Inspection service management system based on artificial intelligence and Internet of Things

By using an inspection service management system based on artificial intelligence and the Internet of Things, the inspection path is dynamically optimized, which solves the problem of fixed inspection paths in existing technologies and enables timely marking of abnormal equipment and rationalized inspection services.

CN118333257BActive Publication Date: 2024-11-22GUANGDONG YIMAOTONG INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410749012.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-12
Publication Date
2024-11-22
Estimated Expiration
2044-06-12

AI Technical Summary

Technical Problem

The inspection paths of existing intelligent inspection equipment are fixed, making it difficult to dynamically optimize them during the inspection process, resulting in low rationality of the inspection process.

Method used

An inspection service management system based on artificial intelligence and the Internet of Things is adopted, including an inspection service module, an inspection anomaly module, and a route customization module. The system dynamically optimizes the inspection route by intelligently analyzing the equipment status and correlation.

Benefits of technology

It enables timely marking of abnormal equipment during inspection and dynamic optimization of the inspection path, ensuring the rationality and effectiveness of equipment inspection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118333257B_ABST
    Figure CN118333257B_ABST
Patent Text Reader

Abstract

The present invention discloses an inspection service management system based on artificial intelligence and the Internet of Things, and relates to the technical field of inspection services. The system discloses an inspection service module, an inspection exception module, and a path customization module. The inspection service module and the inspection exception module are set to control the inspection equipment to perform inspection services on the equipment to be served, and intelligently analyze the status of the equipment to be served through periodic detection, timely mark the inspection exception equipment, set the path customization module, intelligently analyze the relationship between the inspection exception equipment and other equipment to be served, and re-customize the inspection service path of the inspection equipment through correlation analysis, dynamically optimize the inspection service path, and ensure the rational inspection service of the equipment to be served.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of patrol inspection service technology, and more specifically, to a patrol inspection service management system based on artificial intelligence and the Internet of Things. Background Art

[0002] Inspection services are indispensable in all walks of life. For example, manufacturing companies need to regularly inspect production line equipment, and in power systems, power equipment needs to be regularly inspected. Currently, inspection services can be completed through intelligent inspection equipment. Intelligent inspection equipment provides inspection services through predetermined inspection routes. After the inspection service is completed, it can intelligently analyze the problems in the inspection process. However, the inspection paths of intelligent inspection equipment are currently fixed, and it is difficult to dynamically optimize the inspection paths according to inspection problems during the inspection process, resulting in low rationality in the inspection process. Summary of the invention

[0003] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an inspection service management system based on artificial intelligence and the Internet of Things.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] Inspection service management system based on artificial intelligence and the Internet of Things, including inspection service module, inspection exception module, and path customization module;

[0006] The inspection service module controls the inspection device to perform inspection services on the device to be served according to the inspection service route. When the inspection device moves to the location of the device to be served, the inspection device performs inspection services on the device to be served.

[0007] The inspection abnormality module is used to mark the inspection abnormality equipment according to the detection service result;

[0008] The path customization module marks the device to be served associated with the patrol abnormal device as a priority service device, and then obtains the patrol association value between the patrol abnormal device and the priority service device, and customizes a new patrol service route for the patrol device.

[0009] Furthermore, the inspection equipment performs inspection services on the equipment to be served. Specifically, based on H periodic intervals, service inspection data of the equipment to be served is obtained at each periodic node, and the service inspection data of M periodic nodes of the equipment to be served are obtained in total, and then M service inspection logs are generated. The service inspection logs include service inspection time and equipment status.

[0010] Furthermore, the device status of the service detection log is obtained in the following manner: the service detection data is used as the input data of the service detection data model to obtain the service detection value of the device to be served, and the service detection threshold high value and the service detection threshold low value are set; when the service detection value of the device to be served is greater than the service detection threshold high value, the status of the device to be served is marked as a normal status; when the service detection value of the device to be served is less than the service detection threshold low value, the status of the device to be served is marked as an abnormal status; when the service detection value of the device to be served is between the service detection threshold high value and the service detection threshold low value, the status of the device to be served is marked as an edge status.

[0011] Furthermore, the service detection data model is obtained in the following manner: collect multiple service detection data, assign different labels to different service detection data, the labels are service detection values, divide the service detection data into a training set and a validation set, and obtain the service detection data model through iterative training of a neural network. The numerical range of the service detection value is (0~3). The larger the numerical value of the service detection value, the more normal the device status of the device to be served, and the smaller the numerical value of the service detection value, the more abnormal the device status of the device to be served.

[0012] Furthermore, the inspection abnormal devices are marked according to the detection service results, specifically: the inspection value of the device to be served is obtained, and the inspection threshold is set. When the inspection value of the device to be served is greater than or equal to the inspection threshold, the inspection device is controlled to perform inspection services on subsequent devices to be served according to the inspection service route; when the inspection value of the device to be served is less than the inspection threshold, the device to be served is marked as an inspection abnormal device, and an inspection abnormality log is generated. The inspection abnormality log includes the abnormal marking time and the inspection value.

[0013] Furthermore, the inspection value of the device to be served is obtained in the following manner: sort the M service detection logs of the device to be served in the order of service detection time, compare the device states of the two adjacent service detection logs after sorting, when the device states are the same, no corresponding processing is performed, when the device states are different, the state fluctuation times of the device to be served are increased by one, the state fluctuation times of the device to be served are summed up to obtain the total state fluctuation times, and marked as SZC, the service detection values ​​of the device to be served are summed up to obtain the total service detection value, and marked as GSD, when the device state of the service detection log is normal, mark the service detection log as a normal detection log, sort all normal detection logs in the order of service detection time, calculate the time difference between the service detection times of the two adjacent normal detection logs after sorting, obtain the normal detection interval, sum all normal detection intervals and take the average, obtain the average normal detection interval, and mark it as PYB, and use the formula The inspection value TYZ of the equipment to be serviced is obtained, where a1 is the total number of state fluctuation coefficients, a2 is the total value coefficient of service detection, and a3 is the average normal interval coefficient of detection.

[0014] Furthermore, the devices to be served that are associated with the patrol abnormality devices are marked as priority service devices. Specifically, the relationship between the patrol abnormality devices and other devices to be served is obtained, and through knowledge graph association analysis, the devices to be served that are associated with the patrol abnormality devices are marked as priority service devices.

[0015] Furthermore, the inspection correlation value of the inspection abnormal device and the priority service device is obtained by the following method: the historical inspection abnormal value and the historical service detection value of the inspection abnormal device are obtained and marked as , A1 is the historical inspection abnormality value of the inspection abnormal device, A2 is the historical service detection value of the inspection abnormal device, obtain the historical inspection abnormality value and historical service detection value of the priority service device, and mark them as , B1 is the historical inspection abnormality value of the priority service device, B2 is the historical service detection value of the priority service device, and the inspection correlation value between the inspection abnormality device and the priority service device is obtained using the cosine similarity calculation formula.

[0016] Furthermore, a new inspection service route is customized for the inspection equipment, specifically: setting inspection association thresholds;

[0017] When the inspection correlation value is greater than or equal to the inspection correlation threshold, the priority service device is marked as a queue-jumping inspection device, and the distance difference between the position of the queue-jumping inspection device and the position of the inspection abnormal device is calculated to obtain the inspection distance difference and marked as HFG. The inspection correlation value of the queue-jumping inspection device is marked as MKL. Using the formula Get the queue-jumping inspection value CVZ of the queue-jumping inspection device, where the value of d1 is 5, sort all the queue-jumping inspection devices in descending order according to the queue-jumping inspection value, and customize new inspection service routes for the inspection devices in the sorted order;

[0018] When the inspection association value is less than the inspection association threshold, the priority service device is marked back as a waiting-for-service device.

[0019] Furthermore, the historical inspection anomaly value is obtained by the following method: obtain all inspection anomaly logs of the equipment to be served before the current time of the system, sort all inspection anomaly logs in the order of the anomaly marking time, calculate the time difference between the two adjacent anomaly marking times after sorting, obtain the anomaly marking interval, sum up all the anomaly marking intervals and take the average value to obtain the average anomaly marking interval, and mark it as FER, obtain the total number of inspection anomaly logs and mark it as ZPK, sum up the inspection values ​​of all inspection anomaly logs and take the average value to obtain the average anomaly inspection value, and mark it as HJT, and use the formula Get the historical inspection abnormality value CED of the device to be serviced, where b1 is the average abnormality mark interval coefficient, b2 is the inspection abnormality log quantity coefficient, and b3 is the average abnormal inspection value coefficient;

[0020] The historical service detection value is obtained by the following method: obtain all service detection logs of the device to be serviced before the current system time, obtain the total number of service detection logs with the device status in normal state, and mark it as SEY, sum up all inspection values ​​of the device to be serviced before the current system time and take the average value to obtain the average inspection value, and mark it as WZM, and use the formula The historical service detection value GPB of the device to be serviced is obtained, where c1 is the normal state log quantity coefficient and c2 is the average inspection value coefficient.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] Set up inspection service module and inspection exception module, control the inspection equipment to provide inspection services to the equipment to be served, and intelligently analyze the status of the equipment to be served through periodic detection, mark the inspection exception equipment in time, set up path customization module, intelligently analyze the relationship between the inspection exception equipment and other equipment to be served, and re-customize the inspection service path of the inspection equipment through correlation analysis, dynamically optimize the inspection service path, and ensure the rational inspection service of the equipment to be served. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A flowchart for customizing a new inspection service route. DETAILED DESCRIPTION

[0024] Reference Figure 1 , an inspection service management system based on artificial intelligence and the Internet of Things, including inspection service module, inspection exception module, and path customization module.

[0025] The inspection service module: the inspection device performs inspection services on the equipment to be served according to the inspection service route. When the inspection device moves to the position of the equipment to be served, the inspection device performs detection services on the equipment to be served. Based on H periodic intervals, the service detection data of the equipment to be served is obtained at each periodic node, and the service detection data of M periodic nodes of the equipment to be served are obtained in total, and then M service detection logs are generated. The service detection logs include the service detection time (i.e., the Beijing time for obtaining the service detection data), and the equipment status (i.e., one of the normal status, abnormal status, and edge status). The service detection data is used as the input data of the service detection data model to obtain the service detection value of the equipment to be served.

[0026] Example: Inspection service for power system. There are multiple power equipment in the power system. The equipment to be serviced is the power equipment. Each power equipment is set at a different location. The inspection route can be customized according to the distance and position relationship between the power equipment. The inspection is completed by the inspection equipment. The inspection equipment moves along the inspection route to the location of the power equipment and obtains the voiceprint data of the power equipment. The voiceprint data of the power equipment is used as the input data of the service detection data model to obtain the service detection value of the power equipment.

[0027] The service detection data model is obtained by the following method: collecting multiple service detection data, which can be actual service detection data or service detection data simulated by computer, assigning different labels to different service detection data, the labels are service detection values, dividing the service detection data into training sets and validation sets, and obtaining the service detection data model through iterative training of neural networks. The value range of the service detection value is (0~3), the larger the value of the service detection value, the more normal the device status of the device to be served, and the smaller the value of the service detection value, the more abnormal the device status of the device to be served.

[0028] Set the service detection threshold high value and service detection threshold low value, where the service detection threshold high value is greater than the service detection threshold low value. The service detection threshold high value and the service detection threshold low value are both system preset thresholds and can be modified according to actual needs.

[0029] When the service detection value of the device to be served is greater than the service detection high threshold value, the state of the device to be served is marked as a normal state.

[0030] When the service detection value of the device to be served is less than the service detection threshold lower value, the state of the device to be served is marked as an abnormal state.

[0031] When the service detection value of the device to be served is between the service detection threshold upper value and the service detection threshold lower value, the state of the device to be served is marked as an edge state.

[0032] The inspection anomaly module: sorts the M service detection logs of the device to be served in the order of service detection time, compares the device states of the two adjacent service detection logs after sorting, and when the device states are the same, does not perform corresponding processing. When the device states are different, increases the number of state fluctuations of the device to be served by one, sums the number of state fluctuations of the device to be served, obtains the total number of state fluctuations, and marks it as SZC, sums the service detection values ​​of the device to be served, obtains the total service detection value, and marks it as GSD. When the device state of the service detection log is normal, marks the service detection log as a normal detection log, sorts all normal detection logs in the order of service detection time, calculates the time difference between the service detection times of the two adjacent normal detection logs after sorting, obtains the normal detection interval, sums all normal detection intervals and takes the average, obtains the average normal detection interval, and marks it as PYB. Use the formula The inspection value TYZ of the equipment to be serviced is obtained, where a1 is the total number of state fluctuation coefficients, a2 is the total service detection coefficient, and a3 is the average normal detection interval coefficient. The value of a1 is 4.56, the value of a2 is 0.62, and the value of a3 is 1.81.

[0033] Set the inspection threshold. The inspection threshold is a system preset threshold and can be modified according to actual needs.

[0034] When the inspection value of the device to be served is greater than or equal to the inspection threshold, the inspection device is controlled to perform inspection services on subsequent devices to be served according to the inspection service route.

[0035] When the inspection value of the device to be serviced is less than the inspection threshold, the device to be serviced is marked as an inspection abnormal device, and an inspection abnormality log is generated. The inspection abnormality log includes the abnormal marking time (i.e., the Beijing time when the device to be serviced is marked as an inspection abnormal device) and the inspection value.

[0036] Set up inspection service module and inspection exception module, control the inspection equipment to provide inspection service to the equipment to be served, and conduct intelligent analysis on the status of the equipment to be served through periodic detection, and mark the inspection exception equipment in time.

[0037] The path customization module obtains the relationship between the patrol abnormal device and other devices to be served, and through knowledge graph association analysis, marks the devices to be served associated with the patrol abnormal device as priority service devices.

[0038] The devices to be serviced are represented in the form of a knowledge graph. For example, the relationships in the knowledge graph represent the associations between the devices to be serviced, such as supply-demand relationships, affiliation, etc., to ensure that the knowledge graph can accurately reflect the relationships between the devices to be serviced.

[0039] Obtain the historical inspection abnormality values ​​and historical service detection values ​​of the inspection abnormality devices and mark them as , A1 is the historical inspection abnormality value of the inspection abnormal device, A2 is the historical service detection value of the inspection abnormal device, obtain the historical inspection abnormality value and historical service detection value of the priority service device, and mark them as , B1 is the historical inspection abnormality value of the priority service device, B2 is the historical service detection value of the priority service device, and the inspection correlation value of the inspection abnormal device and the priority service device is obtained. The calculation formula of cosine similarity is: .

[0040] Set the inspection association threshold. The inspection association threshold is a system preset threshold and can be modified according to actual needs.

[0041] When the inspection correlation value is greater than or equal to the inspection correlation threshold, the priority service device is marked as a queue-jumping inspection device, and the distance difference between the position of the queue-jumping inspection device and the position of the inspection abnormal device is calculated to obtain the inspection distance difference and marked as HFG. The inspection correlation value of the queue-jumping inspection device is marked as MKL. Using the formula The queue-jumping inspection value CVZ of the queue-jumping inspection device is obtained, where the value of d1 is 5, and all queue-jumping inspection devices are sorted in descending order according to the queue-jumping inspection value, and new inspection service routes are customized for the inspection devices according to the sorting order.

[0042] When the inspection association value is less than the inspection association threshold, the priority service device is marked back as a waiting-for-service device.

[0043] The inspection correlation values ​​of the inspection abnormal devices and the priority service devices are obtained using the cosine similarity algorithm.

[0044] For example, if the historical inspection abnormality value of the inspection abnormal device is 8.8, the historical service detection value of the inspection abnormal device is 4.5, the historical inspection abnormality value of the priority service device is 8.6, and the historical service detection value of the priority service device is 4.1, then the inspection correlation value of the inspection abnormal device and the priority service device is .

[0045] The historical inspection anomaly value is obtained in the following way: obtain all inspection anomaly logs of the device to be served before the current time of the system, sort all inspection anomaly logs in the order of the anomaly marking time, calculate the time difference between the two adjacent anomaly marking times after sorting, obtain the anomaly marking interval, sum up all the anomaly marking intervals and take the average value to obtain the average anomaly marking interval, and mark it as FER, obtain the total number of inspection anomaly logs and mark it as ZPK, sum up the inspection values ​​of all inspection anomaly logs and take the average value to obtain the average anomaly inspection value, and mark it as HJT, and use the formula The historical inspection abnormality value CED of the device to be serviced is obtained, where b1 is the average abnormal mark interval coefficient, b2 is the inspection abnormality log quantity coefficient, and b3 is the average abnormal inspection value coefficient. The value of b1 is 1.38, the value of b2 is 0.62, and the value of b3 is 0.18.

[0046] The historical service detection value is obtained by the following method: obtain all service detection logs of the device to be serviced before the current system time, obtain the total number of service detection logs with the device status in normal state, and mark it as SEY, sum up all inspection values ​​of the device to be serviced before the current system time and take the average value to obtain the average inspection value, and mark it as WZM, and use the formula The historical service detection value GPB of the device to be serviced is obtained, where c1 is the normal state log quantity coefficient, c2 is the average inspection value coefficient, the value of c1 is 3.61, and the value of c2 is 0.82.

[0047] Set up a path customization module to intelligently analyze the relationship between inspection-abnormal equipment and other equipment to be serviced, and re-customize the inspection service path of the inspection equipment through correlation analysis, dynamically optimize the inspection service path, and ensure reasonable inspection services for the equipment to be serviced.

[0048] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0049] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0050] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0051] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0052] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0053] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0054] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0055] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Inspection service management system based on artificial intelligence and Internet of Things, characterized by: Including inspection service module, inspection exception module and path customization module; The inspection service module controls the inspection device to perform inspection services on the device to be served according to the inspection service route. When the inspection device moves to the location of the device to be served, the inspection device performs inspection services on the device to be served. The inspection abnormality module is used to mark the inspection abnormality equipment according to the detection service result; The path customization module marks the to-be-serviced device associated with the inspection abnormal device as a priority service device, and then obtains the inspection association value between the inspection abnormal device and the priority service device, and customizes a new inspection service route for the inspection device; Mark the inspection abnormal devices according to the detection service results, specifically: obtain the inspection value of the device to be served, set the inspection threshold, when the inspection value of the device to be served is greater than or equal to the inspection threshold, control the inspection device to perform inspection services on the subsequent devices to be served according to the inspection service route, when the inspection value of the device to be served is less than the inspection threshold, mark the device to be served as an inspection abnormal device, generate an inspection abnormal log, and the inspection abnormal log includes the abnormal marking time and the inspection value; The inspection value of the device to be served is obtained in the following way: sort the M service detection logs of the device to be served in the order of service detection time, compare the device states of the two adjacent service detection logs after sorting, when the device states are the same, no corresponding processing is performed, when the device states are different, the state fluctuation times of the device to be served are increased by one, the state fluctuation times of the device to be served are summed up to obtain the total state fluctuation times, and marked as SZC, the service detection values ​​of the device to be served are summed up to obtain the total service detection value, and marked as GSD, when the device state of the service detection log is normal, mark the service detection log as a normal detection log, sort all normal detection logs in the order of service detection time, calculate the time difference between the service detection times of the two adjacent normal detection logs after sorting, obtain the normal detection interval, sum all normal detection intervals and take the average, obtain the average normal detection interval, and mark it as PYB, use the formula Get the inspection value TYZ of the equipment to be serviced, where a1 is the total number of state fluctuation coefficients, a2 is the total value coefficient of service detection, and a3 is the average normal interval coefficient of detection; Customize new inspection service routes for inspection equipment, specifically: set inspection association thresholds; When the inspection correlation value is greater than or equal to the inspection correlation threshold, the priority service device is marked as a queue-jumping inspection device, and the distance difference between the position of the queue-jumping inspection device and the position of the inspection abnormal device is calculated to obtain the inspection distance difference and marked as HFG. The inspection correlation value of the queue-jumping inspection device is marked as MKL. Using the formula Get the queue-jumping inspection value CVZ of the queue-jumping inspection device, where the value of d1 is 5, sort all the queue-jumping inspection devices in descending order according to the queue-jumping inspection value, and customize new inspection service routes for the inspection devices in the sorted order; When the inspection association value is less than the inspection association threshold, the priority service device is marked back as a waiting-for-service device.

2. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 1 is characterized in that: The inspection equipment performs inspection services on the equipment to be served. Specifically, based on H periodic intervals, at each periodic node, the service inspection data of the equipment to be served is obtained, and the service inspection data of M periodic nodes of the equipment to be served is obtained in total, and then M service inspection logs are generated. The service inspection logs include service inspection time and equipment status.

3. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 2 is characterized in that: The device status of the service detection log is obtained in the following way: the service detection data is used as the input data of the service detection data model to obtain the service detection value of the device to be served, and the service detection threshold high value and the service detection threshold low value are set. When the service detection value of the device to be served is greater than the service detection threshold high value, the status of the device to be served is marked as normal status. When the service detection value of the device to be served is less than the service detection threshold low value, the status of the device to be served is marked as abnormal status. When the service detection value of the device to be served is between the service detection threshold high value and the service detection threshold low value, the status of the device to be served is marked as marginal status.

4. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 3 is characterized in that: The service detection data model is obtained in the following way: collect multiple service detection data, assign different labels to different service detection data, the label is the service detection value, divide the service detection data into a training set and a validation set, and obtain the service detection data model through iterative training of a neural network. The numerical range of the service detection value is (0~3). The larger the numerical value of the service detection value, the more normal the device status of the device to be served is, and the smaller the numerical value of the service detection value, the more abnormal the device status of the device to be served is.

5. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 1 is characterized in that: The devices to be served that are associated with the patrol abnormality devices are marked as priority service devices. Specifically, the relationship between the patrol abnormality devices and other devices to be served is obtained, and through knowledge graph association analysis, the devices to be served that are associated with the patrol abnormality devices are marked as priority service devices.

6. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 1 is characterized in that: The inspection correlation value of the inspection abnormal device and the priority service device is obtained by the following method: obtain the historical inspection abnormal value and historical service detection value of the inspection abnormal device and mark them as , A1 is the historical inspection abnormality value of the inspection abnormal device, A2 is the historical service detection value of the inspection abnormal device, obtain the historical inspection abnormality value and historical service detection value of the priority service device, and mark them as , B1 is the historical inspection abnormality value of the priority service device, B2 is the historical service detection value of the priority service device, and the inspection correlation value between the inspection abnormality device and the priority service device is obtained using the cosine similarity calculation formula.

7. The inspection service management system based on artificial intelligence and the Internet of Things according to claim 6 is characterized in that: The historical inspection anomaly value is obtained in the following way: obtain all inspection anomaly logs of the device to be served before the current time of the system, sort all inspection anomaly logs in the order of the anomaly marking time, calculate the time difference between the two adjacent anomaly marking times after sorting, obtain the anomaly marking interval, sum up all the anomaly marking intervals and take the average value to obtain the average anomaly marking interval, and mark it as FER, obtain the total number of inspection anomaly logs and mark it as ZPK, sum up the inspection values ​​of all inspection anomaly logs and take the average value to obtain the average anomaly inspection value, and mark it as HJT, and use the formula Get the historical inspection abnormality value CED of the device to be serviced, where b1 is the average abnormality mark interval coefficient, b2 is the inspection abnormality log quantity coefficient, and b3 is the average abnormal inspection value coefficient; The historical service detection value is obtained by the following method: obtain all service detection logs of the device to be serviced before the current system time, obtain the total number of service detection logs with the device status in normal state, and mark it as SEY, sum up all inspection values ​​of the device to be serviced before the current system time and take the average value to obtain the average inspection value, and mark it as WZM, and use the formula The historical service detection value GPB of the device to be serviced is obtained, where c1 is the normal state log quantity coefficient and c2 is the average inspection value coefficient.