it only appears once within a period of time and other monitoring devices have not collected this out-of-town license plate, the number of abnormal times of the monitoring device that collected this out-of-town license plate is incremented by one. Thus, the license plate that appears occasionally is also added to the number of abnormal times. Even if the license plate can obtain a matching result and a verification result, it is regarded as one abnormal time, improving the accuracy of the number of abnormal times.

[0069] In some embodiments, obtaining the current cycle data of multiple monitoring devices includes: accessing the current cycle data of the multiple monitoring devices to a computing platform to obtain the current cycle data of the multiple monitoring devices; wherein, the computing platform stores historical cycle data within a preset time period before the current cycle.

[0070] Specifically, the current cycle data collected by the multiple monitoring devices is accessed to the computing platform, thereby obtaining the current cycle data of the multiple monitoring devices, and the computing platform includes a storage space for storing the historical cycle data within a preset time period before the current cycle, so as to facilitate judging the fault detection result in combination with the historical cycle data.

[0071] Further, after obtaining the current cycle data of the multiple monitoring devices, it further includes: accessing the device information data of the multiple monitoring devices to the computing platform to obtain the device information data of the multiple monitoring devices; wherein, the device information data includes the preset location information and the preset identification information of each monitoring device.

[0072] Specifically, each monitoring device corresponds to device information data before installation. After accessing the device information data of the multiple monitoring devices to the computing platform, the device information data of the multiple monitoring devices is obtained. Among them, the device information data includes the preset location information and the preset identification information of each monitoring device. The preset location information corresponds to the planned installation location of the monitoring device. That is to say, the device information data includes the device identifiers and the planned installation locations of all monitoring devices in the monitoring area, so as to facilitate detecting whether the monitoring device is offline and whether there is a location deviation.

[0073] In a specific application scenario, the current cycle data is accessed to the computing platform in the way of Kafka to meet the high-throughput current cycle data.

[0074] Further, before determining the fault detection results of each monitoring device based on the false capture detection results and speed detection results of each monitoring device, it further includes: determining the clock synchronization detection results of each monitoring device based on the time node corresponding to the current cycle data of each monitoring device and the time node when the current cycle data is accessed to the computing platform; and / or, determining the traffic detection results of each monitoring device based on the data volume and data distribution period of the current cycle data of each monitoring device and the data volume of the historical cycle data; and / or, determining the offline detection results of each monitoring device based on the preset identification information in the device information data, the device identification information of all monitoring devices that have collected the current cycle data, and the data distribution period of the current cycle data of each monitoring device; and / or, determining the position detection results of each monitoring device based on the preset position information in the device information data and the real-time position information of each monitoring device; wherein, the traffic detection results, offline detection results, and position detection results are related to the monitoring devices, and the false capture detection results and speed detection results are related to the preset target.

[0075] In an application scenario, by comparing the time node corresponding to the current cycle data of each monitoring device and the time node when the current cycle data is accessed to the computing platform, the time node corresponding to the current cycle data is theoretically earlier than the time node when the current cycle data is accessed to the computing platform. If the time node corresponding to the current cycle data is later than the time node when the current cycle data is accessed to the computing platform, it indicates that the clock of the monitoring device and the computing platform is not synchronized, and the clock synchronization detection result is abnormal, otherwise it is normal.

[0076] In another application scenario, determine whether the data volume of the current cycle of the monitoring device is abnormal, determine whether there is a data-free period in the data distribution period of the current cycle data, and determine whether the data volume of the current cycle data is much smaller than the average value of the data volume of the historical cycle data, so as to finally determine the traffic detection results of each monitoring device.

[0077] In yet another application scenario, determine whether all the monitoring devices corresponding to the preset identification in the device information data have collected the current cycle data, and determine whether there is a long data-free period in the current cycle data collected by the monitoring device, so as to finally determine the offline detection results of each monitoring device.

[0078] In yet another application scenario, compare the real-time position information feedback by each monitoring device and the preset position information in the device information data. If the distance between the real-time position information of the monitoring device and the preset position information exceeds the distance threshold, the position detection result of the corresponding monitoring device is abnormal, otherwise it is normal.

[0079] It should be noted that for the clock synchronization detection result, traffic detection result, offline detection result, and location detection result, one or several detection methods can be selected based on different application scenarios to enrich the basis for judging the fault detection result. Among them, the traffic detection result, offline detection result, and location detection result are related to the location of the monitoring device or the collected data, and the false capture detection result and speed detection result are related to the recognition result or moving speed of the preset target.

[0080] Therefore, it can be understood that based on the false capture detection result and speed detection result of each monitoring device, the fault detection result of each monitoring device is determined, including: based on the false capture detection result and speed detection result of each monitoring device, and / or the clock synchronization detection result, and / or the traffic detection result, and / or the offline detection result and / or the location detection result, the fault detection result of each monitoring device is determined. When any one of the false capture detection result, speed detection result, clock synchronization detection result, traffic detection result, offline detection result, and location detection result is abnormal, the fault detection result of the corresponding monitoring device is that there is a fault.

[0081] In a specific application scenario, based on the data volume and data distribution period of the current cycle data of each monitoring device, and the data volume of the historical cycle data, the traffic detection result of each monitoring device is determined, including: if the data volume of the current cycle data of any monitoring device is less than the current traffic threshold, or the data volume of the current cycle data of any monitoring device is less than the historical traffic threshold, or there is no data in a time period exceeding the first time threshold in the data distribution period of the current cycle data of any monitoring device, the traffic detection result of the corresponding monitoring device is abnormal, otherwise it is normal; where the current traffic threshold is determined based on the capture volume for the preset target, and the historical traffic threshold is determined based on the average value of the data volume of the historical cycle data.

[0082] Specifically, when the current cycle data collected by the monitoring device meets any of the following scenarios, the traffic detection result of the corresponding monitoring device is abnormal. The above scenarios include: the data volume of the current cycle data is less than the current traffic threshold, or the data volume of the current cycle data is less than the historical traffic threshold, or there is no data in a time period exceeding the first time threshold in the data distribution period of the current cycle data. Among them, the current traffic threshold is less than the historical traffic threshold, the current traffic threshold is determined based on the capture volume for the preset target, the historical traffic threshold is obtained by multiplying the average value of the historical cycle data by the first coefficient, and the first coefficient can be any value between 0.5 and 1. The first time threshold is obtained by multiplying the cycle time period corresponding to the current cycle data by the second coefficient, and the second coefficient can be any value between 0.1 and 0.2, so as to enrich the traffic detection method by setting multiple judgment scenarios.

[0083] In another specific application scenario, based on the preset identification information in the device information data, the device identification information of all monitoring devices that have collected the current cycle data, and the data distribution period of the current cycle data of each monitoring device, determine the offline detection results of each monitoring device, including: if the preset identification information of any monitoring device in the device information data does not match the device identification information of the monitoring device that has collected the current cycle data, or there is no data in a period exceeding the second time threshold in the data distribution period of the current cycle data of any monitoring device, the offline detection result of the corresponding monitoring device is abnormal, otherwise it is normal; where the second time threshold is greater than the first time threshold.

[0084] Specifically, when the current cycle data collected by the monitoring device meets any of the following scenarios, the offline detection result of the corresponding monitoring device is abnormal. The above scenarios include: the preset identification information existing in the device information data does not match the identification information of the monitoring device that has collected the current cycle data, that is, there is a monitoring device corresponding to the preset identification information that has not collected the current cycle data, or there is no data in a period exceeding the second time threshold in the data distribution period of the current cycle data. Among them, the second time threshold is obtained by multiplying the cycle time period corresponding to the current cycle data by a third coefficient. The third coefficient can be any value in the range of 0.2 - 0.5, and the second time threshold is greater than the first time threshold to distinguish between traffic anomalies and device offline, so as to enrich the offline detection method by setting multiple judgment scenarios.

[0085] Please refer to Figure 4 , Figure 4 FIG. is a schematic structural diagram of an embodiment of an electronic device according to the present application. The electronic device 40 includes a memory 401 and a processor 402 that are coupled to each other. Among them, the memory 401 stores program data (not shown in the figure), and the processor 402 calls the program data to implement the method in any of the above embodiments. For the description of related content, please refer to the detailed description of the above method embodiments and will not be repeated here.

[0086] Please refer to Figure 5 , Figure 5 FIG. is a schematic structural diagram of an embodiment of a computer-readable storage medium according to the present application. The computer-readable storage medium 50 stores program data 500. When the program data 500 is executed by a processor, it implements the method in any of the above embodiments. For the description of related content, please refer to the detailed description of the above method embodiments and will not be repeated here.

[0087] It should be noted that the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods of each embodiment of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs and other various media that can store program codes.

[0090] The above is only the embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for detecting faults of monitoring devices, characterized in that, the method includes: obtaining current cycle data of multiple monitoring devices; wherein, at least one preset target is collected in the current cycle data; based on the current cycle data of each monitoring device, determining the false shooting detection results of each monitoring device for the preset target; and, based on the real-time position information and current cycle data of each monitoring device, determining the estimated moving speed of the preset target between at least some of the monitoring devices; taking the monitoring devices with the estimated moving speed exceeding the speed threshold as the monitoring devices to be tested, determining the inspection moving speed of the preset target between the monitoring devices to be tested and the reference monitoring devices within their preset ranges, and obtaining the speed detection results of the monitoring devices to be tested based on the inspection moving speed; wherein, there are a first number of inspection moving speeds corresponding to the preset target between the monitoring devices to be tested and the reference monitoring devices within their preset ranges, and the speed detection results are obtained based on the following steps: among the first number of inspection moving speeds, determining the second number of inspection moving speeds exceeding the speed threshold; traversing all the reference monitoring devices within the preset range, and based on the first number and the second number respectively corresponding to the monitoring device to be tested and each reference monitoring device, determining the speed detection results of the monitoring device to be tested; based on the false shooting detection results and speed detection results of each monitoring device, determining the fault detection results of each monitoring device.

2. The method for detecting faults of monitoring devices according to claim 1, characterized in that, the determining the estimated moving speed of the preset target between at least some of the monitoring devices based on the real-time position information and current cycle data of each monitoring device includes: based on the current cycle data of each monitoring device, determining the moving trajectories of each preset target; for each preset target, among the monitoring devices corresponding to the moving trajectory of the preset target, based on the real-time position information of the monitoring device and the time node when the monitoring device collects the preset target, determining the estimated moving speed of the preset target between two adjacent monitoring devices; traversing all preset targets to determine the estimated moving speed of the preset target between at least some of the monitoring devices.

3. The method for detecting faults of monitoring devices according to claim 1, characterized in that, the determining the inspection moving speed of the preset target between the monitoring device to be tested and the reference monitoring devices within its preset range includes: determining the first number of times the preset target is collected between the monitoring device to be tested and the reference monitoring device; based on the real-time position information of the monitoring device to be tested and the reference monitoring device, and the time nodes when the monitoring device to be tested and the reference monitoring device collect the preset target, determining the inspection moving speed of each preset target between the monitoring device to be tested and the reference monitoring device.

4. The method for detecting faults of monitoring devices according to claim 3, characterized in that, Determining the speed detection result of the to-be-tested monitoring device based on the respectively corresponding first quantity and second quantity between the to-be-tested monitoring device and each of the reference monitoring devices includes: In response to the first quantity and the second quantity corresponding between the to-be-tested monitoring device and at least one of the reference monitoring devices both exceeding a number threshold, determining that the speed detection result of the to-be-tested monitoring device is abnormal; wherein, the number threshold is proportional to the sum of the number of the to-be-tested monitoring device and all the corresponding reference monitoring devices.

5. The monitoring device fault detection method according to claim 1, wherein, Determining the false capture detection result of each monitoring device for the preset target based on the current cycle data of each monitoring device includes: Extracting the preset target from the current cycle data of each monitoring device, matching the extracted preset target with the targets in the database to obtain a matching result; and, verifying the extracted preset target to obtain a verification result; wherein, the database includes multiple targets of the same type as the preset target; Based on the matching result and the number of times the verification result is abnormal, determining the false capture detection result of each monitoring device for the preset target.

6. The monitoring device fault detection method according to claim 1, wherein, Obtaining the current cycle data of multiple monitoring devices includes: Connecting the current cycle data of multiple monitoring devices to a computing platform to obtain the current cycle data of multiple monitoring devices; wherein, the computing platform stores historical cycle data within a preset time period before the current cycle. After obtaining the current cycle data of multiple monitoring devices, it further includes: Connecting the device information data of multiple monitoring devices to the computing platform to obtain the device information data of multiple monitoring devices; wherein, the device information data includes the preset location information and preset identification information of each monitoring device.

7. The monitoring device fault detection method according to claim 6, wherein, Before determining the fault detection result of each monitoring device based on the false capture detection result and speed detection result of each monitoring device, it further includes: Based on the time node corresponding to the current cycle data of each monitoring device and the time node when the current cycle data is connected to the computing platform, determining the clock synchronization detection result of each monitoring device; and / or, based on the data volume and data distribution period of the current cycle data of each monitoring device, and the data volume of the historical cycle data, determining the traffic detection result of each monitoring device; and / or, based on the preset identification information in the device information data and the device identification information of all the monitoring devices that have collected the current cycle data, and the data distribution period of the current cycle data of each monitoring device, determining the offline detection result of each monitoring device; And / or, based on the preset location information in the device information data and the real-time location information of each of the monitoring devices, determine the location detection results of each of the monitoring devices; wherein, the traffic detection result, the offline detection result, and the location detection result are related to the monitoring devices, and the false capture detection result and the speed detection result are related to the preset target; Determining the fault detection results of each of the monitoring devices based on the false capture detection results and speed detection results of each of the monitoring devices includes: Based on the false capture detection results and the speed detection results of each of the monitoring devices, and / or the clock synchronization detection result, and / or the traffic detection result, and / or the offline detection result and / or the location detection result, determine the fault detection results of each of the monitoring devices.

8. The monitoring device fault detection method according to claim 7, wherein, Determining the traffic detection results of each of the monitoring devices based on the data volume and data distribution period of the current cycle data of each of the monitoring devices, and the data volume of the historical cycle data includes: If the data volume of the current cycle data of any one of the monitoring devices is less than the current traffic threshold, or the data volume of the current cycle data of any one of the monitoring devices is less than the historical traffic threshold, or there is no data in a time period exceeding the first time threshold in the data distribution period of the current cycle data of any one of the monitoring devices, then the traffic detection result of the corresponding monitoring device is abnormal, otherwise it is normal; wherein, the current traffic threshold is determined based on the capture quantity for the preset target, and the historical traffic threshold is determined based on the average value of the data volume of the historical cycle data; Determining the offline detection results of each of the monitoring devices based on the preset identification information in the device information data, the device identification information of all the monitoring devices that have collected the current cycle data, and the data distribution period of the current cycle data of each of the monitoring devices includes: If the preset identification information of any one of the monitoring devices in the device information data does not match the device identification information of the monitoring device that has collected the current cycle data, or there is no data in a time period exceeding the second time threshold in the data distribution period of the current cycle data of any one of the monitoring devices, then the offline detection result of the corresponding monitoring device is abnormal, otherwise it is normal; wherein, the second time threshold is greater than the first time threshold.

9. An electronic device, wherein, includes: A memory and a processor coupled to each other, wherein the memory stores program data, and the processor calls the program data to execute the method according to any one of claims 1-8.

10. A computer-readable storage medium, on which program data is stored, wherein, The program data, when executed by a processor, implements the method according to any one of claims 1-8.

Images