Evaluation system and method for improving mycoplasma pneumoniae detection participation degree through relay detection

Abstract

The invention discloses an evaluation system and method for improving mycoplasma pneumoniae detection participation degree through relay detection, and belongs to the field of data analysis, and the system comprises a data collection module which is used for collecting behavior data of research people; the data preprocessing module is used for carrying out data cleaning, integration and preprocessing on the behavior data; the model training module is used for obtaining a participation degree evaluation model; the evaluation import module is used for acquiring an output result of the participation degree evaluation model and importing the output result into an evaluation database of researchers for clustering segmentation; and the task allocation module is used for adjusting and allocating the detection tasks according to the evaluation segmentation result of the researchers. According to the method and the device, the technical problem that an effective method for evaluating and intelligently improving the participation degree of mycoplasma pneumoniae detection is lacked in the prior art is solved, and the effects of quantitatively evaluating the participation degree of researchers through a data-driven machine learning model and optimizing task allocation according to the evaluation result are achieved; therefore, the overall efficiency and quality of mycoplasma pneumoniae detection are improved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and in particular to an evaluation system and method for improving the participation rate of Mycoplasma pneumoniae detection through relay testing. Background Art

[0002] In the detection of Mycoplasma pneumoniae, evaluating and improving the participation of testers is a key factor in ensuring the quality and efficiency of testing. Figure 3 As shown in the figure, the relay test method is to let people receive free health tests, then inform the participants that someone has kindly paid for them, and ask them if they are willing to donate to support more people to receive free health test services. This method can significantly increase the participation rate of various health tests. However, the relay test is applied to the detection of Mycoplasma pneumoniae, and it is difficult to meet the actual needs in terms of effective evaluation and intelligent improvement of the participation rate of Mycoplasma pneumoniae detection. At present, the method of evaluating the participation of testers mainly relies on manual statistics and judgment. This method is not only time-consuming and labor-intensive, but also difficult to efficiently and objectively reflect the actual performance of testers. For example, only by whether to participate in the test and the number of tests to evaluate the participation rate, it is impossible to comprehensively measure the quality and efficiency of the test and improve the test indicators through intelligent analysis. Summary of the invention

[0003] The present application aims to solve the technical problem that there is a lack of effective methods to evaluate and intelligently improve the participation rate of Mycoplasma pneumoniae detection in the prior art by providing an evaluation system and method for improving the participation rate of Mycoplasma pneumoniae detection through relay detection.

[0004] In view of the above problems, the present application provides an evaluation system and method for improving the participation rate of Mycoplasma pneumoniae detection through relay testing.

[0005] The first aspect disclosed in the present application provides an evaluation system for improving the participation of Mycoplasma pneumoniae testing in relay testing, the system comprising: a data collection module for collecting behavioral data of a research population, including testing time, number of tests, task completion status, and abnormal reporting rate; a data preprocessing module for performing data cleaning, integration, and preprocessing on the behavioral data, constructing a training data set, and segmenting the training data set to determine training data and test data; a model training module for performing model training and testing based on a machine learning algorithm through training data and test data, and converging to obtain a participation evaluation model, the participation evaluation model being used to perform quantitative participation evaluation on multiple indicators of input researchers; an evaluation import module for obtaining the output results of the participation evaluation model, importing them into the evaluation database of the researchers, and clustering and segmenting all researchers in the evaluation database; a task allocation module for adjusting and allocating detection tasks according to the evaluation segmentation results of the researchers.

[0006] Another aspect disclosed in the present application provides an evaluation method for improving the participation of Mycoplasma pneumoniae testing in relay testing, the method comprising: collecting behavioral data of the research population, including testing time, number of tests, task completion status, and abnormal reporting rate; performing data cleaning and integration preprocessing on the behavioral data, constructing a training data set, and segmenting the training data set to determine training data and test data; based on a machine learning algorithm, performing model training and testing through training data and test data, and converging to obtain a participation evaluation model, the participation evaluation model is used to quantitatively evaluate the participation of multiple indicators input into the researchers; obtaining the output results of the participation evaluation model, importing them into the evaluation database of the researchers, and clustering and segmenting all the researchers in the evaluation database; and adjusting and allocating the detection tasks according to the evaluation segmentation results of the researchers.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The data collection module is used to collect behavioral data of the research population, including detection time, number of detections, task completion status, and abnormal reporting rate, so as to obtain comprehensive original data and provide a basis for subsequent analysis. The data preprocessing module is used to clean and integrate the collected behavioral data, construct a training data set, and segment the training data set to determine the training data and test data to ensure data quality and prepare for model training. The model training module is used to train and test the model based on the machine learning algorithm through the training data and test data, and converge to obtain the participation evaluation model, which is used to quantitatively evaluate the participation of multiple indicators of the input researchers. The evaluation import module is used to obtain the output results of the participation evaluation model and import them into the evaluation database of the researchers, cluster and segment all the researchers in the evaluation database, systematically manage the model evaluation results, and classify the researchers. The task allocation module is used to adjust the detection task allocation according to the evaluation segmentation results of the researchers, which solves the technical problem of the lack of effective methods to evaluate and intelligently improve the participation of Mycoplasma pneumoniae detection in the existing technology, and achieves the technical effect of quantitatively evaluating the participation of researchers through data-driven machine learning models, and optimizing task allocation accordingly, thereby improving the overall efficiency and quality of Mycoplasma pneumoniae detection.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1A structural schematic diagram of an evaluation system for improving the participation rate of Mycoplasma pneumoniae detection by relay detection is provided for an embodiment of the present application.

[0011] Figure 2 A flowchart of a method for evaluating the use of relay testing to improve the participation rate of Mycoplasma pneumoniae testing is provided for the embodiment of the present application;

[0012] Figure 3 Schematic diagram of the implementation mode of the relay detection method in the embodiment of the present application;

[0013] Explanation of the accompanying drawings: data collection module 11, data preprocessing module 12, model training module 13, evaluation import module 14, task allocation module 15. DETAILED DESCRIPTION

[0014] The overall idea of ​​the technical solution provided by this application is as follows:

[0015] The embodiment of the present application provides an evaluation system and method for improving the participation rate of Mycoplasma pneumoniae detection by relay testing, and realizes objective evaluation of detection participation and optimal allocation of tasks through data-driven and machine learning technology. The modular design is adopted, and the whole process from data collection to task allocation is automated through the collaborative work of multiple functional modules.

[0016] Specifically, first, the data collection module is used to obtain comprehensive behavioral data of the research population, including multi-dimensional information such as detection time, number of detections, task completion status, and abnormal reporting rate. Subsequently, the data preprocessing module cleans and integrates these raw data to construct a high-quality training data set. On this basis, the model training module uses machine learning algorithms to converge on a participation evaluation model that can quantitatively evaluate multiple indicators of researchers through repeated learning of training data and test data. The evaluation results are systematically managed through the evaluation import module and used to cluster and segment researchers. Afterwards, the task allocation module realizes the intelligent adjustment and allocation of detection tasks based on these evaluation and classification results.

[0017] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0018] Embodiment 1

[0019] like Figure 1 As shown, the embodiment of the present application provides an evaluation system for improving the participation rate of Mycoplasma pneumoniae detection through relay detection, and the system includes:

[0020] The data collection module 11 is used to collect behavioral data of the research population, including detection duration, number of detections, task completion status, and abnormality reporting rate.

[0021] Specifically, the data collection module 11 is used to collect behavioral data of the research population during the Mycoplasma pneumoniae detection process. Among them, the behavioral data include but are not limited to the detection time, the number of tests, the completion of tasks and the abnormal reporting rate. The detection time records the time required for each research subject to complete a single Mycoplasma pneumoniae test in minutes. The number of tests counts the total number of Mycoplasma pneumoniae tests completed by each research subject within a specified time period (such as a week or a month). The task completion status records whether the research subject completes all assigned test tasks according to the predetermined plan, which can be expressed as the completion rate (number of completed tasks / total number of tasks). The abnormal reporting rate counts the proportion of abnormalities or errors in the test reports submitted by the research subjects, and the calculation method is the number of abnormal reports divided by the total number of reports. Among them, the data collection module 11 can obtain these behavioral data in a variety of ways, such as automatic recording by the detection equipment, manual input by the researchers, or questionnaires. These data will provide a basis for subsequent participation evaluation and help to fully understand the performance and participation of the research population in the Mycoplasma pneumoniae detection process. Among them, the data collection module 11 can obtain these behavioral data in a variety of ways, such as automatic recording by the detection equipment, manual input by the researchers, or questionnaires. These data will provide a basis for subsequent engagement assessments and help to fully understand the performance and level of engagement of the study population in the M. pneumoniae testing process.

[0022] The data preprocessing module 12 is used to perform data cleaning and integration preprocessing on the behavior data, construct a training data set, and segment the training data set to determine training data and test data.

[0023] Specifically, the data preprocessing module 12 first performs data cleaning and integration preprocessing on the collected behavioral data, including but not limited to processing missing values, removing outliers, unifying data formats, etc., in order to improve data quality and ensure the accuracy of subsequent analysis. For example, for missing values ​​in the detection time data, the mode of the feature is used to fill; for obviously unreasonable outliers, such as negative detection times, they may be deleted. After the data cleaning is completed, the data preprocessing module 12 will integrate the preprocessed behavioral data to construct a training data set. In this process, an evaluation mapping relationship between features such as detection time, detection times, task completion, and abnormal reporting rate and participation is established based on expert experience or predefined rules. Afterwards, the data preprocessing module 12 divides the constructed training data set to determine training data and test data. For example, a random sampling method is used to divide the entire data set into training data and test data according to a certain ratio (such as 7:3 or 8:2). Among them, the training data is used for model learning and parameter adjustment, while the test data is used to evaluate the performance and generalization ability of the model.

[0024] The model training module 13 is used to perform model training and testing based on the machine learning algorithm through the training data and the test data, and converge to obtain a participation evaluation model, and the participation evaluation model is used to perform a quantitative participation evaluation on multiple indicators of the input researchers.

[0025] Specifically, the model training module 13 first selects an appropriate machine learning algorithm as a basis. For example, support vector machine (SVM) is selected as the core algorithm. After the algorithm is selected, the model training module 13 uses the training data to train the model. During the training process, the model will continuously adjust its internal parameters to minimize the error between the predicted results and the actual results. For the support vector machine, it includes selecting a suitable kernel function (such as radial basis function RBF), adjusting the kernel function parameters (such as γ value) and the penalty parameter C value. After the training is completed, the model training module 13 uses the test data to evaluate the performance of the model. The evaluation indicators include accuracy, precision, recall, etc. If the model performance does not meet the preset goals, the model training module 13 optimizes by adjusting hyperparameters or increasing the number of training rounds until the model performance reaches the expected level. After that, the model training module 13 outputs a converged participation evaluation model. The model can receive multiple indicators from researchers as input, including but not limited to detection time, number of detections, task completion, abnormal reporting rate, etc., and outputs a quantitative participation score.

[0026] The evaluation import module 14 is used to obtain the output results of the participation evaluation model, import them into the evaluation database of researchers, and perform clustering and segmentation on all researchers in the evaluation database.

[0027] Specifically, the evaluation import module 14 first obtains the evaluation results of the participation evaluation model for each researcher. For example, the result is a quantitative score or grade, reflecting the degree of participation of the researcher in the Mycoplasma pneumoniae detection process. The evaluation import module 14 imports these results into a pre-set researcher evaluation database, and stores them in association with other information of the researcher (such as personal basic information, detection history, etc.). After completing the data import, the evaluation import module 14 clusters and segments all researchers in the evaluation database, and groups researchers with similar participation characteristics to facilitate subsequent task allocation and management. Among them, cluster segmentation can use a variety of algorithms, such as K-means clustering or hierarchical clustering. In this embodiment, researchers can be divided into multiple levels according to the participation score, such as high participation, moderate participation, and low participation.

[0028] In addition, the evaluation import module 14 performs further cluster analysis based on other characteristics of the researchers. For example, researchers are re-clustered based on factors such as research location, age, family income, and parental education. This multi-dimensional cluster analysis can generate more detailed cluster labels and provide a more accurate basis for subsequent task allocation. At the same time, the cluster segmentation results of the evaluation import module 14 can be updated regularly to reflect the dynamic changes in the researchers' participation. For example, a cluster analysis is re-performed every week or month to capture the changing trend of researchers' participation. This dynamic update mechanism helps to maintain the timeliness and accuracy of the evaluation results.

[0029] Through the processing of the evaluation import module 14, a structured and hierarchical researcher evaluation database is formed, which provides important support for subsequent task allocation and management. It not only helps to identify highly engaged researchers, but also helps to find low-engagement researchers who need additional support or incentives, thereby improving the overall detection efficiency and quality.

[0030] The task allocation module 15 is used to adjust and allocate the detection tasks according to the evaluation segmentation results of the researchers.

[0031] Specifically, the task assignment module 15 first obtains the output results of the evaluation import module 14, including the researcher's participation score, cluster segmentation results, and multi-dimensional cluster labels. Based on this information, the task assignment module 15 establishes a mapping association between the segmentation level and cluster labels and the researchers, and presents this information in a visual way on the task management interface, so that managers can intuitively understand the overall distribution of researchers.

[0032] When performing specific task assignment, the task assignment module 15 first obtains the preset task assignment information of the detection task. This information may include the number, type, difficulty, etc. of tasks. Subsequently, the task assignment module 15 parses the characteristic information of each detection task, including but not limited to geographical characteristics, difficulty characteristics, support demand characteristics, etc. For example, some detection tasks may need to be carried out in a specific area, or need to be completed by researchers with specific skills. Afterwards, the task assignment module 15 uses these task characteristics as search targets and performs correlation analysis on the segmentation level and clustering labels of the researchers. Through this analysis, the researchers most relevant to a specific detection task can be screened out. For example, for detection tasks with higher difficulty, researchers with high participation and high skill levels are given priority; for tasks that need to be carried out in a specific area, researchers in the area are given priority.

[0033] Through the intelligent allocation of the task allocation module 15, the efficient allocation and execution of Mycoplasma pneumoniae detection tasks can be achieved, the overall detection efficiency and quality can be improved, and at the same time, appropriate incentives can be given according to the performance of researchers to form a virtuous cycle of detection ecosystem.

[0034] Furthermore, the data preprocessing module includes the following execution steps:

[0035] Processing missing values ​​and outliers on the behavior data, and unifying the data formats from different sources to complete preprocessing of the behavior data;

[0036] Based on the preprocessed behavioral data, an evaluation mapping relationship between the detection duration, number of detections, task completion status, abnormality reporting rate and participation is established to construct the training data set.

[0037] In a feasible implementation, first, the data preprocessing module 12 processes missing values ​​and outliers for the collected behavioral data. For missing values, a variety of strategies are adopted, such as using the mean, median or mode of the feature to fill in, or using more complex interpolation methods. For example, for missing values ​​of detection time, the average value of the researcher's past detection time is used to fill in. For outliers, a reasonable threshold range is set, and data out of the range is regarded as abnormal and processed, such as deleting it or setting it as a boundary value. Secondly, the data preprocessing module 12 performs unified format processing on data from different sources. Because behavioral data may come from multiple channels, such as automatically recorded detection equipment data, data manually entered by researchers, questionnaire data, etc. Unified format processing ensures that all data can be consistently processed and interpreted in subsequent analysis.

[0038] After completing the above preprocessing steps, the data preprocessing module 12 establishes an evaluation mapping relationship between key indicators such as detection time, number of detections, task completion, abnormal reporting rate and participation based on the processed behavioral data. The establishment of this mapping relationship can be based on expert experience, historical data analysis or predefined rules. For example, a weighted formula is set to assign different weights to each indicator according to its importance, and the participation score is calculated comprehensively. Afterwards, based on these mapping relationships, the data preprocessing module 12 constructs a training data set, which includes the preprocessed behavioral data as input features, and the participation score calculated according to the mapping relationship as the target variable.

[0039] Through preprocessing, the data quality of the input model can be ensured, and the accuracy and reliability of the subsequent participation evaluation model can be improved.

[0040] Furthermore, the data preprocessing module also includes the following execution steps:

[0041] For missing values ​​in the behavior data, the mode of the feature is used to fill in the missing values ​​to complete the missing value processing;

[0042] Deleting outliers in the behavior data to complete outlier processing;

[0043] After removing the outliers, the continuity analysis of the data features was performed, and when there were missing values, the mode filling process was repeated.

[0044] In a feasible implementation, first, for the missing values ​​in the behavior data, the data preprocessing module 12 uses the mode of the feature to fill, which can maintain the discrete characteristics of the data and is particularly suitable for categorical variables or discrete numerical variables. For example, for the feature of the number of tests, if most researchers perform 3 tests within a week, then for the missing number of tests, using 3 to fill can better reflect the central trend of the data and reduce the deviation caused by filling. Secondly, the data preprocessing module 12 deletes the outliers in the behavior data. The determination of outliers can be based on preset rules or statistical methods, such as the 3σ principle or the interquartile range method (IQR). For example, if the detection time of a researcher far exceeds the normal range, it will be identified as an outlier and deleted from the data set to remove extreme data points that may affect the accuracy of model training. After the outlier is deleted, the data preprocessing module 12 performs a continuity analysis of the data features to check whether the outlier deletion has caused new data missing or discontinuity. If it is found that some features have new missing after deleting the outlier, the mode filling method is used again for processing. This iterative processing method ensures the integrity and continuity of the data.

[0045] Through a refined data preprocessing process, we can more effectively handle various data problems that may arise in the actual detection process, provide high-quality data input for subsequent model training, and thus improve the accuracy and reliability of participation assessment.

[0046] Furthermore, the model training module includes the following execution steps:

[0047] Build a support vector machine, select the kernel function and kernel function parameters, set the C value, and train the support vector machine using training data;

[0048] The trained support vector machine is tested for accuracy using test data, the kernel function parameters and C value are adjusted according to the test results, and training is iterated until the test accuracy reaches the target value, thereby obtaining the engagement evaluation model.

[0049] In a preferred embodiment, first, the model training module 13 constructs a support vector machine as the core algorithm for participation evaluation. When constructing the support vector machine, the model training module 13 selects an appropriate kernel function and corresponding kernel function parameters, such as a linear kernel, a polynomial kernel, and a radial basis function kernel. In this embodiment, the RBF kernel is selected, which can effectively handle nonlinear relationships and is suitable for complex participation evaluation scenarios. At the same time, the model training module 13 sets the penalty parameter C value to control the complexity and fault tolerance of the model. Next, the model training module 13 uses the pre-processed training data to perform preliminary training on the support vector machine. During the training process, the optimal decision boundary is found to maximize the interval between different participation categories. After the training is completed, the model training module 13 will use the pre-reserved test data to perform an accuracy test on the trained support vector machine, aiming to evaluate the generalization ability of the model, that is, the performance of the model on unseen data. The test results will be used to determine whether the model has achieved the expected performance level. If the test accuracy does not reach the preset target value, the model training module 13 adjusts the kernel function parameters (such as the γ value of the RBF kernel) and the C value according to the test results, such as through grid search, random search or Bayesian optimization. After adjustment, the model training module 13 retrains the support vector machine using the new parameter settings and tests again. The process of training-testing-adjusting parameters will be continuously iterated until the test accuracy of the model reaches the preset target value. After that, the model training module 13 outputs the optimized participation evaluation model.

[0050] Through model training, a highly optimized and stable participation assessment model was constructed, which can not only accurately evaluate the participation of researchers in Mycoplasma pneumoniae testing, but also adapt to the characteristics of different populations and testing environments.

[0051] Furthermore, evaluating the import module includes the following execution steps:

[0052] According to the evaluation results in the evaluation database, the evaluation level is divided and multi-level researcher clusters are constructed;

[0053] The multi-level researcher clusters are re-clustered based on research location, age, family income, and parents' education level to generate cluster labels.

[0054] In a feasible implementation, the evaluation import module 14 first obtains the evaluation results output by the participation evaluation model, and imports these results into a preset evaluation database. Based on these evaluation results, an evaluation grade segmentation operation is performed to divide the participation score into multiple levels, such as high participation (Grade A), moderate participation (Grade B), and low participation (Grade C). This grading method can intuitively reflect the degree of participation of researchers, which is convenient for subsequent management and incentives. Based on this, the evaluation import module 14 constructs a multi-level researcher cluster, laying the foundation for further refined management.

[0055] Subsequently, the evaluation import module 14 re-clustered the multi-level researcher clusters, aiming to further consider the personal characteristics of researchers on the basis of the level of participation, so as to achieve more accurate classification and management. Specifically, the re-clustering was based on four key characteristics: research location, age, family income, and parental education. This multi-dimensional feature re-clustering takes into account the possible environmental, cultural, and resource differences in different geographical locations, the possible differences in participation among different age groups, the potential association between family economic status and researcher motivation and ability to participate, and the possible impact of parental education background on researcher participation.

[0056] Through multi-dimensional feature re-clustering, the evaluation import module 14 generates a comprehensive cluster label for each researcher. For example, a researcher may be labeled as: "Grade A-Urban-Youth-Middle Income-Higher Education Background". This refined cluster label can more comprehensively describe the characteristics of the researcher, provide a more accurate basis for subsequent task allocation and management, and help improve the participation in the test. It can also provide more suitable incentives and support measures for researchers with different characteristics, thereby improving the overall detection effect and research quality.

[0057] Furthermore, the task allocation module includes the following execution steps:

[0058] Establishing the segmentation level and the mapping association between the cluster labels and the researchers, performing visual conversion, and sending to the relay inspection task management interface;

[0059] Obtaining preset task allocation information of the detection task;

[0060] Analyze the characteristic information of the detection task, including regional characteristics, difficulty characteristics, and support requirement characteristics;

[0061] The regional characteristics, difficulty characteristics, and support requirement characteristics are used as search targets, and correlation analysis is performed on the segmentation levels and clustering labels of the researchers to screen the correspondence between the researchers with the highest correlation and the detection tasks;

[0062] The researcher relationships in the preset task assignment information are adjusted by screening the researcher relationships.

[0063] In a feasible implementation, first, the task assignment module 15 establishes a mapping association between the segmentation level and the clustering label and the researcher, and associates the multi-dimensional classification results generated by the evaluation import module 14 with the specific researcher information. Subsequently, these associated information are converted into a visual form, such as a chart or an interactive interface, and sent to the relay inspection task management interface. This visual display enables managers to intuitively understand the distribution and characteristics of researchers, and facilitates subsequent task assignment decisions. Secondly, the task assignment module 15 obtains the preset task assignment information of the detection task, including basic elements such as the total amount, type, and time schedule of the task, to provide an initial framework for task assignment.

[0064] Next, the task assignment module 15 performs feature analysis on the detection task. The key features of each detection task are extracted, mainly including three aspects: regional features (such as the location of task execution), difficulty features (such as technical requirements, time limits) and support demand features (such as required resources, auxiliary personnel). The analysis of these features lays the foundation for subsequent accurate matching. Based on the task features obtained by the analysis, the task assignment module 15 uses the regional features, difficulty features and support demand features as search targets, and performs correlation analysis on the segmentation level and clustering labels of researchers, aiming to find the most suitable researchers for performing specific tasks. For example, for difficult detection tasks, researchers with high participation (A level) and strong technical background are given priority; for tasks in a specific region, researchers in the region are matched first. Through correlation analysis, the researchers most relevant to the detection task are screened out, and a preliminary correspondence between tasks and personnel is established. Afterwards, the task assignment module 15 uses the screened researcher relationship to adjust the researcher relationship in the preset task assignment information, ensuring that the final task assignment plan not only takes into account the preset task requirements, but also makes full use of the optimization results based on participation evaluation and feature clustering.

[0065] Through a refined task allocation process, intelligent and personalized allocation of Mycoplasma pneumoniae detection tasks can be achieved, which not only improves the efficiency and quality of task execution, but also provides appropriate task challenges and support based on the characteristics and performance of researchers, forming a virtuous cycle of detection ecosystem, thereby comprehensively improving the participation and effectiveness of Mycoplasma pneumoniae detection.

[0066] Furthermore, the detection tasks are adjusted and allocated according to the evaluation and segmentation results of the researchers, and then the following are included:

[0067] Tracking the execution results of the detection task adjustment;

[0068] Evaluate the researchers in the task based on the execution results and determine the characteristics of the researchers whose execution results meet the execution requirements;

[0069] The researcher characteristics are fed back to the relay inspection task management interface, and the researcher relationship search and adjustment are performed again based on the fed-back researcher characteristics as the search target.

[0070] In a preferred embodiment, first, the execution results of the adjusted detection tasks are continuously tracked, including indicators of multiple aspects such as task completion rate, detection quality, and time efficiency. By monitoring these indicators in real time, the actual situation of task execution can be grasped in a timely manner, providing data support for subsequent evaluation and optimization. Secondly, based on the collected execution results, the researchers involved in the task are evaluated. This evaluation process not only considers the completion of the task, but also analyzes the special skills, problem-solving ability, teamwork spirit, etc. demonstrated by the researchers during the execution process. Through a comprehensive evaluation, researchers who perform well in actual execution and meet or exceed the execution requirements are identified, and the common characteristics of these researchers are summarized.

[0071] Then, the characteristics of these researchers with outstanding performance are fed back to the relay inspection task management interface. These characteristics include skill level, work attitude, adaptability and other aspects. By intuitively displaying these characteristics on the management interface, managers are provided with more abundant decision-making basis. Afterwards, based on these feedback researcher characteristics as new search targets, the researcher relationship search and task allocation adjustment are re-performed, thereby continuously optimizing the accuracy and effectiveness of task allocation.

[0072] Through continuous tracking, evaluation and optimization, we can continuously learn and adapt to changes in the actual testing environment, improve the accuracy and effectiveness of task allocation, and significantly enhance the participation of researchers.

[0073] In summary, the evaluation system for improving the participation rate of Mycoplasma pneumoniae detection by relay detection provided by the embodiment of the present application has the following technical effects:

[0074] The data collection module is used to collect behavioral data of the research population, including detection time, number of detections, task completion, and abnormal reporting rate. By collecting multi-dimensional data, it provides comprehensive data support for the objective evaluation of participation. The data preprocessing module is used to clean and integrate the behavioral data, build a training data set, and segment the training data set to determine the training data and test data. By building and segmenting the training data set, it is prepared for the subsequent machine learning model training and ensures the effectiveness of model training. The model training module is used to train and test the model based on the machine learning algorithm through training data and test data, and converge to obtain the participation evaluation model. The participation evaluation model is used to quantitatively evaluate the participation of multiple indicators of the input researchers. Through iterative learning of training data and test data, a model that can objectively and quantitatively evaluate the participation of researchers is constructed. The evaluation import module is used to obtain the output results of the participation evaluation model, import it into the evaluation database of the researchers, and cluster and segment all researchers in the evaluation database, realizing the effective organization and management of the evaluation results and providing a data basis for subsequent task allocation. The task allocation module is used to adjust and allocate detection tasks according to the evaluation and segmentation results of researchers. It can allocate tasks according to the actual performance and capabilities of researchers, thereby improving the overall detection efficiency and quality.

[0075] Embodiment 2

[0076] Based on the same inventive concept as the evaluation system for improving the participation rate of Mycoplasma pneumoniae detection in the aforementioned embodiment, Figure 2 As shown, the embodiment of the present application provides a method for evaluating the relay detection to improve the participation rate of Mycoplasma pneumoniae detection, the method comprising:

[0077] Collect behavioral data of the study population, including test duration, number of tests, task completion, and abnormality reporting rate;

[0078] Performing data cleaning and integration preprocessing on the behavior data, constructing a training data set, and segmenting the training data set to determine training data and test data;

[0079] Based on the machine learning algorithm, the model is trained and tested through the training data and the test data, and a participation evaluation model is obtained through convergence. The participation evaluation model is used to quantitatively evaluate the participation of multiple indicators of the input researchers;

[0080] Obtaining the output results of the participation evaluation model, importing them into the evaluation database of researchers, and performing clustering segmentation on all researchers in the evaluation database;

[0081] The detection tasks are adjusted and allocated according to the evaluation and segmentation results of the researchers.

[0082] Furthermore, the behavior data is cleaned and integrated for preprocessing to construct a training data set, including:

[0083] Processing missing values ​​and outliers on the behavior data, and unifying the data formats from different sources to complete preprocessing of the behavior data;

[0084] Based on the preprocessed behavioral data, an evaluation mapping relationship between the detection duration, number of detections, task completion status, abnormality reporting rate and participation is established to construct the training data set.

[0085] Furthermore, the behavior data is processed for missing values ​​and outliers, including:

[0086] For missing values ​​in the behavior data, the mode of the feature is used to fill in the missing values ​​to complete the missing value processing;

[0087] Deleting outliers in the behavior data to complete outlier processing;

[0088] After removing the outliers, the continuity analysis of the data features was performed, and when there were missing values, the mode filling process was repeated.

[0089] Furthermore, obtaining the participation evaluation model includes:

[0090] Build a support vector machine, select the kernel function and kernel function parameters, set the C value, and train the support vector machine using training data;

[0091] The trained support vector machine is tested for accuracy using test data, the kernel function parameters and C value are adjusted according to the test results, and training is iterated until the test accuracy reaches the target value, thereby obtaining the engagement evaluation model.

[0092] Furthermore, all researchers in the evaluation database are clustered and segmented, including:

[0093] According to the evaluation results in the evaluation database, the evaluation level is divided and multi-level researcher clusters are constructed;

[0094] The multi-level researcher clusters are re-clustered based on research location, age, family income, and parents' education level to generate cluster labels.

[0095] Furthermore, the detection task adjustment and allocation according to the evaluation segmentation results of the researchers includes:

[0096] Establishing the segmentation level and the mapping association between the cluster labels and the researchers, performing visual conversion, and sending to the relay inspection task management interface;

[0097] Obtaining preset task allocation information of the detection task;

[0098] Analyze the characteristic information of the detection task, including regional characteristics, difficulty characteristics, and support requirement characteristics;

[0099] The regional characteristics, difficulty characteristics, and support requirement characteristics are used as search targets, and correlation analysis is performed on the segmentation levels and clustering labels of the researchers to screen the correspondence between the researchers with the highest correlation and the detection tasks;

[0100] The researcher relationships in the preset task assignment information are adjusted by screening the researcher relationships.

[0101] Furthermore, the detection task is adjusted and allocated according to the evaluation segmentation results of the researchers, and then it also includes:

[0102] Tracking the execution results of the detection task adjustment;

[0103] Evaluate the researchers in the task based on the execution results and determine the characteristics of the researchers whose execution results meet the execution requirements;

[0104] The researcher characteristics are fed back to the relay inspection task management interface, and the researcher relationship search and adjustment are performed again based on the fed-back researcher characteristics as the search target.

[0105] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0106] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. An evaluation system for improving the participation rate of Mycoplasma pneumoniae detection by relay detection, characterized in that: include: The data collection module is used to collect behavioral data of the research population, including test duration, number of tests, task completion, and abnormal reporting rate; A data preprocessing module is used to perform data cleaning and integration preprocessing on the behavior data, construct a training data set, and segment the training data set to determine training data and test data; A model training module, which is used to perform model training and testing based on the training data and the test data based on a machine learning algorithm, and converge to obtain a participation evaluation model, wherein the participation evaluation model is used to perform a quantitative participation evaluation on multiple indicators of input researchers; An evaluation import module is used to obtain the output results of the participation evaluation model, import them into the evaluation database of researchers, and perform clustering and segmentation on all researchers in the evaluation database; The task allocation module is used to adjust and allocate detection tasks according to the evaluation segmentation results of researchers.

2. The evaluation system for improving the participation rate of Mycoplasma pneumoniae detection by relay detection according to claim 1, characterized in that: The data preprocessing module includes the following execution steps: Processing missing values ​​and outliers on the behavior data, and unifying the data formats from different sources to complete preprocessing of the behavior data; Based on the preprocessed behavioral data, an evaluation mapping relationship between the detection duration, number of detections, task completion status, abnormality reporting rate and participation is established to construct the training data set.

3. The evaluation system for improving the participation rate of Mycoplasma pneumoniae detection by relay detection according to claim 2, characterized in that: The data preprocessing module also includes the following execution steps: For missing values ​​in the behavior data, the mode of the feature is used to fill in the missing values ​​to complete the missing value processing; Deleting outliers in the behavior data to complete outlier processing; After removing the outliers, the continuity analysis of the data features was performed, and when there were missing values, the mode filling process was repeated.

4. The evaluation system for improving the participation rate of Mycoplasma pneumoniae detection by relay detection according to claim 2, characterized in that: The model training module includes the following execution steps: Build a support vector machine, select the kernel function and kernel function parameters, set the C value, and train the support vector machine using training data; The trained support vector machine is tested for accuracy using test data, the kernel function parameters and C value are adjusted according to the test results, and training is iterated until the test accuracy reaches the target value, thereby obtaining the engagement evaluation model.

5. The evaluation system for improving the participation rate of Mycoplasma pneumoniae detection by relay detection according to claim 1, characterized in that: Evaluating the import module includes the following execution steps: According to the evaluation results in the evaluation database, the evaluation level is divided and multi-level researcher clusters are constructed; The multi-level researcher clusters are re-clustered based on research location, age, family income, and parents' education level to generate cluster labels.

6. The evaluation system for improving the participation rate of Mycoplasma pneumoniae detection by relay detection according to claim 5, characterized in that: The task allocation module includes the following execution steps: Establishing the segmentation level and the mapping association between the cluster labels and the researchers, performing visual conversion, and sending to the relay inspection task management interface; Obtaining preset task allocation information of the detection task; Analyze the characteristic information of the detection task, including regional characteristics, difficulty characteristics, and support requirement characteristics; The regional characteristics, difficulty characteristics, and support requirement characteristics are used as search targets, and correlation analysis is performed on the segmentation levels and clustering labels of the researchers to screen the correspondence between the researchers with the highest correlation and the detection tasks; The researcher relationships in the preset task assignment information are adjusted by screening the researcher relationships.

7. The evaluation system for improving the participation rate of Mycoplasma pneumoniae detection by relay detection according to claim 6, characterized in that: The detection task is adjusted and allocated according to the evaluation and segmentation results of the researchers, and then it also includes: Tracking the execution results of the detection task adjustment; Evaluate the researchers in the task based on the execution results and determine the characteristics of the researchers whose execution results meet the execution requirements; The researcher characteristics are fed back to the relay inspection task management interface, and the researcher relationship search and adjustment are performed again based on the fed-back researcher characteristics as the search target.

8. A method for evaluating the participation of relay testing in improving Mycoplasma pneumoniae testing, characterized in that: include: Collect behavioral data of the study population, including test duration, number of tests, task completion, and abnormality reporting rate; Performing data cleaning and integration preprocessing on the behavior data, constructing a training data set, and segmenting the training data set to determine training data and test data; Based on the machine learning algorithm, the model is trained and tested through the training data and the test data, and a participation evaluation model is obtained through convergence. The participation evaluation model is used to quantitatively evaluate the participation of multiple indicators of the input researchers; Obtaining the output results of the participation evaluation model, importing them into the evaluation database of researchers, and performing clustering segmentation on all researchers in the evaluation database; The detection tasks are adjusted and allocated according to the evaluation and segmentation results of the researchers.

Images