Task performance determination method and apparatus, electronic device, and storage medium

Abstract

The present application provides a kind of task performance determination method, device, electronic equipment and storage medium, the method comprises: the electrocardio characteristic parameter, blood oxygen characteristic parameter and workload of user when executing instruction response task are collected;The electrocardio characteristic parameter and blood oxygen characteristic parameter are input to fatigue state estimation model, and the fatigue state grade output by fatigue state estimation model is obtained;According to fatigue state grade and workload, the task performance of user when executing instruction response task is determined;Wherein, fatigue state estimation model is with fatigue state evaluation scale as label, based on electrocardio characteristic parameter sample, blood oxygen characteristic parameter sample and fatigue state grade sample is obtained by training.Fatigue state estimation model is based on the electrocardio characteristic parameter and blood oxygen characteristic parameter with higher correlation with fatigue state, can obtain fatigue state grade with higher accuracy, and then combined with workload, obtain task performance with higher accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a task performance determination method and device, electronic equipment and a storage medium. BACKGROUND

[0002] Fatigue state is a psychophysiological state of cognitive performance decline caused by long-term execution of high-intensity cognitive activities. When the human body enters a fatigue state, the body temperature rises, the oxygen consumption intensifies, and other conditions occur, which to some extent affects the normal metabolism of the body, aggravates the feeling of fatigue, and thus seriously affects the work efficiency and ability of the operator when performing tasks.

[0003] The traditional task performance determination method often uses subjective evaluation method or objective evaluation method to determine the fatigue state of the operator, and then determines the corresponding task performance. However, the former is based on the post-recall of the operator, which leads to strong subjectivity of the subjective evaluation method, is easily affected by the memory of the operator, and is difficult to monitor and evaluate the fatigue state of the operator in real time and accurately during the operation process. The latter is mainly based on a large number of physiological parameter characteristics (such as eye movement, electromyogram, heart rate, pulse, blood oxygen saturation, and electroencephalogram characteristics) of the operator. If a physiological parameter characteristic is not accurate, it will also lead to an inability to accurately evaluate the fatigue state of the operator during the operation process. In this way, neither the subjective evaluation method nor the objective evaluation method can determine a fatigue state with high accuracy, resulting in an inaccurate final task performance. SUMMARY

[0004] The present application provides a task performance determination method, device, electronic equipment and storage medium to solve the problem that neither the subjective evaluation method nor the objective evaluation method can determine a fatigue state with high accuracy in the prior art, resulting in an inaccurate final task performance. Based on the high correlation between the electrocardiogram characteristic parameters and the blood oxygen characteristic parameters and the fatigue state, through a trained fatigue state estimation model, the data calculation is simplified, a fatigue state grade with high accuracy is obtained, and then combined with the work load, a task performance with high accuracy is obtained.

[0005] The present application provides a task performance determination method, comprising the following steps.

[0006] Collecting electrocardiogram characteristic parameters, blood oxygen characteristic parameters and work load of the user when performing an instruction response task;

[0007] Inputting the electrocardiogram characteristic parameters and the blood oxygen characteristic parameters into a fatigue state estimation model to obtain a fatigue state grade output by the fatigue state estimation model;

[0008] determine a task performance of the user in performing the instruction response task according to the fatigue state grade and the workload;

[0009] The fatigue state estimation model is trained based on an electrocardio characteristic parameter sample, an oxygen saturation characteristic parameter sample and a fatigue state grade sample with a fatigue state evaluation scale as a label.

[0010] According to the fatigue state grade, a reaction time proportion influence coefficient, an error rate proportion influence coefficient and a workload critical value corresponding to abnormal operation of the user under the fatigue state grade are determined.

[0011] According to the reaction time calculation formula, the reaction time is determined. work +b;t represents the reaction time, a represents a first coefficient in the reaction time proportion influence coefficient, l represents the workload, and b represents a second coefficient in the reaction time proportion influence coefficient. work

[0012] According to the error rate calculation formula, the error rate is determined.

[0013] ;

[0014] r represents the error rate, a represents a first coefficient in the error rate proportion influence coefficient, Q represents the workload critical value, and b represents a second coefficient in the error rate proportion influence coefficient.

[0015] ​According to the task performance determination method provided by the application, the task performance is determined according to the reaction time and the error rate, and the task performance determination method comprises the following steps: determining the task performance according to a task performance calculation formula; wherein the task performance calculation formula is:

[0016] ;

[0017] wherein, S represents the task performance; S tired T represents the longest reaction time critical value required by the user to complete the instruction response task; and C represents the number of all operations when the user completes the instruction response task.

[0018] According to the task performance determination method provided by the application, the fatigue state estimation model is obtained based on the following steps: acquiring the electrocardiogram characteristic parameter sample, the blood oxygen characteristic parameter sample, and the fatigue state evaluation scale; inputting the electrocardiogram characteristic parameter sample and the blood oxygen characteristic parameter sample into a support vector machine model to obtain the fatigue state grade sample output by the support vector machine model; and performing model parameter updating on the support vector machine model according to the fatigue state evaluation scale and the fatigue state grade sample to obtain the trained fatigue state estimation model.

[0019] According to the task performance determination method provided by the application, the electrocardiogram characteristic parameter at least comprises: a standard deviation, a total power value, and a low-frequency range power and high-frequency range power ratio calculated through heart rate variation data, and a mean value, a standard deviation, a maximum value, a minimum value, a normalized mean value, a normalized maximum value, a normalized minimum value, and a normalized standard deviation calculated through heart rate data; and the blood oxygen characteristic parameter at least comprises: a mean value, a standard deviation, a maximum value, a minimum value, a normalized mean square error, a normalized maximum value, and a normalized minimum value calculated through blood oxygen data.

[0020] The application further provides a task performance determination device, comprising the following modules:

[0021] The data acquisition device is used for acquiring the electrocardiogram characteristic parameter, the blood oxygen characteristic parameter, and the work load of the user when the user performs the instruction response task.

[0022] The fatigue evaluation device is used for inputting the electrocardiogram characteristic parameter and the blood oxygen characteristic parameter into a fatigue state estimation model to obtain a fatigue state grade output by the fatigue state estimation model.

[0023] A data processing apparatus is configured to determine a task performance of the user in performing the instruction response task according to the fatigue state level and the workload, wherein the fatigue state estimation model is trained based on the electrocardiogram feature parameter sample, the blood oxygen feature parameter sample and the fatigue state level sample, and labeled by a fatigue state evaluation scale.

[0024] The application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the task performance determination method according to any one of the above when executing the computer program.

[0025] The application further provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the task performance determination method according to any one of the above.

[0026] The application further provides a computer program product, which includes a computer program, and the computer program is executable on a processor to implement the task performance determination method according to any one of the above.

[0027] The task performance determination method, device, electronic device and storage medium provided by the application collect electrocardiogram feature parameters, blood oxygen feature parameters and workload of a user in performing an instruction response task, input the electrocardiogram feature parameters and the blood oxygen feature parameters into a fatigue state estimation model to obtain a fatigue state level output by the fatigue state estimation model, determine a task performance of the user in performing the instruction response task according to the fatigue state level and the workload, and wherein the fatigue state estimation model is trained based on electrocardiogram feature parameter samples, blood oxygen feature parameter samples and fatigue state level samples, and labeled by a fatigue state evaluation scale. The method is based on electrocardiogram feature parameters and blood oxygen feature parameters which have a high correlation with fatigue state, and through the trained fatigue state estimation model, the fatigue state level with high accuracy can be obtained while simplifying data calculation, and then the task performance with high accuracy can be obtained in combination with the workload. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0029] Figure 1 is a flowchart of the task performance determination method provided by the application.

[0030] Figure 2It is a simple schematic diagram of the flight personnel and the machine respectively executing instruction response tasks provided by the present application.

[0031] Figure 3 It is a scene schematic diagram of the man-machine cooperation executing instruction response tasks provided by the present application.

[0032] Figure 4 It is a whole schematic diagram of the task performance determination method provided by the present application.

[0033] Figure 5 It is a structure schematic diagram of the task performance determination device provided by the present application.

[0034] Figure 6 It is a structure schematic diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0035] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without any creative work under the premise, belong to the protection scope of the present application.

[0036] In order to better understand the embodiments of the present application, first, the background art is described in detail:

[0037] In the case of the operating personnel being the flight personnel, the fatigue state of the flight personnel is affected by the operating task, operating time and resource reserve and other factors. The flight personnel will execute a series of complex human-computer interaction operations when executing the operating task, so that the physical strength and cognitive resources of the flight personnel are continuously consumed, and the fatigue degree of the flight personnel is continuously improved with the increase of the operating time. When the flight personnel is in the fatigue state, the physical strength and cognitive resources can be recovered through rest or sleep, and even special intervention adjustment is needed to recover the work ability. When the resource reserve is sufficient, the human body can withstand more consumption, and the recovery is faster. When the resource reserve is insufficient due to lack of sleep, the human body will enter the fatigue state faster, and the recovery is slower.

[0038] In the air combat task scenario, the flight personnel are often in the working environment of high mobility, high noise, high vibration, information overload, long flight time, night flight against biological laws, etc., which can easily induce the flight personnel to have cognitive fatigue state. Cognitive fatigue is a state of exhaustion and depletion of individual cognitive ability after a long time of high cognitive load tasks or activities. It is a feeling of fatigue caused by long-term continuous concentration, attention and thinking of the brain. However, a certain cognitive fatigue can be converted into physical fatigue, causing double burden on physiology and psychology. In the state of fatigue, the short-term memory of the human body is prone to obstacles, such as an over-fatigued flight personnel may forget the numbers displayed on the instrument he just saw, forget the conversation with other flight personnel a few minutes ago. In addition, the flight personnel will have slower reaction speed, logical confusion in thinking, and even may lead to decline in physiological motor skills and inability to maintain normal operation, thereby causing an increase in decision-making error rate and a large deviation of task performance from the expectation. Therefore, fatigue state mainly affects the execution ability of flight personnel.

[0039] The traditional task performance determination method often uses subjective evaluation method or objective evaluation method to determine the fatigue state of the worker, and then determines the corresponding task performance. Among them, the former mainly evaluates the fatigue state through the form of evaluation scale, usually uses the Karolinska Sleepiness Scale, Stanford Sleepiness Scale, etc. Since the subjective evaluation method is based on the post-recall of the worker, it has strong subjectivity and is easily affected by the memory of the worker, so it is difficult to monitor and evaluate the fatigue state of the worker in the working process in real time and accurately. The latter mainly takes a large number of physiological parameter characteristics of the worker as the basis. If a physiological parameter characteristic is not accurate enough, it will also lead to the inability to accurately evaluate the fatigue state of the worker in the working process.

[0040] Due to the complication of combat system and combat style, the scene situation information faced by the flight personnel in the battlefield presents an exponential growth. At the same time, the complexity of the task itself, the uncertainty of the battlefield working environment and the variability of the collaborative working mode also cause the flight personnel to be too tired.

[0041] Therefore, how to effectively improve the accuracy of determining the fatigue state and then improve the accuracy of determining the task performance has become a technical problem to be solved.

[0042] To solve the above technical problems, the task performance determination method provided by the present application comprises the following steps: collecting electrocardio characteristic parameters, blood oxygen characteristic parameters and work load of a user when the user is executing an instruction response task; inputting the electrocardio characteristic parameters and the blood oxygen characteristic parameters into a fatigue state estimation model to obtain a fatigue state grade output by the fatigue state estimation model; and determining a task performance of the user when the user is executing the instruction response task according to the fatigue state grade and the work load; wherein the fatigue state estimation model is obtained by training electrocardio characteristic parameter samples, blood oxygen characteristic parameter samples and fatigue state grade samples based on a fatigue state evaluation scale as a label. The method is based on electrocardio characteristic parameters and blood oxygen characteristic parameters which have a high correlation with fatigue state, and through the trained fatigue state estimation model, the fatigue state grade with high accuracy can be obtained while simplifying data calculation, and then the task performance with high accuracy can be obtained in combination with the work load. In addition, for the air combat task scenario of the flight personnel, the task performance can be used to support the deployment of the flight personnel in the air combat task and the planning of the pre-war task comprehensive design.

[0043] The following is an example of an operating personnel being a flight personnel, before implementing the task performance determination method provided by the present application, the following processes are further included:

[0044] Process 1: Design a comprehensive fatigue induction test.

[0045] The fatigue state of the flight personnel is mainly affected by factors such as sleep, work intensity, emotion and stress, in order to ensure that the flight personnel reach different levels of fatigue state before executing the instruction response task, a certain test subject is needed to actively induce the fatigue state of the flight personnel as a precondition for subsequent tests. Commonly used means include but are not limited to sleep deprivation and strenuous exercise.

[0046] Process 2: Construct a test module that can be used to evaluate the fatigue state of the flight personnel.

[0047] The evaluation of the fatigue state of the flight personnel mainly includes subjective evaluation method or objective evaluation method.

[0048] The subjective evaluation method is to evaluate the fatigue state through the form of an evaluation scale, usually using the Karolinska Sleepiness Scale, Stanford Sleepiness Scale, etc. The fatigue state evaluation scale used for subjective evaluation combines the characteristics of the Subjective Fatigue Rating Scale, Athlete Psychological Fatigue Questionnaire, Visual Analog Scale, etc., and is formulated according to the actual situation of the flight personnel. The flight personnel fills in each item, answers "yes" or "no" according to their own state, records the score of each item of the flight personnel, and forms the subjective evaluation of the flight personnel on their own fatigue state.

[0049] Objective evaluation method: by the fatigue state related higher electrocardio characteristic parameter sample and blood oxygen characteristic parameter sample, research the two kinds of sample characteristics fusion evaluation flight personnel fatigue state monitoring model, with the fatigue state evaluation scale as the label, carry out support vector machine model (Support Vector Machine, SVM) training, obtain the trained fatigue state estimation model.

[0050] Process 3: Extract test feature data, that is, collect electrocardio characteristic parameter samples and blood oxygen characteristic parameter samples.

[0051] The electrocardio characteristic parameter samples and blood oxygen characteristic parameter samples recorded in the test process are analyzed in time domain and frequency domain, and the analyzed features are mainly divided into two categories: one is the segmented data directly measured in the test process, and the other is the standardized data relative to the resting state. At this time, the analyzed features can be expressed as: f={f1,f2,⋯,f i ,⋯,f 18}, wherein f i is the i-th physiological feature.

[0052] Specifically, the electrocardio characteristic parameters can at least include: standard deviation f1, total power value f2, and low frequency range power to high frequency range power ratio f3 calculated by heart rate variation data (also known as heart rate variability), and mean f4, standard deviation f5, maximum f6, minimum f7, normalized mean f8, normalized maximum f9, normalized minimum f 10 and normalized standard deviation f 11 calculated by heart rate data. The blood oxygen characteristic parameters can at least include: mean f 12 , standard deviation f 13 , maximum f 14 , minimum f 15 , normalized mean f 16 , normalized maximum f 17 and normalized minimum f 18 calculated by blood oxygen data.

[0053] Process 4: Construct a fatigue state evaluation model.

[0054] The fatigue state is classified into three categories, and the fatigue state grade is obtained. Specifically, according to the characteristics of the test data sample (i.e., the above-mentioned electrocardio characteristic parameter sample and the blood oxygen characteristic parameter sample), a support vector machine model is selected as a training model, which can effectively avoid overfitting for small samples of the test and has good generalization ability. The core of the support vector machine model is the construction of the kernel function. Optionally, the commonly used kernel functions can include Gaussian kernel function, linear kernel function, polynomial kernel function and Sigmoid kernel function. The fatigue state classification based on multiple physiological characteristic parameters belongs to a typical nonlinear high-dimensional space data classification problem. Therefore, the model is constructed based on the Gaussian kernel function, the support vector machine model is verified and trained by the K-fold cross method, the data is fully utilized, the performance of the support vector machine model under a certain group of specific data segmentation states is avoided, the generalization performance of the support vector machine model is improved, and the grid search method is used to optimize the penalty factor (C) and the kernel function width (γ).

[0055] For example, in combination with the above-mentioned flow 2, flow 3 and flow 4, the fatigue state estimation model is trained based on the following steps: obtaining the electrocardio characteristic parameter sample, the blood oxygen characteristic parameter sample and the fatigue state evaluation scale; inputting the electrocardio characteristic parameter sample and the blood oxygen characteristic parameter sample into the support vector machine model to obtain the fatigue state grade sample output by the support vector machine model; updating the model parameters of the support vector machine model according to the fatigue state evaluation scale and the fatigue state grade sample to obtain the trained fatigue state estimation model.

[0056] The trained fatigue state estimation model is a fatigue state three-classification evaluation model.

[0057] In the process of training the support vector machine model, the electronic device can first obtain the electrocardio characteristic parameter sample, the blood oxygen characteristic parameter sample and the fatigue state evaluation scale; then, the electronic device inputs the electrocardio characteristic parameter sample and the blood oxygen characteristic parameter sample as input data into the to-be-trained model, that is, into the support vector machine model, analyzes and classifies the input data through the support vector machine model to obtain the prediction data, that is, the fatigue state grade sample; then, the electronic device analyzes the error by combining the fatigue state evaluation scale with the fatigue state grade sample to update the model parameters of the support vector machine model, and obtains the trained fatigue state estimation model. The fatigue state estimation model does not need to be trained with a large amount of sample data, but only depends on the electrocardio characteristic parameter sample and the blood oxygen characteristic parameter sample which have high correlation with the fatigue state, so that a fatigue state estimation model with high accuracy can be obtained for subsequent output of the fatigue state grade.

[0058] Flow 5: Design an evaluation method for the task performance of flight personnel.

[0059] For the instruction response task, the task performance mainly depends on the reaction execution ability of the pilot, and the response delay, logical timing function performance of the machine system. It should be noted that the reaction execution ability is an inherent characteristic of the human body, and different individuals have different ability performances. For the same individual, the reaction execution ability performance remains relatively stable and only changes due to factors such as practice and forgetting. However, in a specific task scenario, the ability performance of the pilot will be affected by the state of mind and show significant and dynamic changes.

[0060] Among them, the reaction execution ability refers to the ability of an individual to quickly respond after receiving a stimulus, which is very important for activities such as handling emergencies, responding to emergencies, and high-speed movement, such as temporary instruction tasks. According to the coupling relationship of the man-machine ring system, the task performance of the man-machine ring system ultimately reflects the response to the task demand, so under the condition that the ability of man-machine can be measured and controlled, the work ability performance can be represented by the task performance, and the reaction execution ability can be represented by the corresponding task performance of the corresponding instruction response.

[0061] In the process of designing the task performance method, in the task scenario of fatigue estimation, the task performance of the pilot can be calculated by the task completion quality, which can be quantitatively evaluated by using indicators such as operation accuracy and behavior reaction time, which can reflect the quality of the pilot's interactive operation when completing a specific task (such as an instruction response task), and the reaction execution ability of the pilot can be represented by related indicators. By evaluating the reaction time of the pilot from receiving the instruction of the ground commander to executing the operation, and the proportion of abnormal operation (i.e. invalid operation and / or error operation) in all operations when performing a specific task, the task performance is comprehensively evaluated.

[0062] Optionally, the initial calculation formula of the task performance is as follows:

[0063] ;

[0064] Among them, represents the task performance; t represents the reaction time; r represents the error rate; T represents the longest reaction time critical value required by the user to complete the instruction response task; and C represents the number of all operations of the user when completing the instruction response task.

[0065] Process 6, variable selection and definition of the instruction response task.

[0066] For the instruction response task, the performance indicators (such as task performance ) corresponding to the two dimensions of reaction time t and error rate r are mainly concerned.

[0067] For example, Figure 2The diagram shown is a schematic representation of a scenario where flight personnel and machines respectively execute command response tasks, as provided by this invention. Figure 2 In China, the performance indicators for flight personnel in executing command response tasks can be represented by P. Ha (t,r) represents the performance index of a machine executing instruction response tasks, which can be represented by P. Ma (t,r) represents.

[0068] In practical applications, a complete command response task typically involves both human and machine-executed phases. The operational phases of a command response task can be represented by Stp. a express.

[0069] For example, such as Figure 3 The image shown is a schematic diagram of a scenario for human-machine collaborative execution of instruction response tasks provided by this invention. Figure 3 In this context, the command response to the task's requirements can be achieved using P. damand (t,r) indicates that from... Figure 3 As can be seen, a single instruction response task can have multiple paths from the task instruction to the response execution. The job flow path can be represented by E. work-path This means that each execution stage introduces a corresponding response time and error rate, and the combined performance of multiple sequential execution stages is the sum of the response time and error rate of all stages. Figure 3 In the diagram, the orange dashed box illustrates a path where all stages are performed by flight personnel. The overall mission performance can be represented by Pa(t,r)=P Ha1 +P Ha2 +P Ha3 The green dashed box illustrates the path where the pilot performs the first two execution stages, and the machine performs the last stage. The overall mission performance can be represented by Pa(t,r)=P. Ha1 +P Ha2 +P Ma3 express.

[0070] As the flight crew achieved different fatigue levels, S tired The changes in the aircraft's ability to respond to commands and the variations in its processing performance for different command signals under different operating conditions can, through adjustments to operational procedures and processes, alter the workload borne by flight personnel. work On the other hand, it will change the cumulative result of reaction time and error rate in task performance.

[0071] The method for determining task performance provided by this invention will be described in detail below.

[0072] Figure 1 This is a flowchart illustrating the task performance determination method provided by the present invention, as shown below. Figure 1As shown, the method comprises:

[0073] Step 101, collect electrocardio characteristic parameters, blood oxygen characteristic parameters and workloads of a user when performing an instruction response task.

[0074] Step 102, input the electrocardio characteristic parameters and the blood oxygen characteristic parameters into a fatigue state estimation model to obtain a fatigue state level output by the fatigue state estimation model.

[0075] The fatigue state estimation model is trained based on electrocardio characteristic parameter samples, blood oxygen characteristic parameter samples and fatigue state level samples with a fatigue state evaluation scale as a label.

[0076] Since the fatigue state estimation model has been pre-trained, after collecting physiological index data of the user when performing the instruction response task, i.e., the electrocardio characteristic parameters and the blood oxygen characteristic parameters, the electronic device can directly input the electrocardio characteristic parameters and the blood oxygen characteristic parameters as input data into the trained fatigue state estimation model to output a fatigue state level with higher accuracy.

[0077] It should be noted that since the fatigue state estimation model can process fatigue states in three categories, the fatigue state level output by the fatigue state estimation model is one of a low fatigue state, a medium fatigue state and a high fatigue state.

[0078] The entire process does not require a large number of physiological parameter characteristics, but only relies on electrocardio characteristic parameters and blood oxygen characteristic parameters with higher correlation with fatigue states. Through the trained fatigue state estimation model, a fatigue state level with higher accuracy can be obtained, and the model calculation process is simplified and the data processing efficiency is improved.

[0079] Step 103, determine a task performance of the user when performing the instruction response task according to the fatigue state level and the workload.

[0080] In some embodiments, the electronic device determines the task performance of the user when performing the instruction response task according to the fatigue state level and the workload, which can include: the electronic device determines a reaction time proportion influence coefficient, an error rate proportion influence coefficient according to the fatigue state level, and a workload critical value corresponding to abnormal operation of the user under the fatigue state level; the electronic device determines a reaction time of the user when performing the instruction response task according to the workload and the reaction time proportion influence coefficient; the electronic device determines an error rate of the user when performing the instruction response task according to the workload, the error rate proportion influence coefficient and the workload critical value; and the electronic device determines the task performance according to the reaction time and the error rate.

[0081] In the process of determining the task performance of the user in performing the instruction response task, the corresponding reaction time proportion influence coefficient, error rate proportion influence coefficient and workload critical value are different due to different fatigue state levels, so the electronic device can determine the corresponding reaction time proportion influence coefficient, error rate proportion influence coefficient and workload critical value based on the fatigue state level output by the fatigue state estimation model; then, the workload and reaction time proportion influence coefficient are calculated to obtain the reaction time, and the workload, error rate proportion influence coefficient and workload critical value are calculated to obtain the error rate, and then the reaction time is combined to determine the task performance of the user.

[0082] In some embodiments, the electronic device determines the reaction time of the user in performing the instruction response task according to the workload and the reaction time proportion influence coefficient, which can include that the electronic device determines the reaction time according to a reaction time calculation formula.

[0083] The reaction time calculation formula is: t = a x l work +b;

[0084] t represents the reaction time; a represents a first coefficient in the reaction time proportion influence coefficient; l work represents the workload; and b represents a second coefficient in the reaction time proportion influence coefficient.

[0085] The electronic device can obtain the reaction time of the user in performing the instruction response task with high accuracy according to the reaction time calculation formula.

[0086] In some embodiments, the electronic device determines the error rate of the user in performing the instruction response task according to the workload, error rate proportion influence coefficient and workload critical value, which can include that the electronic device determines the error rate according to an error rate calculation formula.

[0087] The error rate calculation formula is: ;

[0088] r represents the error rate; a represents a first coefficient in the error rate proportion influence coefficient; Q represents the workload critical value; and b represents a second coefficient in the error rate proportion influence coefficient.

[0089] The electronic device can obtain the error rate of the user in performing the instruction response task with high accuracy according to the reaction time calculation formula.

[0090] That is, the first and second coefficients in the reaction time proportion influence coefficient, the first and second coefficients in the error rate proportion influence coefficient, and the workload critical value are different corresponding to different fatigue state levels.

[0091] In some embodiments, the electronic device determines the task performance according to the reaction time and the error rate, including: determining the task performance according to a task performance calculation formula.

[0092] wherein the task performance calculation formula is:

[0093]

[0094] wherein, S represents the task performance; S represents the fatigue state level; T represents the longest reaction time critical value required by the user to complete the instruction response task; and C represents the number of all operations when the user completes the instruction response task. tired

[0095] According to the reaction time calculation formula, the electronic device can obtain the task performance of the user in executing the instruction response task with high accuracy.

[0096] In the embodiments of the present application, the electrocardio characteristic parameters, the blood oxygen characteristic parameters and the workload of the user in executing the instruction response task are collected; the electrocardio characteristic parameters and the blood oxygen characteristic parameters are input into a fatigue state estimation model to obtain the fatigue state level output by the fatigue state estimation model; and the fatigue state level and the workload are used to determine the task performance of the user in executing the instruction response task; wherein the fatigue state estimation model is obtained by training based on the electrocardio characteristic parameter samples, the blood oxygen characteristic parameter samples and the fatigue state level samples with the fatigue state evaluation scale as the label. The method based on the electrocardio characteristic parameters and the blood oxygen characteristic parameters with high correlation with the fatigue state, through the trained fatigue state estimation model, can obtain the fatigue state level with high accuracy while simplifying the data calculation, and then obtain the task performance with high accuracy in combination with the workload.

[0097] In order to better understand the task performance determination method provided by the present application, the task performance determination method can be described as a whole, as shown in Figure 4 Fig. 1 is a whole schematic diagram of the task performance determination method provided by the present application. As can be seen from Figure 4 , when the instruction response task demand occurs, the instruction task response scene can be set in advance, at this time, the electronic device can evaluate the fatigue state of the user in executing the instruction response task, specifically, the fatigue state estimation model is obtained by training based on the electrocardio characteristic parameter samples, the blood oxygen characteristic parameter samples and the fatigue state level samples with the fatigue state evaluation scale as the label. Then, the electronic device inputs the collected electrocardio characteristic parameters and blood oxygen characteristic parameters into the fatigue state estimation model to obtain the fatigue state level output by the fatigue state estimation model, and obtains the task performance of the user in executing the instruction response task through the task performance calculation formula in combination with the task examination index data (such as the reaction time and the error rate). ​​

[0098] The whole process can obtain a fatigue state grade with high accuracy and a task performance with high accuracy by training a fatigue state estimation model based on electrocardio characteristic parameters and blood oxygen characteristic parameters with high correlation with fatigue state, while simplifying data calculation.

[0099] In order to better understand the task performance determination method provided by the present application, the following will take a high-intensity continuous operation task as an example to specifically illustrate the task performance determination method shown in the above process 1-process 6 and Figure 1 The task performance determination method can include the following steps:

[0100] Step 1: Design a ground simulation test.

[0101] In the comprehensive fatigue induction test, in order to simulate the state influence caused by long-time continuous operation of flight personnel in the air, 11 professional flight personnel first run on a treadmill for two times, each time for 7 minutes (min), to induce different fatigue states by setting the slope level of running, and then enter a flight simulation system based on a cockpit simulation platform for a 7min flight task. In order to reduce the influence of external factors on physiological parameter acquisition, a flexible electrocardio sensor and an earmuff type blood oxygen monitoring system are used to collect the electrocardio signals and blood oxygen signals of the flight personnel, and the subjective evaluation of the flight personnel in the fatigue state is collected before and after the execution of the instruction response task. Before each test, all flight personnel sit quietly for 7min and keep their breath stable, and the physiological signals in this process are collected as a resting state control group.

[0102] Step 2: Design a subjective scale, i.e., a fatigue state evaluation scale.

[0103] The fatigue state evaluation scale used for subjective evaluation combines the characteristics of the Subjective Fatigue Rating Scale, the Athlete Psychological Fatigue Questionnaire, the Visual Analog Scale, and is formulated according to the actual situation of the flight personnel. The flight personnel fill in each item, and according to their own state, they circle "yes" or "no". The 10th, 13th and 14th items in the subjective evaluation questionnaire are reverse scoring, i.e., "yes" is 0 points and "no" is 1 point. Other items are forward scoring, i.e., "yes" is 1 point and "no" is 0 point. The sum of the scores of the 1st to 8th items is the physical fatigue score, and the sum of the scores of the 9th to 14th items is the cognitive fatigue value. The sum of the two is the total fatigue score. The highest total score is 14, and the higher the score, the more serious the fatigue of the flight personnel. The preliminary set threshold is 3 and 9, i.e., a score of 0-3 is considered not tired, 4-9 is moderate fatigue, and 10-14 is severe fatigue, so that the subjective fatigue feeling degree of the testees after the task can be obtained.

[0104] Exemplarily, the question descriptions of the subjective evaluation questionnaire are shown in Table 1.

[0105] Table 1:

[0106]

[0107] As can be seen from Table 1, the subjective evaluation questionnaire has 14 questions.

[0108] Step 3: Collect and process data.

[0109] The fatigue significance of the 18 characteristic parameters involved in the above process 3 is analyzed, wherein P < 0.05 is significant, and the analysis results are shown in Table 2.

[0110] Table 2:

[0111]

[0112] As can be seen from Table 2, the total power value f2, the mean value f4, the standardized mean value f8 of the electrocardiogram characteristic parameters, and the mean value f 12 , the minimum value f 15 , the standardized mean square deviation f 16 and the standardized minimum value f 18 of the blood oxygen characteristic parameters all show an upward trend with the aggravation of the fatigue state; the low-frequency range power and high-frequency range power ratio f3, the standard deviation f5 and the standardized standard deviation f 11 of the electrocardiogram characteristic parameters all first decrease and then increase with the change of the fatigue state characteristic value; the minimum value f7 and the standardized minimum value f 10 of the electrocardiogram characteristic parameters all first increase and then decrease with the change of the fatigue state characteristic value.

[0113] Among them, the standard deviation f1, the maximum value f6, the standardized maximum value f9 of the electrocardiogram characteristic parameters, and the standard deviation f 13 , the maximum value f 14 and the standardized maximum value f 17 of the blood oxygen characteristic parameters are not significantly related to the change of the fatigue state. That is, 12 of the 18 characteristic parameters are significantly related to the change of the fatigue state.

[0114] Step 4: Construct a fatigue state evaluation model.

[0115] The support vector machine model takes the results of the fatigue state evaluation scale as the label, takes the 12 characteristic parameters with significant as the input data of the model training, and based on the K-fold cross-validation method, the 33 groups of samples of the comprehensive fatigue are respectively trained by 8-fold cross-validation, and the test results are shown in Table 3, in %.

[0116] Wherein, H represents the sample data set of model training, H1 represents the first group of data as the test group of the model, and other data groups (i.e. H2-H8) as the training group, the model is constructed by support vector machine model, and the value represents the accuracy of the model when the first group of data is used as the test group.

[0117] Table 3:

[0118]

[0119] As can be seen from Table 3, the average (Mean) of the comprehensive fatigue recognition accuracy of the model between different groups of subjects is 82.6%, that is, the fatigue state estimation model constructed has good applicability for recognizing the comprehensive fatigue state in the flight task. The fatigue state estimation model provides a feasible scheme for effectively identifying the fatigue state grade of the flight personnel, and can support real-time and effective evaluation of the fatigue state of the flight personnel based on the electrocardiogram signal and the blood oxygen signal, and provide a method for intervention and improvement of abnormal state.

[0120] Step 5: Flight test and data acquisition.

[0121] As a test scenario, a typical flight personnel is selected for continuous tracking, and the blood oxygen saturation, heart rate and electrocardiogram parameters of the flight personnel during the flight are collected during the instruction response task, and a questionnaire survey on the fatigue degree of the flight personnel is conducted. During the test, considering the influence of high-intensity flight on safety, a conventional task is selected after sufficient training, so that the stress state of the flight personnel is normal. By setting ground command guidance and not using dynamic confrontation, the situational awareness state of the flight personnel is maintained at a high level.

[0122] The fatigue state evaluation model is used to evaluate the fatigue state grade of the flight personnel, and the subjective fatigue evaluation result of the subjective evaluation questionnaire is compared, as shown in Table 4.

[0123] Table 4:

[0124]

[0125] In order to eliminate the influence of individual differences, the same flight personnel is selected to perform the above instruction response task, and by analyzing the data shown in Table 4, it can be known that:

[0126] For the same flight personnel, the fatigue state level is consistent with the subjective fatigue evaluation result when the sleep is sufficient on the day before flight, and the fatigue state level is low fatigue state; when the sleep is insufficient on the day before flight due to the execution of night flight task, the fatigue state level is low fatigue state to moderate fatigue state, which is consistent with the subjective fatigue evaluation result; the fatigue state level of the second flight is consistent with the subjective fatigue evaluation result, which is moderate fatigue state; when the flight time increases, the fatigue state level is moderate fatigue state to high fatigue state, which is consistent with the subjective fatigue evaluation result. That is, the fatigue state evaluation model can accurately distinguish the fatigue state level of the flight personnel, and has good consistency with the subjective fatigue evaluation result, and the model evaluation is effective.

[0127] It can be known from the comparison between the fatigue state level of real-time evaluation and the subjective fatigue evaluation result that the fatigue state evaluation model can accurately identify the change of the fatigue state of the flight personnel in the flight process, and the subjective evaluation method has a lag effect due to the after-recalling effect, and mainly reflects the final state of the fatigue of the flight personnel. Therefore, the fatigue state evaluation model constructed in the application has good accuracy and real-time performance, and can perform real-time evaluation on the fatigue state of the flight personnel in the task process.

[0128] Therefore, it can be known that the fatigue state of the human body can be affected by the resource reserve and the operation time, and the fatigue state is from low to moderate to high with the continuous operation time, which indicates that the large-intensity continuous flight scenario is effective. When the operation time is long and the resource reserve is poor, the model evaluation result is moderate fatigue state and high fatigue state, the fatigue state evaluation model can correctly distinguish the fatigue state, and has good consistency with the subjective fatigue evaluation result, and the model evaluation is effective.

[0129] That is, the leave-one-out method is used to cross-validate the model, and the model is confirmed to be reasonable and reliable by mutual confirmation with the subjective fatigue evaluation result of the subjective evaluation questionnaire.

[0130] Step 6: Flight test data analysis result.

[0131] In the flight test scenario, the tasks ordered by the ground command center and executed by the flight personnel are all command response tasks. The application selects five typical command response tasks of flight test for analysis, and the work load and fatigue state level are shown in Tables 5-9.

[0132] Table 5:

[0133]

[0134] Table 6:

[0135]

[0136] Table 7:

[0137]

[0138] Table 8:

[0139]

[0140] Table 9:

[0141]

[0142] Wherein, T represents the instruction response task; Q1 represents the visual channel; Q2 represents the auditory channel; Q3 represents the cognitive channel; Q4 represents the fine motor channel; Q5 represents the speech channel; Q6 represents the gross motor channel; and Q7 represents the time resource.

[0143] Step 7: Task performance calculation.

[0144] The task performance corresponding to different workloads and fatigue state grades is shown in Table 10.

[0145] Table 10:

[0146]

[0147] Step 8: Parameter estimation of the task performance corresponding to the instruction response task.

[0148] For the first coefficient a and the second coefficient b in the reaction time calculation formula, which need to identify the influence coefficient of the fatigue state grade on the reaction time ratio, based on the previous large intensity flight test data, fatigue state grades S tired are selected as moderate fatigue state and high fatigue state, and workloads l work are the statistical results of the reaction time under low, medium and high conditions for parameter identification. Among them, a=0.0161, b=0.7407 correspond to the moderate fatigue state; a=0.0377, b=1.6411 correspond to the high fatigue state. Based on this, the above reaction time calculation formula can be obtained:

[0149] t1=0.0161×l work +0.7407, R 2 =0.9008, t1 represents the reaction time corresponding to the moderate fatigue state;

[0150] t2=0.0377×l work +1.6411, R 2 =0.8086, t1 represents the reaction time corresponding to the high fatigue state.

[0151] For the first coefficient a and the second coefficient β in the reaction time calculation formula, which need to identify the fatigue state level to affect the error rate proportion coefficient, based on the previous high-intensity flight test data, fatigue state level S tired The parameter identification is carried out for the error rate statistical results under the moderate fatigue state and the high fatigue state. The working load critical value Q corresponding to the moderate fatigue state is 41.1; the Q corresponding to the high fatigue state is 21.5; a = 0.0009, β = 0.0061. Based on this, the above error rate calculation formula can be obtained:

[0152] r = 0.0009 x l work -0.0061, R 2 = 1.

[0153] From the above analysis, the working load-fatigue state level-instruction response task performance influence law is as follows:

[0154] The fatigue state level has an approximate proportional adjustment effect on the working load-task performance curve. The higher the fatigue state level, the higher the degree of task performance decline and the faster the decline with the working load. The reaction time increases approximately proportionally with the increase of the fatigue state, and the reaction time increases more rapidly with the increase of the working load. The abnormal operation starts to appear in the moderate fatigue state high working load area, and the error rate in the high fatigue state medium and high working load area increases significantly.

[0155] The fatigue state level has a cumulative effect on the task performance. In the current three-class fatigue state, the same level fatigue state will aggravate the decline of the task performance caused by the reaction time effect. The reason for this phenomenon is that fatigue state is a continuous change state, and fatigue state changes continuously with the accumulation of working time. Therefore, in the high fatigue state, the fatigue state will continue to increase with the increase of working time, and the task performance will continue to decline.

[0156] The task performance determination method provided by the application has been preliminarily applied to flight tests, and the scientific and effective method has been proved in practical application, and has achieved great results in the engineering technical field, and has the popularization value.

[0157] The task performance determination device provided by the application is described below. The task performance determination device described below can be correspondingly referred to the task performance determination method described above.

[0158] Figure 5 The structure diagram of the task performance determination device provided by the application is shown in FIG. 1. Figure 5 As shown in FIG. 1, the device comprises:

[0159] The data acquisition device 501 is configured to acquire electrocardio characteristic parameters, blood oxygen characteristic parameters and a workload of a user when the user performs an instruction response task.

[0160] The fatigue evaluation device 502 is configured to input the electrocardio characteristic parameters and the blood oxygen characteristic parameters into a fatigue state estimation model to obtain a fatigue state grade output by the fatigue state estimation model.

[0161] The data processing device 503 is configured to determine a task performance of the user when the user performs the instruction response task according to the fatigue state grade and the workload. The fatigue state estimation model is obtained by training based on electrocardio characteristic parameter samples, blood oxygen characteristic parameter samples and fatigue state grade samples, and taking a fatigue state evaluation scale as a label.

[0162] Optionally, the data processing device 503 is specifically configured to determine a reaction time proportion influence coefficient, an error rate proportion influence coefficient and a workload critical value corresponding to abnormal operation of the user under the fatigue state grade according to the fatigue state grade; determine a reaction time of the user when the user performs the instruction response task according to the workload and the reaction time proportion influence coefficient; determine an error rate of the user when the user performs the instruction response task according to the workload, the error rate proportion influence coefficient and the workload critical value; and determine the task performance according to the reaction time and the error rate.

[0163] Optionally, the data processing device 503 is specifically configured to determine the reaction time according to a reaction time calculation formula; wherein the reaction time calculation formula is t = a x l work +b; t represents the reaction time; a represents a first coefficient in the reaction time proportion influence coefficient; l work represents the workload; and b represents a second coefficient in the reaction time proportion influence coefficient.

[0164] Optionally, the data processing device 503 is specifically configured to determine the error rate according to an error rate calculation formula; wherein the error rate calculation formula is:

[0165] r represents the error rate; a represents a first coefficient in the error rate proportion influence coefficient; Q represents the workload critical value; and b represents a second coefficient in the error rate proportion influence coefficient.

[0166] Optionally, the data processing device 503 is specifically configured to determine the task performance according to a task performance calculation formula; wherein the task performance calculation formula is:

[0167]

[0168] wherein, ​​represents the task performance; S tired represents the fatigue state level; T represents a longest reaction time threshold value required by the user to complete the instruction response task; and C represents the number of all operations when the user completes the instruction response task.

[0169] Optionally, the fatigue state estimation model is obtained based on the following steps: obtaining the electrocardio characteristic parameter sample, the blood oxygen characteristic parameter sample, and the fatigue state evaluation scale; inputting the electrocardio characteristic parameter sample and the blood oxygen characteristic parameter sample into a support vector machine model to obtain the fatigue state level sample output by the support vector machine model; and performing model parameter updating on the support vector machine model according to the fatigue state evaluation scale and the fatigue state level sample to obtain the trained fatigue state estimation model.

[0170] Optionally, the electrocardio characteristic parameter at least includes: a standard deviation, a total power value, and a low frequency range power to high frequency range power ratio calculated from heart rate variation data, and a mean value, a standard deviation, a maximum value, a minimum value, a normalized mean value, a normalized maximum value, a normalized minimum value, and a normalized standard deviation calculated from heart rate data; and the blood oxygen characteristic parameter at least includes: a mean value, a standard deviation, a maximum value, a minimum value, a normalized mean square deviation, a normalized maximum value, and a normalized minimum value calculated from blood oxygen data.

[0171] Figure 6 An example of an entity structure diagram of an electronic device is shown in FIG. 1. Figure 6 As shown in FIG. 1, the electronic device can include a processor 610, a communications interface 620, a memory 630, and a communications bus 640, wherein the processor 610, the communications interface 620, and the memory 630 complete mutual communication through the communications bus 640. The processor 610 can invoke a logical instruction in the memory 630 to execute a task performance determination method, which includes: collecting electrocardio characteristic parameters, blood oxygen characteristic parameters, and a workload of a user when performing an instruction response task; inputting the electrocardio characteristic parameters and the blood oxygen characteristic parameters into a fatigue state estimation model to obtain a fatigue state level output by the fatigue state estimation model; and determining a task performance of the user when performing the instruction response task according to the fatigue state level and the workload, wherein the fatigue state estimation model is obtained based on an electrocardio characteristic parameter sample, a blood oxygen characteristic parameter sample, and a fatigue state level sample with a fatigue state evaluation scale as a label.

[0172] Further, the logic instructions in the memory 630 described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0173] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program can be executed by a processor to enable a computer to perform the task performance determination method provided by the above-mentioned methods. The method comprises: collecting electrocardio characteristic parameters, blood oxygen characteristic parameters and workloads of a user when the user performs an instruction response task; inputting the electrocardio characteristic parameters and the blood oxygen characteristic parameters into a fatigue state estimation model to obtain a fatigue state grade output by the fatigue state estimation model; and determining a task performance of the user when the user performs the instruction response task according to the fatigue state grade and the workload. The fatigue state estimation model is obtained by training based on electrocardio characteristic parameter samples, blood oxygen characteristic parameter samples and fatigue state grade samples with a fatigue state evaluation scale as a label.

[0174] In another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the task performance determination method provided by the above-mentioned methods. The method comprises: collecting electrocardio characteristic parameters, blood oxygen characteristic parameters and workloads of a user when the user performs an instruction response task; inputting the electrocardio characteristic parameters and the blood oxygen characteristic parameters into a fatigue state estimation model to obtain a fatigue state grade output by the fatigue state estimation model; and determining a task performance of the user when the user performs the instruction response task according to the fatigue state grade and the workload. The fatigue state estimation model is obtained by training based on electrocardio characteristic parameter samples, blood oxygen characteristic parameter samples and fatigue state grade samples with a fatigue state evaluation scale as a label.

[0175] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0176] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0177] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for determining task performance, characterized in that, include: Collect the user's electrocardiogram characteristics, blood oxygen characteristics, and workload when executing command response tasks; The electrocardiogram characteristic parameters and the blood oxygen characteristic parameters are input into the fatigue state estimation model to obtain the fatigue state level output by the fatigue state estimation model; Based on the fatigue state level, determine the reaction time proportional influence coefficient, the error rate proportional influence coefficient, and the workload threshold corresponding to the user's abnormal operation under the fatigue state level. The user's reaction time when executing the instruction response task is determined based on the workload and the reaction time ratio influence coefficient. The error rate of the user when executing the instruction response task is determined based on the workload, the error rate proportionality coefficient, and the workload threshold. Based on the reaction time and the error rate, determine the user's task performance when executing the instruction response task; The fatigue state estimation model is obtained by training a fatigue state evaluation scale with electrocardiogram characteristic parameter samples, blood oxygen characteristic parameter samples and fatigue state level samples. The formula for calculating the task performance is as follows: ； in, The task performance is represented by t; the reaction time is represented by r; the error rate is represented by S. tired Indicates the fatigue state level; l work The workload is represented by T; the longest response time threshold required for the user to complete the instruction response task is represented by C; and the workload threshold is represented by Q.

2. The method according to claim 1, characterized in that, Determining the user's reaction time when executing the instruction response task based on the workload and the reaction time proportional influence coefficient includes: The reaction time is determined according to the reaction time calculation formula; The formula for calculating the reaction time is: t = a × l work +b; a represents the first coefficient in the reaction time ratio influence coefficient; b represents the second coefficient in the reaction time ratio influence coefficient.

3. The method according to claim 2, characterized in that, Determining the error rate of the user when executing the instruction response task based on the workload, the error rate proportionality coefficient, and the workload threshold includes: The error rate is determined according to the error rate calculation formula; The error rate calculation formula is as follows: ; α represents the first coefficient in the error rate proportional influence coefficient; β represents the second coefficient in the error rate proportional influence coefficient.

4. The method according to any one of claims 1-3, characterized in that, The fatigue state estimation model is trained based on the following steps; Obtain the electrocardiogram characteristic parameter samples, blood oxygen characteristic parameter samples, and the fatigue state evaluation scale; The electrocardiogram feature parameter samples and the blood oxygen feature parameter samples are input into the support vector machine model to obtain the fatigue state level samples output by the support vector machine model. Based on the fatigue state evaluation scale and the fatigue state level samples, the model parameters of the support vector machine model are updated to obtain the trained fatigue state estimation model.

5. The method according to any one of claims 1-3, characterized in that, The electrocardiogram characteristic parameters include at least: the standard deviation, total power value, and the ratio of low-frequency range power to high-frequency range power calculated from heart rate variability data, as well as the mean, standard deviation, maximum value, minimum value, standardized mean, standardized maximum value, standardized minimum value, and standardized standard deviation calculated from heart rate data. Blood oxygen characteristic parameters include at least the mean, standard deviation, maximum value, minimum value, standardized root mean square deviation, standardized maximum value, and standardized minimum value calculated from blood oxygen data.

6. A task performance determination device, characterized in that, include: The data acquisition device is used to collect the user's electrocardiogram characteristic parameters, blood oxygen characteristic parameters, and workload when executing command response tasks; A fatigue assessment device is used to input the electrocardiogram characteristic parameters and the blood oxygen characteristic parameters into a fatigue state estimation model to obtain the fatigue state level output by the fatigue state estimation model. A data processing device is configured to: determine a reaction time proportional influence coefficient, an error rate proportional influence coefficient, and a workload threshold corresponding to an abnormal operation by the user at the fatigue level, based on the fatigue level; determine the user's reaction time when executing the instruction response task based on the workload and the reaction time proportional influence coefficient; determine the user's error rate when executing the instruction response task based on the workload, the error rate proportional influence coefficient, and the workload threshold; and determine the user's task performance when executing the instruction response task based on the reaction time and the error rate. The fatigue state estimation model is obtained by training a fatigue state evaluation scale with electrocardiogram characteristic parameter samples, blood oxygen characteristic parameter samples and fatigue state level samples. The formula for calculating the task performance is as follows: ； in, The task performance is represented by t; the reaction time is represented by r; the error rate is represented by S. tired Indicates the fatigue state level; l work The workload is represented by T; the longest response time threshold required for the user to complete the instruction response task is represented by C; and the workload threshold is represented by Q.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the task performance determination method as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the task performance determination method as described in any one of claims 1 to 5.

Images