Operation and maintenance on-duty management method and device based on machine learning, medium and equipment

Abstract

The invention provides an operation and maintenance on-duty management method and device based on machine learning, a medium and equipment. The method comprises the steps of obtaining multi-dimensional operation and maintenance data in a historical time period; performing time sequence analysis on the operation and maintenance data to obtain a change rule of the operation and maintenance workload along with time; according to the change rule of the operation and maintenance workload along with time, predicting the operation and maintenance workload in a future time period by adopting a machine learning algorithm to obtain a predicted operation and maintenance workload; according to a preset constraint condition and a pre-constructed operation and maintenance personnel information base, determining a solution space meeting the preset constraint condition; according to an intelligent optimization algorithm, screening out an optimal solution meeting the prediction operation and maintenance workload demand from the solution space; and generating a duty table of operation and maintenance work according to the optimal solution. According to the embodiment of the invention, intelligent management of operation and maintenance work is realized.

Description

Technical Field

[0001] The present invention relates to the field of operation and maintenance management technology, and in particular to an operation and maintenance duty management method, device, medium, and equipment based on machine learning. Background Art

[0002] The existing operation and maintenance system often relies on manual 24-hour monitoring and manual handling of various operation and maintenance events, especially at night or on holidays. The traditional operation and maintenance duty management model faces many challenges in dealing with large-scale and highly complex operation and maintenance scheduling scenarios, and there are various problems such as unbalanced resource allocation, difficulty in dealing with emergencies, and neglect of individual differences and needs of operation and maintenance personnel. Moreover, errors in duty management can easily lead to high labor costs, limited response speed, untimely fault detection and handling, low operation and maintenance efficiency, and low customer satisfaction. Therefore, it is urgent to introduce advanced intelligent operation and maintenance technologies to solve these problems and realize intelligent management of operation and maintenance work. Summary of the invention

[0003] In response to at least one of the above technical problems, an embodiment of the present invention provides an operation and maintenance duty management method, device, medium, and equipment based on machine learning.

[0004] According to the first aspect, the operation and maintenance duty management method based on machine learning provided by an embodiment of the present invention includes:

[0005] Obtain multi-dimensional operation and maintenance data within the historical time period;

[0006] Performing time series analysis on the operation and maintenance data to obtain a law of changes in the operation and maintenance workload over time;

[0007] According to the change pattern of the operation and maintenance workload over time, a machine learning algorithm is used to predict the operation and maintenance workload in a future time period to obtain a predicted operation and maintenance workload;

[0008] According to preset constraints and a pre-built operation and maintenance personnel information database, a solution space that satisfies the preset constraints is determined; wherein the preset constraints include at least one of the requirements for daily working hours, the skill requirements for different positions, the control of continuous duty days not exceeding a preset number of days, the personal demands of the operation and maintenance personnel, and the vacation arrangements of the operation and maintenance personnel; the solution space includes multiple optional solutions, each of which includes the duty information of each operation and maintenance personnel, and the operation and maintenance personnel information database includes the relevant information of each operation and maintenance personnel;

[0009] According to the intelligent optimization algorithm, the optimal solution that meets the predicted operation and maintenance workload requirements is selected from the solution space;

[0010] A duty roster for operation and maintenance work is generated based on the optimal solution.

[0011] In one embodiment, the method further comprises:

[0012] Obtain external factors that affect changes in operation and maintenance workload;

[0013] According to the external influencing factors, the predicted operation and maintenance workload is adjusted; wherein the external influencing factors include at least one of the enterprise's business development plan, new product launch plan and marketing activity arrangement;

[0014] Correspondingly, the selecting an optimal solution that meets the predicted operation and maintenance workload demand from the solution space includes: selecting an optimal solution that meets the adjusted predicted operation and maintenance workload demand from the solution space.

[0015] In one embodiment, the step of selecting an optimal solution that meets the predicted operation and maintenance workload requirement from the solution space according to an intelligent optimization algorithm includes:

[0016] According to the genetic algorithm, an optional solution that meets the demand of the predicted operation and maintenance workload and has the highest fitness function value is selected from the solution space, and the optional solution is used as the optimal solution;

[0017] Among them, the fitness function corresponding to the fitness function value comprehensively considers the workload balance, the skill matching between the operation and maintenance personnel and the position, and the fatigue index of the staff; among them, the more consecutive days an operation and maintenance personnel is on duty, the higher the fatigue index of the operation and maintenance personnel.

[0018] In one embodiment, the method further comprises:

[0019] Real-time monitoring of multi-dimensional operation data of equipment;

[0020] Monitor the operation and maintenance status of each operation and maintenance personnel; wherein the operation and maintenance status includes at least one of workload, on-the-job status, and operation and maintenance event processing progress;

[0021] If any of the monitored multi-dimensional operating data exceeds the corresponding threshold, an alarm is generated;

[0022] Push the alarm to the operation and maintenance personnel through at least one channel notification method, and provide an alarm dashboard for the front-line on-duty personnel;

[0023] According to the urgency of the alarm, a reminder to start the emergency plan is issued to the operation and maintenance personnel whose skills match and whose operation and maintenance status meets the requirements, so that the operation and maintenance personnel can deploy resources to solve the problem corresponding to the alarm.

[0024] In one embodiment, the method further comprises:

[0025] Summarize daily alarms;

[0026] Generate a corresponding daily duty report based on the daily summarized alarm data and the daily duty information in the duty table, and display the daily duty report on the user interface;

[0027] The workload of the staff, the rationality of the shift arrangement, and the equipment operation indexes are displayed on the user interface in the form of charts or reports.

[0028] In one embodiment, the alarm includes: at least one of the alarm occurrence time, alarm processing time, alarm object, alarm name, alarm source, alarm description, alarm number and alarm level.

[0029] In one embodiment, the method further comprises:

[0030] When an unforeseen situation occurs, the duty schedule is adjusted according to the unforeseen situation; wherein the unforeseen situation includes at least one of a sudden increase in operation and maintenance workload and leave of absence by operation and maintenance personnel;

[0031] When the duty roster is adjusted, notify the reviewer to review and approve the adjusted duty roster;

[0032] After approval, shift change notification information or substitute shift notification information will be issued.

[0033] According to the second aspect, the operation and maintenance duty management device based on machine learning provided by the embodiment of the present invention includes:

[0034] The first acquisition module is used to acquire multi-dimensional operation and maintenance data within a historical time period;

[0035] A time series analysis module is used to perform time series analysis on the operation and maintenance data to obtain the change pattern of the operation and maintenance workload over time;

[0036] A workload prediction module is used to predict the operation and maintenance workload in a future time period using a machine learning algorithm according to the change pattern of the operation and maintenance workload over time, so as to obtain a predicted operation and maintenance workload;

[0037] A first determination module is used to determine a solution space that meets the preset constraints according to preset constraints and a pre-built operation and maintenance personnel information database; wherein the preset constraints include at least one of the requirements for daily working hours, the skill requirements for different positions, the control of continuous duty days not exceeding a preset number of days, the personal demands of the operation and maintenance personnel, and the vacation arrangements of the operation and maintenance personnel; the solution space includes multiple optional solutions, each of which includes the duty information of each operation and maintenance personnel, and the operation and maintenance personnel information database includes the relevant information of each operation and maintenance personnel;

[0038] A first screening module is used to screen out an optimal solution that meets the predicted operation and maintenance workload requirements from the solution space according to an intelligent optimization algorithm;

[0039] A duty schedule generating module is used to generate a duty schedule for operation and maintenance work according to the optimal solution.

[0040] According to a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute the method provided in the first aspect.

[0041] According to a fourth aspect, an embodiment of the present invention provides a computing device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method provided in the first aspect is implemented.

[0042] The machine learning-based operation and maintenance duty management method, device, medium, and equipment provided in the embodiment of the present invention obtain multidimensional operation and maintenance data in a historical time period, and then perform time series analysis on the operation and maintenance data to obtain the law of change of the operation and maintenance workload over time, and then use a machine learning algorithm to predict the operation and maintenance workload in the future time period to obtain the predicted operation and maintenance workload. Then, according to the preset constraints and the pre-built operation and maintenance personnel information library, the solution space that meets the preset constraints is determined, and then the optimal solution that meets the predicted operation and maintenance workload requirements is screened from the solution space to generate a duty table for operation and maintenance work. The embodiment of the present invention can reduce labor costs, realize efficient, intelligent, and reliable intelligent scheduling, and reduce negligence and misjudgment caused by human factors through deep mining and intelligent analysis of operation and maintenance data, and reasonable allocation and adjustment of resources. Automatically optimize resource allocation according to the predicted operation and maintenance workload to ensure that there are enough operation and maintenance personnel with corresponding skills on duty during critical periods and peak periods, avoid waste of manpower, and improve operation and maintenance response speed and processing efficiency. Taking into account factors such as the work fatigue and personal skills of the operation and maintenance personnel, and formulating more humane and reasonable duty arrangements will help improve job satisfaction and team cohesion. In short, the embodiments of the present invention integrate big data analysis, machine learning technology, and intelligent optimization algorithms to accurately predict the operation and maintenance workload, scientifically and reasonably arrange the shifts of the operation and maintenance on-duty personnel, effectively improve the utilization rate of human resources, reduce labor costs, and reduce the operation and maintenance risks caused by unreasonable scheduling. At the same time, it pays attention to the work intensity and personal wishes of the operation and maintenance personnel to ensure the stable and efficient operation of the operation and maintenance work. The embodiments of the present invention introduce advanced intelligent operation and maintenance technologies to realize the intelligent management of operation and maintenance work. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flowchart of an operation and maintenance duty management method based on machine learning in one embodiment of the present invention;

[0044] Figure 2 This is a structural block diagram of an operation and maintenance duty management device based on machine learning in one embodiment of the present invention. DETAILED DESCRIPTION

[0045] In a first aspect, an embodiment of the present invention provides an operation and maintenance duty management method based on machine learning, see Figure 1 The method comprises the following steps S110 to S160:

[0046] S110, obtaining multi-dimensional operation and maintenance data within a historical period;

[0047] For example, obtain multi-dimensional operation and maintenance data in the past week.

[0048] Among them, multi-dimensional operation and maintenance data includes the historical frequency of equipment failures, the time spent on handling each failure, the difficulty of resolving various types of failures, business peak periods, seasonal patterns, changes in operation and maintenance workload during special holidays or large-scale events, etc.

[0049] S120, performing time series analysis on the operation and maintenance data to obtain a change pattern of the operation and maintenance workload over time;

[0050] That is, the time series analysis method is used to deeply explore the time characteristics of operation and maintenance data and identify the change pattern of operation and maintenance workload over time.

[0051] S130, predicting the operation and maintenance workload in a future time period using a machine learning algorithm according to the change pattern of the operation and maintenance workload over time, to obtain a predicted operation and maintenance workload;

[0052] Among them, machine learning algorithms, for example, the autoregressive integrated moving average model (ARIMA model), the long short-term memory network (LSTM network), etc.

[0053] It can be seen that by inputting the change pattern of the operation and maintenance workload over time into the machine learning algorithm, the predicted operation and maintenance workload is obtained.

[0054] After this series of data analysis and prediction processes, the specific values ​​of the operation and maintenance workload in the future time period can be given in advance, providing a reliable basis for subsequent scheduling, ensuring that the on-duty personnel configuration matches the actual operation and maintenance needs, and effectively improving the operation and maintenance response speed and service quality.

[0055] S140, determining a solution space that satisfies the preset constraints according to the preset constraints and a pre-built operation and maintenance personnel information database;

[0056] Among them, the preset constraints include at least one of the requirements for daily working hours, skill requirements for different positions, controlling the number of consecutive duty days to not exceed the preset number of days, the personal demands of the operation and maintenance personnel, and the vacation arrangements of the operation and maintenance personnel; the solution space includes multiple optional solutions, and each optional solution includes the duty information of each operation and maintenance personnel.

[0057] The operation and maintenance personnel information database includes relevant information of each operation and maintenance personnel. The relevant information includes basic information of the operation and maintenance personnel, classification, position, skills, fatigue model, etc. The classification of operation and maintenance personnel includes first-line engineers, on-duty personnel, second-line engineers who provide technical support, and third-line product development lines. The operation and maintenance personnel information database provides detailed basic data for intelligent scheduling.

[0058] Among them, the shift scheduling plan must comply with the provisions of labor laws and regulations on working hours, so there must be certain requirements for daily working hours.

[0059] S150, selecting an optimal solution that meets the predicted operation and maintenance workload requirement from the solution space according to an intelligent optimization algorithm;

[0060] In one embodiment, the step of selecting an optimal solution that meets the predicted operation and maintenance workload requirement from the solution space according to the intelligent optimization algorithm in S150 may include:

[0061] According to the genetic algorithm, an optional solution that meets the demand of the predicted operation and maintenance workload and has the highest fitness function value is selected from the solution space, and the optional solution is used as the optimal solution;

[0062] Among them, the fitness function corresponding to the fitness function value comprehensively considers the workload balance, the skill matching between the operation and maintenance personnel and the position, and the fatigue index of the staff; among them, the more consecutive days an operation and maintenance personnel is on duty, the higher the fatigue index of the operation and maintenance personnel.

[0063] It can be seen that by searching the solution space that meets the preset constraints, the optional solution that meets the requirements of the predicted operation and maintenance workload and has the highest fitness function value is found as the optimal solution to achieve intelligent scheduling. In the intelligent scheduling scenario, the optional solution is a scheduling plan, and each scheduling plan is regarded as an individual in the population. By iteratively calculating the fitness function, the scheduling plan is continuously screened and improved, gradually approaching the global optimal solution.

[0064] The fitness function comprehensively considers the workload balance, the skill matching between the operation and maintenance personnel and the position, and the fatigue index of the personnel. The fitness function can also introduce weight factors, such as giving higher priority to operation and maintenance personnel with high skill matching, to avoid delays caused by skill mismatch.

[0065] It can be seen that the embodiment of the present invention takes into account multiple factors when scheduling: skill matching of operation and maintenance personnel, fatigue, continuous duty day limit, personal preference, future operation and maintenance workload, emergency level distribution, etc.

[0066] S160: Generate a duty roster for operation and maintenance work according to the optimal solution.

[0067] The duty list includes duty information such as duty date, duty shift, duty mode, duty post, work tasks, log content and work content to be handed over of each operation and maintenance personnel.

[0068] In one embodiment, the method may further include:

[0069] Obtain external factors that affect changes in operation and maintenance workload;

[0070] According to the external influencing factors, the predicted operation and maintenance workload is adjusted; wherein the external influencing factors include at least one of the enterprise's business development plan, new product launch plan and marketing activity arrangement;

[0071] Correspondingly, the selecting an optimal solution that meets the predicted operation and maintenance workload demand from the solution space includes: selecting an optimal solution that meets the adjusted predicted operation and maintenance workload demand from the solution space.

[0072] It can be seen that in the embodiment of the present invention, the predicted operation and maintenance workload is adjusted in combination with external factors such as the enterprise's business development plan, new product launch plan, marketing activity arrangement, etc., to increase the accuracy of the predicted operation and maintenance workload.

[0073] In one embodiment, the method may further include:

[0074] Real-time monitoring of multi-dimensional operation data of equipment;

[0075] Monitor the operation and maintenance status of each operation and maintenance personnel; wherein the operation and maintenance status includes at least one of workload, on-the-job status, and operation and maintenance event processing progress;

[0076] If any of the monitored multi-dimensional operating data exceeds the corresponding threshold, an alarm is generated;

[0077] Push the alarm to the operation and maintenance personnel through at least one channel notification method, and provide an alarm dashboard for the front-line on-duty personnel;

[0078] According to the urgency of the alarm, a reminder to start the emergency plan is issued to the operation and maintenance personnel whose skills match and whose operation and maintenance status meets the requirements, so that the operation and maintenance personnel can deploy resources to solve the problem corresponding to the alarm.

[0079] It can be seen that by accessing various operation and maintenance monitoring tools and systems, multi-dimensional operation data such as operation and maintenance events, equipment status, network traffic, business performance, etc. are collected in real time, and the workload, on-the-job status, progress of event handling, etc. of each operation and maintenance personnel are tracked and recorded, forming a complete panoramic view of the operation and maintenance status. Once the key indicators are monitored to exceed the threshold, an abnormality or an emergency occurs, an alarm is immediately issued, and then the relevant operation and maintenance personnel or managers are notified to take countermeasures through multiple channels such as the work order system, SMS, email, WeChat, and phone. At the same time, according to the urgency of the event and the matching of personnel skills, the emergency plan can be activated and resources can be automatically allocated to ensure that the problem is solved in a timely and effective manner.

[0080] In one embodiment, the method provided by the embodiment of the present invention may further include:

[0081] Summarize daily alarms;

[0082] Generate a corresponding daily duty report based on the daily summarized alarm data and the daily duty information in the duty table, and display the daily duty report on the user interface;

[0083] The workload of the staff, the rationality of the shift arrangement, and the equipment operation indexes are displayed on the user interface in the form of charts or reports.

[0084] It can be seen that the alarms generated every day can be summarized to obtain daily summarized alarm data. Based on the daily summarized alarm data and the daily duty information in the duty table, the duty daily report is formed and displayed on the user interface. On the user interface, users can view the duty table. Administrators can view, modify and approve the duty table. The user interface provides rich visual charts and reports to display key indicators such as the workload of operation and maintenance personnel, the rationality of scheduling, and abnormal situations.

[0085] In actual scenarios, the alarm information generated during the operation and maintenance process is obtained, and an alarm dashboard and alarm event list are generated based on the alarm information. The resource objects in the configuration management database are connected. When an alarm is generated, the alarm information can be automatically sent to the current on-duty personnel, providing an alarm dashboard for the front-line on-duty personnel.

[0086] The alarm may include: at least one of the alarm occurrence time, alarm processing time, alarm object, alarm name, alarm source, alarm description, alarm number and alarm level.

[0087] In one embodiment, the method provided by the embodiment of the present invention may further include:

[0088] When an unforeseen situation occurs, the duty schedule is adjusted according to the unforeseen situation; wherein the unforeseen situation includes at least one of a sudden increase in operation and maintenance workload and leave of absence by operation and maintenance personnel;

[0089] When the duty roster is adjusted, notify the reviewer to review and approve the adjusted duty roster;

[0090] After approval, shift change notification information or substitute shift notification information will be issued.

[0091] For example, when there is a sudden increase in the operation and maintenance workload, temporary leave, illness or other unforeseen personnel changes, the original duty plan will be automatically adjusted to ensure that the operation and maintenance work proceeds smoothly and the service quality will not be reduced due to staff shortage or overload. After the duty schedule is adjusted, an approval request will be sent to the reviewer. Only after the reviewer approves it, a shift change notification or substitute shift notification will be issued to make the adjusted duty schedule effective.

[0092] Among them, the user interface has the interactive function of accepting shift adjustment information or substitute shift information submitted by operation and maintenance personnel.

[0093] For example, when the CPU utilization of the server in the company's operation and maintenance environment increases abnormally, the system will automatically execute the following process: the monitoring tool detects that the CPU utilization exceeds the set threshold; the intelligent analysis engine compares historical data and the current system status to determine whether there may be a system attack or application failure; measures are taken to isolate the attack traffic or restart the faulty application; the operation and maintenance personnel are notified through the duty management interface and SMS, email, WeChat, phone, and work order system, and an alarm dashboard is provided for the front-line duty personnel; the alarm event list and the duty information are summarized to generate and export the duty daily report. After the above steps, the scheduling results can be viewed and approved at a glance.

[0094] An application scenario of an embodiment of the present invention: A large cloud computing company has a complex IT infrastructure, covering many server clusters, databases, network equipment and various business systems. The operation and maintenance needs generated every day are not only frequent but also highly random. It is necessary for this large cloud computing company to deploy an operation and maintenance duty management system based on machine learning.

[0095] It can be seen that the embodiments of the present invention reasonably allocate and adjust resources, reduce labor costs, achieve efficient, intelligent, and reliable intelligent scheduling, and reduce negligence and misjudgment caused by human factors through deep mining and intelligent analysis of operation and maintenance data. Automatically optimize resource allocation according to the predicted operation and maintenance workload to ensure that there are sufficient operation and maintenance personnel with corresponding skills on duty during critical periods and peak hours, avoid waste of manpower, and improve operation and maintenance response speed and processing efficiency. In the face of sudden operation and maintenance events or personnel changes, the scheduling plan can be flexibly adjusted to ensure the continuity and reliability of operation and maintenance work. Considering factors such as work fatigue, vacation needs, and personal skills of operation and maintenance personnel, formulating more humane and reasonable duty arrangements will help improve job satisfaction and team cohesion.

[0096] It can be seen that the embodiments of the present invention, by integrating big data analysis, machine learning technology and optimization algorithms, can accurately predict the operation and maintenance workload, scientifically and reasonably arrange the shifts of operation and maintenance personnel on duty, effectively improve the utilization rate of human resources, reduce labor costs, and reduce the operation and maintenance risks caused by unreasonable scheduling. At the same time, it pays attention to the work intensity and personal wishes of the operation and maintenance personnel to ensure the stable and efficient operation of the operation and maintenance work.

[0097] In a second aspect, an embodiment of the present invention provides an operation and maintenance duty management device based on machine learning, see Figure 2 , the device 100 comprises:

[0098] The first acquisition module 110 is used to acquire multi-dimensional operation and maintenance data within a historical time period;

[0099] A time series analysis module 120 is used to perform time series analysis on the operation and maintenance data to obtain a change pattern of the operation and maintenance workload over time;

[0100] The workload prediction module 130 is used to predict the operation and maintenance workload in a future time period using a machine learning algorithm according to the change pattern of the operation and maintenance workload over time, so as to obtain a predicted operation and maintenance workload;

[0101] The first determination module 140 is used to determine a solution space that meets the preset constraints according to the preset constraints and the pre-built operation and maintenance personnel information database; wherein the preset constraints include at least one of the requirements for daily working hours, the skill requirements for different positions, the number of consecutive duty days not exceeding the preset number of days, the personal demands of the operation and maintenance personnel, and the vacation arrangements of the operation and maintenance personnel; the solution space includes multiple optional solutions, each of which includes the duty information of each operation and maintenance personnel, and the operation and maintenance personnel information database includes the relevant information of each operation and maintenance personnel;

[0102] A first screening module 150 is used to screen out an optimal solution that meets the predicted operation and maintenance workload requirement from the solution space according to an intelligent optimization algorithm;

[0103] The duty schedule generating module 160 is used to generate a duty schedule for operation and maintenance work according to the optimal solution.

[0104] In one embodiment, the device may further include:

[0105] The second acquisition module is used to obtain external factors that affect changes in operation and maintenance workload;

[0106] A first adjustment module is used to adjust the predicted operation and maintenance workload according to the external influencing factors; wherein the external influencing factors include at least one of the enterprise's business development plan, new product launch plan and marketing activity arrangement;

[0107] Correspondingly, the first screening module is specifically used to screen out the optimal solution that meets the adjusted predicted operation and maintenance workload demand from the solution space.

[0108] In one embodiment, the first screening module is specifically used to: according to a genetic algorithm, screen out from the solution space an optional solution that meets the requirements of the predicted operation and maintenance workload and has the highest fitness function value, and use the optional solution as the optimal solution; wherein the fitness function corresponding to the fitness function value comprehensively considers the workload balance, the skill matching between the operation and maintenance personnel and the position, and the fatigue index of the staff; wherein, the more consecutive days an operation and maintenance personnel is on duty, the higher the fatigue index of the operation and maintenance personnel.

[0109] In one embodiment, the device may further include:

[0110] The first monitoring module is used to monitor the multi-dimensional operation data of the equipment in real time;

[0111] The second monitoring module is used to monitor the operation and maintenance status of each operation and maintenance personnel; wherein the operation and maintenance status includes at least one of the workload, the on-the-job status and the operation and maintenance event processing progress;

[0112] An alarm generation module is used to generate an alarm if any data in the monitored multi-dimensional operation data exceeds a corresponding threshold;

[0113] An alarm push module is used to push the alarm to the operation and maintenance personnel through at least one channel notification method, and provide an alarm dashboard for the front-line on-duty personnel;

[0114] The plan initiation module is used to send an emergency plan initiation reminder to the operation and maintenance personnel whose skills match and whose operation and maintenance conditions meet the requirements according to the urgency of the alarm, so that the operation and maintenance personnel can deploy resources to solve the problem corresponding to the alarm.

[0115] In one embodiment, the device may further include:

[0116] Alarm summary module, used to summarize daily alarms;

[0117] A daily report generation module is used to generate a corresponding daily report on duty based on the daily summary of alarm data and the daily duty information in the duty table, and display the daily report on duty on the user interface;

[0118] The first display module is used to display the workload of the staff, the rationality of the shift arrangement, and the equipment operation indexes on the user interface in the form of charts or reports.

[0119] In one embodiment, the alarm includes: at least one of the alarm occurrence time, alarm processing time, alarm object, alarm name, alarm source, alarm description, alarm number and alarm level.

[0120] In one embodiment, the device may further include:

[0121] A duty schedule adjustment module, used to adjust the duty schedule according to unforeseen circumstances when an unforeseen circumstance occurs; wherein the unforeseen circumstance includes at least one of a sudden increase in operation and maintenance workload and an operation and maintenance personnel taking leave;

[0122] An adjustment approval module is used to notify the reviewer to approve the adjusted duty schedule when the duty schedule is adjusted;

[0123] The adjustment notification module is used to issue shift adjustment notification information or substitute shift notification information after approval.

[0124] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the device provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0125] In a third aspect, an embodiment of the present invention provides a computer-readable medium, on which computer instructions are stored. When the computer instructions are executed by a processor, the processor executes the method provided in the first aspect.

[0126] Specifically, a system or device equipped with a storage medium can be provided, on which software program code that implements the functions of any of the above-mentioned embodiments is stored, and a computer (or CPU or MPU) of the system or device can be enabled to read and execute the program code stored in the storage medium.

[0127] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0128] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0129] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0130] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0131] It is understandable that the explanation, specific implementation methods, beneficial effects, examples, etc. of the relevant contents in the computer-readable medium provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0132] In a fourth aspect, an embodiment of the present specification provides a computing device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the method in any embodiment of the specification.

[0133] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the computing device provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0134] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0135] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention can be implemented by hardware, software, widgets, or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0136] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for operation and maintenance duty management based on machine learning, characterized in that: include: Obtain multi-dimensional operation and maintenance data within a historical period; Performing time series analysis on the operation and maintenance data to obtain a law of change of the operation and maintenance workload over time; According to the change pattern of the operation and maintenance workload over time, a machine learning algorithm is used to predict the operation and maintenance workload in a future time period to obtain a predicted operation and maintenance workload; According to preset constraints and a pre-built operation and maintenance personnel information database, a solution space that satisfies the preset constraints is determined; wherein the preset constraints include at least one of the requirements for daily working hours, the skill requirements for different positions, the control of continuous duty days not exceeding a preset number of days, the personal demands of the operation and maintenance personnel, and the vacation arrangements of the operation and maintenance personnel; the solution space includes multiple optional solutions, each of which includes the duty information of each operation and maintenance personnel, and the operation and maintenance personnel information database includes the relevant information of each operation and maintenance personnel; According to the intelligent optimization algorithm, the optimal solution that meets the predicted operation and maintenance workload requirements is selected from the solution space; A duty roster for operation and maintenance work is generated based on the optimal solution.

2. The method according to claim 1, characterized in that Also includes: Obtain external factors that affect changes in operation and maintenance workload; According to the external influencing factors, the predicted operation and maintenance workload is adjusted; wherein the external influencing factors include at least one of the enterprise's business development plan, new product launch plan and marketing activity arrangement; Correspondingly, the selecting an optimal solution that meets the predicted operation and maintenance workload demand from the solution space includes: selecting an optimal solution that meets the adjusted predicted operation and maintenance workload demand from the solution space.

3. The method according to claim 1, characterized in that The step of selecting an optimal solution that meets the predicted operation and maintenance workload requirement from the solution space according to the intelligent optimization algorithm includes: According to the genetic algorithm, an optional solution that meets the demand of the predicted operation and maintenance workload and has the highest fitness function value is selected from the solution space, and the optional solution is used as the optimal solution; Among them, the fitness function corresponding to the fitness function value comprehensively considers the workload balance, the skill matching between the operation and maintenance personnel and the position, and the fatigue index of the staff; among them, the more consecutive days an operation and maintenance personnel is on duty, the higher the fatigue index of the operation and maintenance personnel.

4. The method according to claim 1, characterized in that: Also includes: Real-time monitoring of multi-dimensional operation data of equipment; Monitor the operation and maintenance status of each operation and maintenance personnel; wherein the operation and maintenance status includes at least one of workload, on-the-job status, and operation and maintenance event processing progress; If any of the monitored multi-dimensional operating data exceeds the corresponding threshold, an alarm is generated; Push the alarm to the operation and maintenance personnel through at least one channel notification method, and provide an alarm dashboard for the front-line on-duty personnel; According to the urgency of the alarm, a reminder to start the emergency plan is issued to the operation and maintenance personnel whose skills match and whose operation and maintenance status meets the requirements, so that the operation and maintenance personnel can deploy resources to solve the problem corresponding to the alarm.

5. The method according to claim 4, characterized in that Also includes: Summarize daily alarms; Generate a corresponding daily duty report based on the daily summarized alarm data and the daily duty information in the duty table, and display the daily duty report on the user interface; The workload of the staff, the rationality of the shift arrangement, and the equipment operation indicators are displayed on the user interface in the form of charts or reports.

6. The method according to claim 4, characterized in that The alarm includes: at least one of the alarm occurrence time, alarm processing time, alarm object, alarm name, alarm source, alarm description, alarm number and alarm level.

7. The method according to claim 1, characterized in that Also includes: When an unforeseen situation occurs, the duty schedule is adjusted according to the unforeseen situation; wherein the unforeseen situation includes at least one of a sudden increase in operation and maintenance workload and an operation and maintenance personnel taking leave; When the duty roster is adjusted, notify the reviewer to review and approve the adjusted duty roster; After approval, shift change notification information or substitute shift notification information will be issued.

8. An operation and maintenance duty management device based on machine learning, characterized in that: include: The first acquisition module is used to acquire multi-dimensional operation and maintenance data within a historical time period; A time series analysis module is used to perform time series analysis on the operation and maintenance data to obtain the change pattern of the operation and maintenance workload over time; A workload prediction module is used to predict the operation and maintenance workload in a future time period using a machine learning algorithm according to the change pattern of the operation and maintenance workload over time, so as to obtain a predicted operation and maintenance workload; A first determination module is used to determine a solution space that meets the preset constraints according to preset constraints and a pre-built operation and maintenance personnel information database; wherein the preset constraints include at least one of the requirements for daily working hours, the skill requirements for different positions, the control of continuous duty days not exceeding a preset number of days, the personal demands of the operation and maintenance personnel, and the vacation arrangements of the operation and maintenance personnel; the solution space includes multiple optional solutions, each of which includes the duty information of each operation and maintenance personnel, and the operation and maintenance personnel information database includes the relevant information of each operation and maintenance personnel; A first screening module is used to screen out an optimal solution that meets the predicted operation and maintenance workload requirements from the solution space according to an intelligent optimization algorithm; A duty schedule generating module is used to generate a duty schedule for operation and maintenance work according to the optimal solution.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

10. A computing device, characterized in that: The method comprises a memory and a processor, wherein the memory stores executable codes, and when the processor executes the executable codes, the method according to any one of claims 1 to 7 is implemented.

Images