Cloud-edge collaborative intelligent operation and maintenance system, method and device and storage medium

Abstract

The invention relates to the technical field of intelligent operation and maintenance, in particular to a cloud-edge collaborative intelligent operation and maintenance system, method and equipment and a storage medium. According to the cloud-edge collaborative intelligent operation and maintenance system, an edge layer collects operation data in real time and preprocesses the operation data; the edge intelligent operation and maintenance management layer is responsible for monitoring the operation state of equipment, predicting a fault and planning a maintenance task in advance; and the cloud collaboration layer is responsible for training the deep learning model, formulating a global operation and maintenance strategy and a resource configuration scheme, intelligently generating an optimal operation and maintenance scheduling scheme, storing and updating an operation and maintenance knowledge base, and synchronizing the operation and maintenance scheduling scheme to the edge end in real time. According to the cloud-side collaborative intelligent operation and maintenance system, method and equipment and the storage medium, optimal utilization of resources and maximization of operation and maintenance efficiency are realized, the operation and maintenance efficiency, the system reliability and the intelligent level are effectively improved, the operation and maintenance cost is reduced, continuous and stable operation of services is guaranteed, and the cloud-side collaborative intelligent operation and maintenance system and method have wide application prospects and remarkable benefits.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent operation and maintenance, and particularly relates to a cloud-edge collaborative intelligent operation and maintenance system, method, device, and storage medium. Background Art

[0002] With the development of the Internet of Everything, the number of devices and the amount of data have shown an explosive growth. Traditional centralized operation and maintenance face many challenges, such as high data transmission latency, large bandwidth occupancy, and concentrated failure risks of central nodes. The emergence of edge computing has brought new opportunities for the transformation of the operation and maintenance mode. It sinks the computing power to the edge side, realizing local processing and rapid response of data.

[0003] However, there are still deficiencies in current edge intelligent operation and maintenance technologies, lacking an efficient cloud-edge collaborative mechanism, resulting in the edge side and the cloud acting independently, unable to fully utilize the advantages of both, and unable to achieve the optimal utilization of resources and the maximization of operation and maintenance efficiency.

[0004] In order to achieve the complementary advantages of the edge side and the cloud, improve the operation and maintenance efficiency and quality, the present invention proposes a cloud-edge collaborative intelligent operation and maintenance system, method, device, and storage medium. Summary of the Invention

[0005] The present invention aims to make up for the deficiencies of the prior art and provides a simple and efficient cloud-edge collaborative intelligent operation and maintenance system, method, device, and storage medium.

[0006] The present invention is implemented through the following technical solutions: A cloud-edge collaborative intelligent operation and maintenance system includes an edge layer, an edge intelligent operation and maintenance management layer, and a cloud collaborative layer; The edge layer includes a large number of edge devices deployed near the data source, such as edge servers, intelligent sensors, etc. These devices are responsible for real-time collection of the operation data of the devices and systems, and performing preliminary preprocessing, including data cleaning, filtering, and compression operations, to reduce the data transmission burden; The edge intelligent operation and maintenance management layer is the core control unit at the edge side, including a device status monitoring module, a fault prediction module, and an adaptive learning module, responsible for real-time analysis of the data collected by the devices in the edge layer, monitoring the operation status of the devices in the edge layer, predicting the faults of the devices in the edge layer, and planning maintenance tasks in advance according to the prediction results; The device status monitoring module is responsible for using machine learning algorithms and threshold rules to perform real-time analysis of the data collected by the devices in the edge layer, monitoring the operation status of the devices in the edge layer, and promptly discovering abnormal situations; when an anomaly is detected, the device status monitoring module quickly triggers an early warning mechanism and sends the warning information to the cloud and operation and maintenance personnel; The fault prediction module is responsible for accurately predicting possible future faults of the device based on historical data and the device performance degradation model, and planning maintenance tasks in advance to reduce losses caused by sudden faults; The adaptive learning module is responsible for continuously collecting new data and new fault cases during the operation and maintenance process, updating model parameters in real time, and optimizing algorithm performance, so that the system can adapt to changes in the device operation environment and adjustments in business requirements; The cloud collaboration layer includes a deep model training module, a global data analysis and decision-making module, an intelligent scheduling module, and a knowledge sharing and updating module, which are responsible for providing computing resources and massive data storage capabilities, training a custom-selected deep learning model, formulating global operation and maintenance strategies and resource allocation plans, intelligently generating the optimal operation and maintenance scheduling plan, storing and updating the operation and maintenance knowledge base, and synchronizing it to the edge side in real time.

[0007] The deep model training module is responsible for training a deep learning model using massive historical operation and maintenance data and professional domain knowledge; The deep model training module selects a convolutional neural network (CNN) to predict the fault type, and selects a long short-term memory network (LSTM) to predict the difficulty and required time range for estimating fault repair.

[0008] The global data analysis and decision-making module is responsible for analyzing the operation trends of devices and systems from a macro level, mining potential problems and optimization spaces, formulating global operation and maintenance strategies and resource allocation plans, and providing guidance for intelligent decision-making at the edge side; The intelligent scheduling module is responsible for comprehensively considering various factors, including device geographical location, fault urgency, operation and maintenance personnel skills and workload, spare parts inventory, and delivery time, and intelligently generating the optimal operation and maintenance scheduling plan to improve operation and maintenance efficiency; The knowledge sharing and updating module is responsible for establishing an operation and maintenance knowledge base, storing and updating device maintenance manuals, fault solutions, and expert experience information, and synchronizing it to the edge side in real time to enhance the operation and maintenance decision-making ability of the edge side.

[0009] A cloud-edge collaborative intelligent operation and maintenance method includes the following steps: Step S1: After the edge layer device is started, various operation data of the connected device are collected according to a preset sampling frequency. After local preprocessing, the data is packed and sent to the edge intelligent operation and maintenance management layer through a secure encrypted communication protocol; Local preprocessing includes data cleaning, filtering, and compression operations; Step S2: The device status monitoring module of the edge intelligent operation and maintenance management layer receives the data packet, parses out specific monitoring indicators, and uses machine learning algorithms to determine the device status; If it is determined to be in a normal state, continue monitoring; If it is determined to be abnormal, immediately generate a warning message, record key data, including abnormal device information, fault characteristics, and occurrence time, and push the warning message to the terminal device of the operation and maintenance personnel, and at the same time transmit it to the fault prediction module and the cloud collaboration layer; In the step S2, the machine learning algorithms include support vector machines and decision trees.

[0010] Step S3: After receiving the abnormal data, the fault prediction module of the edge intelligent operation and maintenance management layer combines the historical data of the corresponding edge layer device and the fault modes of the same type of devices, uses the deep learning model to predict the development trend and the final fault type of the fault, estimates the difficulty of fault repair and the required time range, and synchronizes it to the cloud collaboration layer for further analysis and verification; In the step S3, a convolutional neural network CNN is used to predict the fault type, and a long short-term memory network LSTM is used to predict the estimated difficulty of fault repair and the required time range.

[0011] Step S4: After receiving the warning message and the fault prediction result from the edge intelligent operation and maintenance management layer, the cloud collaboration layer uses its powerful computing resources to deeply mine and analyze the data, verify the prediction result of the edge intelligent operation and maintenance management layer, and provide optimized fault handling suggestions and decision-making support for the edge side according to the global operation and maintenance strategy and resource status, and send the decision-making suggestions to the intelligent scheduling module; Step S5: The intelligent scheduling module retrieves resource information according to the received fault handling suggestions, including operation and maintenance personnel, spare parts warehouses, and transportation tools, starts the intelligent scheduling algorithm to comprehensively evaluate various factors, including device geographical location, fault urgency, operation and maintenance personnel skills and workload, spare parts inventory, and delivery time, generates a complete scheduling instruction including the list of dispatched operation and maintenance personnel, task assignment details, action route planning, and spare parts allocation list, and issues it to each execution entity (operation and maintenance personnel, logistics distribution system, etc.) to direct on-site operation and maintenance operations; In the step S5, the intelligent scheduling algorithm uses a genetic algorithm and / or an ant colony algorithm.

[0012] Step S6: The operation and maintenance personnel arrive at the fault site according to the scheduling instruction, use the remote assistance functions provided by the edge layer device (such as real-time video transmission, expert online diagnosis interface, etc.), combine their own skills and experience, and the decision-making support information provided by the cloud, to conduct on-site troubleshooting and repair of the device fault; During the repair process, the edge layer device continuously collects data and feeds back the repair progress and device status changes to the edge intelligent operation and maintenance management layer and the cloud collaboration layer, so as to adjust the scheduling plan in time or provide further technical support; Step S7: After the fault repair is completed, the operation and maintenance personnel enter the maintenance results into the edge-layer device and upload them to the edge intelligent operation and maintenance management layer and the cloud collaboration layer through the edge layer; Through the adaptive learning module of the edge intelligent operation and maintenance management layer, a comprehensive review of this operation and maintenance event is carried out, valuable data and experience are customarily extracted and integrated into the model training dataset for updating and optimizing the device status monitoring model, the fault prediction model, and the intelligent scheduling algorithm to improve the overall performance and intelligent level of the system; At the same time, the cloud collaboration layer updates this operation and maintenance data and experience to the operation and maintenance knowledge base to achieve the sharing and inheritance of knowledge and provide richer references for subsequent operation and maintenance work.

[0013] A cloud-edge collaborative intelligent operation and maintenance device, characterized by comprising: One or more processors, one or more memories, and one or more programs, where one or more programs are stored in the one or more memories and are configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0014] A readable storage medium, characterized in that: a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the above-mentioned method is implemented.

[0015] The beneficial effects of the present invention are: The cloud-edge collaborative intelligent operation and maintenance system, method, device, and storage medium achieve the optimal utilization of resources and the maximization of operation and maintenance efficiency, effectively improve the operation and maintenance efficiency, reliability, and intelligent level of equipment and systems in various industries, reduce operation and maintenance costs, ensure the continuous and stable operation of services, and have broad application prospects and remarkable benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Att Figure 1 It is a schematic diagram of the architecture of the cloud-edge collaborative intelligent operation and maintenance system of the present invention.

[0018] Att Figure 2 It is a schematic diagram of the cloud-edge collaborative intelligent operation and maintenance method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] To enable those skilled in the art to better understand the technical solutions in the present invention, the following will, in conjunction with the embodiments of the present invention, clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0020] The cloud-edge collaborative intelligent operation and maintenance system includes an edge layer, an edge intelligent operation and maintenance management layer, and a cloud collaborative layer; The edge layer includes a large number of edge devices deployed near the data source, such as edge servers, intelligent sensors, etc. These devices are responsible for real-time collection of the operation data of the devices and systems, and perform preliminary preprocessing, including data cleaning, filtering, and compression operations, to reduce the data transmission burden; The edge intelligent operation and maintenance management layer is the core control unit at the edge end, including a device status monitoring module, a fault prediction module, and an adaptive learning module, which are responsible for real-time analysis of the data collected by the edge layer devices, monitoring the operation status of the edge layer devices, predicting the faults of the edge layer devices, and planning maintenance tasks in advance according to the prediction results; The device status monitoring module is responsible for using machine learning algorithms and threshold rules to perform real-time analysis on the data collected by the edge layer devices, monitoring the operation status of the edge layer devices, and promptly detecting abnormal situations; when an anomaly is detected, the device status monitoring module quickly triggers an early warning mechanism and sends the warning information to the cloud and operation and maintenance personnel; The fault prediction module is responsible for accurately predicting the possible future faults of the devices based on historical data and device performance degradation models, using deep learning algorithms, and planning maintenance tasks in advance to reduce the losses caused by sudden faults; The adaptive learning module is responsible for continuously collecting new data and new fault cases during the operation and maintenance process, real-time updating model parameters, and optimizing algorithm performance, so that the system can adapt to changes in the device operation environment and adjustments in business requirements; The cloud collaborative layer includes a deep model training module, a global data analysis and decision-making module, an intelligent scheduling module, and a knowledge sharing and updating module, which are responsible for providing computing resources and massive data storage capabilities, training custom-selected deep learning models, formulating global operation and maintenance strategies and resource allocation plans, intelligently generating the optimal operation and maintenance scheduling plan, storing and updating the operation and maintenance knowledge base, and synchronizing it to the edge end in real time.

[0021] The deep model training module is responsible for using massive historical operation and maintenance data and professional domain knowledge for deep learning model training; The deep model training module selects a Convolutional Neural Network (CNN) to predict the fault type, and selects a Long Short-Term Memory Network (LSTM) to predict the difficulty and the required time range for estimating fault repair.

[0022] The global data analysis and decision-making module is responsible for analyzing the operation trends of devices and systems from a macro level, mining potential problems and optimization spaces, formulating global operation and maintenance strategies and resource allocation plans, and providing guidance for intelligent decision-making at the edge. The intelligent scheduling module is responsible for comprehensively considering various factors, including device geographical location, fault urgency, operation and maintenance personnel skills and workload, spare part inventory, and delivery time, and intelligently generating an optimal operation and maintenance scheduling plan to improve operation and maintenance efficiency. The knowledge sharing and update module is responsible for establishing an operation and maintenance knowledge base, storing and updating device maintenance manuals, fault solutions, and expert experience information, and synchronizing them to the edge in real time to enhance the operation and maintenance decision-making ability at the edge.

[0023] This cloud-edge collaborative intelligent operation and maintenance method includes the following steps: Step S1: After the edge layer device is started, it collects various operation data of the connected devices at a preset sampling frequency. After local preprocessing, the data is packed and sent to the edge intelligent operation and maintenance management layer through a secure encrypted communication protocol. Local preprocessing includes data cleaning, filtering, and compression operations. Step S2: The device status monitoring module of the edge intelligent operation and maintenance management layer receives the data packet, parses out the specific monitoring indicators, and uses machine learning algorithms to determine the device status. If it is determined to be in a normal state, continue to monitor. If it is determined to be abnormal, immediately generate a warning message, record key data, including abnormal device information, fault characteristics, and occurrence time, and push the warning message to the operation and maintenance personnel's terminal device, and at the same time transmit it to the fault prediction module and the cloud collaborative layer. In step S2, the machine learning algorithms include Support Vector Machine (SVM) and Decision Tree.

[0024] Step S3: After receiving the abnormal data, the fault prediction module of the edge intelligent operation and maintenance management layer combines the historical data of the corresponding edge layer device and the fault modes of the same type of devices, uses a deep learning model to predict the development trend and the final fault type of the fault, estimates the difficulty and the required time range for fault repair, and synchronizes it to the cloud collaborative layer for further analysis and verification. In step S3, a Convolutional Neural Network (CNN) is used to predict the fault type, and a Long Short-Term Memory Network (LSTM) is used to predict the difficulty and the required time range for estimating fault repair.

[0025] Step S4. After receiving the warning information and fault prediction results from the edge intelligent operation and maintenance management layer, the cloud collaboration layer utilizes its powerful computing resources to deeply mine and analyze the data, verify the prediction results of the edge intelligent operation and maintenance management layer, and provide optimized fault handling suggestions and decision-making support for the edge side according to the global operation and maintenance strategies and resource status, and send the decision-making suggestions to the intelligent scheduling module; Step S5. The intelligent scheduling module retrieves resource information according to the received fault handling suggestions, including operation and maintenance personnel, spare part warehouses, and transportation vehicles, starts the intelligent scheduling algorithm to comprehensively evaluate various factors, including the geographical location of the equipment, the urgency of the fault, the skills and workload of the operation and maintenance personnel, the spare part inventory, and the delivery time, generates a complete scheduling instruction including the list of dispatched operation and maintenance personnel, the details of task allocation, the action route planning, and the spare part allocation list, and issues it to each executing entity (operation and maintenance personnel, logistics distribution system, etc.) to direct on-site operation and maintenance operations; In the said step S5, the intelligent scheduling algorithm adopts a genetic algorithm and / or an ant colony algorithm.

[0026] Step S6. The operation and maintenance personnel arrive at the fault site according to the scheduling instruction, utilize the remote assistance functions provided by the edge layer devices (such as real-time video backhaul, expert online diagnosis interface, etc.), combine their own skills and experience, and the decision-making support information provided by the cloud, to conduct on-site troubleshooting and repair of the equipment fault; During the repair process, the edge layer devices continuously collect data and feedback the repair progress and equipment status changes to the edge intelligent operation and maintenance management layer and the cloud collaboration layer, so as to adjust the scheduling plan in a timely manner or provide further technical support; Step S7. After the fault repair is completed, the operation and maintenance personnel enter the repair result into the edge layer device, and upload it to the edge intelligent operation and maintenance management layer and the cloud collaboration layer through the edge layer; Through the adaptive learning module of the edge intelligent operation and maintenance management layer, a comprehensive review of this operation and maintenance event is carried out, valuable data and experience are customarily extracted and integrated into the model training dataset for updating and optimizing the equipment status monitoring model, the fault prediction model, and the intelligent scheduling algorithm, so as to improve the overall performance and intelligent level of the system; At the same time, the cloud collaboration layer updates this operation and maintenance data and experience to the operation and maintenance knowledge base to realize the sharing and inheritance of knowledge and provide richer references for subsequent operation and maintenance work.

[0027] The computer-readable storage medium storing one or more programs, the one or more programs include instructions, and when the instructions are executed by the intelligent operation and maintenance device with cloud-edge collaboration, the intelligent operation and maintenance device with cloud-edge collaboration executes any one of the above methods.

[0028] The intelligent operation and maintenance device with cloud-edge collaboration includes: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the above methods.

[0029] In summary, the cloud-edge collaborative intelligent operation and maintenance system, method, device, and storage medium give full play to the advantages of low latency, high bandwidth of edge computing, and the powerful computing ability and massive storage of cloud computing through the cloud-edge collaborative mechanism, realize the optimal utilization of resources and the maximization of operation and maintenance efficiency, effectively improve the operation and maintenance efficiency, reliability, and intelligent level of equipment and systems in various industries, reduce the operation and maintenance costs, ensure the continuous and stable operation of the business, and have broad application prospects and remarkable benefits.

[0030] The above-described embodiments are only one of the specific implementation manners of the present invention, and the general changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent operation and maintenance system for cloud-edge collaboration, characterized in that: It includes an edge layer, an edge intelligent operation and maintenance management layer, and a cloud collaborative layer; The edge layer includes edge devices deployed near the data source, which are responsible for real-time collection of the operation data of devices and systems, and performing preliminary preprocessing, including data cleaning, filtering, and compression operations, to reduce the data transmission burden; The edge intelligent operation and maintenance management layer is the core control unit at the edge end, including a device status monitoring module, a fault prediction module, and an adaptive learning module, which are responsible for real-time analysis of the data collected by the edge layer devices, monitoring the operation status of the edge layer devices, predicting the faults of the edge layer devices, and planning maintenance tasks in advance according to the prediction results; The cloud collaborative layer includes a deep model training module, a global data analysis and decision-making module, an intelligent scheduling module, and a knowledge sharing and updating module, which are responsible for providing computing resources and massive data storage capabilities, training custom-selected deep learning models, formulating global operation and maintenance strategies and resource allocation plans, intelligently generating the optimal operation and maintenance scheduling plan, storing and updating the operation and maintenance knowledge base, and synchronizing it to the edge end in real time.

2. The cloud-edge collaborative intelligent operation and maintenance system according to claim 1, wherein: The device status monitoring module is responsible for using machine learning algorithms and threshold rules to perform real-time analysis on the data collected by the edge layer devices, monitoring the operation status of the edge layer devices, and promptly detecting abnormal situations; when an anomaly is detected, the device status monitoring module triggers an early warning mechanism and sends the warning information to the cloud and operation and maintenance personnel; The fault prediction module is responsible for predicting the faults of the devices based on historical data and device performance degradation models, and using deep learning algorithms to plan maintenance tasks in advance to reduce the losses caused by sudden faults; The adaptive learning module is responsible for continuously collecting new data and new fault cases during the operation and maintenance process, real-time updating model parameters, and optimizing algorithm performance, so that the system can adapt to changes in the device operation environment and adjustments in business requirements.

3. The cloud-edge collaborative intelligent operation and maintenance system according to claim 1, characterized in that: The deep model training module is responsible for training deep learning models using massive historical operation and maintenance data and professional domain knowledge; The global data analysis and decision-making module is responsible for analyzing the operation trends of devices and systems from a macro level, mining potential problems and optimization spaces, formulating global operation and maintenance strategies and resource allocation plans, and providing guidance for intelligent decision-making at the edge end; The intelligent scheduling module is responsible for comprehensively considering various factors, including device geographical location, fault urgency, operation and maintenance personnel skills and workload, spare parts inventory, and delivery time, to intelligently generate the optimal operation and maintenance scheduling plan to improve operation and maintenance efficiency; The knowledge sharing and updating module is responsible for establishing an operation and maintenance knowledge base, storing and updating device maintenance manuals, fault solutions, and expert experience information, and synchronizing it to the edge end in real time to enhance the operation and maintenance decision-making ability of the edge end.

4. The cloud-edge collaborative intelligent operation and maintenance system according to claim 3, wherein: The deep model training module selects a convolutional neural network (CNN) to predict the fault type, and selects a long short-term memory network (LSTM) to predict the difficulty and required time range for estimating fault repair.

5. A cloud-edge collaborative intelligent operation and maintenance method, characterized in that: It includes the following steps: After the edge layer device starts, it collects various operation data of the connected devices according to a preset sampling frequency. After local preprocessing, the data is packed and sent to the edge intelligent operation and maintenance management layer through a secure encrypted communication protocol; Local preprocessing includes data cleaning, filtering, and compression operations; Step S2: The device status monitoring module of the edge intelligent operation and maintenance management layer receives the data packet, parses out the specific monitoring indicators, and uses machine learning algorithms to determine the device status; If it is determined to be in a normal state, continue monitoring; If it is determined to be abnormal, immediately generate a warning message, record the key data, including abnormal device information, fault characteristics, and occurrence time, and push the warning message to the terminal device of the operation and maintenance personnel, and at the same time transmit it to the fault prediction module and the cloud collaboration layer; Step S3: After receiving the abnormal data, the fault prediction module of the edge intelligent operation and maintenance management layer combines the historical data of the corresponding edge layer device and the fault modes of the same type of devices, uses a deep learning model to predict the development trend and the final fault type of the fault, estimates the difficulty and the required time range for fault repair, and synchronizes it to the cloud collaboration layer for further analysis and verification; Step S4: After receiving the warning message and the fault prediction result from the edge intelligent operation and maintenance management layer, the cloud collaboration layer uses its powerful computing resources to deeply mine and analyze the data, verify the prediction result of the edge intelligent operation and maintenance management layer, and provide optimized fault handling suggestions and decision-making support for the edge side according to the global operation and maintenance strategy and resource status, and send the decision-making suggestions to the intelligent scheduling module; Step S5: The intelligent scheduling module retrieves the resource information according to the received fault handling suggestions, including operation and maintenance personnel, spare part warehouses, and transportation tools, starts the intelligent scheduling algorithm to comprehensively evaluate various factors, including the device geographical location, fault urgency, operation and maintenance personnel skills and workload, spare part inventory, and delivery time, generates a complete scheduling instruction including the list of dispatched operation and maintenance personnel, task assignment details, action route planning, and spare part allocation list, and issues it to each execution entity to direct on-site operation and maintenance operations; Step S6: The operation and maintenance personnel arrive at the fault site according to the scheduling instruction, use the remote assistance function provided by the edge layer device, combine their own skills and experience, and the decision-making support information provided by the cloud, to conduct on-site troubleshooting and repair of the device fault; During the repair process, the edge layer device continuously collects data and feeds back the repair progress and device status changes to the edge intelligent operation and maintenance management layer and the cloud collaboration layer, so as to adjust the scheduling plan in time or provide further technical support; Step S7: After the fault repair is completed, the operation and maintenance personnel enter the repair result into the edge layer device, and upload it to the edge intelligent operation and maintenance management layer and the cloud collaboration layer through the edge layer; Through the adaptive learning module of the edge intelligent operation and maintenance management layer, conduct a comprehensive review of this operation and maintenance event, customarily extract valuable data and experience, and integrate them into the model training dataset for updating and optimizing the device status monitoring model, fault prediction model, and intelligent scheduling algorithm, so as to improve the overall performance and intelligent level of the system; Meanwhile, the cloud collaboration layer updates the operation and maintenance data and experience to the operation and maintenance knowledge base to achieve the sharing and inheritance of knowledge and provide richer references for subsequent operation and maintenance work.

6. The intelligent operation and maintenance method for cloud-edge collaboration according to claim 5, wherein: In the step S2, the machine learning algorithms include support vector machines and decision trees.

7. The intelligent operation and maintenance method of cloud-edge collaboration according to claim 5, characterized in that: In the step S3, a convolutional neural network (CNN) is used to predict the fault type, and a long short-term memory network (LSTM) is used to predict the difficulty and the required time range for estimating fault repair.

8. The intelligent operation and maintenance method of cloud-edge collaboration according to claim 5, characterized in that: In the step S5, the intelligent scheduling algorithm uses a genetic algorithm and / or an ant colony algorithm.

9. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions that, when executed by the intelligent operation and maintenance device with cloud-edge collaboration, cause the intelligent operation and maintenance device with cloud-edge collaboration to perform any of the methods according to claims 5 to 8.

10. An intelligent operation and maintenance device for cloud-edge collaboration, characterized in that: Comprising: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods according to claims 5 to 8.

Images