Mandarin level tester management method and system

Abstract

The invention belongs to the technical field of mandarin test management, and discloses a mandarin level tester management method and system, and the method comprises the steps: collecting and obtaining tester basic information data, examination equipment data, examination room capacity data and examiner resource data; preprocessing the obtained basic information data of the testers, the examination equipment data, the examination room capacity data and the examiner resource data to obtain a testee information feature data set, an equipment feature data set, an examination room feature data set and an examiner feature data set; performing weighted fusion on the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set; training according to the comprehensive feature data set to obtain an examination room resource prediction model, and predicting to obtain examination room resource data; constructing an examination room resource allocation database according to the examination room resource data; examination room, examiner and equipment resources can be reasonably allocated, and resource utilization maximization is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of Mandarin test management, and more specifically, to a method and system for managing Mandarin proficiency test personnel. Background Art

[0002] The patent with the patent announcement number CN114417293A discloses a method for managing a Mandarin proficiency test, comprising the following steps: S1: the management host guides the examinee to enter the examination room according to the number of examinees waiting for the examination in the examination room; S2: the management host performs identity authentication by reading the examinee's ID card information and face information; if the identity authentication is passed, step S3 is performed; if the identity authentication is not passed, the administrator is notified for review; S3: the management host randomly assigns a test question within the examination range to be associated with the examinee's information, and prints a paper preparation reminder sheet to the examinee; S4: the examinee randomly selects an idle examination machine for identity authentication login; the examination machine extracts the test questions assigned by the management host from the test question bank according to the examinee's information, and starts the examination. After the examination, the examination machine feeds back the status information of the examination machine to the management host. The present invention solves the problems of low efficiency, high cost, and inapplicability to the Mandarin test environment in the prior art, and provides a method and system for managing the examination room of the Mandarin proficiency test, which has the characteristics of high efficiency, low cost, and adaptability to the Mandarin test.

[0003] The existing methods and systems for managing people who take Putonghua proficiency tests have the following main problems: The system lacks a simplified formula for weight coefficient tuning. It needs to manually adjust the weight of each feature data set step by step, which results in cumbersome calculation steps, increased calculation amount and time cost, and slow overall iteration speed. Due to the lack of optimization process for feature weight setting, the system may not accurately reflect the actual contribution of each feature to model performance, resulting in imbalance in resource allocation and inability to achieve efficient resource scheduling. Without building a Gaussian process model, it is impossible to accurately fit the relationship between hyperparameter configuration and model accuracy; this may lead to unreasonable hyperparameter configuration, affect the final performance of the model, and reduce the prediction accuracy; the lack of a mechanism to gradually optimize the hyperparameter configuration may cause the model to stagnate in performance and make it difficult to reach the optimal state, increasing the complexity and uncertainty of model tuning; the hyperparameter search process is long and inefficient, with slow convergence, wasting a lot of computing resources and time; no exploration is introduced, especially in the early stage, the search for unexplored areas is insufficient, the model may fall into the local optimal solution too early, and miss a better hyperparameter configuration; the lack of a dynamic adjustment mechanism for the balance coefficient restriction formula may lead to the inability to achieve the best balance between exploring new configurations and using existing configurations, thereby affecting the flexibility and adaptability of the optimization process and resulting in inefficiency; The lack of an effective task matrix and standardized processing may result in candidates not being evenly allocated to various examination rooms, causing some examination rooms to be overloaded and others to be idle, affecting the rational use of overall resources; the failure to automatically find the best allocation method may lead to conflicts among candidates in time or location, which in turn affects the smooth progress of the examination and increases the waiting time and inconvenience of candidates; factors such as examination time, equipment failure rate and examiner absence rate are not taken into account, and unnecessary additional costs may be incurred during allocation, resulting in an increase in the overall allocation cost, which in turn affects the budget and resource allocation; the lack of an intelligent resource allocation mechanism may lead to the idleness or overuse of resources such as examination rooms, examiners and equipment, increasing resource waste and management costs; the lack of row and column standardization and matrix adjustment methods may make the calculation process cumbersome and inefficient, increasing the time and manpower costs required for resource allocation and reducing the overall efficiency of the system.

[0004] In view of this, the present invention proposes a method and system for managing people taking a Putonghua Proficiency Test to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for managing people taking a Putonghua proficiency test, comprising: S1. Obtain basic information data of testers, test equipment data, test room capacity data and examiner resource data; S2, preprocessing the acquired tester basic information data, test equipment data, test room capacity data and examiner resource data to obtain a tester information feature data set, a device feature data set, a test room feature data set and an examiner feature data set; S3, weighted fusion of the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set; training a test room resource prediction model based on the comprehensive feature data set to predict the test room resource data; S4, constructing an examination room resource allocation database according to the examination room resource data; S5. Intelligently allocate the test time and location of testers in the next n time periods according to the test room resource allocation database.

[0006] Furthermore, the basic information data of the tester includes name, ID number, contact information, age, registration time and scheduled examination time; the examination equipment data includes the number of equipment, equipment model, equipment status and equipment maintenance records; the examination room capacity data includes the number of examination rooms, examination room location distribution, maximum examination room capacity and examination room usage status; the examiner resource data includes the number of examiners, examiner qualifications, examiner work arrangement time and examiner work arrangement location.

[0007] Furthermore, the method of preprocessing the acquired tester basic information data, test equipment data, test room capacity data and examiner resource data to obtain a tester information feature data set, a device feature data set, a test room feature data set and an examiner feature data set includes: Use the OPTICS algorithm to identify and remove outliers in the tester basic information data, test equipment data, test room capacity data, and examiner resource data, and obtain the processed tester information feature data set, equipment feature data set, test room feature data set, and examiner feature data set; The processed tester information feature data set, device feature data set, examination room feature data set and examiner feature data set are normalized and converted into standard normal distribution to obtain normalized tester information feature data set, device feature data set, examination room feature data set and examiner feature data set.

[0008] Furthermore, the method of weightedly fusing the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set includes: The normalized tester information feature dataset, equipment feature dataset, examination room feature dataset and examiner feature dataset are fused through a weighted model to obtain a comprehensive feature dataset; the tester information feature dataset is recorded as , the device feature dataset is recorded as , the examination room feature dataset is recorded as ; The examiner feature dataset is recorded as ; The weighted model is: ;in, It is a comprehensive feature dataset; is the weight coefficient of the tester information feature data set; is the weight coefficient of the device feature data set; is the weight coefficient of the examination room feature data set; is the weight coefficient of the examiner feature data set; The weight coefficient of each feature data set in the weighted model is designed to optimize the weight coefficient of each feature data set.

[0009] Furthermore, the method of designing the weight coefficient of each feature data set in the weighted model so that the weight coefficient of each feature data set reaches the optimum includes: The weight coefficient of each feature data set in the weighted model is adjusted by the weight coefficient tuning formula; the weight coefficient tuning formula is: ;in, For the The weight coefficient of the feature data set; For the The number of feature types in a feature dataset; is the total number of all feature data sets; For the The number of feature types in a feature dataset; and An index of the number of feature types.

[0010] Furthermore, the training method of the examination room resource allocation model includes: The data set is divided into a training set, a validation set and a test set, and an examination room resource allocation model is constructed; the sample set is a subset of the data set, and each sample set includes a historical comprehensive feature data set and corresponding examination room resource data; the examination room resource allocation model is a gradient boosting decision tree model; Build a gradient boosted decision tree model and initialize it, setting the number of trees and depth hyperparameters; fit the model to the data set, and calculate the difference between the predicted result and the true label to get the residual of the model in the current iteration; use the residual as the target variable to build a new decision tree model; add the new decision tree model to the initial gradient boosted decision tree model and weight it according to the learning rate; repeat the steps until the preset number of iterations is reached and stop training; Use the test set to evaluate the performance of the trained gradient boosting decision tree model, and use the coefficient of determination to evaluate the difference between the predicted results and the true labels; The coefficient of determination is ;in, For the test set The true value of samples; The model predicts The predicted value of samples; is the mean of all true values ​​in the test set; is the total number of samples in the test set; is the index of the sample; According to the evaluation results, the number of trees and the depth hyperparameters are adjusted to optimize the model's hyperparameters to obtain a trained examination room resource allocation model; the trained examination room resource allocation model is used to predict the current comprehensive feature data to obtain the corresponding examination room resource data.

[0011] Furthermore, the method for tuning the hyperparameters of the model includes: S71. Define the hyperparameters that need to be tuned for the model. , the optimization goal of the model is to maximize the accuracy of the model; S72. construct a hyperparameter space, where the hyperparameter space is a multidimensional grid, in which each dimension represents a hyperparameter; in the hyperparameter space, randomly select a set of initial hyperparameter configurations to train the model; after each training, evaluate the performance indicators of the model by calculating the accuracy, thereby establishing an initial data set; S73. Based on the initial data set , build a Gaussian process model to fit the relationship between hyperparameter configuration and accuracy, output the predicted mean and standard deviation of each configuration, and form a probability distribution model between the initial hyperparameter configuration and accuracy; S74. In each iteration, the next hyperparameter configuration is dynamically adjusted and selected through different sampling criteria, and the current number of iterations is preset to , the optimal hyperparameter configuration is ; The exploration of unknown hyperparameters is enhanced by using the upper confidence bound criterion formula; the upper confidence bound criterion formula is: ;in, For the The hyperparameter configuration selected in the iteration; For hyperparameter configuration The model accuracy prediction mean under ; is the prediction standard deviation under the hyperparameter configuration; is the balance coefficient, which is used to adjust the balance between hyperparameter exploration and utilization; The balance coefficient for adjusting the exploration and utilization of hyperparameters is limited by the balance coefficient limitation formula; the balance coefficient limitation formula is: ;in, For the The number of iterations and hyperparameter configurations is The balance coefficient when A constant to adjust the intensity of exploration; is the number of iterations; Configure the number of hyperparameters; S75, improving the segmentation and refinement of the high probability area by using a probability improvement criterion formula; the probability improvement criterion formula is: ;in, is the current optimal accuracy; For hyperparameter configuration The model accuracy function under is a probability function used to calculate the performance improvement probability of the current candidate hyperparameter configuration; For hyperparameter configuration The accuracy rate exceeds The probability of is the threshold of the probability of improvement, which is used to control the improvement of the current optimal solution; S76. In the selected hyperparameter configuration Next, train the model and calculate the accuracy , get the performance indicators of the current configuration, add the new hyperparameter configuration and the corresponding performance indicators to the dataset, and use the updated dataset Retrain the Gaussian process model; S77. When the number of iterations reaches a preset number, the hyperparameter configuration with the best accuracy is selected as the optimal configuration of the final model.

[0012] Furthermore, the method for constructing an examination room resource allocation database according to the examination room resource data includes: The examination room resource allocation database is a relational database MySQL; a database table is designed based on the acquired examination room resource data, the created database table is associated, and the specific examination room resource data is inserted using the SQL language; Flask is used to create an API framework, and a processing function is written at each API endpoint to implement the data addition, deletion, modification and query functions, thereby obtaining a constructed examination room resource allocation database.

[0013] Furthermore, the method for intelligently allocating the examination time and examination location of testers in the next n time periods according to the examination room resource allocation database includes: S91. Construct a task matrix according to the examination room resource allocation database, wherein the task matrix is: ;in, Task Matrix; is the number of testers; is the number of examination rooms; To be the first Assign testers to The cost value of each examination room; S92. Task Matrix For each row of , find the minimum value of the row by the row normalization formula and subtract it from all elements of the row so that at least one element in each row is zero; the row normalization formula is: ;in, For the Assign testers to The cost value of each examination room; For the The minimum value of the row, that is, The minimum cost value among the costs assigned to all examination rooms by the tester; Task Matrix For each column of , find the minimum value of the column by the column normalization formula and subtract it from all elements of the row so that at least one element in each column is zero; the column normalization formula is: ;in, For the The minimum value of the column, that is, The minimum cost value among the allocated costs of all testers in the examination room; Through the dynamic cost update formula Assign testers to The cost of each examination room Adjustment is made; the dynamic cost update formula is: ;in, is the cost value after dynamic adjustment; is the proportionality factor, used to adjust the scale of the overall cost; For exam time; For examination room equipment failure rate; For examination room The examiner absence rate; is the number of examination locations; S93. Check the distribution of zero elements in each row and column, and use the least horizontal and vertical straight lines to cover all zero elements; define is the minimum number of straight lines required for coverage, if , then the optimal allocation solution is found and the algorithm terminates; if , then matrix adjustment is required; among them, for and The smaller value of ; S94. Find the minimum value among the uncovered elements , adjust the task matrix elements; for the uncovered elements, subtract the minimum value ; For the elements covered by the two straight lines, add the minimum value , adjust the task matrix to generate new zero elements; S95, repeat steps S94-S95 until it can be used horizontal lines and The vertical lines cover all zero elements, that is, ; Select non-conflicting zero elements from the final matrix so that only one zero element is selected in each row and column to form the optimal resource allocation plan.

[0014] A mandarin proficiency test personnel management system, comprising: The data acquisition module is used to obtain the basic information data of the testers, the test equipment data, the test room capacity data and the examiner resource data; The data processing module is used to pre-process the acquired tester basic information data, test equipment data, test room capacity data and examiner resource data to obtain a tester information feature data set, a device feature data set, a test room feature data set and an examiner feature data set; The examination room resource prediction module is used to perform weighted fusion on the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set; train the examination room resource prediction model based on the comprehensive feature data set to predict the examination room resource data; An examination room resource allocation database construction module is used to construct an examination room resource allocation database according to the examination room resource data; The intelligent allocation module is used to intelligently allocate the examination time and examination location of testers in the next n time periods according to the examination room resource allocation database.

[0015] Technical effects and advantages of a method and system for managing people with Mandarin proficiency tests of the present invention: By introducing the weight coefficient tuning formula, the weight adjustment process is simplified, unnecessary calculation steps are reduced, the iteration speed of the model is accelerated, and the overall calculation efficiency of the resource allocation system is improved; different weights are automatically assigned according to the number of feature types, avoiding the subjectivity of artificial weight setting, making the contribution of features more scientific and reasonable; By constructing a Gaussian process model, the relationship between hyperparameter configuration and model accuracy can be more accurately fitted; by gradually optimizing the hyperparameter configuration, the final configuration of the model can achieve a higher accuracy; by adjusting the balance between exploration and utilization at different iteration stages through phased sampling criteria (such as the upper confidence bound criterion and the probability improvement criterion), the hyperparameter search process is effectively shortened and the convergence speed is improved; by introducing exploration through the upper confidence bound criterion formula, especially in the initial stage, the search intensity of the unexplored area of ​​the hyperparameter space is increased, which helps to discover potential better configurations and reduce the risk of local optimality; by using the balance coefficient restriction formula, the balance between exploration and utilization can be dynamically adjusted, so that the best trade-off is achieved between exploring new configurations and utilizing existing excellent configurations, making the optimization process more adaptable; Through the task matrix and standardized processing steps, the best allocation method is automatically found to ensure that each candidate can be assigned to a suitable examination room, avoid conflicts and improve allocation efficiency; the dynamic cost update formula takes into account factors such as examination time, equipment failure rate and examiner absence rate, thereby optimizing the cost when candidates are assigned to examination rooms and minimizing the overall allocation cost; through intelligent resource allocation, the rational use of resources such as examination rooms, examiners and equipment is guaranteed, so that resource allocation is more balanced and the vacancy rate of examination rooms is reduced; the use of automated intelligent allocation methods reduces the errors that may be caused by manual allocation and ensures the accuracy and fairness of allocation; through row and column standardization and matrix adjustment, the allocation range is quickly narrowed, making the calculation process more concise and efficient, thereby greatly shortening the resource allocation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a process flow of a method for managing people taking a Putonghua proficiency test according to the present invention; Figure 2 The present invention is a schematic diagram of the structure of a mandarin proficiency test personnel management system. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1: Please refer to Figure 1 As shown, this embodiment provides a method for managing people who take a Putonghua proficiency test, including: S1. Obtain basic information data of testers, test equipment data, test room capacity data and examiner resource data; S2, preprocessing the acquired tester basic information data, test equipment data, test room capacity data and examiner resource data to obtain a tester information feature data set, a device feature data set, a test room feature data set and an examiner feature data set; S3, weighted fusion of the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set; training a test room resource prediction model based on the comprehensive feature data set to predict the test room resource data; S4, constructing an examination room resource allocation database according to the examination room resource data; S5. Intelligently allocate the test time and location of testers in the next n time periods according to the test room resource allocation database.

[0019] The basic information data of testers includes name, ID number, contact information, age, registration time and scheduled exam time; the exam equipment data includes the number of equipment, equipment model, equipment status and equipment maintenance records; the exam room capacity data includes the number of exam rooms, the location distribution of exam rooms, the maximum capacity of exam rooms and the usage status of exam rooms; the examiner resource data includes the number of examiners, examiner qualifications, examiner work schedule and examiner work schedule location.

[0020] The basic information data of the testers is obtained through querying the Putonghua Proficiency Tester Management Terminal; the test equipment data is collected and obtained through IoT sensors deployed in the test room; the test room capacity data and examiner resource data are obtained through MySQL database records; The method of preprocessing the acquired tester basic information data, test equipment data, test room capacity data and examiner resource data to obtain a tester information feature data set, a device feature data set, a test room feature data set and an examiner feature data set includes: Use the OPTICS algorithm to identify and remove outliers in the tester basic information data, test equipment data, test room capacity data, and examiner resource data, and obtain the processed tester information feature data set, equipment feature data set, test room feature data set, and examiner feature data set; The processed tester information feature data set, device feature data set, examination room feature data set and examiner feature data set are normalized and converted into standard normal distribution to obtain normalized tester information feature data set, device feature data set, examination room feature data set and examiner feature data set.

[0021] The method of weightedly fusing the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set includes: The normalized tester information feature dataset, equipment feature dataset, examination room feature dataset and examiner feature dataset are fused through a weighted model to obtain a comprehensive feature dataset; the tester information feature dataset is recorded as , the device feature dataset is recorded as , the examination room feature dataset is recorded as ; The examiner feature dataset is recorded as ; The weighted model is: ;in, It is a comprehensive feature dataset; is the weight coefficient of the tester information feature data set; is the weight coefficient of the device feature data set; is the weight coefficient of the examination room feature data set; is the weight coefficient of the examiner feature data set; The weight coefficient of each feature data set in the weighted model is designed to optimize the weight coefficient of each feature data set.

[0022] Methods for designing the weight coefficient of each feature data set in the weighted model so that the weight coefficient of each feature data set reaches the optimal value include: The weight coefficient of each feature data set in the weighted model is adjusted by the weight coefficient tuning formula; the weight coefficient tuning formula is: ;in, For the The weight coefficient of the feature data set; For the The number of feature types in a feature dataset; is the total number of all feature data sets; For the The number of feature types in a feature dataset; and is the index of the number of feature types; For example, the number of feature types of the tester information feature data set is 3, the number of feature types of the equipment feature data set is 5, the number of feature types of the examination room feature data set is 2, and the number of feature types of the examiner feature data set is 4; Then the weight coefficient of the tester information feature data set is , the weight coefficient of the device feature dataset , the weight coefficient of the examination room feature dataset , the weight coefficient of the examiner feature dataset ; Then verify that the sum of these weight coefficients is 0.21+0.36+0.14+0.29=1.

[0023] The training methods of the examination room resource allocation model include: The data set is divided into a training set, a validation set and a test set, and an examination room resource allocation model is constructed; the sample set is a subset of the data set, and each sample set includes a historical comprehensive feature data set and corresponding examination room resource data; the examination room resource allocation model is a gradient boosting decision tree model; Build a gradient boosted decision tree model and initialize it, setting the number of trees and depth hyperparameters; fit the model to the data set, and calculate the difference between the predicted result and the true label to get the residual of the model in the current iteration; use the residual as the target variable to build a new decision tree model; add the new decision tree model to the initial gradient boosted decision tree model and weight it according to the learning rate; repeat the steps until the preset number of iterations is reached and stop training; Use the test set to evaluate the performance of the trained gradient boosting decision tree model, and use the coefficient of determination to evaluate the difference between the predicted results and the true labels; The coefficient of determination is ;in, For the test set The true value of samples; The model predicts The predicted value of samples; is the mean of all true values ​​in the test set; is the total number of samples in the test set; is the index of the sample; According to the evaluation results, the number of trees and the depth hyperparameters are adjusted to optimize the model's hyperparameters to obtain a trained examination room resource allocation model; the trained examination room resource allocation model is used to predict the current comprehensive feature data to obtain the corresponding examination room resource data.

[0024] Methods for tuning model hyperparameters include: S71. Define the hyperparameters that need to be tuned for the model. , the optimization goal of the model is to maximize the accuracy of the model; S72. construct a hyperparameter space, where the hyperparameter space is a multidimensional grid, in which each dimension represents a hyperparameter; in the hyperparameter space, randomly select a set of initial hyperparameter configurations to train the model; after each training, evaluate the performance indicators of the model by calculating the accuracy, thereby establishing an initial data set; S73. Based on the initial data set , build a Gaussian process model to fit the relationship between hyperparameter configuration and accuracy, output the predicted mean and standard deviation of each configuration, and form a probability distribution model between the initial hyperparameter configuration and accuracy; S74. In each iteration, the next hyperparameter configuration is dynamically adjusted and selected through different sampling criteria, and the current number of iterations is preset to , the optimal hyperparameter configuration is ; The exploration of unknown hyperparameters is enhanced by using the upper confidence bound criterion formula; the upper confidence bound criterion formula is: ;in, For the The hyperparameter configuration selected in the iteration; For hyperparameter configuration The model accuracy prediction mean under ; is the prediction standard deviation under the hyperparameter configuration; is the balance coefficient, which is used to adjust the balance between hyperparameter exploration and utilization; The balance coefficient for adjusting the exploration and utilization of hyperparameters is limited by the balance coefficient limitation formula; the balance coefficient limitation formula is: ;in, For the The number of iterations and hyperparameter configurations is The balance coefficient when A constant to adjust the intensity of exploration; is the number of iterations; Configure the number of hyperparameters; For example, the constant that adjusts the exploration intensity is 30. At the fourth iteration, the number of hyperparameter configurations is 10. The balance coefficient at this time is ; S75, improving the segmentation and refinement of the high probability area by using a probability improvement criterion formula; the probability improvement criterion formula is: ;in, is the current optimal accuracy; For hyperparameter configuration The model accuracy function under is a probability function used to calculate the performance improvement probability of the current candidate hyperparameter configuration; For hyperparameter configuration The accuracy rate exceeds The probability of is the threshold of the probability of improvement, which is used to control the improvement of the current optimal solution; The size of this value affects the exploration tendency when selecting the next candidate configuration; if If it is large, we need to find a configuration that can significantly improve the accuracy; if it is small, we allow a smaller improvement in order to more finely optimize the configuration near the known optimal solution; S76. In the selected hyperparameter configuration Next, train the model and calculate the accuracy , get the performance indicators of the current configuration, add the new hyperparameter configuration and the corresponding performance indicators to the dataset, and use the updated dataset Retrain the Gaussian process model; S77. When the number of iterations reaches a preset number, the hyperparameter configuration with the best accuracy is selected as the optimal configuration of the final model.

[0025] The method for constructing an examination room resource allocation database according to examination room resource data includes: The examination room resource allocation database is a relational database MySQL; a database table is designed based on the acquired examination room resource data, the created database table is associated, and the specific examination room resource data is inserted using the SQL language; Flask is used to create an API framework, and a processing function is written at each API endpoint to implement the data addition, deletion, modification and query functions, thereby obtaining a constructed examination room resource allocation database.

[0026] The method for intelligently allocating the examination time and examination location of testers in the future n time periods according to the examination room resource allocation database includes: S91. Construct a task matrix according to the examination room resource allocation database, wherein the task matrix is: ;in, Task Matrix; is the number of testers; is the number of examination rooms; To be the first Assign testers to The cost value of each examination room; S92. Task Matrix For each row of , find the minimum value of the row by the row normalization formula and subtract it from all elements of the row so that at least one element in each row is zero; the row normalization formula is: ;in, For the Assign testers to The cost value of each examination room; For the The minimum value of the row, that is, The minimum cost value among the costs assigned to all examination rooms by the tester; Task Matrix For each column of , find the minimum value of the column by the column normalization formula and subtract it from all elements of the row so that at least one element in each column is zero; the column normalization formula is: ;in, For the The minimum value of the column, that is, The minimum cost value among the allocated costs of all testers in the examination room; Through the dynamic cost update formula Assign testers to The cost of each examination room Adjustment is made; the dynamic cost update formula is: ;in, is the cost value after dynamic adjustment; is the proportionality factor, used to adjust the scale of the overall cost; For exam time; For examination room equipment failure rate; For examination room The examiner absence rate; is the number of examination locations; along with and As the value increases, its impact on the cost will not increase linearly, but will gradually slow down, thus avoiding some extreme values ​​from having too great an impact on the cost; Use a logarithmic function to reduce the cost effect, and avoid excessively reducing costs by infinitely increasing the number of examination rooms; For example, the test time is 3 hours and the test room The equipment failure rate is 5%, The examiner absence rate is 10%, the number of examination locations is 3, and the proportionality factor is is 10, then the dynamically adjusted cost value ; S93. Check the distribution of zero elements in each row and column, and use the least horizontal and vertical straight lines to cover all zero elements; define is the minimum number of straight lines required for coverage, if , then the optimal allocation solution is found and the algorithm terminates; if , then matrix adjustment is required; among them, for and The smaller value of ; S94. Find the minimum value among the uncovered elements , adjust the task matrix elements; for the uncovered elements, subtract the minimum value ; For the elements covered by the two straight lines, add the minimum value , adjust the task matrix to generate new zero elements; S95, repeat steps S94-S95 until it can be used horizontal lines and The vertical lines cover all zero elements, that is, ; Select non-conflicting zero elements from the final matrix so that only one zero element is selected in each row and column to form the optimal resource allocation plan.

[0027] In this embodiment, the weight adjustment process is simplified by introducing a weight coefficient tuning formula, unnecessary calculation steps are reduced, the iteration speed of the model is accelerated, and the overall calculation efficiency of the resource allocation system is improved; different weights are automatically assigned according to the number of feature types, avoiding the subjectivity of manually setting weights, making the contribution of features more scientific and reasonable; By constructing a Gaussian process model, the relationship between hyperparameter configuration and model accuracy can be more accurately fitted; by gradually optimizing the hyperparameter configuration, the final configuration of the model can achieve a higher accuracy; by adjusting the balance between exploration and utilization at different iteration stages through phased sampling criteria (such as the upper confidence bound criterion and the probability improvement criterion), the hyperparameter search process is effectively shortened and the convergence speed is improved; by introducing exploration through the upper confidence bound criterion formula, especially in the initial stage, the search intensity of the unexplored area of ​​the hyperparameter space is increased, which helps to discover potential better configurations and reduce the risk of local optimality; by using the balance coefficient restriction formula, the balance between exploration and utilization can be dynamically adjusted, so that the best trade-off is achieved between exploring new configurations and utilizing existing excellent configurations, making the optimization process more adaptable; Through the task matrix and standardized processing steps, the best allocation method is automatically found to ensure that each candidate can be assigned to a suitable examination room, avoid conflicts and improve allocation efficiency; the dynamic cost update formula takes into account factors such as examination time, equipment failure rate and examiner absence rate, thereby optimizing the cost when candidates are assigned to examination rooms and minimizing the overall allocation cost; through intelligent resource allocation, the rational use of resources such as examination rooms, examiners and equipment is guaranteed, so that resource allocation is more balanced and the vacancy rate of examination rooms is reduced; the use of automated intelligent allocation methods reduces the errors that may be caused by manual allocation and ensures the accuracy and fairness of allocation; through row and column standardization and matrix adjustment, the allocation range is quickly narrowed, making the calculation process more concise and efficient, thereby greatly shortening the resource allocation time.

[0028] Example 2: Please refer to Figure 2 As shown, this embodiment provides a management system for people who need to take a Putonghua proficiency test, including: The data acquisition module is used to obtain the basic information data of the testers, the test equipment data, the test room capacity data and the examiner resource data; The data processing module is used to pre-process the acquired tester basic information data, test equipment data, test room capacity data and examiner resource data to obtain a tester information feature data set, a device feature data set, a test room feature data set and an examiner feature data set; The examination room resource prediction module is used to perform weighted fusion on the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set; train the examination room resource prediction model based on the comprehensive feature data set to predict the examination room resource data; An examination room resource allocation database construction module is used to construct an examination room resource allocation database according to the examination room resource data; The intelligent allocation module is used to intelligently allocate the examination time and examination location of testers in the next n time periods according to the examination room resource allocation database.

[0029] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for managing people taking a Putonghua proficiency test, characterized in that: include: S1. Obtain basic information data of testers, test equipment data, test room capacity data and examiner resource data; S2, preprocessing the acquired tester basic information data, test equipment data, test room capacity data and examiner resource data to obtain a tester information feature data set, a device feature data set, a test room feature data set and an examiner feature data set; S3, weighted fusion of the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set; training a test room resource prediction model based on the comprehensive feature data set to predict the test room resource data; S4, constructing an examination room resource allocation database according to the examination room resource data; S5. Intelligently allocate the test time and location of testers in the next n time periods according to the test room resource allocation database.

2. A method for managing people taking a Putonghua proficiency test according to claim 1, characterized in that: The basic information data of the tester includes name, ID number, contact information, age, registration time and scheduled examination time; the examination equipment data includes the number of equipment, equipment model, equipment status and equipment maintenance records; the examination room capacity data includes the number of examination rooms, examination room location distribution, maximum examination room capacity and examination room usage status; the examiner resource data includes the number of examiners, examiner qualifications, examiner work schedule and examiner work schedule location.

3. A method for managing people taking a Putonghua proficiency test according to claim 2, characterized in that: The method of preprocessing the acquired tester basic information data, test equipment data, test room capacity data and examiner resource data to obtain a tester information feature data set, a device feature data set, a test room feature data set and an examiner feature data set includes: Use the OPTICS algorithm to identify and remove outliers in the tester basic information data, test equipment data, test room capacity data, and examiner resource data, and obtain the processed tester information feature data set, equipment feature data set, test room feature data set, and examiner feature data set; The processed tester information feature data set, device feature data set, examination room feature data set and examiner feature data set are normalized and converted into standard normal distribution to obtain normalized tester information feature data set, device feature data set, examination room feature data set and examiner feature data set.

4. A method for managing people taking a Putonghua proficiency test according to claim 3, characterized in that: The method of weightedly fusing the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set includes: The normalized tester information feature dataset, equipment feature dataset, examination room feature dataset and examiner feature dataset are fused through a weighted model to obtain a comprehensive feature dataset; the tester information feature dataset is recorded as , the device feature dataset is recorded as , the examination room feature dataset is recorded as ; The examiner feature dataset is recorded as ; The weighted model is: ;in, It is a comprehensive feature dataset; is the weight coefficient of the tester information feature data set; is the weight coefficient of the device feature data set; is the weight coefficient of the examination room feature data set; is the weight coefficient of the examiner feature data set; The weight coefficient of each feature data set in the weighted model is designed to optimize the weight coefficient of each feature data set.

5. A method for managing people taking a Putonghua proficiency test according to claim 4, characterized in that: The method of designing the weight coefficient of each feature data set in the weighted model so that the weight coefficient of each feature data set reaches the optimum includes: The weight coefficient of each feature data set in the weighted model is adjusted by the weight coefficient tuning formula; the weight coefficient tuning formula is: ;in, For the The weight coefficient of the feature data set; For the The number of feature types in a feature dataset; is the total number of all feature data sets; For the The number of feature types in a feature dataset; and An index of the number of feature types.

6. A method for managing people taking a Putonghua proficiency test according to claim 5, characterized in that: The training method of the examination room resource allocation model includes: Divide the data set into training set, validation set and test set, and build an examination room resource allocation model; The sample set is a subset of the data set, and each sample set includes a historical comprehensive feature data set and corresponding examination room resource data; the examination room resource allocation model is a gradient boosting decision tree model; Build a gradient boosting decision tree model and initialize it, setting the number and depth hyperparameters of the tree; The model fits the data set and calculates the difference between the predicted result and the true label to obtain the residual of the model in the current iteration; uses the residual as the target variable to build a new decision tree model; adds the new decision tree model to the initial gradient boosting decision tree model and weights it according to the learning rate; repeats the steps until the preset number of iterations is reached and stops training; Use the test set to evaluate the performance of the trained gradient boosting decision tree model, and use the coefficient of determination to evaluate the difference between the predicted results and the true labels; The coefficient of determination is ;in, For the test set The true value of samples; The model predicts The predicted value of samples; is the mean of all true values ​​in the test set; is the total number of samples in the test set; is the index of the sample; According to the evaluation results, the number of trees and the depth hyperparameters are adjusted to optimize the model's hyperparameters to obtain a trained examination room resource allocation model; the trained examination room resource allocation model is used to predict the current comprehensive feature data to obtain the corresponding examination room resource data.

7. A method for managing people taking a Putonghua proficiency test according to claim 6, characterized in that: The method for tuning the hyperparameters of the model includes: S71. Define the hyperparameters that need to be tuned for the model. , the optimization goal of the model is to maximize the accuracy of the model; S72. construct a hyperparameter space, where the hyperparameter space is a multidimensional grid, in which each dimension represents a hyperparameter; in the hyperparameter space, randomly select a set of initial hyperparameter configurations to train the model; after each training, evaluate the performance indicators of the model by calculating the accuracy, thereby establishing an initial data set; S73. Based on the initial data set , build a Gaussian process model to fit the relationship between hyperparameter configuration and accuracy, output the predicted mean and standard deviation of each configuration, and form a probability distribution model between the initial hyperparameter configuration and accuracy; S74. In each iteration, the next hyperparameter configuration is dynamically adjusted and selected through different sampling criteria, and the current number of iterations is preset to , the optimal hyperparameter configuration is ; The exploration of unknown hyperparameters is enhanced by using the upper confidence bound criterion formula; the upper confidence bound criterion formula is: ;in, For the The hyperparameter configuration selected in the iteration; For hyperparameter configuration The model accuracy prediction mean under ; is the prediction standard deviation under the hyperparameter configuration; is the balance coefficient, which is used to adjust the balance between hyperparameter exploration and utilization; The balance coefficient for adjusting the exploration and utilization of hyperparameters is limited by the balance coefficient limitation formula; the balance coefficient limitation formula is: ;in, For the The number of iterations and hyperparameter configurations is The balance coefficient when A constant for adjusting the intensity of exploration; is the number of iterations; Configure the number of hyperparameters; S75, improving the segmentation and refinement of the high probability area by using a probability improvement criterion formula; the probability improvement criterion formula is: ;in, is the current optimal accuracy; For hyperparameter configuration The model accuracy function under is a probability function used to calculate the performance improvement probability of the current candidate hyperparameter configuration; For hyperparameter configuration The accuracy rate exceeds The probability of is the threshold of the probability of improvement, which is used to control the improvement of the current optimal solution; S76. In the selected hyperparameter configuration Next, train the model and calculate the accuracy , get the performance indicators of the current configuration, add the new hyperparameter configuration and the corresponding performance indicators to the dataset, and use the updated dataset Retrain the Gaussian process model; S77. When the number of iterations reaches a preset number, the hyperparameter configuration with the best accuracy is selected as the optimal configuration of the final model.

8. A method for managing people taking a Putonghua proficiency test according to claim 7, characterized in that: The method for constructing an examination room resource allocation database according to examination room resource data comprises: The examination room resource allocation database is a relational database MySQL; a database table is designed based on the acquired examination room resource data, the created database table is associated, and the specific examination room resource data is inserted using the SQL language; Flask is used to create an API framework, and a processing function is written at each API endpoint to implement the data addition, deletion, modification and query functions, thereby obtaining a constructed examination room resource allocation database.

9. A method for managing people taking a Putonghua proficiency test according to claim 8, characterized in that: The method for intelligently allocating the examination time and examination location of testers in the future n time periods according to the examination room resource allocation database includes: S91. Construct a task matrix according to the examination room resource allocation database. The task matrix is: ;in, Task Matrix; is the number of testers; is the number of examination rooms; To be the first Assign testers to The cost value of each examination room; S92. Task Matrix For each row of , find the minimum value of the row by the row normalization formula and subtract it from all elements of the row so that at least one element in each row is zero; the row normalization formula is: ;in, For the Assign testers to The cost value of each examination room; For the The minimum value of the row, that is, The minimum cost value among the costs assigned to all examination rooms by the tester; Task Matrix For each column of , find the minimum value of the column by the column normalization formula and subtract it from all elements of the row so that at least one element in each column is zero; the column normalization formula is: ;in, For the The minimum value of the column, that is, The minimum cost value among the allocated costs of all testers in the examination room; Through the dynamic cost update formula Assign testers to The cost of each examination room Adjustment is made; the dynamic cost update formula is: ;in, is the cost value after dynamic adjustment; is the proportionality factor, used to adjust the scale of the overall cost; For exam time; For examination room equipment failure rate; For examination room The examiner absence rate; is the number of examination locations; S93. Check the distribution of zero elements in each row and column, and use the least horizontal and vertical straight lines to cover all zero elements; define is the minimum number of straight lines required for coverage, if , then the optimal allocation solution is found and the algorithm terminates; if , then matrix adjustment is required; among them, for and The smaller value of ; S94. Find the minimum value among the uncovered elements , adjust the task matrix elements; for the uncovered elements, subtract the minimum value ; For the elements covered by the two straight lines, add the minimum value , adjust the task matrix to generate new zero elements; S95, repeat steps S94-S95 until it can be used horizontal lines and The vertical lines cover all zero elements, that is, ; Select non-conflicting zero elements from the final matrix so that only one zero element is selected in each row and column to form the optimal resource allocation plan.

10. A management system for personnel of Mandarin proficiency test, used to implement a management method for personnel of Mandarin proficiency test as claimed in any one of claims 1 to 9, characterized in that: include: The data acquisition module is used to obtain the basic information data of the testers, the test equipment data, the test room capacity data and the examiner resource data; The data processing module is used to pre-process the acquired tester basic information data, test equipment data, test room capacity data and examiner resource data to obtain a tester information feature data set, a device feature data set, a test room feature data set and an examiner feature data set; The examination room resource prediction module is used to perform weighted fusion on the tester information feature data set, the equipment feature data set, the examination room feature data set and the examiner feature data set to obtain a comprehensive feature data set; train the examination room resource prediction model based on the comprehensive feature data set to predict the examination room resource data; An examination room resource allocation database construction module is used to construct an examination room resource allocation database according to the examination room resource data; The intelligent allocation module is used to intelligently allocate the examination time and examination location of testers in the next n time periods according to the examination room resource allocation database.

Images