Electric power personnel scheduling method, system and product
By constructing a task scheduling graph and classification model, the problem of lack of predictability in power task scheduling in existing technologies is solved. It enables the selection of reasonable scheduling schemes from a large talent database, thereby improving the predictability and efficiency of scheduling.
Patent Information
- Application Number
- CN202511015194.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-23
- Publication Date
- 2025-10-31
AI Technical Summary
Existing technologies cannot effectively match the vast talent database, resulting in a lack of predictability in power task scheduling outcomes.
By constructing a task scheduling graph and a trained classification model, reasonable candidate scheduling schemes are selected, and the execution results of the scheduling schemes are predicted to reduce losses.
It enables the selection of reasonable candidate scheduling schemes from a large talent dataset, improving the predictability and efficiency of task scheduling.
Smart Images
Figure CN120875403A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power personnel dispatching, specifically to a power personnel dispatching method, system, and product. Background Technology
[0002] In the power grid system, by establishing talent files to record information on all employees, a complete file system is formed. When scheduling personnel, the relevant information is matched based on the personnel files to select suitable talents for corresponding positions.
[0003] However, in existing technologies, relevant personnel are usually assessed and analyzed by the human resources department, and then corresponding personnel are recommended. However, existing technologies cannot effectively match the huge talent database, and the results of task scheduling lack predictability. Summary of the Invention
[0004] The purpose of this invention is to provide a method, system, and product for dispatching power personnel. First, a task dispatch map is constructed using historical data on power personnel's participation in power tasks. Then, the task dispatch map is used to preliminarily determine the candidate dispatch schemes for the task dispatch set. Finally, a trained classification model is used to determine whether the candidate dispatch schemes can be used as the final dispatch schemes. This allows for the selection of reasonable candidate dispatch schemes from a large talent dataset. Furthermore, the classification model can predict the execution results of tasks under the dispatch schemes in advance, so as to intervene in advance and reduce losses.
[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a power dispatching method, comprising: For each power worker, obtain all power tasks that the power worker participated in; The performance of power personnel in each power task is evaluated based on a pre-built evaluation mechanism, and the current task is determined as suitable for the power personnel based on the evaluation results. Using power personnel as points and the relationship between power personnel and adaptation tasks as edges, a task scheduling graph is constructed. The length of each edge in the task scheduling graph corresponds to the evaluation result to quantify the degree of adaptation between power personnel and adaptation tasks.
[0006] Obtain the task scheduling set to be assigned, and determine the alternative scheduling schemes to assign the task scheduling set to power personnel based on the task scheduling map; The candidate scheduling schemes are input into a pre-trained classification model to predict the qualified category of the candidate scheduling schemes; If the conditions are met, the task scheduling set will be scheduled according to the proposed scheduling scheme; if the conditions are not met, the next available scheme will be determined as the proposed scheduling scheme in descending order of the sum of the side lengths between all power tasks and power personnel.
[0007] Optionally, the evaluation of the performance of power personnel in each power task based on a pre-built evaluation mechanism includes: The importance weight values of each dimension of the evaluation mechanism, as well as the importance weight values of each indicator under each dimension, are determined using fuzzy hierarchical analysis. The weighted sum of the actual scores of each indicator is used to obtain the comprehensive score of the current dimension. The weighted sum of the comprehensive scores of each dimension is used to obtain the evaluation result of the performance. If the evaluation result exceeds the preset threshold, the current task is determined to be the adaptation task of the power personnel.
[0008] Optionally, determining the candidate scheduling schemes for allocating the task scheduling set to power personnel based on the task scheduling map includes: For each power task in the task scheduling set, all corresponding and suitable power personnel are determined based on the task scheduling map to obtain the personnel scheduling set; Based on the task scheduling set and the personnel scheduling set, all power tasks are assigned to the corresponding suitable power personnel to obtain multiple optional solutions; Based on the task scheduling graph, for each possible scheme, the sum of the side lengths between all power tasks and power personnel is calculated to determine the candidate scheduling scheme.
[0009] Optionally, the training process of the classification model includes: The training samples are constructed by taking the vector formed by the correspondence between each power task and power personnel in the task scheduling set as input and the actual recorded task results as the true labels of qualified categories. The classification model is trained using the training samples, and the trained classification model is obtained after the loss function converges.
[0010] Optionally, using the qualified category of the actually recorded task result as the true label includes: If more than a preset proportion of power task records in the task scheduling set are successful, the real label is determined to be qualified; otherwise, the real label is determined to be unqualified.
[0011] Optionally, the classification model is built based on a support vector machine model.
[0012] Optionally, the dimensions of the evaluation mechanism include task experience, personal ability, professional skills, learning ability, and task contribution.
[0013] Optionally, the step of determining the importance weight values of each dimension of the evaluation mechanism, and the importance weight values of each indicator under each dimension, using fuzzy hierarchical analysis includes: When the evaluation result of the evaluation mechanism is used as a higher-level factor, each dimension is used as a lower-level factor; when the dimension is used as a higher-level factor, each indicator is used as a lower-level factor. A priority relationship matrix is established based on pairwise comparisons of the relative importance of lower-level factors to upper-level factors; The priority relation matrix is transformed into a fuzzy consistent matrix using additive consistency. The importance weight value of each lower-level factor under the upper-level factor is determined based on the fuzzy consistency matrix. Secondly, the present invention provides a power personnel dispatching system, comprising: The acquisition module is used to acquire all the power tasks that each power worker has participated in. The determination module is used to evaluate the performance of power personnel in each power task based on a pre-built evaluation mechanism, and determine whether the current task is a suitable task for the power personnel based on the evaluation results. The module is used to construct a task scheduling graph with power personnel as the points and the relationship between power personnel and adaptation tasks as the edges. The allocation module is used to obtain the task scheduling set to be allocated, and to determine the alternative scheduling schemes for allocating the task scheduling set to power personnel based on the task scheduling map. The scheduling module is used to input the candidate scheduling schemes into a pre-trained classification model to predict the qualified category of the candidate scheduling schemes. If the candidate scheduling scheme is qualified, the task scheduling set is scheduled according to the candidate scheduling scheme. If the candidate scheduling scheme is unqualified, the next available scheme is determined as the candidate scheduling scheme in descending order of the sum of the side lengths between all power tasks and power personnel.
[0014] Thirdly, the present invention provides a computer program product including instructions that, when executed by a processor, cause the processor to perform the power personnel dispatching method.
[0015] Compared with existing technologies, this invention has the following advantages: This invention constructs a task scheduling map by using historical data of power personnel's participation in power tasks. Then, based on the sum of the side lengths between all power tasks and power personnel in the optional schemes, it preliminarily filters out candidate scheduling schemes in the task scheduling set through the task scheduling map. Finally, it uses a trained classification model to determine whether the candidate scheduling scheme can be used as the final scheduling scheme. This allows for the selection of reasonable candidate scheduling schemes from a large talent dataset, and the classification model can predict the execution results of tasks under the scheduling scheme in advance, so as to intervene in advance to reduce losses. Attached Figure Description
[0016] Figure 1 This is a flowchart of a power personnel dispatching method in Example 1. Detailed Implementation
[0017] It should be noted that the technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments and specific features described herein are detailed descriptions of the technical solution of the present invention, not limitations thereof. Where there is no conflict, the embodiments and technical features described herein can be combined with each other. The term "and / or" merely describes 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 " / " generally indicates that the preceding and following related objects have an "or" relationship. Example 1
[0018] To make the purpose, technical solution, and advantages of this invention patent clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments.
[0019] Combination Figure 1 This embodiment provides a power personnel dispatching method, which includes: Step S1: For each power worker, obtain all the power tasks they have participated in. Since the allocation of power tasks usually takes into account the educational background and performance evaluation of power workers, the power tasks they have participated in are more representative and provide a reasonable basis for subsequent scheduling.
[0020] Step S2: Based on a pre-built evaluation mechanism, evaluate the performance of each power task participated in by the power personnel, and determine whether the current task is a suitable task for the power personnel based on the evaluation results. In a specific embodiment, fuzzy hierarchical analysis is used to determine the importance weight values of each dimension and the importance weight values of each indicator under each dimension. The weighted sum of the actual scores of each indicator is used to obtain the comprehensive score of the current dimension. The weighted sum of the comprehensive scores of each dimension is used to obtain the evaluation result of the performance. If the evaluation result exceeds a preset threshold, the current task is determined to be a suitable task for the power personnel.
[0021] Step S3: Construct a task scheduling graph with power personnel as points and the relationship between power personnel and adaptation tasks as edges. The length of each edge in the task scheduling graph corresponds to the evaluation result to quantify the degree of adaptation between power personnel and adaptation tasks.
[0022] In this embodiment, the historical matching data of power personnel and power tasks that were originally scattered are represented as a structured knowledge graph. The evaluation result used in step S2 to determine the degree of fit between power personnel and power tasks is quantified by using the length of the connection edge between power personnel and the matching task, so as to serve as the evaluation basis for subsequent candidate scheduling schemes.
[0023] In addition, dispatchers or managers can intuitively view the adaptation relationship network between power personnel and power tasks through the graphical interface of the task scheduling graph. Power tasks with more connecting edges can be understood as hot tasks, and power personnel with more and longer connecting edges can be understood as core personnel, so as to facilitate human intervention in decision-making.
[0024] Step S4: Obtain the task scheduling set to be assigned, and determine the candidate scheduling schemes to assign the task scheduling set to power personnel based on the task scheduling map; In a specific embodiment, for each power task in the task scheduling set, all corresponding and suitable power personnel are determined based on the task scheduling graph to obtain a personnel scheduling set; based on the task scheduling set and the personnel scheduling set, all power tasks are assigned to the corresponding and suitable power personnel to obtain multiple optional schemes; based on the task scheduling graph, for each optional scheme, the sum of the side lengths between all power tasks and power personnel is calculated to determine the candidate scheduling scheme.
[0025] Specifically, this embodiment can quickly identify the power personnel evaluated as suitable for the task type in historical data for each power task in the task scheduling set using the task scheduling graph as an index. This significantly narrows down the range of candidates. Task scheduling requires attempting to assign all new tasks to a specific person in each pool of suitable personnel. In practical applications, since a power task may have multiple suitable personnel, and a single power personnel may be suitable for multiple tasks (but each power task can only be assigned to one power personnel), multiple alternative solutions are obtained. For each generated alternative solution, the connection edges corresponding to power personnel are queried in the task scheduling graph. The sum of the edge lengths represents the overall suitability level of the scheduling solution (the smaller the sum or the larger the weight, the higher the overall suitability). Multiple candidate scheduling solutions are selected in descending order of priority based on the sum of edge lengths, thus completing the pre-screening and sorting before inputting into the classification model. This avoids the classification model being interfered with by a large number of low-quality solutions, reduces the computational burden of the classification model, improves prediction efficiency, and achieves predictive scheduling.
[0026] Step S5: Input the candidate scheduling scheme into the pre-trained classification model to predict the qualified category of the candidate scheduling scheme; if qualified, schedule the task scheduling set according to the candidate scheduling scheme; if unqualified, determine the next optional scheme as the candidate scheduling scheme in descending order of the sum of the side lengths between all power tasks and power personnel.
[0027] The training process of the classification model includes: constructing training samples using a vector formed by the correspondence between each power task and power personnel in the task scheduling set as input, and using the actual recorded task results as the true labels for qualified categories; training the classification model using the training samples, and obtaining the trained classification model after the loss function converges. Using the actual recorded task results as the true labels includes: if more than a preset proportion of power task records in the task scheduling set are successful, then the true label is determined to be qualified; otherwise, the true label is determined to be unqualified. In a specific embodiment, the classification model is a Support Vector Machine (SVM) classification model. The SVM classification model is trained using the training samples until the loss function converges to determine the optimal decision boundary. This embodiment uses a hinge loss function, and further predicts and classifies qualified categories based on the optimal decision boundary.
[0028] In another specific embodiment, step S2 specifically includes: Step S21: Establish a multi-dimensional evaluation mechanism with performance as the overall goal; in this embodiment, the dimensions of the evaluation mechanism include task experience, personal ability, professional skills, learning ability, and task contribution.
[0029] Step S22: Use the fuzzy hierarchical analysis method (AHP) to determine the importance weight values of each dimension, and the importance weight values of each indicator under each dimension; Specifically, when the evaluation result of the evaluation mechanism is used as a higher-level factor, each dimension is used as a lower-level factor; when the dimension is used as a higher-level factor, each indicator is used as a lower-level factor. A priority relationship matrix is established based on pairwise comparisons of the relative importance of lower-level factors to upper-level factors. The priority relationship matrix is a matrix established by pairwise comparisons of the relative importance of lower-level factors to upper-level factors, also known as a fuzzy complementarity matrix. The priority relationship matrix is represented as follows: ; Where R represents the priority relation matrix, This represents the fuzzy relationship between the i-th element and the j-th element in the lower layer. represents the preset importance weight values of the i-th and j-th factors in the lower layer, respectively; n represents the number of lower-layer factors; and represents the difference coefficient. In this embodiment... ; The larger the value, the more importance the decision-maker places on the differences in importance between factors; this will be expressed quantitatively using a scale of 0.1-0.9. The priority relation matrix is transformed into a fuzzy consistent matrix using additive consistency. ; ; ; The importance weight value of each lower-level factor under the upper-level factor is determined based on the fuzzy consistency matrix, specifically including: According to the formula It can be calculated sorted vector ,in, Let represent the importance weight value determined by the i-th factor in the lower level, and 'a' represent the influence factor. The smaller 'a' is, the more the decision-maker values the influence of the importance between factors. The importance weight values of each factor are then derived.
[0030] Step S23: The weighted sum of the actual scores for each indicator yields the comprehensive score for the current dimension. The weighted sum of the comprehensive scores for each dimension then yields the performance evaluation result. This embodiment involves multiple dimensions, providing performance evaluation results based on employee performance at different levels. The formula for calculating the performance evaluation result is:
[0031] in The weight of the Kth dimension, ; The score is for the k-th dimension, with a value between 0 and 10. Bonus points are awarded for special achievements, but the percentage is less than 10% of the total score. Example 2
[0032] Based on the same inventive concept as Embodiment 1, this embodiment provides a power personnel dispatching system, which includes: The acquisition module is used to acquire all the power tasks that each power worker has participated in. The determination module is used to evaluate the performance of power personnel in each power task based on a pre-built evaluation mechanism, and determine whether the current task is a suitable task for the power personnel based on the evaluation results. The module is used to construct a task scheduling graph with power personnel as the points and the relationship between power personnel and adaptation tasks as the edges. The allocation module is used to obtain the task scheduling set to be allocated, and to determine the alternative scheduling schemes for allocating the task scheduling set to power personnel based on the task scheduling map. The scheduling module is used to input the candidate scheduling schemes into a pre-trained classification model to predict the qualified category of the candidate scheduling schemes. If the category is qualified, the task scheduling set is scheduled according to the candidate scheduling scheme. Example 3
[0033] Based on the same inventive concept as Embodiment 1, this embodiment provides a computer program product, including instructions that, when executed by a processor, cause the processor to perform the power personnel dispatching method.
[0034] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0035] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0036] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0037] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0038] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.
Claims
1. A method for dispatching power personnel, characterized in that, include: For each power worker, obtain all power tasks that the power worker participated in; The performance of power personnel in each power task is evaluated based on a pre-built evaluation mechanism, and the current task is determined as suitable for the power personnel based on the evaluation results. Using power personnel as points and the relationship between power personnel and adaptation tasks as edges, a task scheduling graph is constructed. The length of each edge in the task scheduling graph corresponds to the evaluation result to quantify the degree of adaptation between power personnel and adaptation tasks. Obtain the task scheduling set to be assigned, and determine the alternative scheduling schemes to assign the task scheduling set to power personnel based on the task scheduling map; The candidate scheduling schemes are input into a pre-trained classification model to predict the qualified category of the candidate scheduling schemes; If the conditions are met, the task scheduling set will be scheduled according to the proposed scheduling scheme; if the conditions are not met, the next available scheme will be determined as the proposed scheduling scheme in descending order of the sum of the side lengths between all power tasks and power personnel.
2. The power personnel dispatching method according to claim 1, characterized in that, The evaluation of the performance of power personnel in each power task based on the pre-built evaluation mechanism includes: The importance weight values of each dimension of the evaluation mechanism, as well as the importance weight values of each indicator under each dimension, are determined using fuzzy hierarchical analysis. The weighted sum of the actual scores of each indicator is used to obtain the comprehensive score of the current dimension. The weighted sum of the comprehensive scores of each dimension is used to obtain the evaluation result of the performance. If the evaluation result exceeds the preset threshold, the current task is determined to be the adaptation task of the power personnel.
3. The power personnel dispatching method according to claim 1, characterized in that, The step of determining the candidate scheduling schemes for allocating the task scheduling set to power personnel based on the task scheduling map includes: For each power task in the task scheduling set, all corresponding and suitable power personnel are determined based on the task scheduling map to obtain the personnel scheduling set; Based on the task scheduling set and the personnel scheduling set, all power tasks are assigned to the corresponding suitable power personnel to obtain multiple optional solutions; Based on the task scheduling graph, for each possible scheme, the sum of the side lengths between all power tasks and power personnel is calculated to determine the candidate scheduling scheme.
4. The power personnel dispatching method according to claim 1, characterized in that, The training process of the classification model includes: The training samples are constructed by taking the vector formed by the correspondence between each power task and power personnel in the task scheduling set as input and the actual recorded task results as the true labels of qualified categories. The classification model is trained using the training samples, and the trained classification model is obtained after the loss function converges.
5. The power personnel dispatching method according to claim 4, characterized in that, The true labels that are qualified categories based on the actual recorded task results include: If more than a preset proportion of power task records in the task scheduling set are successful, the real label is determined to be qualified; otherwise, the real label is determined to be unqualified.
6. The power personnel dispatching method according to claim 4, characterized in that, The classification model is built based on the support vector machine model.
7. The power personnel dispatching method according to claim 2, characterized in that, The evaluation mechanism includes various dimensions such as task experience, personal ability, professional skills, learning ability, and task contribution.
8. The power personnel dispatching method according to claim 7, characterized in that, The steps for determining the importance weights of each dimension of the evaluation mechanism, and the importance weights of each indicator under each dimension, using fuzzy hierarchical analysis include: When the evaluation result of the evaluation mechanism is used as a higher-level factor, each dimension is used as a lower-level factor; when the dimension is used as a higher-level factor, each indicator is used as a lower-level factor. A priority relationship matrix is established based on pairwise comparisons of the relative importance of lower-level factors to upper-level factors; The priority relation matrix is transformed into a fuzzy consistent matrix using additive consistency. The importance weight value of each lower-level factor under the upper-level factor is determined based on the fuzzy consistency matrix.
9. A power personnel dispatching system, characterized in that, include: The acquisition module is used to acquire all the power tasks that each power worker has participated in. The determination module is used to evaluate the performance of power personnel in each power task based on a pre-built evaluation mechanism, and determine whether the current task is a suitable task for the power personnel based on the evaluation results. The construction module is used to construct a task scheduling graph with power personnel as the point and the relationship between power personnel and adaptation tasks as the edge. The length of each edge of the task scheduling graph corresponds to the evaluation result to quantify the degree of adaptation between power personnel and adaptation tasks. The allocation module is used to obtain the task scheduling set to be allocated, and to determine the alternative scheduling schemes for allocating the task scheduling set to power personnel based on the task scheduling map. The scheduling module is used to input the candidate scheduling schemes into a pre-trained classification model to predict the qualified category of the candidate scheduling schemes; if qualified, the task scheduling set is scheduled according to the candidate scheduling schemes; if unqualified, the next available scheme is determined as the candidate scheduling scheme in descending order of the sum of the side lengths between all power tasks and power personnel.
10. A computer program product, comprising instructions, characterized in that, When executed by a processor, the instruction causes the processor to perform the power personnel dispatching method according to any one of claims 1 to 8.