Campus security equipment diagnosis system based on Internet of Things

Abstract

The invention discloses a campus security equipment diagnosis system based on the Internet of Things, and belongs to the technical field of security equipment, and the system specifically comprises the steps: setting a target region and an inspection period, obtaining monitoring equipment in the target region, and carrying out the statistics of the fault information and operation indexes of any monitoring equipment in the inspection period; clustering the monitoring equipment according to the operation indexes of the monitoring equipment to generate a plurality of category clusters; any category cluster is selected, fault information of all the monitoring devices in the category cluster is obtained, the monitoring devices with the total number of times of faults larger than or equal to a preset number-of-times threshold value serve as to-be-determined devices, the fault distances between the to-be-determined devices and all the monitoring devices are calculated, and operation inspection scores of the to-be-determined devices are calculated; if the operation maintenance score is larger than or equal to the preset risk threshold value, the to-be-determined equipment serves as the target monitoring equipment needing operation maintenance in the next operation maintenance period, the monitoring equipment needing maintenance can be screened, the labor cost and the time cost needed by maintenance are reduced, and the operation maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of security equipment, and in particular to a campus security equipment diagnosis system based on the Internet of Things. Background Art

[0002] Campus refers to the campus area of ​​a school or university, including teaching buildings, libraries, laboratories, student dormitories, canteens, sports facilities and other related facilities. It is the main place for education and academic activities, and also the place where students and faculty members study, live and socialize. Smart campus refers to the use of advanced technologies such as the Internet, big data, and artificial intelligence to collect, integrate, analyze and apply various information within the campus, so as to realize intelligent, efficient and convenient teaching, management, services and other aspects. In the process of campus management, campus safety issues have received widespread attention. Campus security measures are mainly achieved through manual inspections and surveillance cameras. Network video surveillance systems are widely used in government, education, transportation, finance and other fields for security monitoring of important parts and places due to their intuitive, accurate, timely and information-rich characteristics, and play an irreplaceable role in public security work. In recent years, with the development of the economy and society, the scale of video surveillance networks has been continuously expanded, and the number of monitoring points and cameras has increased dramatically. On the one hand, a large number of monitoring points have improved the technical defense capabilities of the campus, but on the other hand, they have brought huge challenges to the operation and maintenance of the system. During the use of some cameras, due to natural aging and other reasons, the monitoring video will be abnormal. Therefore, it is necessary to conduct regular inspections of the monitoring equipment. However, regular maintenance is bound to be constrained by human resources, and the reliability of monitoring equipment is relatively high. Regular inspections and decommissioning and replacement plans that ignore the risk differences of monitoring equipment will lead to waste of manpower and resources. Summary of the invention

[0003] The purpose of the present invention is to provide a campus security equipment diagnostic system based on the Internet of Things to solve the following technical problems: Some cameras may experience abnormal monitoring videos due to natural aging and other reasons during use. Therefore, regular inspections of monitoring equipment are required. However, regular maintenance is bound to be constrained by human resources, and monitoring equipment has a high reliability. Regular inspections and decommissioning and replacement plans that ignore the risk differences of monitoring equipment will lead to a waste of manpower and resources.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A campus security equipment diagnostic system based on the Internet of Things, comprising: A data acquisition module is used to set a target area and inspection cycle, acquire monitoring equipment in the target area, and count the fault information and operating indicators of any monitoring equipment during the inspection cycle. The operating indicators include the operating temperature, operating humidity, and operating time of the monitoring equipment; the fault information includes the number of faults, fault type, and repair time; The data analysis module is used to select any monitoring device and perform cumulative calculation on the operating indicators of the monitoring device to obtain the cumulative value of the operating time, the cumulative value of the operating temperature and the cumulative value of the operating humidity. The cumulative value of the operating time is used as the horizontal axis, the cumulative value of the operating temperature is used as the vertical axis, and the cumulative value of the operating humidity is used as the vertical axis to construct three-dimensional coordinates, generate feature points corresponding to all monitoring devices, select any feature point as the center, set the clustering radius, calculate the feature point density Y within the clustering radius, obtain the mean value of the feature point density within the clustering radius of all feature points, mark the mean value of the feature point density as MinY, if there is any feature point whose density P within the clustering radius is greater than MinY, mark the feature point as a core point, and generate a category cluster with the core point as the center; The result generation module is used to select any category cluster and obtain the fault information of all monitoring devices in the category cluster, take the monitoring devices whose total number of faults is greater than or equal to a preset number threshold as pending devices, calculate the fault distance between the pending device and all monitoring devices and calculate the operation and inspection score of the pending device based on the fault distance; if the operation and inspection score of the pending device is greater than or equal to a preset risk threshold, the pending device is taken as the target monitoring device that needs to be inspected in the next operation and inspection cycle.

[0005] As a further solution of the present invention: in the data analysis module, the specific calculation process of the cluster radius is: Select any feature point and take it as the center, calculate the Euclidean distance U between the feature point and any other feature point, sum each Euclidean distance to get D, and get the cluster radius R based on the value D. The calculation formula is as follows: ; ; Among them, D is the sum of the Euclidean distance data values ​​of all feature points, and U is the Euclidean distance between any feature points.

[0006] As a further solution of the present invention: in the data analysis module, if there is a non-core point in any category cluster whose density Y within the clustering radius R is also greater than MinY, the category cluster generated by the non-core point is merged with the original category cluster to generate several category clusters.

[0007] As a further solution of the present invention: in the result generation module, the specific calculation process of the fault distance is: ; Wherein, n is all fault types of the monitoring equipment, FMi is the number of times the pending equipment M has fault type i during the inspection cycle, and FNi is the number of times the monitoring equipment N has fault type i during the inspection cycle.

[0008] As a further solution of the present invention: in the result generation module, the calculation process of the operation inspection score is: ; W'= ; Where u is the number of all reference devices, Fpi is the number of faults of the pth reference device in the reference device during the inspection cycle, dp is the fault distance between the reference device and the pending device, Tpi is the average maintenance time corresponding to fault type i, and W' is the operation and inspection score of the pending device.

[0009] As a further solution of the present invention: in the result generation module, if the operation and inspection scores of all monitoring devices in any category cluster are less than the preset risk threshold, all monitoring devices are sorted according to the size of the corresponding operation and inspection scores. The larger the operation and inspection score, the higher the ranking. The first X in the sorting are selected as the monitoring devices that need to be inspected in the next operation and inspection cycle, and X is a preset number value.

[0010] As a further solution of the present invention: if there are two or more monitoring devices with the same operation and inspection scores, they are sorted according to the operation time of the monitoring devices during the inspection cycle. The shorter the operation time, the higher the ranking.

[0011] As a further solution of the present invention: when a certain monitoring device is replaced during the inspection cycle, it does not participate in the execution of subsequent steps and is used as a target monitoring device that needs to be inspected during the next inspection cycle.

[0012] Beneficial effects of the present invention: The present invention first sets the target area and inspection cycle, obtains the monitoring data within the inspection cycle, and provides a basis for subsequent comprehensive analysis; it can be understood that due to the different operating environments of the monitoring equipment, the operating indicators of the equipment (such as temperature and humidity) will be significantly affected by environmental factors. These environmental differences will cause the performance of the equipment to be different in different environments, resulting in different actual operating time, failure mode and risk level of the equipment. By integrating these indicators into a three-dimensional coordinate system for cluster analysis, the actual impact of the environment on the operation of the equipment can be more accurately captured and understood, and more effective risk assessment and maintenance decisions can be made. Select any category cluster and obtain the fault information of all monitoring devices in the category cluster. By using the fault information of all monitored devices, the fault distance between the pending device and other devices is determined, so as to further use the fault distance between each other device and the pending device as a reference and obtain the fault repair time corresponding to each type of fault, evaluate the pending device according to the fault distance and fault repair time, and judge whether the corresponding monitoring device needs to be operated and inspected in the next maintenance cycle according to the evaluation score. The present invention can screen the monitoring equipment that needs to be repaired, reduce the manpower cost and time cost required for maintenance, and improve maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further described below in conjunction with the accompanying drawings.

[0014] Figure 1 The present invention is a schematic diagram of a campus security equipment diagnostic system based on the Internet of Things. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] See also Figure 1 As shown, the present invention is a campus security equipment diagnostic system based on the Internet of Things, comprising: A data acquisition module is used to set a target area and inspection cycle, acquire monitoring equipment in the target area, and count the fault information and operating indicators of any monitoring equipment during the inspection cycle. The operating indicators include the operating temperature, operating humidity, and operating time of the monitoring equipment; the fault information includes the number of faults, fault type, and repair time; The data analysis module is used to select any monitoring device and perform cumulative calculation on the operating indicators of the monitoring device to obtain the cumulative value of the operating time, the cumulative value of the operating temperature and the cumulative value of the operating humidity. The cumulative value of the operating time is used as the horizontal axis, the cumulative value of the operating temperature is used as the vertical axis, and the cumulative value of the operating humidity is used as the vertical axis to construct three-dimensional coordinates, generate feature points corresponding to all monitoring devices, select any feature point as the center, set the clustering radius, calculate the feature point density Y within the clustering radius, obtain the mean value of the feature point density within the clustering radius of all feature points, mark the mean value of the feature point density as MinY, if there is any feature point whose density P within the clustering radius is greater than MinY, mark the feature point as a core point, and generate a category cluster with the core point as the center; The result generation module is used to select any category cluster and obtain the fault information of all monitoring devices in the category cluster, take the monitoring devices whose total number of faults is greater than or equal to a preset number threshold as pending devices, calculate the fault distance between the pending device and all monitoring devices and calculate the operation and inspection score of the pending device based on the fault distance; if the operation and inspection score of the pending device is greater than or equal to a preset risk threshold, the pending device is taken as the target monitoring device that needs to be inspected in the next operation and inspection cycle.

[0017] The present invention first sets the target area and inspection cycle, obtains the monitoring data within the inspection cycle, and provides a basis for subsequent comprehensive analysis; it can be understood that due to the different operating environments of the monitoring equipment, the operating indicators of the equipment (such as temperature and humidity) will be significantly affected by environmental factors. These environmental differences will cause the performance of the equipment to be different in different environments, resulting in different actual operating time, failure mode and risk level of the equipment. By integrating these indicators into a three-dimensional coordinate system for cluster analysis, the actual impact of the environment on the operation of the equipment can be more accurately captured and understood, and more effective risk assessment and maintenance decisions can be made. Select any category cluster and obtain the fault information of all monitoring devices in the category cluster. By using the fault information of all monitored devices, the fault distance between the pending device and other devices is determined, so as to further use the fault distance between each other device and the pending device as a reference and obtain the fault repair time corresponding to each type of fault, evaluate the pending device according to the fault distance and fault repair time, and judge whether the corresponding monitoring device needs to be operated and inspected in the next maintenance cycle according to the evaluation score. The present invention can screen the monitoring equipment that needs to be repaired, reduce the manpower cost and time cost required for maintenance, and improve maintenance efficiency.

[0018] In a preferred implementation of the present invention, in the data analysis module, the specific calculation process of the cluster radius is: Select any feature point and take it as the center, calculate the Euclidean distance U between the feature point and any other feature point, sum each Euclidean distance to get D, and get the cluster radius R based on the value D. The calculation formula is as follows: ; ; Among them, D is the sum of the Euclidean distance data values ​​of all feature points, and U is the Euclidean distance between any feature points.

[0019] In another preferred implementation of the present invention, in the data analysis module, if there is a non-core point in any category cluster whose density Y within the clustering radius R is also greater than MinY, the category cluster generated by the non-core point is merged with the original category cluster to generate several category clusters.

[0020] In another preferred implementation of the present invention, in the result generation module, the specific calculation process of the fault distance is: ; Wherein, n is all fault types of the monitoring equipment, FMi is the number of times the pending equipment M has fault type i during the inspection cycle, and FNi is the number of times the monitoring equipment N has fault type i during the inspection cycle.

[0021] In another preferred implementation of the present invention, in the result generation module, the calculation process of the operation and inspection score is: ); ; Where u is the number of all reference devices, Fpi is the number of faults of the pth reference device in the reference device during the inspection cycle, dp is the fault distance between the reference device and the pending device, Tpi is the average maintenance time corresponding to fault type i, and W' is the operation and inspection score of the pending device.

[0022] In another preferred implementation of the present invention, in the result generation module, if the operation and inspection scores of all monitoring devices in any category cluster are less than the preset risk threshold, all monitoring devices are sorted according to the size of the corresponding operation and inspection scores. The larger the operation and inspection score, the higher the ranking. The first X in the sorting are selected as the monitoring devices that need to be inspected in the next operation and inspection cycle, and X is a preset number value.

[0023] It is understandable that with limited maintenance resources, priority should be given to those monitoring devices with higher maintenance scores to minimize risks and improve the overall stability of the system. By sorting and selecting devices with higher scores, it can be ensured that in the next maintenance cycle, those devices with greater potential problems are given priority, reducing the possibility of monitoring system failure.

[0024] In another preferred implementation of the present invention, if there are two or more monitoring devices with the same operation and inspection scores, they are sorted according to the operation time of the monitoring devices during the inspection cycle. The shorter the operation time, the higher the ranking.

[0025] It is understandable that the longer the monitoring device operates during the inspection cycle, the better the operating stability of the monitoring device, and the shorter the operating time, the worse the operating stability of the monitoring device.

[0026] In another preferred implementation of the present invention, when a certain monitoring device is replaced during the inspection cycle, it does not participate in the execution of subsequent steps and is used as a target monitoring device that needs to be inspected during the next inspection cycle.

[0027] Since the faulty monitoring equipment has been replaced in the current inspection cycle and does not participate in the subsequent steps, duplication of work and waste of resources can be avoided. The replaced monitoring equipment will be included in the next operation and inspection cycle for inspection, which can ensure that the current monitoring equipment problems can be handled in each operation and inspection cycle, and plans can be made for future maintenance cycles to avoid omissions.

[0028] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A campus security equipment diagnostic system based on the Internet of Things, characterized in that: include: A data acquisition module is used to set a target area and inspection cycle, acquire monitoring equipment in the target area, and count the fault information and operating indicators of any monitoring equipment during the inspection cycle. The operating indicators include the operating temperature, operating humidity, and operating time of the monitoring equipment; the fault information includes the number of faults, fault type, and repair time; The data analysis module is used to select any monitoring device and perform cumulative calculation on the operating indicators of the monitoring device to obtain the cumulative value of the operating time, the cumulative value of the operating temperature and the cumulative value of the operating humidity. The cumulative value of the operating time is used as the horizontal axis, the cumulative value of the operating temperature is used as the vertical axis, and the cumulative value of the operating humidity is used as the vertical axis to construct three-dimensional coordinates, generate feature points corresponding to all monitoring devices, select any feature point as the center, set the clustering radius, calculate the feature point density Y within the clustering radius, obtain the mean value of the feature point density within the clustering radius of all feature points, mark the mean value of the feature point density as MinY, if there is any feature point whose density P within the clustering radius is greater than MinY, mark the feature point as a core point, and generate a category cluster with the core point as the center; The result generation module is used to select any category cluster and obtain the fault information of all monitoring devices in the category cluster, take the monitoring devices whose total number of faults is greater than or equal to a preset number threshold as pending devices, calculate the fault distance between the pending device and all monitoring devices and calculate the operation and inspection score of the pending device based on the fault distance; if the operation and inspection score of the pending device is greater than or equal to a preset risk threshold, the pending device is taken as the target monitoring device that needs to be inspected in the next operation and inspection cycle.

2. According to the Internet of Things-based campus security equipment diagnostic system of claim 1, it is characterized in that: In the data analysis module, the specific calculation process of the cluster radius is: Select any feature point and take it as the center, calculate the Euclidean distance U between the feature point and any other feature point, sum each Euclidean distance to get D, and get the cluster radius R based on the value D. The calculation formula is as follows: ； ； Among them, D is the sum of the Euclidean distance data values ​​of all feature points, and U is the Euclidean distance between any feature points.

3. According to the Internet of Things-based campus security equipment diagnostic system of claim 1, it is characterized in that: In the data analysis module, if there is a non-core point in any category cluster whose density Y within the clustering radius R is also greater than MinY, the category cluster generated by the non-core point is merged with the original category cluster to generate several category clusters.

4. The campus security equipment diagnostic system based on the Internet of Things according to claim 1 is characterized in that: In the result generation module, the specific calculation process of the fault distance is: ； Wherein, n is all fault types of the monitoring equipment, FMi is the number of times the pending equipment M has fault type i during the inspection cycle, and FNi is the number of times the monitoring equipment N has fault type i during the inspection cycle.

5. The campus security equipment diagnostic system based on the Internet of Things according to claim 1 is characterized in that: In the result generation module, the calculation process of the operation and inspection score is as follows: ； W'= ； Where u is the number of all reference devices, Fpi is the number of faults of the pth reference device in the reference device during the inspection cycle, dp is the fault distance between the reference device and the pending device, Tpi is the average maintenance time corresponding to fault type i, and W' is the operation and inspection score of the pending device.

6. The campus security equipment diagnostic system based on the Internet of Things according to claim 1 is characterized in that: In the result generation module, if the operation and inspection scores of all monitoring devices in any category cluster are less than the preset risk threshold, all monitoring devices are sorted according to the size of the corresponding operation and inspection scores. The larger the operation and inspection score, the higher the ranking. The first X in the sorting are selected as the monitoring devices that need to be inspected in the next operation and inspection cycle, and X is a preset number value.

7. The campus security equipment diagnostic system based on the Internet of Things according to claim 6 is characterized in that: If there are two or more monitoring devices with the same operation and inspection scores, they will be sorted according to the operating time of the monitoring devices during the inspection cycle. The shorter the operating time, the higher the ranking.

8. The campus security equipment diagnostic system based on the Internet of Things according to claim 1 is characterized in that: When a certain monitoring device is replaced during the inspection cycle, it will not participate in the subsequent steps and will be used as the target monitoring device that needs to be inspected during the next inspection cycle.

Images