Maintenance support guarantee management method and system

Abstract

The invention discloses a maintenance support guarantee management method and system, and the method comprises the steps: receiving a maintenance task order, and obtaining the maintenance task position information and maintenance task level information of the maintenance task order; obtaining a plurality of maintenance branch centers which meet the maintenance task level requirement and have current workload load values lower than a preset workload threshold value in a preset maintenance task position range as candidate maintenance branch centers; when the idle maintenance personnel of at least one candidate maintenance branch center meet the personnel demand of the maintenance task level, selecting one maintenance personnel which is allocated to the candidate maintenance branch center to complete the maintenance task order; when the number of the idle maintenance personnel of each candidate maintenance branch center is smaller than the number of the personnel requirements of the maintenance task level, the maintenance personnel of the multiple candidate maintenance branch centers are allocated to jointly complete the maintenance task order, and the allocated maintenance personnel of the multiple candidate maintenance branch centers meet the personnel requirements of the maintenance task level.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment maintenance support, and particularly relates to a maintenance support management method and system. Background Art

[0002] At present, as equipment becomes increasingly complex and service response requirements continue to increase, traditional maintenance resource allocation methods are difficult to meet the needs of high efficiency and accuracy. Most of the previous allocation methods relied on manual experience or simple rules, such as "nearest allocation", without dynamically combining data from multiple aspects such as the load of sub-centers and personnel skills. Take a certain maintenance node as an example. Although it is very close to the task location, it may already be operating at full capacity. At this time, forcibly assigning tasks is likely to cause task delays or a decline in service quality. On the contrary, some sub-centers that are farther away but have a lower load may have their resources idle because they are not called.

[0003] The existing management systems also lack in-depth correlation analysis between task levels and personnel skills. For example, high-level tasks may be assigned to personnel with low skill levels, or due to the mismatch of the personnel skill structure at the maintenance node, the tasks cannot be completed efficiently. Moreover, these systems generally lack a quantitative load assessment model and it is difficult to balance the workloads of each maintenance node. Some maintenance nodes are in a state of high-load operation for a long time, while the resource utilization rate of other maintenance nodes is very low, which results in a weak fault tolerance ability of the entire system.

[0004] In addition, most traditional methods are based on static data such as preset distance thresholds and cannot real-time understand dynamic factors such as traffic conditions and the task progress of sub-centers, thereby resulting in unstable response times. And these methods only rely on a single indicator such as distance or load, without comprehensively quantifying key factors such as time cost, load balance degree, and skill matching degree. For example, for urgent tasks, the response speed may be sacrificed in the pursuit of skill matching, or the workload of the maintenance node may be overloaded due to only considering the distance factor.

[0005] From the typical implementation methods of the prior art, the following situations exist: First, single-indicator scheduling is adopted, and sorting and allocation are only carried out according to distance or load. For example, some systems give priority to selecting the nearest sub-center, but if the skills of this sub-center do not match, secondary coordination is required, thus delaying time. Second, static threshold screening is used, and a sub-center load threshold is preset, such as 80%, without considering the differences in task complexity. For example, high-level tasks actually consume more resources, which makes the threshold ineffective. Third, relying on manual experience intervention, in the scenario of multi-sub-center cooperation, the dispatcher can only rely on subjective judgment to allocate personnel, and it is easy to cause decision-making deviations due to information asymmetry.

[0006] Generally speaking, there are many deficiencies in the existing technologies. It lacks systematic optimization and does not form a closed-loop optimization of "task requirements - resource status - allocation strategy", and often can only achieve local optimality rather than global optimality. At the same time, the data utilization rate is low, and the skills of personnel at sub-centers, historical task data, etc. have not been fully mined and utilized, and cannot provide strong support for intelligent decision-making. In addition, the scalability is poor. When facing large-scale tasks or complex scenarios, such as multi-unit cross-regional cooperation and support, it is very difficult for traditional methods to quickly generate feasible solutions. Summary of the Invention

[0007] The objective of the embodiments of the present invention is to provide a maintenance support and guarantee management method and system. By dynamically screening candidate maintenance and support sub-centers that meet the task level, and combining the dual allocation strategies of distance and load, the efficient allocation of resources and load balancing are achieved; when a single sub-center cannot meet the requirements, an optimal joint allocation plan is generated through multi-dimensional comprehensive evaluation to ensure the coordinated optimization of task response speed and execution quality; effectively solving problems such as resource waste, response delay, and skill mismatch in traditional scheduling, significantly improving the intelligent level and overall efficiency of maintenance services, and providing a systematic solution for multi-objective decision-making in complex scenarios.

[0008] To solve the above technical problems, the first aspect of the embodiments of the present invention provides a maintenance support and guarantee management method, including the following steps:

[0009] Receive a maintenance task order, and obtain the maintenance task location information and maintenance task level information of the maintenance task order;

[0010] Obtain several maintenance and support sub-centers within the preset range of the maintenance task location that meet the requirements of the maintenance task level and whose current workload load value is lower than the preset workload threshold as candidate maintenance and support sub-centers;

[0011] When the idle maintenance personnel of at least one of the candidate maintenance and support sub-centers meet the personnel requirements of the maintenance task level, select one of the candidate maintenance and support sub-centers to allocate its maintenance personnel to complete the maintenance task order;

[0012] When the idle maintenance personnel of each of the candidate maintenance and support sub-centers are less than the personnel requirements of the maintenance task level, allocate the maintenance personnel of multiple candidate maintenance and support sub-centers to jointly complete the maintenance task order, and the allocated maintenance personnel of multiple candidate maintenance and support sub-centers meet the personnel requirements of the maintenance task level.

[0013] Further, the maintenance task levels include: first-level maintenance tasks, second-level maintenance tasks, and third-level maintenance tasks, and the levels of the maintenance personnel include: junior, intermediate, senior, and expert levels;

[0014] The personnel requirements for the first-level maintenance tasks, the second-level maintenance tasks, and the third-level maintenance tasks respectively correspond to the corresponding preset numbers of primary, intermediate, senior, and / or expert-level maintenance personnel.

[0015] Further, the selecting and dispatching the maintenance personnel of the candidate maintenance sub-centers to complete the maintenance task order includes:

[0016] Obtain the current workload load value of the candidate maintenance sub-centers, and select one of the candidate maintenance sub-centers in ascending order of the current workload load value.

[0017] Further, the calculation formula of the current workload load value WL is:

[0018]

[0019] where L is the maintenance task level value, W j is the work efficiency of the j-th maintenance personnel level of the current candidate maintenance sub-center, F j is the idle quantity of the j-th maintenance personnel level, D h is the distance value between the current candidate maintenance sub-center and its h-th maintenance task location, ω1 is the distance attenuation coefficient between the maintenance task location and the candidate maintenance sub-center, and ω2 is the cosine function coefficient.

[0020] Further, the dispatching the maintenance personnel of multiple candidate maintenance sub-centers to jointly complete the maintenance task order includes:

[0021] Respectively obtain the distance values between multiple candidate maintenance sub-centers and the maintenance task implementation location;

[0022] Respectively obtain the idle quantities of the maintenance personnel at all levels of multiple candidate maintenance sub-centers;

[0023] Based on the distance values and the idle quantities of the maintenance personnel at all levels, select several of the multiple candidate maintenance sub-centers to obtain several maintenance personnel transfer plans respectively;

[0024] Obtain the total time cost of personnel deployment, the load balance degree of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel for each maintenance personnel transfer plan;

[0025] Based on the total time cost of personnel deployment, the load balance degree of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel, calculate the comprehensive evaluation value of each maintenance personnel transfer plan, and conduct maintenance personnel transfer according to the maintenance personnel transfer plan corresponding to the optimal result of the comprehensive evaluation value.

[0026] Further, based on the distance value and the idle numbers of maintenance personnel at all levels, several of the multiple candidate maintenance sub - centers are randomly selected to obtain several maintenance personnel deployment plans respectively, including:

[0027] Randomly select several of the multiple candidate maintenance sub - centers;

[0028] Obtain the skill matching degree between each candidate maintenance sub - center and the maintenance task order, and combine the distance value and the idle numbers of maintenance personnel at all levels to construct a distance matrix of the currently randomly selected candidate maintenance sub - centers;

[0029] Cluster the candidate maintenance sub - centers based on the hierarchical clustering algorithm, and divide the randomly selected several candidate maintenance sub - centers into a main node cluster and several sub - node clusters according to the maintenance task order;

[0030] Take the candidate maintenance sub - center closest to the maintenance task in the main node cluster as the main node, and take the candidate maintenance sub - center closest to the main node in each sub - node cluster as the sub - node;

[0031] Determine the maintenance personnel deployment plan based on the candidate maintenance sub - centers corresponding to the main node and several sub - nodes. After multiple random selections, several maintenance personnel deployment plans are obtained respectively.

[0032] Further, based on the total time cost of personnel deployment, the load balance degree of candidate maintenance sub - centers, and the skill matching degree of maintenance personnel, calculate the comprehensive evaluation value of each maintenance personnel deployment plan, including:

[0033] Based on the multi - objective optimization model, construct the objective function of each maintenance personnel deployment plan. The objective function includes: minimizing the total time cost of personnel deployment, maximizing the load balance degree of candidate maintenance sub - centers, and maximizing the skill matching degree of maintenance personnel;

[0034] Based on the objective function of the maintenance personnel deployment plan, calculate the objective function values of the total time cost of personnel deployment, the load balance degree of candidate maintenance sub - centers, and the skill matching degree of maintenance personnel respectively, and perform normalization processing;

[0035] Based on the normalized objective function values of the total time cost of personnel deployment, the load balance degree of candidate maintenance sub - centers, and the skill matching degree of maintenance personnel, calculate the fitness values of several maintenance personnel deployment plans respectively as the comprehensive evaluation value of each plan;

[0036] Select the maintenance personnel deployment plan with the highest comprehensive evaluation value for the deployment of maintenance personnel.

[0037] Further, calculating the fitness values of a plurality of the maintenance personnel transfer plans respectively based on the objective function values of the total time cost of personnel deployment, the load balance degree of the candidate maintenance sub - centers, and the skill matching degree of the maintenance personnel after normalization, includes:

[0038] Constructing an original vector for each of the maintenance personnel transfer plans based on the objective function values of the total time cost of personnel deployment, the load balance degree of the candidate maintenance sub - centers, and the skill matching degree of the maintenance personnel after normalization;

[0039] Inputting the original vector into a pre - trained auto - encoder model to obtain a low - dimensional feature encoding vector;

[0040] Inputting the low - dimensional feature encoding vector into a pre - trained support vector regression model, and obtaining the fitness value of the maintenance personnel transfer plan based on the support vector regression model.

[0041] Further, the calculation formula for the fitness value of the maintenance personnel transfer plan is:

[0042]

[0043] where T′ is the normalized value of the total time cost of personnel deployment, E′ is the normalized value of the load balance degree of the candidate maintenance sub - centers, F′ is the normalized value of the skill matching degree of the maintenance personnel, and α, β, λ are corresponding coefficients.

[0044] Correspondingly, a second aspect of the embodiments of the present invention provides a maintenance support guarantee management system, which manages maintenance task orders based on the above - mentioned maintenance support guarantee management method, including:

[0045] A task receiving module, which is used to receive a maintenance task order and obtain the maintenance task location information and the maintenance task level information of the maintenance task order;

[0046] A node selection module, which is used to obtain several maintenance sub - centers within the preset range of the maintenance task location that meet the requirements of the maintenance task level and whose current workload load value is lower than the preset workload threshold as candidate maintenance sub - centers;

[0047] A personnel deployment module, which is used to select and deploy the maintenance personnel of one of the candidate maintenance sub - centers to complete the maintenance task order when the idle maintenance personnel of at least one of the candidate maintenance sub - centers meet the personnel requirements of the maintenance task level;

[0048] The personnel allocation module is further configured to, when the number of idle maintenance personnel in each of the candidate maintenance sub - centers is less than the personnel requirement of the maintenance task level, allocate the maintenance personnel of multiple candidate maintenance sub - centers to jointly complete the maintenance task order, and the allocated maintenance personnel of the multiple candidate maintenance sub - centers meet the personnel requirement of the maintenance task level.

[0049] Correspondingly, a third aspect of the embodiments of the present invention provides an electronic device, including: at least one processor; and a memory connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is caused to execute the above - mentioned intelligent substation multi - interval system - level protection function detection method.

[0050] Correspondingly, a fourth aspect of the embodiments of the present invention provides a computer - readable storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the above - mentioned intelligent substation multi - interval system - level protection function detection method is implemented.

[0051] The above - mentioned technical solutions of the embodiments of the present invention have the following beneficial technical effects:

[0052] 1. Through the dynamic screening mechanism and the hierarchical matching strategy, the accurate positioning and rapid response of maintenance resources are realized. The preset range of the task location is delimited, and candidate sub - centers are screened by combining the qualifications, skills and load thresholds of the sub - centers to ensure basic matching. When allocating in a single sub - center, a dual - strategy of "distance priority" or "load priority" is adopted: for emergency tasks, sub - centers in the vicinity are preferentially called to shorten the response time, and for daily tasks, the load - balancing formula is used to avoid local overload. The dynamic switching mechanism effectively solves the contradiction of co - existence of resource idleness and overload in traditional scheduling, increases the utilization rate of sub - centers by 20% - 30%, and shortens the average task response time by 15% - 25%.

[0053] 2. Through the multi - dimensional comprehensive evaluation model, the global optimal decision - making in complex scenarios is realized. When jointly allocating among multiple sub - centers, the system generates multiple transfer plans, calculates the normalized values of time cost, load balance degree and skill matching degree, and conducts a comprehensive evaluation. Compared with the traditional single - index scheduling, this model improves the comprehensive optimization rate of the plan by 40% - 50%, and increases the completion efficiency of cross - sub - center collaborative tasks by more than 35%, ensuring the coordinated optimization of task response speed and execution quality.

[0054] 3. Through the quantification model and normalization process, the standardization and scalability of scheduling decisions are achieved. The time cost formula incorporates the personnel movement speed and distance into the calculation to ensure the comparability of time; the load balance degree formula quantifies the fairness of resource allocation through the standard deviation; the skill matching degree formula combines the skill weights and proficiency levels to ensure the accurate docking of capabilities; the normalization process eliminates the dimensional differences of indicators and supports the dynamic adjustment of weight parameters; this quantification system can quickly adapt to the actual needs of the equipment maintenance and management field, provides a standardized framework for multi-objective decision-making, and significantly enhances the intelligent level and overall efficiency of equipment maintenance services. Description of the Drawings

[0055] Figure 1 is the flowchart of the maintenance support guarantee management method provided by the embodiment of the present invention;

[0056] Figure 2 is the block diagram of the maintenance support guarantee management system module provided by the embodiment of the present invention.

[0057] Reference Signs:

[0058] 1. Task receiving module, 2. Node selection module, 3. Personnel deployment module. Detailed Embodiments

[0059] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In addition, in the following descriptions, the descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present invention.

[0060] Please refer to Figure 1 , the first aspect of the embodiment of the present invention provides a maintenance support guarantee management method, including the following steps:

[0061] Step S100, receive a maintenance task order, and obtain the maintenance task location information and maintenance task level information of the maintenance task order.

[0062] After receiving the maintenance task order through API interfaces, mobile APPs, manual entry, etc., the system first parses the core information in the order, including the geographical coordinates (such as longitude and latitude), detailed address, and surrounding traffic conditions of the location where the maintenance task is to be implemented. At the same time, it determines the task level in combination with factors such as the type of fault, the scope of influence, and the degree of urgency. The maintenance task levels include: level-1 maintenance tasks, level-2 maintenance tasks, and level-3 maintenance tasks, which are stored in association with the required number of maintenance personnel at each level; the levels of maintenance personnel include: junior, intermediate, senior, and expert levels. Among them, the personnel requirements for level-1 maintenance tasks, level-2 maintenance tasks, and level-3 maintenance tasks respectively correspond to the corresponding preset numbers of junior, intermediate, senior, and / or expert-level maintenance personnel. In addition, the address can be automatically parsed through GIS, or the real-time traffic condition data can be obtained by calling the map API, providing a spatial basis for the subsequent screening of sub-centers.

[0063] Step S200: Obtain several maintenance sub-centers within the preset range of the maintenance task location that meet the requirements of the maintenance task level and whose current workload load value is lower than the preset workload threshold as candidate maintenance sub-centers.

[0064] Based on the maintenance task location, a preset range is delimited (such as a circular area with a radius of 50 kilometers or a dynamically adjusted administrative region), and candidate maintenance sub-centers are screened in combination with the task level. The screening conditions include: among the idle maintenance personnel in the maintenance sub-center, there must be qualifications matching the maintenance task level (for example, for level-3 maintenance tasks, at least 3 junior maintenance personnel and 2 senior maintenance personnel are required), and the current workload load value of the maintenance sub-center is lower than the preset threshold (for example, the preset threshold of the maintenance sub-center is 60%). The sub-centers are quickly located through the GIS spatial query function, and the personnel database is synchronously verified to ensure the accuracy of the information. Finally, the candidate sub-centers are sorted according to the priorities such as workload load value, maintenance task level, and distance. If there are no qualified sub-centers within the preset range, the range is expanded and marked as "cross-region support".

[0065] Step S300: When the idle maintenance personnel of at least one candidate maintenance sub-center meet the personnel requirements of the maintenance task level, select one of the candidate maintenance sub-centers to deploy its maintenance personnel to complete the maintenance task order.

[0066] If the number and level of idle personnel in a certain candidate sub-center both meet the maintenance task requirements, preferentially select the sub-center with the shortest distance or the lower load to execute the deployment, automatically allocate the task to the maintenance sub-center console, and push notifications to relevant personnel via text message or APP. At the same time, the number of idle personnel in the maintenance sub-center is deducted in real time, and the task is marked as "allocated".

[0067] If a sub-center breaks down suddenly after the task is allocated, the system triggers a rollback mechanism to re-select the second-best sub-center; for urgent tasks, the system dynamically adjusts the personnel priority and preferentially calls on standby personnel to shorten the response time.

[0068] Step S400, when the number of idle maintenance personnel in each candidate maintenance sub - center is less than the personnel requirement of the maintenance task level, deploy the maintenance personnel from multiple candidate maintenance sub - centers to jointly complete the maintenance task order, and the deployed maintenance personnel from multiple candidate maintenance sub - centers meet the personnel requirement of the maintenance task level.

[0069] When a single maintenance sub - center cannot meet the personnel quantity and / or level requirements of the maintenance task, split the task into sub - requirements according to skills / levels (such as 3 senior workers and 5 intermediate workers), and generate personnel deployment combination plans for multiple maintenance sub - centers. Each personnel deployment combination plan needs to meet the condition that the number of personnel drawn from each maintenance sub - center does not exceed its respective idle number and the total number meets the standard. At the same time, comprehensively evaluate the time cost, load balance degree, and skill matching degree, and the weights of each parameter are dynamically adjusted according to the task type. After deployment, designate a main maintenance sub - center to coordinate the task, and real - time monitor the personnel trajectory through GPS, and trigger the standby route planning in case of abnormal situations.

[0070] Further, deploying the maintenance personnel from the selected candidate maintenance sub - center in step S300 to complete the maintenance task order includes:

[0071] Step S310, obtain the current workload load value of the candidate maintenance sub - center, and select a candidate maintenance sub - center one by one in ascending order of the current workload load value.

[0072] In another alternative embodiment, taking the current workload load of the maintenance sub - center as the core screening condition, by real - time monitoring the work saturation of each maintenance sub - center and sorting them in ascending order of the load value, preferentially select the maintenance sub - center with the smallest load, and balance the workload of each node dynamically to avoid the decline of service capacity caused by local overload, which conforms to the basic goal of "load balancing" in the distributed system.

[0073] Further, the calculation formula of the current workload load value WL is:

[0074]

[0075] where L is the maintenance task level value, W j is the work efficiency of the j - th maintenance personnel level in the current candidate maintenance sub - center, F j is the idle quantity of the j - th maintenance personnel level, D h is the distance value between the current candidate maintenance sub - center and its h - th maintenance task location, ω1 is the distance attenuation coefficient between the maintenance task location and the candidate maintenance sub - center, and ω2 is the cosine function coefficient.

[0076] In the calculation method of the above workload value, the maintenance task level value represents the complexity or importance of the maintenance task. The higher the task level, the greater the load impact on the sub - center. For example, a high - level maintenance task may require more human, material, and time resources, thus increasing the workload load of the sub - center.

[0077] The work efficiency of maintenance personnel at different levels reflects the speed or ability of maintenance personnel at different levels to complete work. Personnel with a higher level and higher efficiency can complete more work in the same time. Therefore, when calculating the load, the higher the efficiency, the stronger the ability to share the load of the sub - center with the same number of people. For example, senior technicians are obviously more efficient than junior technicians. When calculating the load, with the same number of senior technicians, the load on the sub - center is relatively lower.

[0078] The distance factor between the maintenance task location and the corresponding candidate maintenance sub - center plays an important role in load calculation. Generally speaking, the farther the distance, the higher the time and cost required for personnel to reach the task location, which will increase the load of the sub - center to a certain extent. For example, a long - distance task requires the sub - center to invest more transportation resources, or because the time of personnel on the road is longer, the time available for other tasks is reduced, thus increasing the load.

[0079] In addition, the distance attenuation coefficient between the maintenance task location and the candidate maintenance sub - center is used to measure the degree of influence of distance on the load. When the distance attenuation coefficient is large, an increase in distance will cause a significant increase in the load; when the distance attenuation coefficient is small, the influence of distance on the load is relatively small. For example, in some cases, if the distance between the task location and the sub - center is far, but the transportation is convenient, the distance attenuation coefficient can be set relatively small to reflect that the actual influence of distance on the load is relatively weak.

[0080] The number of idle personnel at each maintenance personnel level is a key indicator to measure whether the sub - center has the ability to undertake new tasks. The more idle personnel, the greater the potential of the sub - center to undertake new tasks, and the relatively lower the load. If a sub - center has a large number of idle personnel, it means that it has more human resources that can be allocated and can handle new maintenance tasks relatively easily.

[0081] The cosine function can simulate the influence of some periodic or regular factors on the load. At different time periods of a day and different working days of a week, the work load of the sub - center will show a certain periodic change. Through the adjustment of the cosine function, the load calculation can be made more in line with the fluctuation law in the actual situation.

[0082] Furthermore, the deployment of maintenance personnel from multiple candidate maintenance sub - centers to jointly complete the maintenance task order in step S400 includes:

[0083] Step S410: Obtain the distance values between multiple candidate maintenance sub - centers and the location where the maintenance task is to be implemented respectively.

[0084] First of all, it is necessary to accurately measure the distance between each candidate maintenance sub - center and the actual execution location of the maintenance task. With the help of Geographic Information System (GIS) technology, relying on the longitude and latitude coordinates of the maintenance sub - center and the task implementation location, algorithms such as Euclidean distance algorithm and spherical distance algorithm can be used to accurately calculate the distance value. Accurate distance data is extremely crucial for subsequent personnel allocation decisions. A shorter distance means that the maintenance task can be responded to more quickly, shortening the travel time of personnel, and thus improving the overall maintenance efficiency. For example, if a candidate maintenance sub - center is only 5 kilometers away from the maintenance task implementation location, while another sub - center is 20 kilometers away from it, under the same other conditions, the sub - center with a shorter distance has a significant advantage in terms of the time cost of personnel allocation. In addition, the actual road conditions should also be considered to avoid the problem of a short straight - line distance but a long actual journey.

[0085] Step S420: Obtain the idle quantities of maintenance personnel at all levels in multiple candidate maintenance sub - centers respectively.

[0086] To achieve a reasonable allocation of maintenance personnel, it is necessary to know the idle status of maintenance personnel at different levels in each candidate maintenance sub - center in real - time. The management systems of each maintenance sub - center and the general management system should achieve real - time data synchronization. Maintenance personnel at all levels can be divided according to factors such as skill level, work experience, and the qualification certificates they hold, such as junior, intermediate, and senior maintenance personnel. By accurately grasping the idle quantities of maintenance personnel at all levels, the allocation system can better meet the needs of different skill levels of personnel for maintenance tasks. For example, simple equipment maintenance tasks can be completed by junior maintenance personnel; while complex equipment fault repairs require the participation of intermediate or senior maintenance personnel. If there are 10 junior maintenance personnel idle in a candidate maintenance sub - center, but only 2 intermediate and 1 senior maintenance personnel idle, when allocating personnel, it is necessary to arrange reasonably according to the complexity of the task.

[0087] Step S430: Based on the distance values and the idle quantities of maintenance personnel at all levels, select several from multiple candidate maintenance sub - centers to obtain several maintenance personnel extraction plans respectively.

[0088] By comprehensively considering the two key factors of the distance value and the number of idle maintenance personnel at each level, a plan for dispatching maintenance personnel is formulated. The distance value determines the time required for personnel to reach the location where the maintenance task is to be carried out, and the number of idle maintenance personnel at each level determines whether there are sufficient and skill-matched personnel available for deployment at the sub-center. Multiple algorithms can be used to formulate the plan, such as preferentially selecting the sub-center with a short distance and sufficient idle maintenance personnel meeting the skill requirements. Taking an actual scenario as an example, suppose there are three candidate maintenance sub-centers, A, B, and C. Sub-center A is relatively close to the location where the maintenance task is to be carried out, but only junior maintenance personnel are idle; Sub-center B is at a moderate distance, and both intermediate and junior maintenance personnel are idle; Sub-center C is relatively far away, but there are a large number of idle senior, intermediate, and junior maintenance personnel. If the maintenance task is relatively complex and requires intermediate and senior maintenance personnel, Sub-center B may be given priority, and a dispatching plan can be formulated by combining some senior maintenance personnel from Sub-center C to ensure that both the skill requirements of the task are met and the time cost of personnel deployment is minimized. Through such comprehensive trade-offs, multiple different dispatching plans for maintenance personnel can be generated, and each plan clearly specifies how many maintenance personnel at each level are to be dispatched from which candidate maintenance sub-centers.

[0089] Step S440, obtain the total time cost of personnel deployment, the load balance degree of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel for each maintenance personnel dispatching plan.

[0090] Among them, the total time cost of personnel deployment mainly includes the travel time for personnel to travel from the candidate maintenance sub-center to the location where the maintenance task is to be carried out. The time cost of personnel deployment can be estimated based on the previously obtained distance value and the average speed of different transportation modes (such as different speeds of cars on urban roads and highways). At the same time, the preparation time before personnel departure, such as organizing tools and handing over current work, also needs to be considered. For example, if a dispatching plan requires dispatching personnel from a sub-center at a long distance and there is serious traffic congestion, the total time cost of personnel deployment will be relatively high.

[0091] To avoid some maintenance sub-centers being overworked due to frequent undertaking of maintenance tasks, which may affect the service quality, the load balance degree of the sub-centers needs to be considered. It can be measured by calculating the ratio of the number of remaining idle maintenance personnel in each sub-center after this dispatch to the total number of maintenance personnel in the sub-center. Too high or too low a ratio may indicate unbalanced load of the sub-center. For example, a certain sub-center has a total of 50 maintenance personnel, and only 5 are idle after the dispatch, so its load is relatively heavy; while another sub-center has a total of 30 maintenance personnel, and 20 are idle after the dispatch, so its load is relatively light. A reasonable dispatching plan should try to keep the load of each sub-center at a relatively balanced level.

[0092] According to the specific requirements of the maintenance tasks, evaluate the degree of fit between the skills of the maintenance personnel in the seconded plan and the task requirements. The maintenance tasks can be broken down into different skill modules such as equipment disassembly, fault diagnosis, and repair, and then compare the skills of maintenance personnel at all levels in the seconded plan to calculate the skill matching degree. For example, if the maintenance tasks mainly involve complex equipment fault diagnosis, and most of the seconded personnel in the seconded plan are junior maintenance personnel, whose skills are mainly concentrated on simple equipment maintenance, then the skill matching degree of the maintenance personnel in this plan is relatively low.

[0093] Step S450, based on the total time cost of personnel deployment, the load balance degree of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel, calculate the comprehensive evaluation value of each maintenance personnel seconded plan, and conduct the secondment of maintenance personnel according to the seconded plan corresponding to the optimal result of the comprehensive evaluation value.

[0094] After obtaining the three indicators of the total time cost of personnel deployment, the load balance degree of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel for each maintenance personnel seconded plan, combine these three indicators to calculate the comprehensive evaluation value of each plan. A common algorithm is to assign different weights to each indicator according to its importance to the overall deployment effect. For example, if the maintenance task is time-consuming, the weight of the total time cost of personnel deployment can be set relatively high; if considering the long-term load balance of the sub-centers, the weight of the load balance degree of candidate maintenance sub-centers can be appropriately increased; if the maintenance task has a high technical difficulty and high requirements for the skills of maintenance personnel, the weight of the skill matching degree of maintenance personnel should be increased. After calculating the comprehensive evaluation value of each plan through methods such as weighted summation, the system selects the plan with the optimal comprehensive evaluation value for the actual secondment of maintenance personnel. This can ensure that the most reasonable personnel deployment decision is made based on comprehensive considerations of multiple factors such as time cost, sub-center load, and personnel skills, and the maintenance task order is completed efficiently and with high quality.

[0095] Furthermore, step S430, which randomly selects several from multiple candidate maintenance sub-centers based on the distance value and the idle quantity of maintenance personnel at all levels to obtain several maintenance personnel seconded plans respectively, further includes:

[0096] Step S431, randomly select several from multiple candidate maintenance sub-centers.

[0097] This random selection method can introduce a certain degree of flexibility and diversity, avoiding the limitations that may result from the selection by fixed rules. The number of random selections is not determined arbitrarily, but rather factors such as the scale and complexity of the maintenance task and the total number of candidate sub-centers need to be comprehensively considered. For example, if the scale of the maintenance task is large and requires maintenance personnel with different skill levels, 5 - 8 candidate maintenance sub-centers may be randomly selected; if the task scale is small and relatively simple, selecting 2 - 3 sub-centers may be sufficient. Through random selection, different combinations of sub-centers may be generated each time, which helps to explore potential more optimal allocation plans. Especially in some complex and changeable maintenance scenarios, it can avoid missing more efficient resource allocation methods due to fixed patterns.

[0098] Step S432: Obtain the skill matching degree between each candidate maintenance sub-center and the maintenance task order, and combine the distance value and the idle quantity of maintenance personnel at all levels to construct a distance matrix for the currently randomly selected candidate maintenance sub-centers.

[0099] For the currently randomly selected candidate maintenance sub-centers, calculate their skill matching degree with the maintenance task order, and combine the distance value and the idle quantity of maintenance personnel at all levels to construct a distance matrix. The distance matrix is a symmetric matrix, representing the distances between all pairs of candidate sub-centers. The smaller the distance value, the more similar the characteristics between two sub-centers. The distance calculation method can use the Euclidean distance or other distance measurement methods.

[0100] Step S433: Cluster the candidate maintenance sub-centers based on the hierarchical clustering algorithm, and divide several randomly selected candidate maintenance sub-centers into a main node cluster and several sub-node clusters according to the maintenance task order.

[0101] Hierarchical clustering is a distance-based clustering method. By gradually merging or splitting clusters, a clustering tree (dendrogram) is formed. In agglomerative hierarchical clustering, the algorithm starts with each sub-center as a separate cluster and gradually merges the two closest clusters until all sub-centers are merged into one cluster or the predetermined number of clusters is reached. According to the task requirements, the candidate sub-centers can be divided into a main node cluster and several sub-node clusters. For example, if 1 main node and 2 sub-nodes are needed, the candidate sub-centers are divided into 3 clusters. The clustering result includes a main node cluster and several sub-node clusters, and each cluster contains several candidate sub-centers.

[0102] Step S434: Take the candidate maintenance sub-center closest to the maintenance task in the main node cluster as the main node, and take one candidate maintenance sub-center closest to the main node in each sub-node cluster as the sub-node.

[0103] First, select the sub - center closest to the location where the maintenance task is to be implemented as the main node in the main node cluster. If the distances are the same, select the sub - center with the highest skill matching degree. Then, select the sub - center closest to the main node as the sub - node in the sub - node cluster. If the distances are the same, select the sub - center with the highest skill matching degree. The number of sub - nodes can be determined according to the task requirements. For example, select 1 - 2 sub - centers closest to the main node in each sub - node cluster as sub - nodes. In this way, the role division of the main node and sub - nodes can be clarified. The main node is responsible for undertaking the main tasks, and the sub - nodes are responsible for undertaking the auxiliary tasks.

[0104] Step S435: Determine the maintenance personnel transfer plan based on the corresponding candidate maintenance sub - centers of the main node and several sub - nodes. After multiple random selections, several maintenance personnel transfer plans are obtained respectively.

[0105] Based on the main node and sub - nodes, determine the number of transferred personnel and generate a maintenance personnel transfer plan. According to the task requirements, the number of transferred personnel for the main node and sub - nodes can be determined. For example, 4 people are transferred from the main node (2 junior, 1 intermediate, 1 senior), and 2 people are transferred from the sub - node (1 junior, 1 intermediate); the detailed information of each plan (such as the main node, sub - node, number of transferred personnel, etc.) needs to be recorded. Through multiple random selections, multiple maintenance personnel transfer plans can be generated.

[0106] In multiple random selections, different screening conditions and clustering parameters can be set to increase the diversity of the plans. Finally, by comparing the fitness values of multiple plans, the optimal plan is selected for implementation.

[0107] In an implementation manner of the embodiment of the present invention, calculating the comprehensive evaluation value of each maintenance personnel transfer plan based on the total time cost of personnel allocation, the load balance degree of candidate maintenance sub - centers, and the skill matching degree of maintenance personnel in step S450 further includes:

[0108] Step S451: Based on the multi - objective optimization model, construct the objective function of each maintenance personnel transfer plan. The objective function includes: minimizing the total time cost of personnel allocation, maximizing the load balance degree of candidate maintenance sub - centers, and maximizing the skill matching degree of maintenance personnel.

[0109] In the multi - objective optimization model, it is important to construct the objective function for each maintenance personnel transfer plan. By comprehensively considering the three core elements of the total time cost of personnel allocation, the load balance degree of candidate maintenance sub - centers, and the skill matching degree of maintenance personnel, the optimal personnel transfer plan can be obtained.

[0110] The total time cost of personnel allocation includes the time it takes for personnel to leave the candidate maintenance and repair sub - centers and travel to the location where the maintenance tasks are to be carried out. The travel time involved during this period also constitutes part of the total time cost of personnel allocation. To minimize it, when constructing the objective function, variables related to time cost can be incorporated and given a minimization direction. For example, if the time unit is minutes, the calculated time values for different transportation methods from each sub - center to the task location are used as variables, and in the objective function, the combination of these variables is made to tend to be minimized.

[0111] The load balance degree of each candidate maintenance and repair sub - center is measured by calculating the ratio of the number of remaining idle maintenance personnel in the sub - center after personnel are transferred out to the total number of maintenance personnel in the sub - center. In the construction of the objective function, this ratio is used as a variable, and it is expected that the larger its value, the better. For example, when the ratio of remaining idle personnel in a sub - center after transfer is high, it means that the sub - center still has a relatively large amount of resource reserves after this allocation and has stronger capabilities to handle other potential tasks in the future.

[0112] Maintenance tasks often have different skill requirements, ranging from simple equipment cleaning and maintenance to complex fault diagnosis and repair. The skill matching degree is determined by decomposing the maintenance tasks into specific skill modules such as equipment disassembly, fault diagnosis, and repair, and then comparing the skills possessed by maintenance personnel at all levels in the transfer plan. In the objective function, the skill matching degree is quantified as a numerical variable and a maximization goal is set. For example, if a maintenance task requires advanced fault diagnosis skills, and the number of senior maintenance personnel in the transfer plan is sufficient and their skills highly match the task, then the variable value of this plan in terms of skill matching degree is high, and the objective function uses mathematical relationships to make this variable tend to its maximum value to achieve the maximization of skill matching degree.

[0113] Step S452: Based on the objective function of the maintenance personnel transfer plan, calculate the objective function values of the total time cost of personnel allocation, the load balance degree of candidate maintenance and repair sub - centers, and the skill matching degree of maintenance personnel respectively, and perform normalization processing.

[0114] Based on the previously obtained distance values and information such as the average speed of different transportation methods, accurately calculate the travel time of personnel from each candidate maintenance and repair sub - center to the location where the maintenance tasks are to be carried out. The time for personnel to get ready to depart (such as packing tools, handing over current work, etc.) can also be considered and added to obtain the total time cost of personnel allocation for each maintenance personnel transfer plan. For example, in a certain plan, when transferring personnel from Sub - center A, the distance is 30 kilometers. If traveling by car on the highway at a speed of 80 kilometers per hour and adding a 30 - minute preparation time, the total time cost of personnel allocation for this part can be calculated. Summing up the time costs of all personnel involved in the transfer from all sub - centers gives the objective function value of the total time cost of personnel allocation for this plan.

[0115] For each candidate maintenance and support sub - center, calculate the ratio of the number of remaining idle maintenance and support personnel after this transfer to the total number of maintenance and support personnel in this sub - center. In an implementation manner of this embodiment, there are a total of 60 maintenance and support personnel in Sub - center B. After the transfer, there are 20 idle personnel remaining. Then its load - balancing ratio is 20÷60 = 33%. Combine the ratio values of each sub - center (such as through weighted average, etc., and the weights can be determined according to the scale, importance, etc. of the sub - center) to obtain the objective function value of the load - balancing degree of the candidate maintenance and support sub - centers for this maintenance and support personnel transfer plan.

[0116] After decomposing the maintenance tasks into specific skill modules, conduct a detailed analysis of the skills of the maintenance and support personnel in each transfer plan. For example, a maintenance task includes three skill modules: equipment disassembly, fault diagnosis, and repair. If there are 3 maintenance and support personnel in the transfer plan, 2 of them have the equipment disassembly skill, 1 has the fault diagnosis skill, and no one has the repair skill. By setting the importance weights of the skill modules (such as equipment disassembly weight 0.3, fault diagnosis weight 0.4, repair weight 0.3), calculate the skill - matching score of this plan, which is used as the objective function value of the skill - matching degree of the maintenance and support personnel.

[0117] Since the dimensions and value ranges of the three indicators of the total time cost of personnel allocation, the load - balancing degree of candidate maintenance and support sub - centers, and the skill - matching degree of maintenance and support personnel are different, direct comparison and comprehensive calculation will produce deviations. Therefore, normalization processing is required to convert them to the same value range (usually 0 - 1). A common normalization method is the min - max normalization method. That is, for an indicator value x, calculate it through the formula (x - min)÷(max - min), where min and max are the minimum and maximum values of this indicator in all maintenance and support personnel transfer plans respectively. For example, the minimum value of the total time cost of personnel allocation in all plans is 60 minutes, the maximum value is 180 minutes, and the time cost of a certain plan is 90 minutes. Then its normalized value is (90 - 60)÷(180 - 60)=0.25. Through normalization processing, these three indicators can be operated and compared on the same scale.

[0118] Step S453: Based on the objective function values of the total time cost of personnel allocation, the load - balancing degree of candidate maintenance and support sub - centers, and the skill - matching degree of maintenance and support personnel after normalization processing, calculate the fitness values of several maintenance and support personnel transfer plans respectively, as the comprehensive evaluation value of each plan.

[0119] Based on the objective function values of the total time cost of personnel allocation, the load - balancing degree of candidate maintenance and support sub - centers, and the skill - matching degree of maintenance and support personnel after normalization processing, calculate the fitness value of each maintenance and support personnel transfer plan. This fitness value is used as the comprehensive evaluation value of this plan.

[0120] Step S454: Select the maintenance personnel transfer plan with the highest comprehensive evaluation value for the transfer of maintenance personnel.

[0121] After calculating the comprehensive evaluation values of all maintenance personnel transfer plans, the system will automatically screen out the plan with the highest comprehensive evaluation value. This plan achieves the best balance in the three key aspects of the total time cost of personnel allocation, the load balance of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel. For example, among multiple plans, the comprehensive evaluation value of a certain plan is 0.7, which is higher than other plans. This means that this plan performs the best in terms of time cost control, sub-center load balance, and personnel skills meeting task requirements. Selecting this plan for the actual transfer of maintenance personnel can ensure the efficient and high-quality completion of maintenance tasks to the greatest extent, while taking into account the long-term operational stability of the sub-center and realizing the rational allocation of resources.

[0122] Furthermore, based on the objective function values of the total time cost of personnel allocation, the load balance of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel after normalization in step S453, calculate the fitness values of several maintenance personnel transfer plans, including:

[0123] Step S453a: Based on the objective function values of the total time cost of personnel allocation, the load balance of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel after normalization, construct the original vector of each maintenance personnel transfer plan.

[0124] Based on the objective function values after normalization (the total time cost of personnel allocation, the load balance of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel), construct the original vector of each maintenance personnel transfer plan. Normalization processes the objective function values into the range [0, 1] to ensure the comparability of each objective in the comprehensive evaluation. Each dimension of the original vector corresponds to a normalized objective function value. For example, for a maintenance personnel transfer plan, its original vector can be expressed as [T′, E′, F′], where T′ is the normalized total time cost of personnel allocation, E′ is the normalized load balance degree, and F′ is the normalized skill matching degree. The original vector is the basic input data for the multi-objective optimization problem and is used for subsequent feature extraction and fitness value calculation.

[0125] Step S453b: Input the original vector into the pre-trained autoencoder model to obtain the low-dimensional feature encoding vector.

[0126] Input the original vector into the pre-trained autoencoder model to obtain a low-dimensional feature encoding vector. An autoencoder is an unsupervised learning model commonly used for data dimensionality reduction and feature extraction. By compressing the input data into a low-dimensional space (encoding) and then reconstructing it back to the original space (decoding), it learns the latent representation of the data. The pre-trained autoencoder model has been trained with historical data and can effectively extract the low-dimensional features of the original vector. The low-dimensional feature encoding vector can better reflect the latent structure of the original data, while reducing the data dimension and improving the computational efficiency. For example, after passing through the autoencoder, the original vector [T′, E′, F′] may be compressed into a 2-dimensional feature encoding vector [f1, f2].

[0127] Step S453c: Input the low-dimensional feature encoding vector into the pre-trained support vector regression model, and obtain the fitness value of the maintenance personnel deployment plan based on the support vector regression model.

[0128] Input the low-dimensional feature encoding vector into the pre-trained support vector regression (SVR) model, and obtain the fitness value of the maintenance personnel deployment plan based on the support vector regression model. Support vector regression predicts a continuous value output by fitting the relationship between the input features and the target values. The pre-trained support vector regression model has been trained with historical data (including low-dimensional feature encoding vectors and corresponding fitness values) and can predict the fitness value based on the low-dimensional features. For example, after inputting the low-dimensional feature encoding vector [f1, f2] into the support vector regression model, the fitness value is output, which reflects the comprehensive performance of the maintenance personnel deployment plan and is used to compare and select the optimal plan.

[0129] Specifically, the calculation formula for the fitness value of the maintenance personnel deployment plan in step S450 is:

[0130]

[0131] where T′ is the normalized total time cost of personnel allocation, E′ is the normalized load balance degree of candidate maintenance sub-centers, F′ is the normalized skill matching degree of maintenance personnel, and α, β, and λ are corresponding coefficients.

[0132] The above calculation formula for the fitness value evaluates the advantages and disadvantages of different maintenance personnel deployment plans by comprehensively considering the three key factors of the normalized total time cost of personnel allocation, the load balance degree of candidate maintenance sub-centers, and the skill matching degree of maintenance personnel.

[0133] First, weights α, β, and λ are introduced into the formula, corresponding to time cost, load balance degree, and skill matching degree respectively. This weighted processing method reflects the relative importance of different factors in the decision-making process. For example, if time cost is more critical in practical applications, a higher weight can be assigned to α. The setting of weights enables the fitness function to flexibly adapt to different actual needs and priorities, thus more accurately reflecting the overall advantages and disadvantages of the scheme.

[0134] Secondly, the formula adopts the reciprocal form. The reciprocal form can normalize the fitness value to the interval [0, 1], which is convenient for comparison and ranking between different schemes. The closer the fitness value is to 1, the better the scheme; the closer it is to 0, the worse the comprehensive performance of the scheme. This normalization processing method makes the fitness value have good interpretability and comparability, facilitating the quick identification of the optimal scheme.

[0135] In the treatment of specific factors, the lower the time cost, the better. Therefore, T′ is directly used as a positive influencing factor. While the higher the load balance degree and skill matching degree, the better. Therefore, (1 - E′) and (1 - F′) are used in the formula to represent the negative impact on fitness respectively, ensuring the logical consistency of the formula: when the performance of a certain factor is poor, the negative impact on the fitness value will be reflected by increasing the value in the denominator, thus reducing the fitness value; on the contrary, when a certain factor performs well, the negative impact on the fitness value is small and the fitness value is relatively high.

[0136] In addition, the "1" in the denominator of the formula plays the role of a base value, avoiding the situation of the denominator being zero, and at the same time providing a baseline for the fitness value. Even if the performance of all factors is very poor, the fitness value will not be zero but approach zero, which is reasonable in practical applications because even if the comprehensive performance of the scheme is not good, there is still a certain feasibility and only further optimization is needed.

[0137] The above calculation formula can not only comprehensively evaluate the advantages and disadvantages of different maintenance personnel transfer schemes through reasonable integration of multiple key factors and the use of weighted and reciprocal forms, but also flexibly adapt to different actual needs and priorities.

[0138] Next, in an optional implementation manner of the embodiment of the present invention, the function formula of the total time cost of personnel allocation is:

[0139]

[0140] Among them, n is the number of candidate maintenance sub - centers, m is the number of levels of maintenance personnel, is the number of maintenance personnel at level j transferred from the i - th candidate maintenance sub - center. The more personnel are transferred, the higher the corresponding time cost; d ij is the number of maintenance personnel at level j transferred from the i - th candidate maintenance sub - center. The more personnel are transferred, the higher the corresponding time cost; d iis the distance between the \(i\)-th candidate maintenance and repair sub-center and the location where the maintenance and repair task is implemented. The farther the distance, the longer the time required for personnel to arrive, and the higher the time cost; \(v\) j is the average moving speed of the \(j\)-th level of maintenance and repair personnel. For maintenance and repair personnel at different levels, due to factors such as transportation equipment, skills, and experience, there may be differences in moving speed. The faster the speed, the shorter the time to reach the task location and the lower the time cost. Through the above formula, the total time cost required to allocate personnel from multiple candidate maintenance and repair sub-centers to complete the maintenance and repair task order can be calculated.

[0141] Normalize the total time cost of personnel allocation to obtain the normalized value of the total time cost of personnel allocation:

[0142]

[0143] where \(T\) max is the maximum value of the total time cost of personnel allocation in all personnel transfer plans for maintenance and repair personnel, and \(T\) min is the minimum value of the total time cost of personnel allocation in all personnel transfer plans for maintenance and repair personnel.

[0144] Through such calculations, the range of the normalized value \(T'\) of the total time cost of personnel allocation obtained is between 0 and 1. If the \(T'\) of a certain plan is close to 0, it means that the total time cost of personnel allocation in this plan is relatively low among all plans; conversely, if \(T'\) is close to 1, it indicates that the time cost of this plan is relatively high.

[0145] Next, in an optional implementation manner of the embodiment of the present invention, the function formula for the load balance degree of the candidate maintenance and repair sub-center is:

[0146]

[0147]

[0148] where \(n\) is the number of candidate maintenance and repair sub-centers, \(m\) is the number of levels of maintenance and repair personnel, \(n\) ij is the number of the \(j\)-th level of maintenance and repair personnel transferred from the \(i\)-th candidate maintenance and repair sub-center, \(L\) i is the original workload of the \(i\)-th candidate maintenance and repair sub-center, \(\omega\) j is the workload weight borne by the \(j\)-th level of maintenance and repair personnel, is the load increase value of the \(i\)-th candidate maintenance and repair sub-center after adding the current maintenance and repair task, \(R\) i is the relative load value of each candidate maintenance and repair sub-center after adding the current maintenance and repair task, is the average value of the relative loads of each candidate maintenance and repair sub-center.

[0149] In the above formula, Calculate the increased load of the \(i\)-th candidate maintenance and support sub-center due to the seconded personnel, which is used to quantify the impact of the seconded personnel on the existing workload of the maintenance and support sub-center and simultaneously reflect the resource consumption of different skill levels. R i Through normalization, eliminate the scale differences of the sub-centers to facilitate horizontal comparison of the load distribution. Use the standard deviation to measure the dispersion degree of the relative load of each maintenance and support sub-center, which is used to quantify the fairness of resource allocation during multi-sub-center collaboration and avoid local overload.

[0150] Perform normalization on the load balance degree of the candidate maintenance and support sub-centers to obtain the normalized value of the load balance degree of the candidate maintenance and support sub-centers:

[0151]

[0152] where, E max is the maximum value of the load balance degree of the candidate maintenance and support sub-centers in all secondment plans of maintenance personnel, and E min is the minimum value of the load balance degree of the candidate maintenance and support sub-centers in all secondment plans of maintenance personnel.

[0153] Through normalization, map the load balance degree E to the interval [-1, 1] to facilitate comprehensive evaluation with other indicators (time cost, skill matching degree); eliminate the influence of the absolute value of the original standard deviation and only retain the relative superiority and inferiority relationship. Since the smaller E is, the higher the balance degree is, and the larger the normalized E' value is, the worse the balance degree is, a positive transformation needs to be carried out in combination with the weight in the comprehensive evaluation formula (such as using 1 - E').

[0154] Next, in an optional implementation manner of the embodiment of the present invention, the function formula of the skill matching degree of maintenance personnel is:

[0155]

[0156] where, \(n\) is the number of candidate maintenance and support sub-centers, \(m\) is the number of levels of maintenance personnel, \(n\) ij is the number of maintenance personnel of the \(j\)-th level seconded to the \(i\)-th candidate maintenance and support sub-center, \(k\) is the \(k\)-th skill required for the current maintenance task, \(W\) is the number of required skills, \(F\) i is the skill matching degree of the seconded personnel of the \(i\)-th candidate maintenance and support sub-center, \(S\) k is the standard requirement value of the \(k\)-th skill that needs to be mastered, \(M\) ik is the average mastery degree value of the \(k\)-th skill by the maintenance personnel of the \(j\)-th level seconded to the \(i\)-th candidate maintenance and support sub-center, \(q\) k is the weight value of the \(j\)-th level maintenance personnel for the \(k\)-th skill in the current maintenance task.

[0157] Perform normalization on the skill matching degree of maintenance personnel to obtain the normalized value of the skill matching degree of maintenance personnel:

[0158]

[0159] Among them, F max is the maximum value of the skill matching degree of maintenance personnel in all the maintenance personnel deployment plans, and F min is the minimum value of the skill matching degree of maintenance personnel in all the maintenance personnel deployment plans.

[0160] The normalized F' is convenient for comparison and comprehensive analysis with other evaluation indicators (such as the total time cost of personnel deployment and the load balance degree of candidate maintenance sub - centers) on the same scale. By mapping the skill matching degree to a unified interval, it can more clearly judge the relative advantages and disadvantages of different deployment plans in terms of skill matching, providing more effective data support for finally selecting the optimal maintenance personnel deployment plan. For example, in the comprehensive evaluation, appropriate weights can be assigned to F' according to different business requirements, and the comprehensive evaluation value can be calculated together with other normalized indicators to make a more reasonable decision.

[0161] Correspondingly, please refer to Figure 2 In the second aspect of the embodiment of the present invention, a maintenance support guarantee management system is provided, which manages maintenance task orders based on the above - mentioned maintenance support guarantee management method, including:

[0162] A task receiving module 1, which is used to receive a maintenance task order and obtain the maintenance task location information and maintenance task level information of the maintenance task order;

[0163] A node selection module 2, which is used to obtain several maintenance sub - centers within the preset range of the maintenance task location that meet the maintenance task level requirements and whose current workload load value is lower than the preset workload threshold as candidate maintenance sub - centers;

[0164] A personnel deployment module 3, which is used to select and deploy the maintenance personnel of a candidate maintenance sub - center to complete the maintenance task order when the idle maintenance personnel of at least one candidate maintenance sub - center meet the personnel requirements of the maintenance task level;

[0165] The personnel deployment module 3 is also used to deploy the maintenance personnel of multiple candidate maintenance sub - centers to jointly complete the maintenance task order when the idle maintenance personnel of each candidate maintenance sub - center are less than the personnel requirements of the maintenance task level, and the deployed maintenance personnel of multiple candidate maintenance sub - centers meet the personnel requirements of the maintenance task level.

[0166] Correspondingly, in the third aspect of the embodiment of the present invention, an electronic device is provided, including: at least one processor; and a memory connected to at least one processor; wherein, the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor to enable at least one processor to execute the above - mentioned maintenance support guarantee management method.

[0167] Correspondingly, a fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the above-mentioned maintenance support guarantee management method is implemented.

[0168] The embodiments of the present invention aim to protect a maintenance support guarantee management method and system. The management method includes the following steps: receiving a maintenance task order, and obtaining the maintenance task location information and maintenance task level information of the maintenance task order; obtaining several maintenance sub-centers within a preset range of the maintenance task location that meet the requirements of the maintenance task level and whose current workload load value is lower than a preset workload threshold as candidate maintenance sub-centers; when the idle maintenance personnel of at least one candidate maintenance sub-center meet the personnel requirements of the maintenance task level, selecting one of the candidate maintenance sub-centers to deploy the maintenance personnel to complete the maintenance task order; when the idle maintenance personnel of each candidate maintenance sub-center are less than the personnel requirements of the maintenance task level, deploying the maintenance personnel of multiple candidate maintenance sub-centers to jointly complete the maintenance task order, and the deployed maintenance personnel of multiple candidate maintenance sub-centers meet the personnel requirements of the maintenance task level. The above technical solutions have the following effects:

[0169] 1. Through the dynamic screening mechanism and hierarchical matching strategy, the accurate positioning and rapid response of maintenance resources are realized. By delimiting the preset range of the task location and combining the qualifications, skills and load thresholds of the sub-centers to screen candidate sub-centers, the basic matching is ensured; when deploying from a single sub-center, the "distance priority" or "load priority" dual strategies are adopted: for urgent tasks, the sub-center in the near distance is preferentially called to shorten the response time, and for daily tasks, the load balancing formula is used to avoid local overload. The dynamic switching mechanism effectively solves the contradiction of coexistence of resource idleness and overload in traditional scheduling, increasing the utilization rate of sub-centers by 20%-30% and shortening the average task response time by 15%-25%;

[0170] 2. Through the multi-dimensional comprehensive evaluation model, the global optimal decision-making in complex scenarios is realized. When jointly deploying from multiple sub-centers, the system generates multiple transfer plans, calculates the normalized values of time cost, load balance degree and skill matching degree, and conducts a comprehensive score; compared with the traditional single-index scheduling, this model improves the comprehensive optimization rate of the plan by 40%-50% and increases the completion efficiency of cross-sub-center collaborative tasks by more than 35%, ensuring the coordinated optimization of task response speed and execution quality;

[0171] 3. Through the quantization model and normalization processing, the standardization and scalability of scheduling decisions are achieved. The time cost formula incorporates the personnel movement speed and distance into the calculation to ensure comparable time; the load balance degree formula quantifies the fairness of resource allocation through the standard deviation; the skill matching degree formula combines skill weights and proficiency levels to ensure accurate ability docking; the normalization processing eliminates the dimensional differences of indicators and supports dynamic adjustment of weight parameters; this quantization system can quickly adapt to the actual needs of the equipment maintenance management field, providing a standardized framework for multi-objective decision-making and significantly enhancing the intelligent level and overall efficiency of equipment maintenance services.

[0172] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0174] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0175] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1Steps of the functions specified in one or more boxes.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that modifications or equivalent replacements can still be made to the specific implementation manners of the present invention. Any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A maintenance support guarantee management method, characterized in that, It includes the following steps: Receive a maintenance task order, and obtain the maintenance task location information and maintenance task level information of the maintenance task order; Obtain several maintenance sub - centers within the preset range of the maintenance task location that meet the requirements of the maintenance task level and whose current workload load value is lower than the preset workload threshold as candidate maintenance sub - centers; When the idle maintenance personnel of at least one of the candidate maintenance sub - centers meet the personnel requirements of the maintenance task level, select one of the candidate maintenance sub - centers to deploy its maintenance personnel to complete the maintenance task order; When the idle maintenance personnel of each of the candidate maintenance sub - centers are less than the personnel requirements of the maintenance task level, deploy the maintenance personnel of multiple candidate maintenance sub - centers to jointly complete the maintenance task order, and the deployed maintenance personnel of multiple candidate maintenance sub - centers meet the personnel requirements of the maintenance task level.

2. The maintenance support guarantee management method according to claim 1, characterized in that The maintenance task levels include: first - level maintenance tasks, second - level maintenance tasks, and third - level maintenance tasks. The levels of the maintenance personnel include: junior, intermediate, senior, and expert levels; The personnel requirements for the first - level maintenance task, the second - level maintenance task, and the third - level maintenance task respectively correspond to the corresponding preset numbers of junior, intermediate, senior, and / or expert - level maintenance personnel.

3. The maintenance support guarantee management method according to claim 1 or 2, characterized in that The selecting one of the candidate maintenance sub - centers to deploy its maintenance personnel to complete the maintenance task order includes: Obtain the current workload load value of the candidate maintenance sub - center, and select one of the candidate maintenance sub - centers in ascending order of the current workload load value.

4. The maintenance support guarantee management method according to claim 3, wherein The current workload value WL is calculated by the following formula: Among them, L is the value of the maintenance task level, and W j is the work efficiency of the j-th maintenance personnel level of the current candidate maintenance sub-center, and F j is the idle quantity of the j-th maintenance personnel level, and D h is the distance value between the current candidate maintenance sub-center and its h-th maintenance task location, ω1 is the distance attenuation coefficient between the maintenance task location and the candidate maintenance sub-center, and ω2 is the cosine function coefficient.

5. The maintenance support guarantee management method according to claim 2, characterized in that The deploying the maintenance personnel of multiple candidate maintenance sub - centers to jointly complete the maintenance task order includes: Respectively obtain the distance values between multiple candidate maintenance sub - centers and the maintenance task implementation location; Respectively obtain the idle numbers of maintenance personnel at all levels of multiple candidate maintenance sub - centers; Based on the distance values and the idle numbers of maintenance personnel at all levels, select several of the multiple candidate maintenance sub - centers to obtain several maintenance personnel deployment plans respectively; Obtain the total time cost of personnel deployment, the load balance degree of candidate maintenance sub - centers, and the skill matching degree of maintenance personnel for each maintenance personnel deployment plan; Based on the total time cost of personnel deployment, the load balance degree of candidate maintenance sub - centers, and the skill matching degree of maintenance personnel, calculate the comprehensive evaluation value of each maintenance personnel deployment plan, and conduct maintenance personnel deployment according to the maintenance personnel deployment plan corresponding to the optimal comprehensive evaluation value result.

6. The maintenance support guarantee management method according to claim 5, characterized in that, The based on the distance values and the idle numbers of maintenance personnel at all levels, select several of the multiple candidate maintenance sub - centers to obtain several maintenance personnel deployment plans respectively includes: Randomly select several of the multiple candidate maintenance sub - centers; Obtain the skill matching degree between each candidate maintenance sub - center and the maintenance task order, and combine the distance values and the idle numbers of maintenance personnel at all levels to construct the distance matrix of the currently randomly selected candidate maintenance sub - centers. Cluster the candidate maintenance and support centers based on the hierarchical clustering algorithm, and divide a number of randomly selected candidate maintenance and support centers into a main node cluster and several sub-node clusters according to the maintenance task orders; Select the candidate maintenance and support center closest to the maintenance task in the main node cluster as the main node, and select one candidate maintenance and support center closest to the main node in each sub-node cluster as the sub-node; Determine the maintenance personnel transfer plan based on the candidate maintenance and support centers corresponding to the main node and several sub-nodes, and obtain several maintenance personnel transfer plans after multiple random selections.

7. The maintenance support guarantee management method according to claim 5, wherein Calculating the comprehensive evaluation value of each maintenance personnel transfer plan based on the total time cost of personnel allocation, the load balance degree of candidate maintenance and support centers, and the skill matching degree of maintenance personnel, including: Based on the multi-objective optimization model, construct the objective function of each maintenance personnel transfer plan, and the objective function includes: minimizing the total time cost of personnel allocation, maximizing the load balance degree of candidate maintenance and support centers, and maximizing the skill matching degree of maintenance personnel; Based on the objective function of the maintenance personnel transfer plan, calculate the objective function values of the total time cost of personnel allocation, the load balance degree of candidate maintenance and support centers, and the skill matching degree of maintenance personnel respectively, and perform normalization processing; Based on the objective function values of the total time cost of personnel allocation, the load balance degree of candidate maintenance and support centers, and the skill matching degree of maintenance personnel after normalization processing, calculate the fitness values of several maintenance personnel transfer plans respectively, as the comprehensive evaluation value of each plan; Select the maintenance personnel transfer plan with the highest comprehensive evaluation value for the transfer of maintenance personnel.

8. The maintenance support guarantee management method according to claim 7, characterized in that Calculating the fitness values of several maintenance personnel transfer plans respectively based on the objective function values of the total time cost of personnel allocation, the load balance degree of candidate maintenance and support centers, and the skill matching degree of maintenance personnel after normalization processing, including: Based on the objective function values of the total time cost of personnel allocation, the load balance degree of candidate maintenance and support centers, and the skill matching degree of maintenance personnel after normalization processing, construct the original vector of each maintenance personnel transfer plan; Input the original vector into the pre-trained autoencoder model to obtain the low-dimensional feature coding vector; Input the low-dimensional feature coding vector into the pre-trained support vector regression model, and obtain the fitness value of the maintenance personnel transfer plan based on the support vector regression model.

9. The maintenance support guarantee management method according to claim 6, characterized in that The calculation formula for the fitness value of the maintenance personnel transfer plan is: Wherein, T′ is the normalized value of the total time cost of personnel allocation, E′ is the normalized value of the load balance degree of candidate maintenance and support centers, F′ is the normalized value of the skill matching degree of maintenance personnel, and α, β, and λ are corresponding coefficients.

10. A maintenance support guarantee management system, characterized in that, Managing the maintenance task order based on the maintenance support guarantee management method according to any one of claims 1-9, including: A task receiving module, which is used to receive the maintenance task order and obtain the maintenance task location information and maintenance task level information of the maintenance task order; A node selection module, which is used to obtain several maintenance sub - centers within the preset range of the maintenance task location that meet the requirements of the maintenance task level and whose current workload value is lower than the preset workload threshold as candidate maintenance sub - centers; A personnel allocation module, which is used to select and allocate the maintenance personnel of one of the candidate maintenance sub - centers to complete the maintenance task order when the idle maintenance personnel of at least one of the candidate maintenance sub - centers meet the personnel requirements of the maintenance task level; The personnel allocation module is also used to allocate the maintenance personnel of multiple candidate maintenance sub - centers to jointly complete the maintenance task order when the idle maintenance personnel of each candidate maintenance sub - center are less than the personnel requirements of the maintenance task level, and the allocated maintenance personnel of multiple candidate maintenance sub - centers meet the personnel requirements of the maintenance task level.

Images