A method and device for scheduling power grid operators

Abstract

The application discloses a kind of power grid operating personnel's scheduling method and device, belong to power grid operating personnel scheduling technical field, the method is: obtaining the power grid operation task information to be executed and the operating personnel information corresponding to schedulable power grid operating personnel, according to the required personnel quantity of task Randomly organized initial personnel set, iteration optimization is carried out using tabu search algorithm, in iteration process, according to the improvement rate of solution Adaptive from the operator library containing combination exchange operator, single-point exchange operator and disturbance exchange operator Select adaptive neighborhood movement operator, operator library is built by the synergy potential index calculated relying on personnel skill set and historical operation data, personnel set is updated using selected operator Until the maximum iteration number is reached, output optimal scheduling scheme and complete personnel scheduling according to scheme, therefore, by implementing the present application, the problem of low personnel utilization efficiency in the existing power grid operating personnel scheduling mode can be solved.

Description

Technical Field

[0001] This application relates to the field of dispatching power grid workers, and more particularly to a method for dispatching power grid workers. Background Technology

[0002] In routine power grid operation and maintenance, as well as emergency repairs, it is often necessary to quickly and efficiently dispatch a team from a large number of personnel with diverse professional skills to perform specific tasks. Power grid operations typically require a high level of skill combination, and a single person cannot cover all task requirements; multiple people need to work together in coordination. Therefore, scientifically scheduling personnel and building an optimally capable operational team that can meet the skill coverage requirements of the task while also taking into account the complementarity of skills and collaborative efficiency among team members is crucial to ensuring the safe and stable operation of the power grid.

[0003] In existing technologies, tabu search algorithms are commonly used to solve combinatorial optimization problems. This algorithm searches locally and utilizes a tabu list to avoid redundant searches and escape local optima, aiming to find the global optimum. When applying tabu search to personnel scheduling, its neighborhood search strategy typically employs a simple single-point exchange operator. In each iteration, it attempts to replace one member of the team with someone from outside the team to generate new candidate teams. However, this single-point exchange strategy has significant technical drawbacks: for complex tasks requiring close collaboration of multiple key skills, such as a task requiring both high-voltage operation and relay protection skills, the single-point exchange operator can only change one skill at a time. This makes it difficult to form a team with a specific skill combination in one step, resulting in a circuitous search process, slow convergence, and low search efficiency. Furthermore, existing technologies do not comprehensively consider the complementarity of skills among personnel and historical cooperation performance, making personnel replacement too indiscriminate and difficult to build highly collaborative work teams. Summary of the Invention

[0004] This application provides a method for dispatching power grid workers, which can solve the problem of low personnel utilization efficiency in the dispatching schemes of power grid workers in the prior art.

[0005] In a first aspect, embodiments of the present invention provide a method for dispatching power grid workers, comprising: Obtain information on power grid operation tasks to be executed and personnel information corresponding to all currently schedulable power grid operation personnel. The power grid operation task information includes the number of personnel required for the task and the set of skills required for the task. The personnel information includes the set of skills and historical operation data. Based on the number of personnel required for the task, a corresponding number of personnel are randomly selected from the power grid workers to form an initial personnel set. A tabu search algorithm is then used to iteratively optimize this initial personnel set until the current iteration reaches a preset maximum iteration count. The personnel set of the current iteration is then used as the power grid worker scheduling scheme for the task to be executed. In each iteration, the improvement rate corresponding to the previous iteration is calculated based on the skill set required for the task and the personnel set of the previous iteration. A neighborhood movement operator is selected from the neighborhood movement operator library for this iteration based on the improvement rate. The personnel set of the current iteration is then updated based on the neighborhood movement operator to obtain the personnel set for the next iteration. The neighborhood movement operator library is constructed based on various collaborative potential indices. The library includes combined exchange operators, single-point exchange operators, and disturbance exchange operators. Each collaborative potential index is determined based on the skill set required for each task and historical work data. The power grid operators are dispatched according to the power grid operator dispatching plan.

[0006] This application provides basic data support for personnel scheduling by acquiring power grid operation task information, including the number of personnel required for the task and the skill set, as well as schedulable personnel information, including personnel skill sets and historical operation data. Secondly, it employs a tabu search algorithm to iteratively optimize the initial personnel set, enabling a systematic global search within a massive personnel combination space. This replaces the blindness of traditional manual scheduling or simple rule-based scheduling, effectively improving the search capability for optimal personnel combinations. Furthermore, in each iteration, it adaptively selects a neighborhood movement operator based on the improvement rate of the previous iteration, overcoming the limitations of the traditional tabu search algorithm's single neighborhood movement strategy. In the rapid improvement phase of the search, efficient operators are used to accelerate the discovery of high-quality solutions, while in the stagnant phase, strong perturbation operators are used to exit the search. The optimal scheduling scheme significantly accelerates algorithm convergence, shortens scheduling decision-making cycles, and improves the quality of the final scheduling plan. Furthermore, a neighborhood movement operator library is constructed based on a collaborative potential index calculated by combining the skill set required for the task with historical personnel work data. This allows personnel combination optimization to move beyond simply adding individual skills to a comprehensive consideration of skill complementarity and historical cooperation performance. This enables the selection of personnel combinations with optimal synergy, avoiding redundant skills and poor teamwork that lead to low operational efficiency and maximizing the overall team's combat capability. Finally, by outputting and executing the optimal scheduling plan, the scientific allocation of power grid workers is achieved, fully leveraging the capabilities of each worker and comprehensively improving the overall utilization efficiency of power grid workers.

[0007] As a preferred example of the first aspect, each of the said synergy potential indices is determined by calculation based on the skill set required for each said task and the said historical operation data, including: For any first power grid operator and second power grid operator among the power grid operators, the skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill set of the first person corresponding to the first power grid operator and the skill set of the second person corresponding to the second power grid operator. The historical performance score between the first power grid operator and the second power grid operator is determined based on the historical work data of the first person corresponding to the information of the first power grid operator and the historical work data of the second person corresponding to the information of the second power grid operator. The synergy potential index between the first power grid operator and the second power grid operator is obtained by summing the skill complementarity and the historical performance score.

[0008] In this preferred example, calculating the skill complementarity of any two individuals reflects the suitability of their skill combination for task requirements, reducing skill overlap and wasted resources, as well as capability gaps. Historical performance scores, obtained by combining historical collaboration data, reflect the actual collaborative performance of the personnel. Summing both data yields a synergy potential index, providing a quantitative reference for team personnel combinations, enabling personnel scheduling to better align with actual operational needs, and improving overall team efficiency.

[0009] As a preferred example of the first aspect, determining the skill complementarity between the first power grid operator and the second power grid operator based on the first person's skill set corresponding to the first person and the second person's skill set corresponding to the second person includes: Calculate the intersection and union of skills between the first individual skill set and the second individual skill set, and calculate the skill coverage score based on the skill union, and calculate the skill redundancy penalty coefficient based on the skill union and the skill intersection. The skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill coverage score and the skill redundancy penalty coefficient.

[0010] In this preferred example, the skill coverage score is obtained by calculating the intersection and union of the skills of two individuals, which reflects the degree to which the skill combination of the two individuals covers the skills required for the task. Simultaneously, the skill redundancy penalty coefficient is calculated to reflect the resource waste caused by skill overlap. Combining these two indicators to determine skill complementarity allows for a more reasonable evaluation of the merits of personnel skill combinations, providing a basis for team member selection and improving the efficiency of personnel skill utilization.

[0011] As a preferred example of the first aspect, determining the historical performance score between the first power grid operator and the second power grid operator based on the historical work data of the first person corresponding to the first power grid operator information and the historical work data of the second person corresponding to the second power grid operator information includes: Based on the historical work data of the first individual and the historical work data of the second individual, the cooperation record data between the first power grid operator and the second power grid operator is determined; Based on the standard working hours and actual working hours in the cooperation record data, the historical efficiency factor between the first power grid operator and the second power grid operator is determined, and based on the work quality score in the cooperation record data, the historical quality factor between the first power grid operator and the second power grid operator is determined. Based on preset efficiency weight coefficients and quality weight coefficients, the historical efficiency factor and the historical quality factor are weighted and summed to obtain a summation result. The summation result is then multiplied by a preset cooperation frequency weight to obtain the historical performance score between the first power grid operator and the second power grid operator.

[0012] In this preferred example, by extracting historical collaboration data from two individuals, historical efficiency factors and historical quality factors are calculated from the dimensions of work hours and quality, respectively, reflecting the actual performance of their past collaborations from different perspectives. Introducing adjustable efficiency and quality weight coefficients allows for adaptation to the needs of different tasks. Combining collaboration frequency weights in the calculation reflects the reliability of the data. The final historical performance score objectively reflects the effectiveness of cooperation between personnel, providing a reference for team composition and helping to improve task completion.

[0013] As a preferred example of the first aspect, the step of selecting the neighborhood move operator for use in the current iteration from the neighborhood move operator library based on the improvement rate includes: If the improvement rate is greater than or equal to the first preset threshold, then the combined exchange operator is selected from the neighborhood move operator library as the neighborhood move operator to be used in this round of iteration; If the improvement rate is less than the first preset threshold and greater than the second preset threshold, then the single-point exchange operator is selected from the neighborhood movement operator library as the neighborhood movement operator to be used in this round of iteration; If the improvement rate is less than or equal to the second preset threshold, then the perturbation exchange operator is selected from the neighborhood mover library as the neighborhood mover operator to be used in this iteration.

[0014] In this preferred example, different intervals are defined based on the rate of improvement of the solution during the iteration process, and different neighborhood movement operators are selected accordingly. When the solution quality improves rapidly, a combined exchange operator is used to optimize the team's internal collaboration structure; when the improvement rate is moderate, a single-point exchange operator is used for fine-tuning local adjustments; and when the improvement stagnates, a perturbation exchange operator is used to jump out of the current search region. This adaptive selection method can match the needs of different search stages, shorten the scheduling scheme generation time, and improve the rationality of personnel combination.

[0015] As a preferred example of the first aspect, updating the personnel set of the current iteration according to the neighborhood movement operator to obtain the personnel set of the next iteration includes: The neighborhood mover operator is used to transform the current set of personnel to generate several candidate sets. The fitness of each candidate set is calculated, and the candidate set with the highest fitness is taken as the best candidate set. Determine whether the move operation of the best candidate set is in the taboo list of the current iteration; if it is not in the taboo list, then use the best candidate set as the personnel set for the next iteration, and add the inverse operation of the move operation that generated the best candidate set to the taboo list. If the best candidate set is in the taboo list, then determine whether the fitness of the best candidate set is greater than the fitness of the best candidate set found so far. If so, then the best candidate set is used as the candidate set for the next iteration.

[0016] In this preferred example, generating a candidate set using the neighborhood move operator and selecting the candidate with the highest fitness as the best candidate guides the search towards a better outcome. Introducing a tabu list and recording the inverse operation of the move operation avoids repeatedly searching for the same personnel combination and reduces ineffective computation. Setting a clemency criterion allows the best candidate from a tabu to be used even if it is better than the historical best, preventing the omission of better personnel combinations and helping the algorithm find a more reasonable scheduling scheme.

[0017] As a preferred example of the first aspect, the transformation of the current iteration's personnel set according to the neighborhood movement operator to generate several candidate personnel sets includes: If the neighborhood movement operator is the combined exchange operator, then the average value of the collaboration potential index between any person in the current iteration's personnel set and all other people in the current iteration's personnel set is calculated to obtain the internal collaboration degree corresponding to that person; the person with the lowest internal collaboration degree in the personnel set is determined as the person to be replaced; each person outside the current iteration's personnel set is taken as a candidate replacement person in turn, and the person to be replaced is replaced to obtain the corresponding set of undetermined personnel, and all sets of undetermined personnel are taken as the candidate personnel sets generated by the combined exchange operator.

[0018] In this preferred example, by calculating the internal synergy of team members, individuals with weak synergy are identified as those to be replaced. Then, replacing these individuals generates a set of all possible candidates. This targeted replacement method avoids the blindness of random exchanges, directly improves the team's internal synergy, and generates a comprehensive candidate set, providing a basis for subsequent screening and helping to obtain a more reasonable personnel combination, thereby improving the overall operational efficiency of the team.

[0019] As a preferred example of the first aspect, the transformation of the current iteration's personnel set according to the neighborhood movement operator to generate several candidate personnel sets includes: If the neighborhood move operator is the single-point exchange operator, then one person is randomly selected from outside the current iteration's personnel set and exchanged with one person randomly selected from within the current iteration's personnel set to obtain each candidate personnel set.

[0020] In this preferred example, a corresponding candidate personnel set is generated by randomly selecting personnel from within and outside the existing personnel set and exchanging them one-to-one. This random pairwise exchange method allows for a small-scale local traversal search around the existing personnel combinations, smoothly fine-tuning the team composition. Combined with an iterative optimization process, this approach gradually refines the existing personnel configuration structure, fills in optimization gaps in local personnel pairings, provides diverse candidate solutions for continuous algorithm iteration and optimization, and helps to steadily optimize the team configuration of power grid workers.

[0021] As a preferred example of the first aspect, the transformation of the current iteration's personnel set according to the neighborhood movement operator to generate several candidate personnel sets includes: If the neighborhood move operator is the perturbation exchange operator, then a preset number of people are randomly removed from the current set of people, and then the same number of people are randomly selected from outside the set of people after the removal to supplement the set of people, thus obtaining each set of candidate people.

[0022] In this preferred example, a predetermined number of personnel are first randomly removed from the current personnel set, and then an equal number of personnel are added from outside to generate a candidate set. By replacing personnel in batches, the fixed structure of existing personnel combinations is broken, broadening the search scope for personnel configuration. This overall reconstruction mode can break free from the limitations of the original personnel combinations, enrich the types of candidate solutions with an iterative optimization mechanism, and avoid the algorithm remaining stuck in a single local combination for a long time, providing more diverse team formation options for power grid operation personnel scheduling.

[0023] In summary, this application provides basic data support for personnel scheduling by acquiring power grid operation task information, including the number of personnel required for the task and the skill set, as well as schedulable personnel information, including personnel skill sets and historical operation data. Secondly, it uses a tabu search algorithm to iteratively optimize the initial personnel set, enabling a systematic global search within a massive personnel combination space. This replaces the blindness of traditional manual scheduling or simple rule-based scheduling, effectively improving the search capability for optimal personnel combinations. Furthermore, in each iteration, it adaptively selects a neighborhood movement operator based on the improvement rate of the previous iteration, breaking through the limitations of the single neighborhood movement strategy of the traditional tabu search algorithm. It uses efficient operators to accelerate the discovery of high-quality solutions during the rapid improvement phase of the search and strong perturbation operators to exit the search during the stagnant phase. Local optima significantly accelerated algorithm convergence, shortened scheduling decision cycles, and improved the quality of the final scheduling scheme. Furthermore, a neighborhood movement operator library was constructed based on a collaborative potential index calculated by combining the skill set required for the task with historical personnel work data. This allows personnel combination optimization to move beyond simply adding individual skills to a comprehensive consideration of skill complementarity and historical cooperation performance. This enables the selection of personnel combinations with optimal synergy, avoiding redundant skills and poor teamwork that lead to low operational efficiency and maximizing the overall team's combat capability. Finally, by outputting and executing the optimal scheduling scheme, the scientific allocation of power grid workers was achieved, fully leveraging the capabilities of each worker and comprehensively improving the overall utilization efficiency of power grid workers.

[0024] Secondly, the present invention provides a dispatching device for power grid operators, comprising: a first dispatching module, a second dispatching module and a third dispatching module; As a preferred example of the second aspect, each of the said synergy potential indices is determined by calculation based on the skill set required for each said task and each of the said historical task data, including: For any first power grid operator and second power grid operator among the power grid operators, the skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill set of the first person corresponding to the first power grid operator and the skill set of the second person corresponding to the second power grid operator. The historical performance score between the first power grid operator and the second power grid operator is determined based on the historical work data of the first person corresponding to the information of the first power grid operator and the historical work data of the second person corresponding to the information of the second power grid operator. The synergy potential index between the first power grid operator and the second power grid operator is obtained by summing the skill complementarity and the historical performance score.

[0025] As a preferred example of the second aspect, determining the skill complementarity between the first power grid operator and the second power grid operator based on the first person's skill set corresponding to the first power grid operator and the second person's skill set corresponding to the second power grid operator includes: Calculate the intersection and union of skills between the first individual skill set and the second individual skill set, and calculate the skill coverage score based on the skill union, and calculate the skill redundancy penalty coefficient based on the skill union and the skill intersection. The skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill coverage score and the skill redundancy penalty coefficient.

[0026] As a preferred example of the second aspect, determining the historical performance score between the first power grid operator and the second power grid operator based on the historical work data of the first person corresponding to the first power grid operator information and the historical work data of the second person corresponding to the second power grid operator information includes: Based on the historical work data of the first individual and the historical work data of the second individual, the cooperation record data between the first power grid operator and the second power grid operator is determined; Based on the standard working hours and actual working hours in the cooperation record data, the historical efficiency factor between the first power grid operator and the second power grid operator is determined, and based on the work quality score in the cooperation record data, the historical quality factor between the first power grid operator and the second power grid operator is determined. Based on preset efficiency weight coefficients and quality weight coefficients, the historical efficiency factor and the historical quality factor are weighted and summed to obtain a summation result. The summation result is then multiplied by a preset cooperation frequency weight to obtain the historical performance score between the first power grid operator and the second power grid operator.

[0027] As a preferred example of the second aspect, the step of selecting the neighborhood move operator for the current iteration from the neighborhood move operator library based on the improvement rate includes: If the improvement rate is greater than or equal to the first preset threshold, then the combined exchange operator is selected from the neighborhood move operator library as the neighborhood move operator to be used in this round of iteration; If the improvement rate is less than the first preset threshold and greater than the second preset threshold, then the single-point exchange operator is selected from the neighborhood movement operator library as the neighborhood movement operator to be used in this round of iteration; If the improvement rate is less than or equal to the second preset threshold, then the perturbation exchange operator is selected from the neighborhood mover library as the neighborhood mover operator to be used in this iteration.

[0028] As a preferred example of the second aspect, updating the personnel set of the current iteration according to the neighborhood movement operator to obtain the personnel set of the next iteration includes: The neighborhood mover operator is used to transform the current set of personnel to generate several candidate sets. The fitness of each candidate set is calculated, and the candidate set with the highest fitness is taken as the best candidate set. Determine whether the move operation of the best candidate set is in the taboo list of the current iteration; if it is not in the taboo list, then use the best candidate set as the personnel set for the next iteration, and add the inverse operation of the move operation that generated the best candidate set to the taboo list. If the best candidate set is in the taboo list, then determine whether the fitness of the best candidate set is greater than the fitness of the best candidate set found so far. If so, then the best candidate set is used as the candidate set for the next iteration.

[0029] As a preferred example of the second aspect, the transformation of the current iteration's personnel set according to the neighborhood movement operator to generate several candidate personnel sets includes: If the neighborhood movement operator is the combined exchange operator, then the average value of the collaboration potential index between any person in the current iteration's personnel set and all other people in the current iteration's personnel set is calculated to obtain the internal collaboration degree corresponding to that person; the person with the lowest internal collaboration degree in the personnel set is determined as the person to be replaced; each person outside the current iteration's personnel set is taken as a candidate replacement person in turn, and the person to be replaced is replaced to obtain the corresponding set of undetermined personnel, and all sets of undetermined personnel are taken as the candidate personnel sets generated by the combined exchange operator.

[0030] As a preferred example of the second aspect, the transformation of the current iteration's personnel set according to the neighborhood movement operator to generate several candidate personnel sets includes: If the neighborhood move operator is the single-point exchange operator, then one person is randomly selected from outside the current iteration's personnel set and exchanged with one person randomly selected from within the current iteration's personnel set to obtain each candidate personnel set.

[0031] As a preferred example of the second aspect, the transformation of the current iteration's personnel set according to the neighborhood movement operator to generate several candidate personnel sets includes: If the neighborhood move operator is the perturbation exchange operator, then a preset number of people are randomly removed from the current set of people, and then the same number of people are randomly selected from outside the set of people after the removal to supplement the set of people, thus obtaining each set of candidate people.

[0032] In summary, this application provides basic data support for personnel scheduling by acquiring power grid operation task information, including the number of personnel required for the task and the skill set, as well as schedulable personnel information, including personnel skill sets and historical operation data. Secondly, it uses a tabu search algorithm to iteratively optimize the initial personnel set, enabling a systematic global search within a massive personnel combination space. This replaces the blindness of traditional manual scheduling or simple rule-based scheduling, effectively improving the search capability for optimal personnel combinations. Furthermore, in each iteration, it adaptively selects a neighborhood movement operator based on the improvement rate of the previous iteration, breaking through the limitations of the single neighborhood movement strategy of the traditional tabu search algorithm. It uses efficient operators to accelerate the discovery of high-quality solutions during the rapid improvement phase of the search and strong perturbation operators to exit the search during the stagnant phase. Local optima significantly accelerated algorithm convergence, shortened scheduling decision cycles, and improved the quality of the final scheduling scheme. Furthermore, a neighborhood movement operator library was constructed based on a collaborative potential index calculated by combining the skill set required for the task with historical personnel work data. This allows personnel combination optimization to move beyond simply adding individual skills to a comprehensive consideration of skill complementarity and historical cooperation performance. This enables the selection of personnel combinations with optimal synergy, avoiding redundant skills and poor teamwork that lead to low operational efficiency and maximizing the overall team's combat capability. Finally, by outputting and executing the optimal scheduling scheme, the scientific allocation of power grid workers was achieved, fully leveraging the capabilities of each worker and comprehensively improving the overall utilization efficiency of power grid workers.

[0033] Another embodiment of this application also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps of the power grid operator scheduling method of this application.

[0034] Another embodiment of this application also provides a computer-readable storage medium item, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform steps such as the dispatching method for power grid operators of this application. Attached Figure Description

[0035] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0036] Figure 1 A flowchart illustrating one embodiment of a method for dispatching power grid workers provided by the present invention; Figure 2 This diagram illustrates the changes in fitness of an adaptive TS algorithm and a conventional TS algorithm with the number of iterations, as shown in an embodiment of a power grid operator scheduling method provided by the present invention. Figure 3 This is a schematic diagram illustrating the selection of the neighborhood mover operator to be used in the current iteration from the operator library, as an embodiment of a scheduling method for power grid workers provided by the present invention. Figure 4 The optimal personnel scheduling solution found by the adaptive TS algorithm and the ordinary TS algorithm in this power grid operation is shown in the following quantitative diagrams: one embodiment of the power grid operation personnel scheduling method provided by the present invention; Figure 5 This is a module structure diagram of one embodiment of a dispatching device for power grid workers provided by the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0039] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0040] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0041] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0042] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0043] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0044] Example 1 Please refer to Figure 1 To address the problem of low personnel utilization efficiency in existing power grid worker scheduling schemes, this application provides a power grid worker scheduling method, comprising: S1. Obtain information on the power grid operation tasks to be executed and the personnel information corresponding to all currently schedulable power grid operation personnel, wherein the power grid operation task information includes the number of personnel required for the task and the set of skills required for the task, and the personnel information includes the set of skills and historical operation data; Specifically, in actual operation scenarios such as daily operation and maintenance and emergency repair of the power grid, complete attribute information of the power grid operation tasks to be implemented is directly collected. The core of the task information includes the number of personnel required for the task, the set of skills required for the task, and also includes the importance weight of each skill. The sum of the importance weights of all skills is limited to 1, which is used for subsequent personnel matching and team capability scoring calculation.

[0045] In actual operations, the skill set required for tasks covers common power grid operation specialties, typically including high-voltage operation, relay protection, and drone inspection. This set can be expanded or reduced based on actual on-site needs. Each skill is assigned a corresponding weight based on its hazard level and criticality. For example, when the required skill set for a task is {high-voltage operation, relay protection, drone inspection}, the weight for high-voltage operation is set to 0.35, the weight for relay protection to 0.45, and the weight for drone inspection to 0.2, satisfying the rule that the total weight is 1. This provides a benchmark for subsequent quantitative calculations of personnel skill coverage and skill complementarity.

[0046] Next, the basic information and historical operation data of all personnel currently in a dispatchable state and capable of participating in this power grid operation task are collected in batches. The personnel information mainly includes individual skill sets, personnel experience levels, and complete historical operation data, as detailed below: Record the list of professional skills possessed by each dispatchable operator, clarifying which power grid operation-specific skills the personnel have; at the same time, mark the personnel's experience level, uniformly divided into three levels: senior technician, intermediate technician, and junior technician, which will be used for experience matching and scoring when forming operation teams in the future, and adapt to the requirements of power grid operation personnel configuration management of experienced mentors and tiered teams.

[0047] The system retrieves all historical operation log data from the historical operation database in the system backend. The database records the core information of each completed power grid operation, including: unique historical operation ID, list of participants for each operation, estimated working hours according to the standard, actual working hours of the operation, and operation quality score. The operation quality score is uniformly evaluated by the power grid acceptance department, and the score range is fixed at [1,5].

[0048] S2. Based on the number of personnel required for the task, a corresponding number of personnel are randomly selected from the power grid operation personnel to form an initial personnel set. A tabu search algorithm is used to iteratively optimize the initial personnel set until the current iteration reaches a preset maximum iteration count. The personnel set of the current iteration is then used as the power grid operation personnel scheduling scheme for the task to be executed. In each iteration, the improvement rate corresponding to the previous iteration is calculated based on the skill set required for the task and the personnel set of the previous iteration. A neighborhood movement operator is selected from the neighborhood movement operator library for this iteration based on the improvement rate. The personnel set of the current iteration is then updated based on the neighborhood movement operator to obtain the personnel set for the next iteration. The neighborhood movement operator library is constructed based on various collaborative potential indices. The neighborhood movement operator library includes combined exchange operators, single-point exchange operators, and disturbance exchange operators. Each collaborative potential index is determined based on the skill set required for each task and historical operation data. In some embodiments, each of the synergy potential indices is determined by calculation based on the skill set required for each of the tasks and historical task data, including: For any first power grid operator and second power grid operator among the power grid operators, the skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill set of the first person corresponding to the first power grid operator and the skill set of the second person corresponding to the second power grid operator. The historical performance score between the first power grid operator and the second power grid operator is determined based on the historical work data of the first person corresponding to the information of the first power grid operator and the historical work data of the second person corresponding to the information of the second power grid operator. The synergy potential index between the first power grid operator and the second power grid operator is obtained by summing the skill complementarity and the historical performance score.

[0049] In some embodiments, determining the skill complementarity between the first power grid operator and the second power grid operator based on the first person's skill set corresponding to the first power grid operator and the second person's skill set corresponding to the second power grid operator includes: Calculate the intersection and union of skills between the first individual skill set and the second individual skill set, and calculate the skill coverage score based on the skill union, and calculate the skill redundancy penalty coefficient based on the skill union and the skill intersection. The skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill coverage score and the skill redundancy penalty coefficient.

[0050] Specifically, determining the skill complementarity between the first power grid operator and the second power grid operator based on the first person's skill set and the second person's skill set can be implemented through the following preferred scheme: For any two people and personnel Acquisition personnel Skill set and personnel Skill set Skills combined Let represent the set of unique skills possessed by both individuals; calculate the intersection of the union of these skills and the set of skills required for the task, where represents the overlapping skills between the unique skills possessed by both individuals and the set of skills required for the task; calculate the sum of the importance weights of all skills in the intersection. Calculate the sum of the importance weights of all skills in the skill set required for the task. ,Will and The ratio of personnel and personnel The skill coverage score between the two individuals, ranging from 0 to 1, is used to assess how well the pair meets the skill requirements for the task.

[0051] Furthermore, firstly, acquire personnel. Skill set and personnel Skill set Skill overlap , represents the set of overlapping skills between two people; calculate the union of skills. The number of skills and the intersection of skills The ratio of the number of skills in a person's character set is obtained by comparing the number of overlapping skills between two people to the total number of unique skills they both possess. and personnel The skill redundancy penalty, with a value between 0 and 1, is used to assess how much unnecessary skill overlap exists in a pair.

[0052] Furthermore, based on skill coverage scores and skill redundancy penalties, personnel calculations are performed. and personnel The complementarity of skills between them is calculated using the following formula: ; in, For personnel and personnel The complementarity of skills between them; For personnel and personnel Skill coverage score between For personnel and personnel Skill redundancy penalty.

[0053] The final skill complementarity score is directly proportional to the skill coverage score and inversely proportional to the skill redundancy penalty. This complementarity is achieved when two players can cover all important task skills and there is minimal skill overlap between them. Approaching 1 and When the value approaches 0, the complementarity of the two skills is at its highest.

[0054] It should be noted that by comprehensively calculating the coverage score of the two personnel's task skills and the redundancy penalty between the two personnel's skills, the skill complementarity between the two personnel can be calculated. This allows for a more refined evaluation of the effectiveness of personnel combinations: it can identify strong combinations where "1+1>2" and avoid overlapping capabilities where "1+1<2". This provides a data basis for building efficient, well-rounded teams that do not waste human resources.

[0055] In some embodiments, determining the historical performance score between the first power grid operator and the second power grid operator based on the historical work data of the first person corresponding to the first power grid operator information and the historical work data of the second person corresponding to the second power grid operator information includes: Based on the historical work data of the first individual and the historical work data of the second individual, the cooperation record data between the first power grid operator and the second power grid operator is determined; Based on the standard working hours and actual working hours in the cooperation record data, the historical efficiency factor between the first power grid operator and the second power grid operator is determined, and based on the work quality score in the cooperation record data, the historical quality factor between the first power grid operator and the second power grid operator is determined. Based on preset efficiency weight coefficients and quality weight coefficients, the historical efficiency factor and the historical quality factor are weighted and summed to obtain a summation result. The summation result is then multiplied by a preset cooperation frequency weight to obtain the historical performance score between the first power grid operator and the second power grid operator.

[0056] Specifically, determining the historical performance score between the first power grid operator and the second power grid operator based on the historical work data of the first person corresponding to the first power grid operator information and the historical work data of the second person corresponding to the second power grid operator information can be implemented through the following preferred scheme: From the historical task database, filter out participants whose names are included in the participant list. and personnel All historical work records, as personnel and personnel The collaboration records; calculating the ratio of the standard estimated working hours to the actual working hours for each collaboration record, as a measure of personnel... and personnel The efficiency of each collaboration, calculated by the personnel and personnel The average efficiency of all collaborations, as a measure of personnel. and personnel The historical efficiency factor is used to evaluate the speed at which two people can complete a task together. If the historical efficiency factor is greater than 1, it means that the average efficiency of the two people working together is higher than the standard.

[0057] It should be noted that if personnel and personnel If there is no record of cooperation, then the personnel and personnel The historical efficiency factor between them is 0.5, indicating that the history of cooperation is unknown.

[0058] Furthermore, computing personnel and personnel The mean of the work quality scores for all collaborative records is used, and then the mean is normalized using the maximum work quality score to obtain the personnel score. and personnel The historical quality factor is used to evaluate the quality of tasks completed by two people working together.

[0059] Furthermore, based on personnel and personnel All collaborations, calculated by personnel and personnel Cooperation frequency weights , For personnel and personnel The total number of collaboration records represents the number of times the two individuals collaborated. This represents the maximum number of collaborations between all personnel in the historical task database. The function is the natural logarithm; the frequency of collaboration weights reflects the importance of the number of collaborations—the more collaborations, the more reliable the data. A logarithmic function is used to smooth the impact of the number of collaborations and avoid extreme values.

[0060] Next, based on the collaboration efficiency, collaboration quality, and collaboration frequency in the two individuals' historical collaboration records, their collaborative historical performance scores are calculated. The specific calculation formula is as follows: ; in, For personnel and personnel Historical performance scores between them; For personnel and personnel Historical efficiency factors between; For personnel and personnel Historical quality factors between For personnel and personnel The frequency weight of cooperation between them; and These are the weighting coefficients for efficiency and quality, respectively. It can be adjusted according to business priorities. For example, for emergency repairs, settings can be configured. , .

[0061] The final collaborative historical performance score is directly proportional to historical work efficiency, work quality, and the number of collaborations. The faster and better a pair of partners completes a task, and the more often they collaborate, the higher their collaborative historical performance score will be.

[0062] In some embodiments, selecting the neighborhood move operator to be used in the current iteration from the neighborhood move operator library based on the improvement rate includes: If the improvement rate is greater than or equal to the first preset threshold, then the combined exchange operator is selected from the neighborhood move operator library as the neighborhood move operator to be used in this round of iteration; If the improvement rate is less than the first preset threshold and greater than the second preset threshold, then the single-point exchange operator is selected from the neighborhood movement operator library as the neighborhood movement operator to be used in this round of iteration; If the improvement rate is less than or equal to the second preset threshold, then the perturbation exchange operator is selected from the neighborhood mover library as the neighborhood mover operator to be used in this iteration.

[0063] In some embodiments, updating the personnel set of the current iteration according to the neighborhood movement operator to obtain the personnel set of the next iteration includes: The neighborhood mover operator is used to transform the current set of personnel to generate several candidate sets. The fitness of each candidate set is calculated, and the candidate set with the highest fitness is taken as the best candidate set. Determine whether the move operation of the best candidate set is in the taboo list of the current iteration; if it is not in the taboo list, then use the best candidate set as the personnel set for the next iteration, and add the inverse operation of the move operation that generated the best candidate set to the taboo list. If the best candidate set is in the taboo list, then determine whether the fitness of the best candidate set is greater than the fitness of the best candidate set found so far. If so, then the best candidate set is used as the candidate set for the next iteration.

[0064] Specifically, the solution in each iteration is a set of... A team of 10 people The number of personnel required for the task; initially, randomly select from all currently available personnel. The initial team consisted of [number] people.

[0065] Regarding the first The team corresponding to the solution in the nth iteration will... The sum of the team's skill coverage score and experience ratio score corresponding to the solution at the next iteration is used as the value of the solution at the next iteration. The fitness of the solution at the nth iteration. Calculate the fitness of the solution at the nth iteration. The improvement rate of the solution in the next iteration is specifically calculated as follows: ; in, For the first The rate of improvement of the solution in the next iteration; , The first Second and third The fitness of the solution at the next iteration; To evaluate the window length. This is a time span parameter used to calculate the rate of improvement of a solution. It represents the number of historical iterations the algorithm reviews when determining whether it has made significant progress or stagnated. This is achieved by observing recent... The changing trend of the solutions in each iteration is used to smooth out the random fluctuations in a single iteration, thereby more accurately evaluating the overall search state of the algorithm; if If the value is too small, the improvement rate will be too sensitive to single random results, leading to excessively frequent and unstable operator switching; if... If the value is too large, the algorithm's response to state changes will be too sluggish. Therefore, The value range is [4, 10]. In the scenario of this invention, Setting it to 5 effectively filters out fluctuations while ensuring the algorithm is sufficiently sensitive to state changes, thus improving speed. A higher value indicates significant improvement in the algorithm and a faster speed. If the value approaches 0, it indicates that the algorithm has stalled.

[0066] In some embodiments, the step of transforming the current set of personnel according to the neighborhood movement operator to generate several sets of candidate personnel includes: If the neighborhood movement operator is the combined exchange operator, then the average value of the collaboration potential index between any person in the current iteration's personnel set and all other people in the current iteration's personnel set is calculated to obtain the internal collaboration degree corresponding to that person; the person with the lowest internal collaboration degree in the personnel set is determined as the person to be replaced; each person outside the current iteration's personnel set is taken as a candidate replacement person in turn, and the person to be replaced is replaced to obtain the corresponding set of undetermined personnel, and all sets of undetermined personnel are taken as the candidate personnel sets generated by the combined exchange operator.

[0067] In some embodiments, the step of transforming the current set of personnel according to the neighborhood movement operator to generate several sets of candidate personnel includes: If the neighborhood move operator is the single-point exchange operator, then one person is randomly selected from outside the current iteration's personnel set and exchanged with one person randomly selected from within the current iteration's personnel set to obtain each candidate personnel set.

[0068] In some embodiments, the step of transforming the current set of personnel according to the neighborhood movement operator to generate several sets of candidate personnel includes: If the neighborhood move operator is the perturbation exchange operator, then a preset number of people are randomly removed from the current set of people, and then the same number of people are randomly selected from outside the set of people after the removal to supplement the set of people, thus obtaining each set of candidate people.

[0069] S3. Dispatch each of the power grid operators according to the power grid operator dispatching plan.

[0070] Furthermore, to verify the effectiveness, convergence performance, and overall superiority or inferiority of the personnel scheduling scheme in the embodiments of this application, a simulation comparison experiment was conducted to verify and analyze the effects. The adaptive tabu search (adaptive TS) algorithm of this application and the ordinary traditional TS algorithm were used to iteratively optimize the scheduling scheme of power grid workers. The fitness changes of the solution in each iteration, the switching process of the algorithm's adaptive operators, and the comparison results of multi-dimensional indicators of the final scheduling scheme were recorded, as shown in the figure below. Figure 2 , Figure 3 and Figure 4 As shown.

[0071] Figure 2This diagram illustrates the changes in fitness of the adaptive TS algorithm and the ordinary TS algorithm with the number of iterations. The red curve represents the fitness change of the solution in the adaptive TS algorithm during the iteration process, while the blue curve represents the fitness change of the ordinary TS algorithm. The curve trends show that the final steady-state plateau height of the algorithm in this application is significantly higher than that of the ordinary TS algorithm in the later stages of iteration. This indicates that the optimal personnel scheduling solution output by the method in this application is superior in terms of overall quality, including skill adaptation, personnel collaboration, and experience allocation. Furthermore, the adaptive TS algorithm has a steeper slope and faster ascent speed in the early and middle stages, enabling it to find high-quality scheduling solutions more quickly. The algorithm's convergence efficiency and optimization speed are significantly better than traditional algorithms.

[0072] Figure 3 This diagram illustrates the adaptive selection of neighborhood movers from the operator library based on the improvement rate of the iterative solution. The step lines in the diagram dynamically jump between three levels: collaborative construction operator, structural reconstruction operator, and fine-tuning operator, fully explaining the algorithm's adaptive operator selection logic: when the quality of the algorithm's iterative solution improves rapidly and is in a rapid breakthrough phase, the collaborative construction operator is automatically selected to conduct local depth mining; when the solution quality stagnates for a long time and the search gets stuck in a local optimum, the structural reconstruction operator is automatically switched to destroy and rebuild the team structure, escaping the local optimum interval; in other stable iteration phases, the fine-tuning operator is selected to perform small-scale neighborhood searches to ensure stable convergence, realizing intelligent and dynamic adaptation of the search strategy.

[0073] Figure 4 This diagram illustrates a multi-dimensional comparison of the optimal scheduling schemes of the adaptive TS algorithm and the ordinary TS algorithm, comparing them horizontally across three core dimensions: skill coverage score, experience allocation score, and internal team collaboration. It can be seen that the adaptive TS algorithm of this application exhibits a particularly strong advantage in the internal collaboration dimension, thanks to the targeted optimization design of the collaboration potential index and the collaboration construction operator. Simultaneously, it also outperforms the ordinary TS algorithm in the two key indicators of skill coverage and experience allocation. This method, while considering personnel skill matching and a reasonable allocation of operational experience, significantly improves the collaborative adaptability of personnel within the operational team, achieving a comprehensive enhancement of the overall capabilities of the power grid operation scheduling team.

[0074] In summary, this application provides basic data support for personnel scheduling by acquiring power grid operation task information, including the number of personnel required for the task and the skill set, as well as schedulable personnel information, including personnel skill sets and historical operation data. Secondly, it uses a tabu search algorithm to iteratively optimize the initial personnel set, enabling a systematic global search within a massive personnel combination space. This replaces the blindness of traditional manual scheduling or simple rule-based scheduling, effectively improving the search capability for optimal personnel combinations. Furthermore, in each iteration, it adaptively selects a neighborhood movement operator based on the improvement rate of the previous iteration, breaking through the limitations of the single neighborhood movement strategy of the traditional tabu search algorithm. It uses efficient operators to accelerate the discovery of high-quality solutions during the rapid improvement phase of the search and strong perturbation operators to exit the search during the stagnant phase. Local optima significantly accelerated algorithm convergence, shortened scheduling decision cycles, and improved the quality of the final scheduling scheme. Furthermore, a neighborhood movement operator library was constructed based on a collaborative potential index calculated by combining the skill set required for the task with historical personnel work data. This allows personnel combination optimization to move beyond simply adding individual skills to a comprehensive consideration of skill complementarity and historical cooperation performance. This enables the selection of personnel combinations with optimal synergy, avoiding redundant skills and poor teamwork that lead to low operational efficiency and maximizing the overall team's combat capability. Finally, by outputting and executing the optimal scheduling scheme, the scientific allocation of power grid workers was achieved, fully leveraging the capabilities of each worker and comprehensively improving the overall utilization efficiency of power grid workers.

[0075] Example 2 like Figure 5 As shown, based on the above method embodiments, corresponding device embodiments are provided; One embodiment of the present invention provides a dispatching device for power grid workers, comprising: a first dispatching module 51, a second dispatching module 52 and a third dispatching module 53; The first scheduling module 51 is used to obtain information on power grid operation tasks to be executed and information on the operators corresponding to all currently schedulable power grid operators. The power grid operation task information includes the number of personnel required for the task and the set of skills required for the task. The operator information includes the set of skills and historical operation data. The second scheduling module 52 is used to randomly select a corresponding number of personnel from the power grid workers according to the number of personnel required for the task, form an initial personnel set, and use a tabu search algorithm to iteratively optimize the initial personnel set until the current iteration reaches a preset maximum iteration number. The personnel set of the current iteration is then used as the power grid worker scheduling scheme for the task to be executed. In each iteration, the improvement rate corresponding to the previous iteration is calculated based on the skill set required for the task and the personnel set of the previous iteration. A neighborhood movement operator is selected from the neighborhood movement operator library for the current iteration based on the improvement rate. The personnel set of the current iteration is then updated based on the neighborhood movement operator to obtain the personnel set for the next iteration. The neighborhood movement operator library is constructed based on various collaborative potential indices, and each collaborative potential index is determined by calculation based on the skill set required for each task and historical work data. The third scheduling module 53 is used to schedule each of the power grid operators according to the power grid operator scheduling plan.

[0076] In some embodiments, each of the synergy potential indices is determined by calculation based on the skill set required for each of the tasks and historical task data, including: For any first power grid operator and second power grid operator among the power grid operators, the skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill set of the first person corresponding to the first power grid operator and the skill set of the second person corresponding to the second power grid operator. The historical performance score between the first power grid operator and the second power grid operator is determined based on the historical work data of the first person corresponding to the information of the first power grid operator and the historical work data of the second person corresponding to the information of the second power grid operator. The synergy potential index between the first power grid operator and the second power grid operator is obtained by summing the skill complementarity and the historical performance score.

[0077] In some embodiments, determining the skill complementarity between the first power grid operator and the second power grid operator based on the first person's skill set corresponding to the first power grid operator and the second person's skill set corresponding to the second power grid operator includes: Calculate the intersection and union of skills between the first individual skill set and the second individual skill set, and calculate the skill coverage score based on the skill union, and calculate the skill redundancy penalty coefficient based on the skill union and the skill intersection. The skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill coverage score and the skill redundancy penalty coefficient.

[0078] In some embodiments, determining the historical performance score between the first power grid operator and the second power grid operator based on the historical work data of the first person corresponding to the first power grid operator information and the historical work data of the second person corresponding to the second power grid operator information includes: Based on the historical work data of the first individual and the historical work data of the second individual, the cooperation record data between the first power grid operator and the second power grid operator is determined; Based on the standard working hours and actual working hours in the cooperation record data, the historical efficiency factor between the first power grid operator and the second power grid operator is determined, and based on the work quality score in the cooperation record data, the historical quality factor between the first power grid operator and the second power grid operator is determined. Based on preset efficiency weight coefficients and quality weight coefficients, the historical efficiency factor and the historical quality factor are weighted and summed to obtain a summation result. The summation result is then multiplied by a preset cooperation frequency weight to obtain the historical performance score between the first power grid operator and the second power grid operator.

[0079] In some embodiments, selecting the neighborhood move operator to be used in the current iteration from the neighborhood move operator library based on the improvement rate includes: If the improvement rate is greater than or equal to the first preset threshold, then the combined exchange operator is selected from the neighborhood move operator library as the neighborhood move operator to be used in this round of iteration; If the improvement rate is less than the first preset threshold and greater than the second preset threshold, then the single-point exchange operator is selected from the neighborhood movement operator library as the neighborhood movement operator to be used in this round of iteration; If the improvement rate is less than or equal to the second preset threshold, then the perturbation exchange operator is selected from the neighborhood mover library as the neighborhood mover operator to be used in this iteration.

[0080] In some embodiments, updating the personnel set of the current iteration according to the neighborhood movement operator to obtain the personnel set of the next iteration includes: The neighborhood mover operator is used to transform the current set of personnel to generate several candidate sets. The fitness of each candidate set is calculated, and the candidate set with the highest fitness is taken as the best candidate set. Determine whether the move operation of the best candidate set is in the taboo list of the current iteration; if it is not in the taboo list, then use the best candidate set as the personnel set for the next iteration, and add the inverse operation of the move operation that generated the best candidate set to the taboo list. If the best candidate set is in the taboo list, then determine whether the fitness of the best candidate set is greater than the fitness of the best candidate set found so far. If so, then the best candidate set is used as the candidate set for the next iteration.

[0081] In some embodiments, the step of transforming the current set of personnel according to the neighborhood movement operator to generate several sets of candidate personnel includes: If the neighborhood movement operator is the combined exchange operator, then the average value of the collaboration potential index between any person in the current iteration's personnel set and all other people in the current iteration's personnel set is calculated to obtain the internal collaboration degree corresponding to that person; the person with the lowest internal collaboration degree in the personnel set is determined as the person to be replaced; each person outside the current iteration's personnel set is taken as a candidate replacement person in turn, and the person to be replaced is replaced to obtain the corresponding set of undetermined personnel, and all sets of undetermined personnel are taken as the candidate personnel sets generated by the combined exchange operator.

[0082] In some embodiments, the step of transforming the current set of personnel according to the neighborhood movement operator to generate several sets of candidate personnel includes: If the neighborhood move operator is the single-point exchange operator, then one person is randomly selected from outside the current iteration's personnel set and exchanged with one person randomly selected from within the current iteration's personnel set to obtain each candidate personnel set.

[0083] In some embodiments, the step of transforming the current set of personnel according to the neighborhood movement operator to generate several sets of candidate personnel includes: If the neighborhood move operator is the perturbation exchange operator, then a preset number of people are randomly removed from the current set of people, and then the same number of people are randomly selected from outside the set of people after the removal to supplement the set of people, thus obtaining each set of candidate people.

[0084] For more detailed steps and working principles of this embodiment, please refer to the relevant description in Embodiment 1, but not limited to these descriptions.

[0085] In summary, this application provides basic data support for personnel scheduling by acquiring power grid operation task information, including the number of personnel required for the task and the skill set, as well as schedulable personnel information, including personnel skill sets and historical operation data. Secondly, it uses a tabu search algorithm to iteratively optimize the initial personnel set, enabling a systematic global search within a massive personnel combination space. This replaces the blindness of traditional manual scheduling or simple rule-based scheduling, effectively improving the search capability for optimal personnel combinations. Furthermore, in each iteration, it adaptively selects a neighborhood movement operator based on the improvement rate of the previous iteration, breaking through the limitations of the single neighborhood movement strategy of the traditional tabu search algorithm. It uses efficient operators to accelerate the discovery of high-quality solutions during the rapid improvement phase of the search and strong perturbation operators to exit the search during the stagnant phase. Local optima significantly accelerated algorithm convergence, shortened scheduling decision cycles, and improved the quality of the final scheduling scheme. Furthermore, a neighborhood movement operator library was constructed based on a collaborative potential index calculated by combining the skill set required for the task with historical personnel work data. This allows personnel combination optimization to move beyond simply adding individual skills to a comprehensive consideration of skill complementarity and historical cooperation performance. This enables the selection of personnel combinations with optimal synergy, avoiding redundant skills and poor teamwork that lead to low operational efficiency and maximizing the overall team's combat capability. Finally, by outputting and executing the optimal scheduling scheme, the scientific allocation of power grid workers was achieved, fully leveraging the capabilities of each worker and comprehensively improving the overall utilization efficiency of power grid workers.

[0086] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided in this application, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0087] Example 3 Based on the above-described embodiments of the power grid operator dispatching method, another embodiment of this application provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the power grid operator dispatching method of any embodiment of this application.

[0088] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete this application. The one or more module units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0089] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0090] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0091] Example 4 Based on the above-described method embodiments, another embodiment of this application provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the power grid operator scheduling method described in any of the above-described method embodiments of this application.

[0092] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

Claims

1. A method for dispatching power grid workers, characterized in that, include: Obtain information on power grid operation tasks to be executed and personnel information corresponding to all currently schedulable power grid operation personnel. The power grid operation task information includes the number of personnel required for the task and the set of skills required for the task. The personnel information includes the set of skills and historical operation data. Based on the number of personnel required for the task, a corresponding number of personnel are randomly selected from the power grid workers to form an initial personnel set. A tabu search algorithm is then used to iteratively optimize this initial personnel set until the current iteration reaches a preset maximum iteration count. The personnel set of the current iteration is then used as the power grid worker scheduling scheme for the task to be executed. In each iteration, the improvement rate corresponding to the previous iteration is calculated based on the skill set required for the task and the personnel set of the previous iteration. A neighborhood movement operator is selected from the neighborhood movement operator library for this iteration based on the improvement rate. The personnel set of the current iteration is then updated based on the neighborhood movement operator to obtain the personnel set for the next iteration. The neighborhood movement operator library is constructed based on various collaborative potential indices. The library includes combined exchange operators, single-point exchange operators, and disturbance exchange operators. Each collaborative potential index is determined based on the skill set required for each task and historical work data. The power grid operators are dispatched according to the power grid operator dispatching plan.

2. The method for dispatching power grid workers as described in claim 1, characterized in that, The aforementioned collaborative potential indices are determined based on the skill set required for each task and the aforementioned historical operational data, including: For any first power grid operator and second power grid operator among the power grid operators, the skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill set of the first person corresponding to the first power grid operator and the skill set of the second person corresponding to the second power grid operator. The historical performance score between the first power grid operator and the second power grid operator is determined based on the historical work data of the first person corresponding to the information of the first power grid operator and the historical work data of the second person corresponding to the information of the second power grid operator. The synergy potential index between the first power grid operator and the second power grid operator is obtained by summing the skill complementarity and the historical performance score.

3. The method for dispatching power grid workers as described in claim 2, characterized in that, The step of determining the skill complementarity between the first power grid operator and the second power grid operator based on the first person's skill set and the second person's skill set includes: Calculate the intersection and union of skills between the first individual skill set and the second individual skill set, and calculate the skill coverage score based on the skill union, and calculate the skill redundancy penalty coefficient based on the skill union and the skill intersection. The skill complementarity between the first power grid operator and the second power grid operator is determined based on the skill coverage score and the skill redundancy penalty coefficient.

4. The method for dispatching power grid workers as described in claim 2, characterized in that, The step of determining the historical performance score between the first power grid operator and the second power grid operator based on the historical work data of the first person corresponding to the first power grid operator information and the historical work data of the second person corresponding to the second power grid operator information includes: Based on the historical work data of the first individual and the historical work data of the second individual, the cooperation record data between the first power grid operator and the second power grid operator is determined; Based on the standard working hours and actual working hours in the cooperation record data, the historical efficiency factor between the first power grid operator and the second power grid operator is determined, and based on the work quality score in the cooperation record data, the historical quality factor between the first power grid operator and the second power grid operator is determined. Based on preset efficiency weight coefficients and quality weight coefficients, the historical efficiency factor and the historical quality factor are weighted and summed to obtain a summation result. The summation result is then multiplied by a preset cooperation frequency weight to obtain the historical performance score between the first power grid operator and the second power grid operator.

5. The method for dispatching power grid workers as described in claim 1, characterized in that, The step of selecting the neighborhood move operator to be used in this iteration from the neighborhood move operator library according to the improvement rate includes: If the improvement rate is greater than or equal to the first preset threshold, then the combined exchange operator is selected from the neighborhood move operator library as the neighborhood move operator to be used in this round of iteration; If the improvement rate is less than the first preset threshold and greater than the second preset threshold, then the single-point exchange operator is selected from the neighborhood movement operator library as the neighborhood movement operator to be used in this round of iteration; If the improvement rate is less than or equal to the second preset threshold, then the perturbation exchange operator is selected from the neighborhood mover library as the neighborhood mover operator to be used in this iteration.

6. The method for dispatching power grid workers as described in claim 1, characterized in that, The step of updating the personnel set of the current iteration according to the neighborhood movement operator to obtain the personnel set of the next iteration includes: The neighborhood mover operator is used to transform the current set of personnel to generate several candidate sets. The fitness of each candidate set is calculated, and the candidate set with the highest fitness is taken as the best candidate set. Determine whether the move operation of the best candidate set is in the taboo list of the current iteration; if it is not in the taboo list, then use the best candidate set as the personnel set for the next iteration, and add the inverse operation of the move operation that generated the best candidate set to the taboo list. If the best candidate set is in the taboo list, then determine whether the fitness of the best candidate set is greater than the fitness of the best candidate set found so far. If so, then the best candidate set is used as the candidate set for the next iteration.

7. The method for dispatching power grid workers as described in claim 6, characterized in that, The process of transforming the current set of personnel according to the neighborhood movement operator to generate several candidate sets includes: If the neighborhood movement operator is the combined exchange operator, then the average value of the collaboration potential index between any person in the current iteration's personnel set and all other people in the current iteration's personnel set is calculated to obtain the internal collaboration degree corresponding to that person; the person with the lowest internal collaboration degree in the personnel set is determined as the person to be replaced; each person outside the current iteration's personnel set is taken as a candidate replacement person in turn, and the person to be replaced is replaced to obtain the corresponding set of undetermined personnel, and all sets of undetermined personnel are taken as the candidate personnel sets generated by the combined exchange operator.

8. The method for dispatching power grid workers as described in claim 6, characterized in that, The process of transforming the current set of personnel according to the neighborhood movement operator to generate several candidate sets includes: If the neighborhood move operator is the single-point exchange operator, then one person is randomly selected from outside the current iteration's personnel set and exchanged with one person randomly selected from within the current iteration's personnel set to obtain each candidate personnel set.

9. The method for dispatching power grid workers as described in claim 6, characterized in that, The process of transforming the current set of personnel according to the neighborhood movement operator to generate several candidate sets includes: If the neighborhood move operator is the perturbation exchange operator, then a preset number of people are randomly removed from the current set of people, and then the same number of people are randomly selected from outside the set of people after the removal to supplement the set of people, thus obtaining each set of candidate people.

10. A dispatching device for power grid operators, characterized in that, include: The first scheduling module, the second scheduling module, and the third scheduling module; The first scheduling module is used to obtain information on power grid operation tasks to be executed and information on the operators corresponding to all currently schedulable power grid operators. The power grid operation task information includes the number of personnel required for the task and the set of skills required for the task. The operator information includes the set of skills and historical operation data. The second scheduling module is used to randomly select a corresponding number of personnel from each of the power grid operation personnel according to the number of personnel required for the task, form an initial personnel set, and use a tabu search algorithm to iteratively optimize the initial personnel set until the current iteration number reaches the preset maximum iteration number. The personnel set of the current iteration is then used as the power grid operation personnel scheduling scheme corresponding to the task to be executed. In each iteration, the improvement rate corresponding to the previous iteration is calculated based on the skill set required for the task and the personnel set of the previous iteration. A neighborhood movement operator is selected from the neighborhood movement operator library for the current iteration based on the improvement rate. The personnel set of the current iteration is then updated based on the neighborhood movement operator to obtain the personnel set for the next iteration. The neighborhood movement operator library is constructed based on various collaborative potential indices, and each collaborative potential index is determined by calculation based on the skill set required for each task and historical operation data. The third scheduling module is used to schedule each of the power grid operators according to the power grid operator scheduling plan.

Images