Electric power personnel assignment method and system

Abstract

The invention relates to the technical field of electric power task assignment, in particular to an electric power personnel assignment method and system, and the method comprises the steps: collecting the learning data and examination data of electric power personnel in a training period; determining a first characteristic value according to the learning data, and determining a second characteristic value according to the assessment data; determining the qualified category of the power personnel according to the practical operation data of the power personnel in the practical operation stage after the training period; processing based on the first feature value and the second feature value to obtain a composite feature; constructing a training sample based on the composite feature and the real label, and training a classification model by using the training sample; and utilizing the trained classification model to predict a qualified category of the power personnel, and assigning the power personnel according to the qualified category. According to the invention, the learning data and the examination data of the electric power personnel in the training period are collected to process the composite features, the classification model is matched to predict the qualified category of the electric power personnel, and the electric power personnel are reasonably assigned and distributed.

Description

Technical Field

[0001] This invention relates to the field of power task assignment technology, specifically to a method and system for assigning power personnel. Background Technology

[0002] Every year, a large number of new power personnel are added to the power system. Due to the large overall number of new power personnel, many of them need to be trained before they can receive task assignments.

[0003] Currently, power personnel are typically assessed after training sessions to determine their ability to perform tasks. However, in practice, many personnel who pass the assessment still have a low success rate in task execution, meaning they lack the actual ability to perform tasks. This is because the test content is relatively limited and cannot cover all the work content that needs to be learned and assessed. Relying solely on test results to classify power personnel as qualified has significant limitations, and the large number of personnel who pass the assessment but lack the necessary skills also negatively impacts the assignment and smooth execution of subsequent power tasks. Summary of the Invention

[0004] The purpose of this invention is to provide a learning and scoring system and method for training power personnel. By collecting learning and assessment data of power personnel during the training period to process composite features, and further training a classification model through composite features to predict the qualification category of power personnel, thereby making reasonable assignments and allocations of power personnel.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a method for assigning power personnel, comprising: Collect learning and assessment data of power personnel during the training period; The first feature value is determined based on the learning data, and the second feature value is determined based on the assessment data; the qualification category of the power personnel is determined based on the practical operation data of the power personnel in the practical operation phase after the training period. A composite feature is obtained by processing based on the first and second feature values; Training samples are constructed based on the composite features and the true labels of the qualified categories. The training samples are then used to train a classification model that takes the composite features as input and the qualified categories as output. The trained classification model is used to predict the qualification category of power personnel after the training period, and the power personnel are assigned according to the qualification category.

[0006] Optionally, the formula for calculating the first feature value R is: ; ; ; Where α, β, and γ are weighting coefficients; A represents daily learning activity; P represents course learning progress; Q represents course test score; F represents login frequency; D represents effective daily learning time; I represents interaction index; C represents completion rate; V represents course learning speed coefficient; T represents effective course learning time; Z represents accuracy rate; K represents course test speed coefficient; and H represents difficulty completion rate.

[0007] Optionally, the calculation formulas for login frequency, effective daily learning time, interaction index, completion rate, course learning speed coefficient, effective course learning time, accuracy rate, course test speed coefficient, and difficulty completion rate are as follows: , , , , T= , , , .

[0008] Optionally, the weighting coefficient γ is dynamically adjusted based on the success rate of power personnel in overcoming difficult problems in the course test. The adjustment rules for the weighting coefficient γ include: When the success rate (H) of solving difficult problems by power personnel is greater than 50%, the weighting coefficient γ is increased. The formula for calculating the adjusted weighting coefficient γ is as follows: In the formula, This represents the adjusted weighting coefficient γ; The weighting coefficient β is dynamically adjusted based on the progress of power personnel in completing the course. The adjustment rules for the weighting coefficient β include: When the course completion progress P of the power personnel does not reach the preset progress, the weighting coefficient β is increased according to the preset rules; the calculation formula for the adjusted weighting coefficient β is as follows: In the formula, This represents the adjusted weighting coefficient β.

[0009] Optionally, the formula for calculating the second eigenvalue E is: J = Original score; ; .

[0010] Optionally, the formula for calculating the composite feature is: , Where a and b are weighting coefficients, R represents the first feature value, E represents the second feature value, and A is a preset threshold.

[0011] Optionally, determining the qualification category of power personnel based on their practical data from the practical training phase following the training period includes: The success rate of power acquisition personnel in each practical task during the practical phase; If the success rate is not lower than the preset success rate threshold, then the qualification category of the power personnel is determined to be qualified; If the success rate is lower than the preset success rate threshold, the qualification category of the power personnel is determined to be unqualified.

[0012] Optionally, training a classification model with composite features as input and qualified categories as output using the training samples includes: The classification model is set as a support vector machine classification model. The support vector machine classification model is trained using the training samples until the loss function converges to determine the optimal decision boundary. The qualified categories are predicted and classified according to the optimal decision boundary.

[0013] Optionally, assigning power personnel according to the qualification category includes: If the predicted qualification level of the power personnel after the training period is qualified, the power personnel will be included in the practical assignment pool for task assignment. If the predicted qualification level of an electrical worker after the training period is unqualified, the worker will be assigned to undergo retraining.

[0014] In a second aspect, the present invention provides an electrical personnel dispatch system, comprising: The data collection module is used to collect learning and assessment data of power personnel during the training period; The determination module is used to determine a first feature value based on the learning data, a second feature value based on the assessment data, and to determine the qualification category of the power personnel based on the practical data of the power personnel in the practical operation phase after the training period. The processing module is used to process the composite feature based on the first feature value and the second feature value; The training module is used to construct training samples based on the composite features and the true labels of the qualified categories, and to train a classification model with the composite features as input and the qualified categories as output using the training samples. The assignment module is used to predict the qualification category of power personnel after the training period using a trained classification model, and to assign power personnel according to the qualification category.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention collects and processes the learning and assessment data of power personnel during the training period to obtain composite features that can contain comprehensive information of learning and assessment dimensions, so as to cooperate with the classification model to predict the qualification category of power personnel, thereby obtaining more accurate prediction results based on more multi-dimensional information, and then making reasonable assignment and allocation of power personnel. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the power personnel assignment method in Example 1. Detailed Implementation

[0017] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention. Example 1

[0018] Combination Figure 1 This embodiment provides a method for assigning power personnel, which includes: Step S1: Collect learning and assessment data of power personnel during the training period; The parameters to be collected in this embodiment include the actual number of login days (and the preset number of login days), average daily study minutes, number of questions and answers, completed class hours (and the preset total class hours), actual learning speed (and the preset standard learning speed), effective study time (and the preset total course time), number of correct questions (and the preset total number of questions), actual time spent (and the preset standard time spent), and number of correctly answered difficult questions (and the preset total number of difficult questions). Step S2: Determine the first feature value based on the learning data, determine the second feature value based on the assessment data, and determine the qualification category of the power personnel based on the practical operation data of the power personnel in the practical operation phase after the training period; Due to the large amount of content involved in the learning and assessment data, this embodiment processes the learning and assessment data to extract the first and second feature values ​​representing the learning and assessment dimensions. The determination of the qualification category primarily considers the success rate of the power personnel's practical tasks. If the success rate is not lower than a preset success rate threshold, the power personnel are determined to be qualified; if the success rate is lower than the preset success rate threshold, the power personnel are determined to be unqualified.

[0019] In a specific embodiment, the formula for calculating the first feature value R is: ; ; ; Where α, β, and γ are weighting coefficients; A represents daily learning activity; P represents course learning progress; Q represents course test score; F represents login frequency; D represents effective daily learning time; I represents interaction index; C represents completion rate; V represents course learning speed coefficient; T represents effective course learning time; Z represents accuracy rate; K represents course test speed coefficient; and H represents difficulty completion rate.

[0020] The calculation formulas for login frequency, effective daily learning time, interaction index, completion rate, course learning speed coefficient, effective course learning time, accuracy rate, course test speed coefficient, and difficulty completion rate are as follows: , , , , T= , , , .

[0021] This embodiment incorporates multi-faceted indicator information from the learning dimension into the first feature value, enabling the subsequent classification model to provide richer content input. Furthermore, for some indicators that significantly reflect the learning ability or attitude of power industry personnel (such as the difficulty level H and course completion progress P), this embodiment provides corresponding adjustment strategies to amplify the influence of these indicators in the first feature value.

[0022] Specifically, the weighting coefficient γ is dynamically adjusted based on the success rate of the power personnel in overcoming difficult problems in the course test. The adjustment rules for the weighting coefficient γ include: when the success rate H of the power personnel in overcoming difficult problems is greater than 50%, the weighting coefficient γ is increased. The calculation formula for the adjusted weighting coefficient γ is as follows: In the formula, This represents the adjusted weighting coefficient γ.

[0023] Furthermore, the weighting coefficient β is dynamically adjusted based on the course completion progress of the power personnel. The adjustment rules for the weighting coefficient β include: when the course completion progress P of the power personnel does not reach the preset progress, the weighting coefficient β is increased according to the preset rules; the calculation formula for the adjusted weighting coefficient β is as follows: ; In the formula, This represents the adjusted weighting coefficient β.

[0024] Furthermore, the formula for calculating the second eigenvalue E is as follows: J = Original score; ; .

[0025] This embodiment incorporates multi-dimensional indicator information from the assessment dimensions through the second feature value, enabling the subsequent classification model to learn from the composite features constructed by the first and second feature values. It determines the qualified category of power personnel from the rich content contained in the first and second feature values, thereby minimizing the inclusion of power personnel with insufficient comprehensive capabilities into the task assignment pool, and thus improving the quality of task assignment personnel and the task success rate.

[0026] Step S3: Obtain a composite feature based on the first feature value and the second feature value; Specifically, the calculation formula for the composite feature is as follows: , Where a and b are weighting coefficients, R represents the first feature value, E represents the second feature value, and A is a preset threshold. In a specific embodiment, a=0.3, b=0.7, and A=70; this embodiment weights the first and second feature values ​​to obtain composite features as input to the classification model, thereby obtaining more accurate prediction results.

[0027] Step S4: Construct training samples based on the composite features and the true labels of the qualified categories. Use the training samples to train a classification model with the composite features as input and the qualified categories as output. In a specific embodiment, the classification model is a support vector machine (SVM) classification model. Use the training samples to train the SVM classification model until the loss function converges to determine the optimal decision boundary. In this embodiment, a hinge loss function is used. Further, the qualified categories are predicted and classified according to the optimal decision boundary.

[0028] Step S5: Use the trained classification model to predict the qualification category of the power personnel after the training period, and assign tasks to the power personnel according to the qualification category. If the predicted qualification category of the power personnel after the training period is qualified, the power personnel are added to the practical assignment pool for task assignment; if the predicted qualification category of the power personnel after the training period is unqualified, the power personnel are assigned to retrain.

[0029] This embodiment uses a classification model to learn from historical data. The trained classification model can predict the qualified category of power personnel in advance based on the learning data and assessment data, thereby avoiding the participation of power personnel who do not actually have the ability to perform the task in task assignment as much as possible, so as to standardize the assignment strategy of power personnel and improve the task success rate.

[0030] In summary, this embodiment collects and processes the learning and assessment data of power personnel during the training period to obtain composite features that contain comprehensive information on both the learning and assessment dimensions. These features are then used in conjunction with a classification model to predict the qualification category of power personnel. This approach, based on more comprehensive dimensional information, yields more accurate prediction results and enables the rational assignment and allocation of power personnel. Example 2

[0031] Based on the same inventive concept as Embodiment 1, this embodiment provides an electrical personnel dispatch system, which includes: The data collection module is used to collect learning and assessment data of power personnel during the training period; The determination module is used to determine a first feature value based on the learning data, a second feature value based on the assessment data, and to determine the qualification category of the power personnel based on the practical data of the power personnel in the practical operation phase after the training period. The processing module is used to process the composite feature based on the first feature value and the second feature value; The training module is used to construct training samples based on the composite features and the true labels, and to train a classification model with the composite features as input and the qualified category as output using the training samples. The assignment module is used to predict the qualification category of power personnel after the training period using a trained classification model, and to assign power personnel according to the qualification category.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for assigning power personnel, characterized in that, include: Collect learning and assessment data of power personnel during the training period; A first feature value is determined based on the learning data, and a second feature value is determined based on the assessment data; And determine the qualification category of power personnel based on the practical data of power personnel during the practical training phase after the training period; A composite feature is obtained by processing based on the first and second feature values; Training samples are constructed based on the composite features and the true labels of the qualified categories. The training samples are then used to train a classification model that takes the composite features as input and the qualified categories as output. The trained classification model is used to predict the qualification category of power personnel after the training period, and the power personnel are assigned according to the qualification category.

2. The method for assigning power personnel according to claim 1, characterized in that, The formula for calculating the first eigenvalue R is: ; ; ; Where α, β, and γ are weighting coefficients; A represents daily learning activity; P represents course learning progress; Q represents course test score; F represents login frequency; D represents effective daily learning time; I represents interaction index; C represents completion rate; V represents course learning speed coefficient; T represents effective course learning time; Z represents accuracy rate; K represents course test speed coefficient; and H represents difficulty completion rate.

3. The method for assigning power personnel according to claim 2, characterized in that, The calculation formulas for login frequency, effective daily learning time, interaction index, completion rate, course learning speed coefficient, effective course learning time, accuracy rate, course test speed coefficient, and difficulty completion rate are as follows: , , , , ,T= , , , 。 4. The method for assigning power personnel according to claim 2, characterized in that, The weighting coefficient γ is dynamically adjusted based on the success rate of electrical personnel in overcoming difficult problems in the course test. The adjustment rules for the weighting coefficient γ include: When the success rate (H) of solving difficult problems by power personnel is greater than 50%, the weighting coefficient γ is increased. The formula for calculating the adjusted weighting coefficient γ is as follows: In the formula, This represents the adjusted weighting coefficient γ; The weighting coefficient β is dynamically adjusted based on the progress of power personnel in completing the course. The adjustment rules for the weighting coefficient β include: When the course completion progress P of the power personnel does not reach the preset progress, the weighting coefficient β is increased according to the preset rules; the calculation formula for the adjusted weighting coefficient β is as follows: In the formula, This represents the adjusted weighting coefficient β.

5. The method for assigning power personnel according to claim 1, characterized in that, The formula for calculating the second eigenvalue E is: J = Original score; ; .

6. The method for assigning power personnel according to claim 1, characterized in that, The formula for calculating the composite feature is as follows: , Where a and b are weighting coefficients, R represents the first feature value, E represents the second feature value, and A is a preset threshold.

7. The method for assigning power personnel according to claim 1, characterized in that, The determination of the qualification category of power personnel based on their practical data during the practical training phase after the training period includes: The success rate of power acquisition personnel in each practical task during the practical phase; If the success rate is not lower than the preset success rate threshold, then the qualification category of the power personnel is determined to be qualified; If the success rate is lower than the preset success rate threshold, the qualification category of the power personnel is determined to be unqualified.

8. The method for assigning power personnel according to claim 1, characterized in that, Training a classification model using the training samples, with composite features as input and the qualified category as output, includes: The classification model is set as a support vector machine classification model. The support vector machine classification model is trained using the training samples until the loss function converges to determine the optimal decision boundary. The qualified categories are predicted and classified according to the optimal decision boundary.

9. The method for assigning power personnel according to claim 1, characterized in that, Assigning power personnel according to the aforementioned qualification categories includes: If the predicted qualification level of the power personnel after the training period is qualified, the power personnel will be included in the practical assignment pool for task assignment. If the predicted qualification level of an electrical worker after the training period is unqualified, the worker will be assigned to undergo retraining.

10. A power personnel dispatching system, characterized in that, include: The data collection module is used to collect learning and assessment data of power personnel during the training period; A determination module is used to determine a first feature value based on the learning data and a second feature value based on the assessment data; The qualification category of power personnel is determined based on the practical data collected during the practical training phase following the training period. The processing module is used to process the composite feature based on the first feature value and the second feature value; The training module is used to construct training samples based on the composite features and the true labels of the qualified categories, and to train a classification model with the composite features as input and the qualified categories as output using the training samples. The assignment module is used to predict the qualification category of power personnel after the training period using a trained classification model, and to assign power personnel according to the qualification category.

Images