An integrated evaluation method for duty efficiency based on artificial intelligence

Abstract

The present invention relates to the technical field of duty efficiency, and specifically, to a comprehensive evaluation method for duty efficiency based on artificial intelligence. It includes the following steps: establishing specific goals for efficiency evaluation and determining key indicators for evaluating duty efficiency; collecting duty data related to the evaluation according to the determined indicators; using the Extreme Gradient Boosting model to analyze the duty data and evaluating the duty efficiency based on the duty scoring rules. The design of the present invention can effectively identify the key factors affecting duty efficiency by using advanced machine learning algorithms such as the Extreme Gradient Boosting model and combining the feature selection process, so as to provide more accurate and fair evaluation results. This not only helps to more truly reflect the work performance of duty personnel, but also promotes the transparency and scientificity of performance management. Considering the characteristics of duty data changing with time and environment, by introducing a dynamic adjustment mechanism, the model can better adapt to the complex situations in actual work.

Description

Technical Field

[0001] The present invention relates to the technical field of duty efficiency evaluation, and specifically, to a comprehensive evaluation method for duty efficiency based on artificial intelligence. Background Art

[0002] Traditional duty efficiency evaluations often rely on manual judgments, which are easily affected by factors such as the personal preferences and experiences of the evaluators, resulting in potentially large deviations in the evaluation results and lacking objectivity and consistency. Previous evaluation methods may only focus on one aspect of performance, such as response speed, while ignoring other important factors, such as task completion quality and customer satisfaction, and are unable to comprehensively reflect the true work efficiency of duty personnel. In the big data era, a large amount of data is generated during the duty process, but traditional methods have not fully utilized this data for in-depth analysis, missing the opportunity to discover potential problems and improvement opportunities through data analysis. Traditional evaluation methods usually adopt fixed standards or models, which are difficult to adapt to the changing factors in the duty environment, such as emergencies and seasonal fluctuations, resulting in a disconnection between the evaluation results and the actual situation. In summary, a comprehensive evaluation method for duty efficiency based on artificial intelligence is provided. Summary of the Invention

[0003] The purpose of the present invention is to provide a comprehensive evaluation method for duty efficiency based on artificial intelligence to solve the problems of strong subjectivity, single evaluation dimension, low data utilization rate, and lack of dynamic adjustment ability in traditional duty as mentioned in the above background art.

[0004] To achieve the above purpose, the present invention provides a comprehensive evaluation method for duty efficiency based on artificial intelligence, including the following steps:

[0005] S1. Establish the goal of efficiency evaluation and determine the indicators for evaluating duty efficiency;

[0006] S2. Collect duty data related to the evaluation according to the indicators for evaluating duty efficiency;

[0007] S3. Use the Extreme Gradient Boosting model to analyze the duty data. For night duty in low light conditions, optimize the Extreme Gradient Boosting model. Based on the analysis results of the model, evaluate the duty efficiency according to the duty scoring rules.

[0008] As a further improvement of this technical solution, in S1, establishing the goal of efficiency evaluation and determining the indicators for evaluating duty efficiency includes the following steps:

[0009] S1.1. Define the duty response time of the efficiency evaluation goal and set the goal;

[0010] S1.2. Determine that the key indicator for evaluating duty efficiency is the average response time.

[0011] As a further improvement of this technical solution, in S2, the duty data includes duty records, duty time, duty frequency, and customer feedback.

[0012] As a further improvement of this technical solution, in S3, according to the analysis result of the model, the duty efficiency is evaluated based on the duty scoring rules, including the following steps:

[0013] S3.1. Preprocess the duty data;

[0014] S3.2. Extract the features related to the duty response time through the duty feature selection model;

[0015] S3.3. Divide the duty data after feature extraction into a training set and a validation set;

[0016] S3.4. Use the training set data to train the extreme gradient boosting model, and adjust the model parameters by minimizing the objective function;

[0017] S3.5. Use the trained model to evaluate new duty data, and evaluate the duty efficiency based on the duty scoring rules.

[0018] As a further improvement of this technical solution, in S3.2, extracting the features related to the duty response time through the duty feature selection model includes the following steps:

[0019] S3.21. Generate new features from the duty data;

[0020] S3.22. Standardize the new features so that the mean of each feature is 0 and the standard deviation is 1;

[0021] S3.23. Construct a duty feature selection model, consider the skewed distribution of the duty response time, optimize the duty feature selection model, and further optimize the duty feature selection model for the dynamic changes of the duty data;

[0022] S3.24. Use the training data set to train the duty feature selection model;

[0023] S3.25. After training, check the coefficients of each feature, and the features with non-zero coefficients are considered to be the features related to the response time.

[0024] As a further improvement of this technical solution, in S3.23, the duty feature selection model is:

[0025] ;

[0026] Considering the skewed distribution of the duty response time, optimize the duty feature selection model:

[0027] ;

[0028] Furthermore, in view of the dynamic changes in the duty data, the duty feature selection model is further optimized:

[0029] ;

[0030] Among them, represents the feature coefficient of the duty feature selection model; represents the estimated value of the optimal feature coefficient; represents the estimated value of the optimal feature coefficient after considering the skewed distribution of the duty response time; represents the estimated value of the optimal feature coefficient after the dynamic changes in the duty data; represents the value of when the following formula reaches the minimum value ; represents the number of duty data records; represents the th target variable of the duty data record; represents the th feature vector of the duty data record; represents the feature corresponding model coefficient; represents the number of features; represents the regularization parameter; represents the index of the duty data record; represents the index of the feature vector; represents the parameter dynamically adjusted based on the data distribution; represents the parameter that controls the influence degree of the weight of the feature on the model complexity under dynamic change conditions; represents the weight of the feature under dynamic change conditions.

[0031] As a further improvement of this technical solution, in S3.4, the extreme gradient boosting model is trained using the training set data, and the model parameters are adjusted by minimizing the objective function, including the following steps:

[0032] S3.41. Establish a response time model error function, and optimize the response time model error function according to different heart rate changes of individuals;

[0033] S3.42. Define the parameters of the extreme gradient boosting model, establish the objective function of the extreme gradient boosting model, optimize the extreme gradient boosting model for duty in remote areas with poor communication, and further optimize the extreme gradient boosting model considering night duty in dim light;

[0034] S3.43. Use the defined parameters and objective function to train the Extreme Gradient Boosting model, and enable the early stopping mechanism during the training process.

[0035] As a further improvement of this technical solution, in S3.41, the response time model error function is:

[0036] ;

[0037] Optimize the response time model error function according to the different heart rate changes of individuals:

[0038] ;

[0039] Among them, represents the error of the response time; represents the error of the response time after considering the different heart rate changes of individuals; represents the actual response time of the th duty data record; represents the actual response time of the th duty data record predicted by the model; represents the number of duty data records; represents the index of the duty data record; represents the number of decision trees; represents the index of the decision tree; represents the regularization term; represents the th decision tree's prediction function; represents the weight related to the heart rate; represents the change in the heart rate of the duty personnel during the duty task.

[0040] As a further improvement of this technical solution, in S3.42, the objective function of the Extreme Gradient Boosting model is:

[0041] ;

[0042] Optimize the Extreme Gradient Boosting model for duty in remote areas with poor communication:

[0043] ;

[0044] Consider night duty in dim light and further optimize the Extreme Gradient Boosting model:

[0045] ;

[0046] Among them, represents the total objective function at the th iteration; represents the total objective function after duty in remote areas with inconvenient communication; represents the total objective function after night duty considering dim light; represents the number of iterations of the extreme gradient boosting model; represents the slope of the objective function at the predicted value of the current response time; represents the curvature of the objective function at the predicted value of the current response time; represents the predicted response time of the decision tree for the th duty data record at the represents the weight factor for adjusting the impact of inconvenient communication areas; represents the indicator function for remote areas; represents the weight for adjusting the impact of night duty; represents the indicator function for night duty; represents the index of the duty data record; represents the regularization term; represents the decision tree model at the

[0047] As a further improvement of this technical solution, in S3.5, the trained model is used to evaluate new duty data, and the duty effectiveness is evaluated based on the duty scoring rules, including the following steps:

[0048] S3.51. Collect new duty data and make the data format consistent with the training data;

[0049] S3.52. Preprocess and standardize the new data;

[0050] S3.53. Generate new features as needed;

[0051] S3.54. Input the standardized new data into the trained model for prediction;

[0052] S3.55. Based on the response time prediction result of the model and the duty scoring rules, interpret the evaluation result of the duty effectiveness.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] 1. In this comprehensive evaluation method of duty effectiveness based on artificial intelligence, by using advanced machine learning algorithms such as the extreme gradient boosting model and combining the feature selection process, this method can effectively identify the key factors affecting duty effectiveness, thereby providing more accurate and fair evaluation results. This not only helps to more truly reflect the work performance of duty personnel, but also promotes the transparency and scientificity of performance management.

[0055] 2. In this comprehensive evaluation method of duty performance based on artificial intelligence, the characteristics of duty data changing with time and environment are considered. By introducing a dynamic adjustment mechanism (such as special optimization for remote areas and night duty), the model can better adapt to the complex situations in actual work. This not only improves the flexibility and practicality of the model, but also promotes the process of continuous improvement and optimization, helps the organization to timely discover and solve the problems existing in the duty process, and thus enhances the overall service quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is the overall method flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] Embodiment: Please refer to Figure 1 As shown, this embodiment provides a comprehensive evaluation method of duty performance based on artificial intelligence, including the following steps:

[0059] S1. Establish the goal of performance evaluation and determine the indicators for evaluating duty performance;

[0060] In this embodiment, establishing the goal of performance evaluation and determining the indicators for evaluating duty performance includes the following steps:

[0061] S1.1. Clearly define the duty response time of the performance evaluation goal and set a goal, such as fixing the average response time at 10 minutes;

[0062] S1.2. Determine that the key indicator for evaluating duty performance is the average response time (the average time from receiving an alarm call to the first responder arriving at the scene).

[0063] S2. Collect duty data related to the evaluation according to the indicators for evaluating duty performance. The data includes duty records, customer feedback, incident handling time, task completion rate, etc.;

[0064] In this embodiment, the duty data includes duty records, duty time, duty frequency, and customer feedback.

[0065] S3. Use the Extreme Gradient Boosting model to analyze the duty data. For night duty in dim light, optimize the Extreme Gradient Boosting model. Based on the analysis results of the model, evaluate the duty performance according to the duty scoring rules;

[0066] In this embodiment, the extreme gradient boosting model is to correct the errors of the previous round of models by gradually adding weak learners (base learners) in an iterative manner, that is, by integrating multiple decision trees, the residual is gradually reduced by an additive model, that is, a new decision tree is added each time to fit the residual of the previous round of predictions; the decision tree can well capture the nonlinear relationship in the data, which makes them particularly suitable for processing complex and nonlinear data sets. In the evaluation of duty efficiency, there may be multiple factors interacting and affecting the response time, and the decision tree can effectively discover these complex relationships; by analyzing a large amount of duty data through the extreme gradient boosting model, it is possible to more accurately predict and evaluate the key indicators such as the response time and task completion of the duty personnel, thereby comprehensively reflecting the duty efficiency; the extreme gradient boosting model can select the factors that have the greatest impact on the duty efficiency from many features, helping managers understand which aspects need to be improved, so as to formulate more targeted optimization measures; the extreme gradient boosting model can process dynamically changing data, adapt to the duty conditions in different time periods and different environments, provide real-time performance evaluation, and support dynamic adjustment and optimization strategies; using the extreme gradient boosting model to analyze duty data and evaluate duty efficiency includes the following steps:

[0067] S3.1. Preprocess the duty data, including cleaning the data and processing missing values and outliers;

[0068] S3.2. Extract relevant features of duty response time through duty feature selection model, including task type, geographical location, task complexity, resource allocation, and ensure that the model only uses the most relevant features for training;

[0069] Among them, the duty feature selection model includes data layer, preprocessing layer, model layer and output layer. The goal of the duty feature selection model is to minimize the complexity of the model as much as possible while minimizing the prediction error, so as to avoid overfitting; the duty feature selection model retains the most important features by compressing unimportant feature coefficients to zero, which makes the model more concise, easier to understand and explain, and helps managers to clarify which factors have the greatest impact on duty response time; through feature selection, the model only needs to consider the most relevant features, which reduces the complexity of the model, reduces the risk of overfitting, and improves the generalization ability of the model; reducing the number of features can significantly reduce the computational cost of the model and speed up training and prediction, which is especially important when dealing with large-scale data sets; by excluding irrelevant or redundant features, the model can focus more on key features, thereby improving the accuracy and stability of prediction; extracting features related to duty response time through the duty feature selection model includes the following steps:

[0070] S3.21. Generate new features from duty data, including extracting duty times, duty duration, and duty frequency features from duty records, and extracting average processing time, maximum processing time, and shortest processing time features from event processing time;

[0071] S3.22. Standardize the new features so that the mean of each feature is 0 and the standard deviation is 1. This step helps to eliminate the impact of feature scale differences on the model.

[0072] S3.23, build a duty feature selection model;

[0073] S3.24. Use the training data set to train the on-duty feature selection model. The model will automatically learn which features have a significant impact on the response time and compress the coefficients of unimportant features to zero. The on-duty feature selection model is a linear model that penalizes larger coefficient values by adding an L1 regularization term to the loss function to achieve the purpose of feature selection. This regularization method can directly compress the coefficients of some unimportant features to zero, effectively achieving feature selection.

[0074] Furthermore, the duty feature selection model is:

[0075] ;

[0076] The duty response time usually presents a skewed distribution, that is, most of the response times are short, while a few of them are long. If this distribution characteristic is not taken into account, the model may overfit the data of short response times and ignore the data of long response times. By optimizing the model, these long-tail effects can be captured more accurately and the accuracy of the overall prediction can be improved. The skewed distribution of data may cause the model to be sensitive to outliers. By optimizing the model, the impact of outliers on the model can be reduced, and the robustness of the model can be improved, so that it can still maintain good performance in the face of extreme values. By considering the skewed distribution, the optimized duty feature selection model can more accurately identify the features that have the greatest impact on the duty response time, which helps to improve the accuracy of feature selection and ensure that the model only uses the most relevant features for training. Considering the skewed distribution of duty response time, the duty feature selection model is optimized:

[0077] ;

[0078] Duty data changes continuously due to factors such as time, environment, and equipment status. By dynamically adjusting the importance of features, the model can better adapt to these changes and provide more accurate evaluation results; the importance of features may vary at different times and in different environments. Through dynamic adjustment, the model can more accurately capture these changes and improve the accuracy of prediction; dynamically adjusting the importance of features can reduce the model's dependence on a specific time period or specific environment, improve the robustness of the model, and enable it to still maintain good performance when facing various changes; through dynamic adjustment, the model can reflect the changes in duty data in real time, provide timely feedback to managers, and help them adjust strategies and resource allocation in a timely manner; further optimize the duty feature selection model for the dynamic changes in duty data:

[0079] ;

[0080] Among them, represents the feature coefficient of the duty feature selection model; represents the estimated value of the optimal feature coefficient; represents the estimated value of the optimal feature coefficient after considering the skewed distribution of the duty response time; represents the estimated value of the optimal feature coefficient after the dynamic changes in the duty data; represents the value of when the following formula reaches the minimum value; represents the number of duty data records; represents the th target variable of the duty data record, that is, the duty response time; represents the th feature vector of the duty data record; represents the feature corresponding model coefficient; represents the number of features; represents the regularization parameter, which is used to control the model complexity and prevent overfitting; represents the index of the duty data record; represents the index of the feature vector; represents the parameter dynamically adjusted based on the data distribution; represents the parameter that controls the influence degree of the weight of feature on the model complexity under dynamic change conditions; represents the weight of feature under dynamic change conditions, which is used to adjust the importance of this feature at different times or in different environments;

[0081] S3.25. After training is completed, check the coefficients of each feature. Features with non-zero coefficients are considered features related to response time;

[0082] S3.3. Divide the on-duty data after feature extraction into a training set and a validation set;

[0083] S3.4. Use the training set data to train the Extreme Gradient Boosting model and adjust the model parameters by minimizing the objective function;

[0084] Among them, by minimizing the objective function, the Extreme Gradient Boosting model can find the optimal model parameters, making the prediction error of the model on the training set the smallest, which helps to improve the prediction accuracy of the model and ensure the reliability of the evaluation results; using the training set data to train the Extreme Gradient Boosting model and adjusting the model parameters by minimizing the objective function includes the following steps:

[0085] S3.41. Establish an error function for the response time model;

[0086] Furthermore, the purpose of establishing the error function for the response time model is to quantify the difference between the model prediction value and the actual value, so as to guide the optimization and parameter adjustment of the model; the error function quantifies the difference between the model prediction value and the actual value through a mathematical formula, providing a specific numerical index. Through the error function, the performance of the model on the training set and the validation set can be evaluated to ensure that the model has good prediction ability; the error function for the response time model is:

[0087] ;

[0088] If an individual has a high heart rate, it indicates that they may be in a high-stress or alert state. The model can accordingly adjust the predicted response time to reflect the possible behavioral changes in this physiologically activated state; the change in heart rate reflects the individual's physiological state and psychological stress, which has a significant impact on the response time. By considering the change in heart rate, the model can more accurately predict the response time and improve the prediction accuracy; the heart rate changes of different individuals are different in different situations (such as tension, fatigue, etc.). By considering these changes, the model can better adapt to the data of different individuals and different situations and improve the robustness of the model; by introducing the change in heart rate as an additional feature, the model can more comprehensively capture the factors affecting the response time and improve the prediction accuracy; optimize the error function for the response time model according to the different heart rate changes of individuals:

[0089] ;

[0090] Among them, represents the error of the response time; represents the error of the response time after considering the different heart rate changes of individuals; Indicates the actual response time of the th duty data record; Indicates the actual response time of the th duty data record predicted by the model; Indicates the number of duty data records; Indicates the index of the duty data record; Indicates the number of decision trees; Indicates the index of the decision tree; Indicates the regularization term used to prevent overfitting; Indicates the th prediction function of the decision tree , is the feature vector of the th duty data record, is the number of leaf nodes of the th decision tree, is the output value of the th leaf node of the th decision tree, is the region corresponding to the th leaf node of the th decision tree; Indicates the weight related to heart rate; Indicates the change in heart rate of the duty personnel during the duty task, used to adjust the response time prediction;

[0091] S3.42. Define the parameters of the extreme gradient boosting model. The parameters include the objective function, evaluation metric, maximum depth of the tree, learning rate, and subsampling ratio, and establish the objective function of the extreme gradient boosting model;

[0092] Furthermore, by establishing the minimization of the objective function, it can ensure that the prediction error of the model on the training set is minimized, thereby improving the prediction accuracy of the model. The objective function of the extreme gradient boosting model is:

[0093] ;

[0094] ;

[0095] Data in remote areas may have special distributions and characteristics. By optimizing the model, these particularities can be captured more accurately, improving the prediction accuracy of the model in remote areas. There may be more noise and outliers in the data of remote areas. By optimizing the model, the robustness of the model can be enhanced, enabling it to maintain good performance when faced with such data. By introducing specific features and adjusting weights, the optimized model can more accurately predict the response time in remote areas, improving the accuracy of predictions. The optimized model can provide a more detailed analysis of the impact of features, helping managers understand which factors have the greatest impact on the duty efficiency in remote areas, and thus formulating more targeted improvement measures. Optimize the extreme gradient boosting model for duty in remote areas with poor communication (such as the Qinghai-Tibet Plateau):

[0096] ;

[0097] Data for night duty may have special distributions and characteristics, such as visual impairments caused by low light and increased fatigue. By optimizing the model, these particularities can be captured more accurately, improving the prediction accuracy of the model in night duty situations. There may be more noise and outliers in the data for night duty. By optimizing the model, the robustness of the model can be enhanced, enabling it to maintain good performance when faced with such data. The optimized model can better adapt to the specific circumstances of night duty, providing more personalized evaluation results to help managers more accurately understand the efficiency of night duty. The optimized model can better adapt to the data changes in night duty, improving the adaptability and generalization ability of the model. Further optimize the extreme gradient boosting model considering night duty with low light:

[0098] ;

[0099] Among them, represents the total objective function at the th iteration; represents the total objective function after duty in remote areas with poor communication; represents the total objective function after considering night duty with low light; represents the number of iterations of the extreme gradient boosting model; represents the curvature of the objective function at the current predicted response time value; represents the predicted response time of the decision tree for the th iteration to the nd duty data record; represents the weight factor for adjusting the impact of areas with poor communication; represents the indicator function for remote areas, which takes the value of 1 when the duty data record is in a remote area with poor communication and 0 otherwise; Represents the weight for adjusting the impact of night duty; Represents the indicator function for night duty, which takes the value of 1 when the duty data record is night duty and 0 otherwise; Represents the index of the duty data record; Represents the regularization term, which is used to control the complexity of the model and prevent overfitting. The regularization term consists of two parts: the structural complexity of the tree and the sum of the squares of the leaf node weights; Represents the decision tree model at the Represents the complexity penalty coefficient of the tree; Represents the number of leaf nodes; Represents the regularization coefficient of the weights; Represents the weight of the leaf node;

[0100] S3.43. Use the defined parameters and objective function to train the extreme gradient boosting model, and enable the early stopping mechanism during training (if the performance on the validation set does not improve in a given number m of consecutive iterations, the training is terminated early, which helps prevent overfitting and can save training time);

[0101] S3.5. Use the trained model to evaluate new duty data and evaluate the duty efficiency (predict the duty response time) based on the duty scoring rules;

[0102] Among them, using the trained model to evaluate new duty data and evaluate the duty efficiency based on the duty scoring rules includes the following steps:

[0103] S3.51. Collect new duty data and make the data format consistent with the training data. The new data includes the following features: the number of duties, duty duration, duty frequency, etc.;

[0104] S3.52. Preprocess and standardize the new data, including data cleaning, removing missing values, outliers, and duplicate values to ensure that the data quality meets the requirements of the model;

[0105] S3.53. Generate new features as needed. For example, extract new features from the duty records (such as the time interval of the last duty), extract new features from the task completion rate (such as the standard deviation of the completion rate), and extract new features from the event handling time (such as the median of the handling time);

[0106] S3.54. Input the standardized new data into the trained model for prediction;

[0107] S3.55. Based on the predicted response time results of the model, interpret the evaluation results of the duty efficiency according to the duty scoring rules, which are specifically as follows: taking 10 minutes of response time as the benchmark, 1 point will be deducted for every 1 minute exceeded in the response time. The efficiency level is: the total score is 100 points, above 90 points is excellent, 80 - 89 points is good, 70 - 79 points is qualified, below 70 points needs improvement. Any response time exceeding 30 minutes will be marked as abnormal and the reason needs to be further investigated.

[0108] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed.

Claims

1. An integrated evaluation method for duty efficiency based on artificial intelligence, characterized in that, It includes the following steps: S1. Establish the goal of performance evaluation and determine the indicators for evaluating duty performance; S2. Collect duty data related to the evaluation according to the indicators for evaluating duty performance; S3. Use the Extreme Gradient Boosting model to analyze the duty data. For night duty in low light conditions, optimize the Extreme Gradient Boosting model. According to the analysis results of the model, evaluate the duty performance based on the duty scoring rules, including the following steps: S3.

1. Preprocess the duty data; S3.

2. Extract the features related to the duty response time through the duty feature selection model, including the following steps: S3.

21. Generate new features from the duty data; S3.

22. Standardize the new features so that the mean of each feature is 0 and the standard deviation is 1; S3.

23. Construct a duty feature selection model. Considering the skewed distribution of the duty response time, optimize the duty feature selection model, and then further optimize the duty feature selection model for the dynamic changes of the duty data; Among them, the duty feature selection model is: ； Considering the skewed distribution of the duty response time, optimize the duty feature selection model: ； For the dynamic changes of the duty data, further optimize the duty feature selection model: ； Among them, represents the feature coefficient of the duty feature selection model; represents the optimal feature coefficient estimate; represents the optimal feature coefficient estimate after considering the skewed distribution of the duty response time; represents the optimal feature coefficient estimate for the dynamic change of the duty data; represents making the following formula reach the minimum value when the value of; represents the number of duty data records; represents the th target variable of the duty data record; represents the th feature vector of the duty data record; represents the feature corresponding model coefficient; represents the number of features; represents the regularization parameter; represents the index of the duty data record; represents the index of the feature vector; represents the parameter dynamically adjusted based on the data distribution; represents controlling the feature under dynamic change conditions, the weight parameter that affects the degree of model complexity; represents the feature weight under dynamic change conditions; S3.

24. Use the training dataset to train the duty feature selection model; S3.

25. After training is completed, check the coefficients of each feature. The features with non-zero coefficients are considered as the features related to the response time; S3.

3. Divide the duty data after feature extraction into a training set and a validation set; S3.

4. Use the training set data to train the Extreme Gradient Boosting model and adjust the model parameters by minimizing the objective function; S3.

5. Use the trained model to evaluate the new duty data and evaluate the duty performance based on the duty scoring rules.

2. The comprehensive evaluation method for duty efficiency based on artificial intelligence according to claim 1, wherein: In the above S1, to establish the goal of performance evaluation and determine the indicators for evaluating duty performance, it includes the following steps: S1.

1. Define the duty response time of the performance evaluation goal and set the goal; S1.

2. Determine that the key indicator for evaluating duty performance is the average response time.

3. The comprehensive evaluation method for duty efficiency based on artificial intelligence according to claim 2, characterized in that: In the above S2, the duty data includes duty records, duty time, duty frequency, and customer feedback.

4. The comprehensive evaluation method for duty efficiency based on artificial intelligence according to claim 1, wherein: In the above S3.4, to use the training set data to train the Extreme Gradient Boosting model and adjust the model parameters by minimizing the objective function, it includes the following steps: S3.

41. Establish a response time model error function. For different heart rate changes of individuals, optimize the response time model error function; Among them, in the above S3.41, the response time model error function is: ； For different heart rate changes of individuals, optimize the response time model error function: ； in, Indicates the error in response time; It indicates the error in response time after individual heart rate changes; Indicates The actual response time of each duty data record; The model predicts the The actual response time of each duty data record; represents the number of decision trees; Represents the index of the decision tree; represents the regularization term; Indicates The prediction function of a decision tree; represents the weight associated with heart rate; Indicates the heart rate change of the on-duty personnel during the duty mission; S3.

42. Define the parameters of the Extreme Gradient Boosting model, establish the objective function of the Extreme Gradient Boosting model. For duty in remote areas with poor communication, optimize the Extreme Gradient Boosting model, and considering night duty in low light conditions, further optimize the Extreme Gradient Boosting model; In the above S3.42, the objective function of the Extreme Gradient Boosting model is: ； For duty in remote areas with poor communication, optimize the Extreme Gradient Boosting model: ； Considering night duty in low light conditions, further optimize the extreme gradient boosting model: ； Among them, represents the total objective function at the th iteration; represents the total objective function after duty in remote areas with inconvenient communication; represents the total objective function after night duty considering dim light; represents the number of iterations of the extreme gradient boosting model; represents the slope of the objective function at the predicted value of the current response time; represents the curvature of the objective function at the predicted value of the current response time; represents the th iteration, the predicted response time of the decision tree for the th duty data record; represents the weight factor for adjusting the impact of areas with inconvenient communication; represents the indicator function for remote areas; represents the weight for adjusting the impact of night duty; represents the indicator function for night duty; represents the regularization term; represents the th iteration of the decision tree model; S3.

43. Use the defined parameters and objective function to train the extreme gradient boosting model and enable the early stopping mechanism during training.

5. The comprehensive evaluation method for duty efficiency based on artificial intelligence according to claim 1, characterized in that: In S3.5, use the trained model to evaluate new duty data and evaluate the duty performance based on the duty scoring rules, including the following steps: S3.

51. Collect new duty data and make the data format consistent with the training data; S3.

52. Preprocess and standardize the new data; S3.

53. Generate new features as needed; S3.

54. Input the standardized new data into the trained model for prediction; S3.

55. Based on the prediction results of the model's response time and the duty scoring rules, interpret the evaluation results of the duty performance.

Images