Method for predicting cognitive competence of testers based on machine learning data processing system

Abstract

The invention provides a method for predicting the cognitive ability of a testee based on a machine learning data processing system, and relates to the field of data processing, and the method comprises the steps: obtaining physiological parameters and behavior parameters of the testee during the execution of a test flight task; on the basis of the physiological parameters, the behavior parameters and a cognitive competence evaluation model, predicting cognitive competence scores of the testers; the cognitive ability evaluation model is obtained based on training of a training sample; the training sample comprises a training physiological parameter, a training behavior parameter and a cognitive ability score label when the training test flight task is executed. The method is suitable for the evaluation process of the testers, and is used for providing a scheme for accurately and comprehensively predicting the cognitive competence of the testers.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a method for pre-testing a pilot's cognitive ability based on a machine learning data processing system. Background Art

[0002] As a key role in the aviation field, the cognitive ability of test pilots plays a vital role in flight safety and mission execution efficiency. The test flight missions performed by test pilots are often accompanied by high complexity and uncertainty, which requires test pilots to have excellent computing ability, language comprehension ability, logical reasoning ability, spatial imagination ability, and quick decision-making ability.

[0003] Therefore, in the process of test pilot management, how to accurately and comprehensively evaluate the cognitive ability of test pilots becomes our need. Summary of the invention

[0004] The present application provides a method for pre-testing pilot cognitive ability based on a machine learning data processing system, which can use a pre-trained artificial intelligence model to evaluate the cognitive ability score of the test pilot, providing a solution for accurately and comprehensively pre-testing the pilot's cognitive ability.

[0005] In a first aspect, the present application provides a method for predicting a test pilot's cognitive ability based on a machine learning data processing system, the method comprising: obtaining physiological parameters and behavioral parameters of the test pilot when performing a test flight mission; based on the physiological parameters, behavioral parameters, and a cognitive ability evaluation model, predicting the test pilot's cognitive ability score; the cognitive ability evaluation model is obtained by training based on training samples; the training samples include training physiological parameters, training behavioral parameters, and cognitive ability score labels when performing a training test flight mission.

[0006] The method for predicting the cognitive ability of test pilots based on a machine learning data processing system provided in the present application can obtain the physiological parameters and behavioral parameters of the test pilots when performing test flight tasks, and then predict the cognitive ability score of the test pilots based on the physiological parameters, behavioral parameters, and cognitive ability evaluation models, and the cognitive ability evaluation models are obtained by training based on training samples; the training samples include training physiological parameters, training behavioral parameters, and cognitive ability score labels when performing training test flight tasks. That is, the device for predicting the cognitive ability of test pilots based on a machine learning data processing system can use a pre-trained artificial intelligence model to predict the cognitive ability score of test pilots, providing a solution for accurately and comprehensively predicting the cognitive ability of test pilots, which is convenient for improving the cognitive ability evaluation level of test pilots.

[0007] Optionally, based on the physiological parameters, behavioral parameters, and cognitive ability evaluation model, the cognitive ability score of the test pilot is predicted, including: determining the complexity parameter of the test flight task based on the physiological parameters and behavioral parameters; inputting the complexity parameter into the cognitive ability evaluation model to obtain the cognitive ability score of the test pilot output by the cognitive ability evaluation model.

[0008] The method for predicting the cognitive ability of test pilots based on a machine learning data processing system provided in the present application can also determine the complexity parameters of the test flight task based on physiological parameters and behavioral parameters, thereby realizing the quantification of task complexity and perceived difficulty of the operation, providing a more accurate and objective basis for the evaluation of operational capabilities, and can be applied to various scenarios that require the evaluation of the difficulty of test flight tasks. It can realize the accurate prediction of the test pilot's perception of difficulty in different task complexity scenarios, thereby understanding the difficulties faced by the test pilot in performing the task.

[0009] Optionally, the physiological parameters include at least one of the following: heart rate parameters, breathing parameters, skin electricity parameters, and eye movement parameters.

[0010] Optionally, the behavioral parameters are determined based on a sub-task approach.

[0011] Optionally, the cognitive ability score is the NASA-TLX.

[0012] Optionally, the method further includes: obtaining a training sample set; the training sample set includes a plurality of training samples; and training an initial model of the cognitive ability assessment model based on the training sample set to obtain the cognitive ability assessment model.

[0013] Optionally, the initial model of the cognitive ability assessment model is trained based on the training sample set to obtain the cognitive ability assessment model, including: determining the complexity parameters of the training test flight task based on the training physiological parameters and training behavioral parameters in the training samples; and training the initial model based on the parameters of the complexity of the training test flight task to obtain the cognitive ability assessment model.

[0014] In a second aspect, the present application provides a device for predicting the cognitive ability of a test pilot based on a machine learning data processing system, the device comprising: an acquisition module and a processing module. The acquisition module is used to acquire the physiological parameters and behavioral parameters of the test pilot when performing a test flight mission; the processing module is used to predict the cognitive ability score of the test pilot based on the physiological parameters, behavioral parameters, and a cognitive ability evaluation model; the cognitive ability evaluation model is obtained by training based on training samples; the training samples include training physiological parameters, training behavioral parameters, and cognitive ability score labels when performing a training test flight mission.

[0015] Optionally, the processing module is specifically used to determine the complexity parameters of the test flight task based on the physiological parameters and the behavioral parameters; input the complexity parameters into the cognitive ability evaluation model to obtain the cognitive ability score of the test pilot output by the cognitive ability evaluation model.

[0016] Optionally, the physiological parameters include at least one of the following: heart rate parameters, breathing parameters, skin electricity parameters, and eye movement parameters.

[0017] Optionally, the behavioral parameters are determined based on a sub-task approach.

[0018] Optionally, the cognitive ability score is the NASA-TLX.

[0019] Optionally, the acquisition module is further used to acquire a training sample set; the training sample set includes multiple training samples; the processing module is further used to train the initial model of the cognitive ability evaluation model based on the training sample set to obtain the cognitive ability evaluation model.

[0020] Optionally, the processing module is specifically used to determine the complexity parameters of the training test flight task based on the training physiological parameters and training behavioral parameters in the training samples; train the initial model based on the parameters of the complexity of the training test flight task to obtain a cognitive ability assessment model.

[0021] In a third aspect, the present application provides an electronic device, which includes a processor and a memory; the memory stores instructions executable by the processor; when the processor is configured to execute the instructions, the electronic device implements the method described in the first aspect above.

[0022] In a fourth aspect, the present application provides a computer program product, including computer instructions. When the computer instructions are executed in an electronic device, the electronic device executes the relevant method described in the first aspect above to implement the method described in the first aspect above.

[0023] In a fifth aspect, the present application provides a readable storage medium, which includes: software instructions; when the software instructions are executed in an electronic device, the electronic device implements the method described in the first aspect above.

[0024] The beneficial effects of the second to fifth aspects mentioned above can be referred to the first aspect and will not be elaborated on again. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A schematic diagram of a flow chart of a method for pre-testing a pilot's cognitive ability based on a machine learning data processing system provided in an embodiment of the present application; Figure 2 Another flowchart of a method for pre-testing a pilot's cognitive ability based on a machine learning data processing system provided in an embodiment of the present application; Figure 3 A schematic diagram of a process for evaluating the cognitive ability of pilots provided in an embodiment of the present application; Figure 4 A schematic diagram of the composition of a device for pre-testing a pilot's cognitive ability based on a machine learning data processing system provided in an embodiment of the present application; Figure 5 A schematic diagram of the composition of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In the following, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", or "third", etc. may explicitly or implicitly include one or more of the features.

[0028] As a key role in the aviation field, the cognitive ability of test pilots plays a vital role in flight safety and mission execution efficiency. The test flight missions performed by test pilots are often accompanied by high complexity and uncertainty, which requires test pilots to have excellent computing ability, language comprehension ability, logical reasoning ability, spatial imagination ability, and quick decision-making ability.

[0029] The test pilot cognitive ability prediction methods provided by related technologies mainly rely on psychological assessment paradigms, such as the Pilot Aptitude Test (PAT). Although such tests can reflect the cognitive ability level of test pilots to a certain extent, they mostly focus on the assessment of single cognitive abilities of test pilots, and the accuracy of the assessment is not high.

[0030] Therefore, how to accurately and comprehensively evaluate the cognitive abilities of test pilots becomes our need.

[0031] Based on this, the embodiment of the present application provides a method for pre-testing the pilot's cognitive ability based on a machine learning data processing system, which can use a pre-trained artificial intelligence model to evaluate the pilot's cognitive ability score, providing an accurate and comprehensive solution for pre-testing the pilot's cognitive ability.

[0032] The execution subject of the method for pre-testing the cognitive ability of pilots based on a machine learning data processing system provided in the embodiment of the present application is a device for pre-testing the cognitive ability of pilots based on a machine learning data processing system (or it can also be understood as a machine learning data processing system). The device for pre-testing the cognitive ability of pilots based on a machine learning data processing system can be a management device on an aircraft (such as a fixed-wing aircraft or a helicopter, etc.), or the device for pre-testing the cognitive ability of pilots based on a machine learning data processing system can also be a management device on an aircraft simulator (such as a variable-stable aircraft or a variable-stable helicopter, etc.). Taking the aforementioned two management devices as electronic devices as an example, the device for pre-testing the cognitive ability of pilots based on a machine learning data processing system can also be a processor (such as a central processing unit (CPU)) in the aforementioned electronic device; or, the device for pre-testing the cognitive ability of pilots based on a machine learning data processing system can also be an application (application, APP) installed in the aforementioned electronic device for executing the method for predicting the cognitive ability of test pilots; or, the device for pre-testing the cognitive ability of pilots based on a machine learning data processing system can also be a functional module in the aforementioned electronic device for executing the method for predicting the cognitive ability of test pilots, etc. The embodiment of the present application is not limited to this.

[0033] For simplicity of description, the following is an introduction using an apparatus for predicting the cognitive ability of a pilot based on a machine learning data processing system as an example of an execution subject of the method for predicting the cognitive ability of a pilot based on a machine learning data processing system provided in an embodiment of the present application.

[0034] Figure 1 The flowchart of the method for pre-testing the pilot's cognitive ability based on the machine learning data processing system provided in the embodiment of the present application is as follows. Figure 1 As shown, the method includes the following steps: S101. Acquire physiological parameters and behavioral parameters of the test pilot when performing a test flight mission.

[0035] The physiological parameters may include at least one of the following: a heart rate parameter, a breathing parameter, a skin electrical parameter, and an eye movement parameter.

[0036] As an example, a test flight task may include multiple subtasks, such as an information screening ability subtask, an attention allocation ability subtask, and a reasoning and decision-making ability subtask, etc. The device for pre-testing the cognitive ability of the test pilot based on the machine learning data processing system can respectively obtain the physiological parameters of the test pilot when performing different subtasks.

[0037] Optionally, the behavior parameters of the test pilot when performing the test flight mission can be determined based on the sub-task method.

[0038] As an example, in the behavioral parameters, using the sub-task method, first complete a primary task, and then complete the secondary task as much as possible if there is spare capacity. Based on the assumption that different types of tasks share the same cognitive operation limit, the higher the cognitive load of the primary task on the test pilot, the less attention the test pilot can allocate to the secondary task, and the worse the performance on the secondary task.

[0039] For example, a detection response task (DRT) can be used to provide a simple stimulus (such as a light or a vibrating buzzer). The stimulus appears randomly every 3-5 seconds, and the test pilot is required to press a key as quickly as possible after the stimulus appears. The test pilot's accuracy and response indicators on the DRT task can be used as behavioral parameters.

[0040] S102. Pre-test the pilot's cognitive ability score based on the physiological parameters, behavioral parameters, and cognitive ability assessment model.

[0041] Among them, the cognitive ability evaluation model is trained based on training samples, and the training samples include training physiological parameters, training behavioral parameters, and cognitive ability scoring labels when performing training test flight tasks. The specific training process of the cognitive ability evaluation model can be referred to in the following embodiments and will not be repeated here.

[0042] As an example, the cognitive ability score may be embodied as the National Aeronautics and Space Administration Task Load Index (NASA-TLX).

[0043] In some possible embodiments, the above S102 may specifically include the following steps: Step 1a: Determine the complexity parameters of the flight test task based on physiological parameters and behavioral parameters.

[0044] As an example, a device for pre-testing a pilot's cognitive ability based on a machine learning data processing system can obtain the physiological parameters and behavioral parameters of each of the multiple test flight tasks, and then respectively calculate the average values ​​to obtain reference physiological parameters and reference behavioral parameters, and then calculate the physiological parameter score based on the difference between the physiological parameters obtained in S101 and the reference physiological parameters, and calculate the behavioral parameter score based on the difference between the behavioral parameters obtained in S101 and the reference behavioral parameters, and then perform weighted summation on the physiological parameter score and the behavioral parameter score to obtain the complexity parameter of the test flight task.

[0045] Step 2a: Input the complexity parameter into the cognitive ability evaluation model to obtain the cognitive ability score of the test pilot output by the cognitive ability evaluation model.

[0046] The cognitive ability assessment model can also be understood as a model for predicting the cognitive ability score of the test pilot based on the complexity parameters of the test pilot when performing the test flight mission.

[0047] The method for predicting the cognitive ability of a test pilot based on a machine learning data processing system provided in the embodiment of the present application can obtain the physiological parameters and behavioral parameters of the test pilot when performing a test flight task, and then determine the cognitive ability score of the test pilot based on the physiological parameters, behavioral parameters, and a cognitive ability evaluation model, wherein the cognitive ability evaluation model is obtained by training based on training samples; the training samples include training physiological parameters, training behavioral parameters, and cognitive ability score labels when performing a training test flight task. That is, the device for predicting the cognitive ability of a test pilot based on a machine learning data processing system can use a pre-trained artificial intelligence model to evaluate the cognitive ability score of the test pilot, providing a solution for accurately and comprehensively evaluating the cognitive ability of the test pilot, which is convenient for improving the cognitive ability evaluation level of the test pilot.

[0048] In addition, the method for predicting the cognitive ability of a test pilot based on a machine learning data processing system provided in the embodiment of the present application can also determine the complexity parameters of the test flight task based on physiological parameters and behavioral parameters, thereby realizing the quantification of the task complexity and the perceived difficulty of the operation, and providing a more accurate and objective basis for the evaluation of the operation ability. It can be applied to various scenarios that require the evaluation of the difficulty of the test flight task, and can realize the accurate prediction of the test pilot's difficulty perception in different task complexity scenarios, thereby understanding the difficulties faced by the test pilot in performing the task.

[0049] The following is an introduction to the process of obtaining the above-mentioned cognitive ability assessment model.

[0050] In some possible embodiments, before the above S101, the device for pre-testing the pilot's cognitive ability based on the machine learning data processing system can also obtain a trained (or pre-trained) cognitive ability assessment model.

[0051] In one possible implementation, a device for pre-testing a pilot's cognitive ability based on a machine learning data processing system can directly obtain a trained cognitive ability assessment model from other equipment.

[0052] For example, a device for pre-testing a pilot's cognitive ability based on a machine learning data processing system can obtain a trained cognitive ability assessment model from other devices by downloading or transferring it to an intermediate storage medium.

[0053] In another possible implementation, the device for pre-testing the pilot's cognitive ability based on the machine learning data processing system can also train the initial model of the cognitive ability evaluation model based on the training sample set to obtain the cognitive ability evaluation model. In this case, Figure 2Another flow chart of the method for pre-testing the pilot's cognitive ability based on the machine learning data processing system provided in the embodiment of the present application. Figure 2 As shown, before the above S101, the method may further include the following steps: S201: Obtain a training sample set.

[0054] Among them, the training sample set includes multiple training samples. As mentioned above, the training samples include training physiological parameters, training behavioral parameters, and cognitive ability score labels of the training test flight task. The process of obtaining the training physiological parameters and training behavioral parameters of the training test flight task in the training sample can refer to the method of obtaining the physiological parameters and behavioral parameters when performing the test flight task in S101 above, and will not be repeated here. The cognitive ability score label can be obtained by the test pilot completing the NASA-TLX self-report after completing the training test flight task.

[0055] S202: Train the initial model of the cognitive ability evaluation model based on the training sample set to obtain the cognitive ability evaluation model.

[0056] In some possible embodiments, the above S202 may specifically include the following steps: Step 1b: Determine the complexity parameters of the training test flight task based on the training physiological parameters and training behavioral parameters in the training samples.

[0057] The specific process of step 1b can refer to the above step 1a, which will not be repeated here.

[0058] Step 2b: Train the initial model based on the parameters of the complexity of the training test flight task to obtain a cognitive ability evaluation model.

[0059] As an example, the initial model may adopt a Support Vector Regression (SVR) model.

[0060] For example, the device for pre-testing the pilot's cognitive ability based on the machine learning data processing system can use the training physiological parameters and training behavioral parameters in the training samples as independent variables, and the cognitive ability score label as the dependent variable to train the SVR model. The device for pre-testing the pilot's cognitive ability based on the machine learning data processing system can convert the training physiological parameters and training behavioral parameters in the training samples into the form of feature matrices and target vectors, and then find a regression model corresponding to a partitioning hyperplane with the largest distance based on the sample space where the feature training set is located, which can be specifically expressed as the following formula: Formula (1) In formula (1), represents the dependent variable, Independent variable, represents the weight vector, Represents the bias term. According to the following formula, the optimal partitioning hyperplane is obtained. and , so that and y The absolute value of the difference between Calculate the loss when: Formula (2) In formula (2), represents the regularization constant, represents the loss function, Indicates The cognitive ability score labels in the training samples. Introducing slack variables and , formula (2) can be rewritten as: Formula (3) By solving the convex quadratic programming problem, the solution to the SVR problem can be obtained, as shown in the following formula: Formula (4) In formula (4), Represents the number of expenditure vectors. and represents the coefficients of the Lagrange multiplier method.

[0061] However, the data sample space collected based on the test flight mission does not necessarily satisfy the assumption of linear separability, so a feature mapping from low latitude to high latitude can be defined Instead of the inner product, the samples are linearly separable in the high-dimensional feature space: Formula (5) After introducing the kernel function, SVR can be rewritten as: Formula (6) In formula (6), Represents the kernel function.

[0062] In some embodiments, the device for pre-testing the pilot's cognitive ability based on the machine learning data processing system can also use a ten-fold cross-validation method to calculate the accuracy of the initial model during the training process. If the accuracy reaches an accuracy threshold, the training can be stopped and the initial model output during training can be used as a cognitive ability evaluation model.

[0063] As an example, a device for pre-testing the pilot's cognitive ability based on a machine learning data processing system can divide the data set into ten parts on average. The first fold uses data sets 1-2 as the test sample set and the remaining data sets 3-10 as the training sample sets to calculate the accuracy. The second fold uses data sets 3-4 as the test sample set and the remaining data sets as the training sample sets to calculate the accuracy. And so on. The accuracy of each ten fold is calculated respectively, and the average accuracy is calculated.

[0064] The method for predicting the cognitive ability of test pilots based on a machine learning data processing system provided in the embodiment of the present application adopts a support vector regression algorithm model that transforms the sample space from nonlinear to linear through a kernel function method, and transforms it into another linear space by replacing the inner product space with a kernel function space without knowing the specific form of the nonlinear transformation function, thereby improving the effect of evaluating the cognitive ability of test pilots and being superior to traditional linear models.

[0065] Based on the understanding of the above embodiments, Figure 3 This is a flow chart of the pilot cognitive ability assessment process provided in the embodiment of the present application. Figure 3 As shown, the method mainly includes the following parts: 1. Characterization of task complexity based on human-computer interaction behavior elements.

[0066] Based on the test flight mission scenarios, a human-machine behavior factor library is constructed to decompose cognitive abilities such as information screening ability, attention allocation ability, and reasoning and decision-making ability. Then, by measuring the physiological and behavioral indicators corresponding to different cognitive abilities, the cognitive load that represents the complexity of the task is calculated.

[0067] 2. Assessment of the perceived difficulty of test pilot tasks.

[0068] The NASA-TLX test paper is used as a subjective assessment method for test pilots' perceived difficulty of tasks. This method evaluates cognitive load from three aspects: task (external requirements caused by the task, including 3 questions: psychological requirements, physiological requirements and time requirements), behavior (the effort required to complete the task perceived by the subjects, including 2 questions: effort and performance) and subject-related (the psychological impact of the task requirements perceived by the subjects, including 1 question: frustration). Each question is scored from 1 to 11.

[0069] 3. Modeling the balance between task complexity and job perceived difficulty.

[0070] Physiological and behavioral data are used to characterize task complexity, and self-reports are used to assess perceived difficulty. These perceived difficulties are regressed with the characteristic factors that affect complexity in the task, and the model of the relationship between the test pilots' perceived difficulty of the task and the task complexity balance is optimized, so as to accurately predict the test pilots' perceived difficulty from the representation of task complexity, thereby improving the level of cognitive ability assessment. The trained model is used to predict the test pilots' cognitive ability level of perceived difficulty of the complexity of the newly input task.

[0071] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the device for pre-testing the pilot's cognitive ability based on the machine learning data processing system includes a hardware structure and / or software module corresponding to the execution of each function. It should be easy to realize that the technical goals in this field are combined with the units and algorithm steps of each example described in the embodiments disclosed in this article. The present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technical goals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0072] In an exemplary embodiment, the present application also provides a device for pre-testing the cognitive ability of a pilot based on a machine learning data processing system. Figure 4 A schematic diagram of the composition of a device for pre-testing pilot cognitive ability based on a machine learning data processing system provided in an embodiment of the present application. Figure 4 As shown, the device includes: an acquisition module 401 and a processing module 402.

[0073] The acquisition module 401 is used to acquire the physiological parameters and behavioral parameters of the test pilot when performing the test flight mission; The processing module 402 is used to predict the cognitive ability score of the test pilot based on the physiological parameters, behavioral parameters, and a cognitive ability evaluation model; the cognitive ability evaluation model is trained based on training samples; the training samples include training physiological parameters, training behavioral parameters, and cognitive ability score labels when performing a training test flight task.

[0074] In some possible embodiments, the processing module 402 is specifically used to determine the complexity parameter of the test flight task based on the physiological parameters and the behavioral parameters; input the complexity parameter into the cognitive ability evaluation model to obtain the cognitive ability score of the test pilot output by the cognitive ability evaluation model.

[0075] In some other possible embodiments, the physiological parameter includes at least one of the following: a heart rate parameter, a breathing parameter, a skin electrical parameter, and an eye movement parameter.

[0076] In some other possible embodiments, the behavior parameters are determined based on a sub-task method.

[0077] In some other possible embodiments, the cognitive ability score is the NASA-TLX (National Aeronautics and Space Administration) Task Load Index.

[0078] In some other possible embodiments, the acquisition module 401 is also used to acquire a training sample set; the training sample set includes multiple training samples; the processing module 402 is also used to train the initial model of the cognitive ability assessment model based on the training sample set to obtain the cognitive ability assessment model.

[0079] In some other possible embodiments, the processing module 402 is specifically used to determine the complexity parameters of the training test flight task based on the training physiological parameters and training behavioral parameters in the training samples; and train the initial model based on the parameters of the complexity of the training test flight task to obtain a cognitive ability assessment model.

[0080] It should be noted that Figure 4 The division of modules in the example is schematic and is only a logical function division. There may be other division methods in actual implementation. For example, two or more functions may be integrated into one processing module. The above integrated modules may be implemented in the form of hardware or in the form of software functional units.

[0081] In an exemplary embodiment, the present application also provides an electronic device. Figure 5 The following is a schematic diagram of the composition of the electronic device provided in the embodiment of the present application. Figure 5 As shown, the electronic device includes: a first processor 10 , a memory 20 , a communication line 30 , a communication interface 40 , and an input / output interface 50 .

[0082] The first processor 10 , the memory 20 , the communication interface 40 and the input / output interface 50 may be connected via a communication line 30 .

[0083] The first processor 10 is used to execute instructions stored in the memory 20 to implement the method for pre-testing the pilot's cognitive ability based on a machine learning data processing system provided in the above-mentioned embodiment of the present application. The first processor 10 can be a CPU, a general-purpose processor network processor (network processor, NP), a digital signal processor (digital signal processing, DSP), a microprocessor, a microcontroller (micro control unit, MCU) / single chip microcomputer (single chip microcomputer) / single chip microcomputer, a programmable logic device (programmable logic device, PLD) or any combination thereof. The first processor 10 can also be any other device with processing functions, such as a circuit, a device or a software module, which is not limited in the embodiment of the present application. In one example, the first processor 10 may include one or more CPUs, such as Figure 5 As an optional implementation, the electronic device may include multiple processors, for example, in addition to the first processor 10, it may also include a second processor 60 ( Figure 5 ) is shown by the dotted line as an example.

[0084] The memory 20 is used to store instructions executable by the first processor 10. For example, the instructions may be computer programs. Optionally, the memory 20 may be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions, or a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage devices, etc., and the embodiments of the present application are not limited to this.

[0085] It should be noted that the memory 20 may exist independently of the first processor 10, or may be integrated with the first processor 10. The memory 20 may be located inside the electronic device, or may be located outside the electronic device, which is not limited in the embodiment of the present application.

[0086] The communication line 30 is used to transmit information between various components included in the electronic device.

[0087] The communication interface 40 is used to communicate with other devices or other communication networks. The other communication networks may be Ethernet, radio access network (RAN), wireless local area network (WLAN), etc. The communication interface 40 may be a module, a circuit, a transceiver or any device capable of achieving communication.

[0088] The input / output interface 50 is used to implement human-computer interaction between a user and an electronic device, for example, to implement action interaction or information interaction between a user and an electronic device.

[0089] Exemplarily, the input / output interface 50 may be a mouse, a keyboard, a display screen, or a touch display screen, etc. Action interaction or information interaction between a user and an electronic device may be achieved through a mouse, a keyboard, a display screen, or a touch display screen, etc.

[0090] It should be noted that Figure 5 The structure shown in the figure does not constitute a limitation on the electronic device, except Figure 4 In addition to the components shown, the electronic device may include more or fewer components than shown, or a combination of certain components, or a different arrangement of components.

[0091] In an exemplary embodiment, the embodiment of the present application further provides a readable storage medium, including software instructions, which, when executed on an electronic device, enables the electronic device to execute any one of the methods provided in the above embodiments.

[0092] In an exemplary embodiment, the embodiment of the present application further provides a computer program product including computer instructions, which, when executed on an electronic device, enables the electronic device to execute any one of the methods provided in the above embodiments.

[0093] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer-executable instructions. When the computer-executable instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer-executable instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer-executable instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0094] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art may understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0095] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0096] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting pilot cognitive ability based on a machine learning data processing system, characterized in that: The method comprises: Obtain the physiological and behavioral parameters of the test pilots when performing test flight tasks; Based on the physiological parameters, the behavioral parameters, and the cognitive ability evaluation model, the cognitive ability score of the test pilot is predicted; the cognitive ability evaluation model is trained based on training samples; the training samples include training physiological parameters, training behavioral parameters, and cognitive ability score labels when performing training test flight tasks.

2. The method according to claim 1, characterized in that The predicting of the test pilot's cognitive ability score based on the physiological parameter, the behavioral parameter, and the cognitive ability assessment model includes: Determining a complexity parameter of the flight test task based on the physiological parameter and the behavioral parameter; The complexity parameter is input into the cognitive ability evaluation model to obtain the cognitive ability score of the test pilot output by the cognitive ability evaluation model.

3. The method according to claim 1, characterized in that The physiological parameters include at least one of the following: heart rate parameters, breathing parameters, skin electricity parameters, and eye movement parameters.

4. The method according to claim 1, characterized in that: The behavior parameters are determined based on a sub-task approach.

5. The method according to claim 1, characterized in that The cognitive ability score is the NASA-TLX, the National Aeronautics and Space Administration's Task Load Index.

6. The method according to claim 1, characterized in that The method further comprises: Acquire a training sample set; the training sample set includes a plurality of the training samples; The initial model of the cognitive ability evaluation model is trained based on the training sample set to obtain the cognitive ability evaluation model.

7. The method according to claim 6, characterized in that The step of training the initial model of the cognitive ability evaluation model based on the training sample set to obtain the cognitive ability evaluation model includes: Determining the complexity parameter of the training flight test task based on the training physiological parameters and the training behavioral parameters in the training sample; The initial model is trained based on the parameters of the complexity of the training test flight task to obtain the cognitive ability assessment model.

8. A device for pre-testing pilot cognitive ability based on a machine learning data processing system, characterized in that: include: Acquisition module and processing module; The acquisition module is used to acquire the physiological parameters and behavioral parameters of the test pilot when performing the test flight mission; The processing module is used to predict the cognitive ability score of the test pilot based on the physiological parameters, the behavioral parameters, and the cognitive ability assessment model; The cognitive ability assessment model is obtained by training based on training samples; The training samples include training physiological parameters, training behavioral parameters, and cognitive ability score labels when performing training test flight tasks.

9. An electronic device, characterized in that: include: Processor and memory; The memory stores instructions executable by the processor; When the processor is configured to execute the instructions, the electronic device implements the method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium includes: software instructions; When the software instructions are executed in an electronic device, the electronic device implements the method according to any one of claims 1 to 7.

Images