A method and system for evaluating the contribution rate of functional channels to pilot workload

Abstract

The present invention relates to a method and system for assessing the contribution of functional channels to pilot workload. The method comprises: step S1: collecting multidimensional physiological data of a test pilot in an aircraft cockpit while completing a task, and processing the data to obtain workload; step S2: classifying the pilot's aircraft task into different subtask functional categories based on attention shift information during the pilot's interaction with the aircraft, thereby obtaining a multidimensional functional channel execution sequence; and step S3: dynamically adjusting the length of the pilot's cognitive time domain segments for different subtask functions to correct the workload, constructing a data regression model to perform data regression on the multidimensional functional channel execution sequence and the corrected workload, and inversely calculating the weight ratio of the functional channels to the pilot's workload to obtain the contribution ratio of the functional channels to the pilot's workload. Compared with existing technologies, the present invention has the advantages of more comprehensive and accurate workload assessment.

Description

Technical Field

[0001] The present invention relates to the technical field of workload measurement and evaluation in the aviation field, and in particular to a method and system for evaluating the contribution rate of functional channels to pilot workload. Background Art

[0002] In complex aircraft operations, the workload incurred by pilots as they complete maneuvers in the cockpit impacts aircraft safety and their own operational judgment. Both excessive and low workloads hinder mission completion. Excessive workloads indicate a heavy workload and a high level of stress, which hinders accuracy when handling highly concurrent tasks. On the other hand, low workloads reduce the frequency of pilot monitoring of instrumentation, increasing the probability of errors and bias in their estimation of aircraft state changes. Furthermore, workload is not a directly measurable physical quantity; changes in workload are often assessed indirectly through measurements of relevant physiological data.

[0003] The existing methods that are widely used to indirectly measure pilot workload include:

[0004] 1) In experimental systems or real flight tests, various sensors are used to obtain pilots' physiological indicators and behavioral movements, such as heart rate, eye movements, EEG, EMG, and hand gestures. After completing the data collection, a clustering model is established to obtain a virtual workload value;

[0005] 2) Use methods such as the NASA-TLX scale to estimate the qualitative score after the pilot completes the flight mission.

[0006] However, despite the differences in flight missions, their components can be categorized based on basic functional attributes, such as navigation and obstacle avoidance. Limited to assessing pilot workload after completing a single flight mission, the aforementioned measurement method cannot analyze the contribution of shared elements across different missions to workload.

[0007] Furthermore, since the pilot's interaction with the aircraft cockpit involves instrument display systems, joystick interaction systems, and various button-type control elements, the pilot's operations in different tasks are all related to these basic interactive operations. Therefore, the existing classification of pilot tasks based solely on task start and completion time is insufficient to fully reflect the contribution of common tasks to pilot workload. Summary of the Invention

[0008] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide a method and system for evaluating the contribution rate of functional channels to pilot workload. The method uses the measured workload of multiple physiological signals and the dynamically divided functional channels to perform a dynamic evaluation of pilot workload, which is more comprehensive and more accurate.

[0009] The purpose of the present invention can be achieved by the following technical solutions:

[0010] According to a first aspect of the present invention, a method for evaluating the contribution of functional channels to pilot workload is provided, the method comprising the following steps:

[0011] Step S1: collecting multi-dimensional physiological data of the pilot in the aircraft cockpit when completing the task, and obtaining the workload after processing;

[0012] Step S2: based on the attention shift information during the interaction between the pilot and the aircraft, the pilot is divided into different subtask function categories when performing the aircraft mission, and a multi-dimensional function channel execution sequence is obtained;

[0013] Step S3: Dynamically adjust the pilot's cognitive time domain segment length for different subtask functions, correct the workload, build a data regression model to perform data regression on the multidimensional functional channel execution sequence and the corrected workload, and solve the reverse process to obtain the contribution rate of the functional channel to the pilot's workload.

[0014] Preferably, the multi-dimensional physiological data in step S1 includes eye movement data, respiratory rate data, heart rate data, pilot's motion control input data measured by a cockpit data recorder, and pilot's control command data for instruments in the cockpit.

[0015] Preferably, the step S1 specifically comprises: collecting multi-dimensional physiological data of the test pilot in the aircraft cockpit when completing the task, fitting and extracting visual features, dynamic features and breathing frequency features respectively to obtain the workload.

[0016] Preferably, the subtask function categories in step S2 include collision avoidance, track control, navigation, communication, equipment monitoring and command decision-making.

[0017] Preferably, in step S3, the pilot's cognitive time domain segment lengths for different subtask functions are dynamically adjusted to correct the workload. Specifically, by adjusting the pilot's set cognitive capacity, according to the quantified cognitive factors of different functional channels, the pilot's cognitive time domain segment lengths of varying lengths during task execution are obtained to correct the workload.

[0018] Preferably, the data regression model in step S3 is a multivariate data regression model with a Gamma distribution of α using Bayesian ridge regression.

[0019] Preferably, step S3 specifically includes the following sub-steps:

[0020] Step S31: Setting the pilot's cognitive capacity;

[0021] Step S32: Calculate the cumulative cognitive factor of the functional channel from the current moment, and solve the cognitive time domain length of the functional channel length that meets the maximum cognitive amount. The expression is:

[0022]

[0023] Where W j is the cognitive time domain segment length, ch ij Represents the dynamic function channel sequence CH={ch ij |i=(1,...,N),j=(1,...,T)} is the i-th functional channel at time j, N is the number of functional channels, and T is the length of the time series;

[0024] Step S33: According to the pilot's cognitive time domain segment length W j , set the workload wl in the time range [t,t+W j ] within the attenuation factor fragment Modify workload;

[0025] The revised workload expression is:

[0026]

[0027] Where, the attenuation factor Obey the given random offset The normal distribution of μ is the mean, σ is the variance;

[0028] Step S34: Using the dynamic function channel sequence CH as input data x and the corrected workload data wl' as output data y, a data regression model is established to perform data regression;

[0029]

[0030] Where ε is the deviation value that conforms to the Gaussian probability distribution;

[0031] Step S35: define workload data wl' as the workload data that obeys input data x β The probability distribution p(β i |y,x)=N(y|βx,α), consider the assumption that p(β|α)=N(β|0,α -1 I N ), solve

[0032] Step S36: Change the pilot's cognitive capacity G to obtain l different non-equal length cognitive time domain segments {W j ,W j+1 ,...,W j+l}, and obtain the contribution ratio of different functional channels to workload {β1,β2,...,β N}; Among them, W j ∪W j+1 ∪...∪W j+l =T, where T is the length of the time series.

[0033] According to a second aspect of the present invention, a system for evaluating the contribution of functional channels to pilot workload is provided, using any of the methods described above, the system comprising:

[0034] A multi-dimensional physiological data acquisition and processing module is used to collect multi-dimensional physiological data of the test pilot in the aircraft cockpit when completing the task and obtain the workload after processing;

[0035] A multi-dimensional functional channel execution sequence calculation module is used to classify the pilot's aircraft mission into different sub-task function categories based on the attention shift information during the interaction between the pilot and the aircraft, and obtain the multi-dimensional functional channel execution sequence;

[0036] The workload dynamic assessment module is used to dynamically adjust the length of the pilot's cognitive time domain segment for different sub-task functions, correct the workload, build a data regression model to perform data regression on the multi-dimensional functional channel execution sequence and the corrected workload, and perform inverse solution to obtain the contribution rate of the functional channel to the pilot's workload.

[0037] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, any one of the methods described above is implemented.

[0038] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, any one of the methods described above is implemented.

[0039] Compared with the prior art, the present invention has the following advantages:

[0040] 1) Non-intrusive workload collection covers all mission flight scenarios, overcoming the shortcomings of traditional pilot workload measurement, such as static parameters, incomplete pilot behavior analysis, and single task settings. It is highly convenient and accurate.

[0041] 2) The present invention dynamically adjusts the length of the pilot's cognitive time segment for different task functions to obtain the contribution rate changes of different functional channels in the cockpit to the pilot's workload, with higher accuracy;

[0042] 3) Considering the interaction between the pilot and the cockpit's task functions in human-machine interaction, by measuring multi-dimensional physiological parameters and considering the contribution of pilots' execution of different task functions to workload, the rational division of task functions during flight can be improved;

[0043] 4) The division of cockpit functional channels during operation is associated with the pilot's cognitive time scale to obtain a more accurate distribution of the dynamic results of the pilot performing different flight functions of the aircraft in human-computer interaction, so that the changes in the contribution rate of different task functional channels to the workload are correlated with time. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flow chart of the method of the present invention;

[0045] Figure 2 A schematic diagram of the categories of multiple physiological signal parameters that need to be measured in the comprehensive workload;

[0046] Figure 3 This is a schematic diagram of the N-dimensional pilot mission channel;

[0047] Figure 4 Schematic diagram of the transformation of cognitive time domain segments and the contribution rate of functional channels to workload obtained from dynamic regression. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0049] Example

[0050] like Figure 1As shown, this embodiment provides a dynamic assessment method for the contribution of non-intrusive functional channels in an aircraft cockpit to pilot workload. The method comprises the following steps: based on the pilot's attention shift during interaction with aircraft mission functions, the pilot is divided into different subtask functional categories when performing aircraft missions, and the dynamic execution time series of multi-dimensional functional channels is quantified. Furthermore, the pilot's cognitive capacity is set, and the cumulative amount of cognitive factors in the functional channels is calculated to obtain variable-length cognitive time domain segments. Workload attenuation factor segments are then established to correct the workload calculated based on multiple physiological parameters. Finally, data regression is used to inversely determine the contribution of functional channels to pilot workload. Specifically, based on a regression comparison analysis of the input divided functional channels and workload, the independent contribution of the interactive multi-dimensional functional channels in the flight cockpit to the pilot's workload is determined when the pilot completes the flight mission.

[0051] The specific steps include:

[0052] Step S1: Collect k-dimensional physiological data of the pilot in the aircraft cockpit when completing the task i∈{1,2,...,k}, T represents the length of the time series.

[0053] Step S2: quantify the subtask function categories involved in the interactive process of the pilot performing the task as functional channels CH;

[0054] Step S3: Dynamically adjust the length W of the pilot's cognitive window during the mission execution process j ;

[0055] Step S4: From the dynamic task function channel and the cognitive window length W j Perform data regression on multiple physiological raw data and the corrected workload wl';

[0056] Step S5: Calculate the weighted proportions {β1, β2, ..., β N}.

[0057] like Figure 2 As shown in the figure, the measurement process of the pilot physiological data required for the cockpit functional channel division is as follows:

[0058] (1) Respiratory rate: A chest strap sensor is used, which can be worn on the pilot's chest to obtain the pilot's respiratory rate and respiratory amplitude data;

[0059] (2) Heart rate signal: A wristband photoelectric sensor is used, which can be conveniently worn on the pilot's upper arm to obtain the pilot's heart rate signal;

[0060] (3) Eye movement signal: The eye tracker is used for measurement. The pilot can wear it on his head easily. If the pilot wears glasses, he can also wear them. The eye tracker measurement does not significantly interfere with other parts of the pilot's line of sight. At the same time, the eye movement accessory needs to use a strap to prevent it from falling off, avoiding the workload fluctuation caused by the pilot's brain being subjected to external pressure for a long time. The pilot's eye movement and voice data are defined as E = {e1, e2, ..., e T};

[0061] (4) The cockpit data recorder measures the pilot's action control inputs and the pilot's control commands for cockpit instruments: Since the cockpit devices available for pilot control include continuous control inputs such as joysticks and discrete control inputs such as buttons on instruments, all of these control data must be recorded. In addition, the injection of real-world simulated fault data and the type of fault will also be recorded.

[0062] like Figure 3 As shown in the figure, the detailed steps for extracting the pilot's dynamic function channel are as follows:

[0063] (1) Develop a basic classification of subtasks for the flight mission, including collision avoidance, track control, navigation, communication, equipment monitoring, and command decision-making;

[0064] (2) When data e i When the pilot looks out the window during the mission or operates the TACS (Traffic Alert and Collision Avoidance System) equipment, the pilot activates the mission function channel for handling collision avoidance;

[0065] (3) When data e i When the pilot notices that the aircraft is moving or the flight recorder records the pilot's direct attitude control of the equipment, the pilot's track control channel is activated;

[0066] (4) When data e i It is extracted that when the pilot is checking altitude information or navigation information, the pilot activates the function channel for handling navigation;

[0067] (5) When data e i The pilot communication channel is activated when the pilot (PF) and the pilot (PM) communicate with each other or when the crew members talk to the ATC (Air Traffic Control) tower.

[0068] (6) When data e iWhen the pilot is detected to have made a long visual stop to confirm the engine status and other positions, the pilot's equipment monitoring function channel is deemed to be activated;

[0069] (7) During the entire process of the pilot performing the flight mission, the pilot's command decision-making function channel is activated.

[0070] like Figure 4 As shown in Figure 2, the transformation of cognitive time domain segments during the pilot's dynamic cognitive decision-making process and the contribution rate of functional channels to workload obtained from dynamic regression are:

[0071] (1) Set the pilot's cognitive capacity G;

[0072] (2) Calculate the cumulative cognitive factor of the functional channel from the current time t and solve the cognitive time domain length of the functional channel length that satisfies the maximum cognitive amount.

[0073] (3) According to the segment length W of the pilot's cognitive time domain j , set the workload wl in the time range [t,t+W j ] within the attenuation factor fragment Calculate the corrected workload

[0074] (4) Use Bayesian ridge regression to regress multivariate data with Gamma distribution α: transform the function channel data CH = {ch ij |i=(1,...,N),j=(1,...,T)} is used as input data x, and the corrected workload data wl' is used as output data y to obtain the data regression model Here we assume that ε conforms to the Gaussian probability distribution;

[0075] (5) Using the large-scale input and output function channels and modified workload data obtained from repeated experiments, it is assumed that the workload data wl' is subject to the input data x β The probability distribution p(β i |y,x)=N(y|βx,α), consider the assumption that p(β|α)=N(β|0,α -1 I N ), solve

[0076] (6) Changing the cognitive capacity G, we obtain different l non-equal length cognitive time domain segments {W j ,W j+1 ,...,W j+l}, using the above method, we can get the contribution ratio of different functional channels to workload {β1,β2,...,β N}.

[0077] Next, a system embodiment of the present invention is provided, which is a system for evaluating the contribution rate of functional channels to pilot workload. The system adopts the above-mentioned method and includes:

[0078] A multi-dimensional physiological data acquisition and processing module is used to collect multi-dimensional physiological data of the test pilot in the aircraft cockpit when completing the task and obtain the workload after processing;

[0079] A multi-dimensional functional channel execution sequence calculation module is used to classify the pilot's aircraft mission into different sub-task function categories based on the attention shift information during the interaction between the pilot and the aircraft, and obtain the multi-dimensional functional channel execution sequence;

[0080] The workload dynamic assessment module is used to dynamically adjust the length of the pilot's cognitive time domain segment for different sub-task functions, correct the workload, build a data regression model to perform data regression on the multi-dimensional functional channel execution sequence and the corrected workload, and perform inverse solution to obtain the contribution rate of the functional channel to the pilot's workload.

[0081] The electronic device of the present invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0082] Many components in a device are connected to the I / O interface, including: input units, such as a keyboard and mouse; output units, such as various types of displays and speakers; storage units, such as magnetic disks and optical disks; and communication units, such as network cards, modems, and wireless communication transceivers. The communication unit allows the device to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks.

[0083] The processing unit performs the various methods and processes described above, such as methods S1 to S5. For example, in some embodiments, methods S1 to S5 can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program can be loaded and / or installed on the device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of methods S1 to S5 described above can be performed. Alternatively, in other embodiments, the CPU can be configured to execute methods S1 to S5 by any other appropriate means (for example, by means of firmware).

[0084] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), and the like.

[0085] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0086] In the context of the present invention, machine-readable medium can be a tangible medium that can contain or store a program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0087] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for evaluating the contribution rate of functional channels to pilot workload, characterized in that: The method comprises the following steps: Step S1: collecting multi-dimensional physiological data of the pilot in the aircraft cockpit when completing the task, and obtaining the workload after processing; Step S2: based on the attention shift information during the interaction between the pilot and the aircraft, the pilot is divided into different subtask function categories when performing the aircraft mission, and a multi-dimensional function channel execution sequence is obtained; Step S3: Dynamically adjust the pilot's cognitive time domain segment length for different subtask functions, correct the workload, build a data regression model to perform data regression on the multidimensional functional channel execution sequence and the corrected workload, reversely solve the weight ratio of the functional channel to the pilot's workload, and obtain the contribution rate of the functional channel to the pilot's workload. The data regression model is a multivariate data regression model with a Gamma distribution of α using Bayesian ridge regression, and specifically includes the following substeps: Step S31: Setting the pilot's cognitive capacity; Step S32: Calculate the cumulative cognitive factor of the functional channel from the current moment, and solve the cognitive time domain length of the functional channel length that meets the maximum cognitive amount. The expression is: Where W j is the cognitive time domain segment length, ch ij Represents the dynamic function channel sequence CH = {ch ij |i=(1,...,N),j=(1,...,T)} is the i-th functional channel at time j, N is the number of functional channels, and T is the length of the time series; Step S33: According to the pilot's cognitive time domain segment length W j , set the workload wl in the time range [t,t+W j ] within the attenuation factor fragment Modify workload; The revised workload expression is: Where, the attenuation factor Obey the given random offset The normal distribution of μ is the mean, σ is the variance; Step S34: Using the dynamic function channel sequence CH as input data x and the corrected workload data wl' as output data y, a data regression model is established to perform data regression; Where ε is the deviation value that conforms to the Gaussian probability distribution; Step S35: define workload data wl' as the workload data that obeys input data x β The probability distribution p(β i |y,x)=N(y|βx,α), consider the assumption that p(β|α)=N(β|0,α -1 I N ), solve Step S36: Change the pilot's cognitive capacity G to obtain l different non-equal length cognitive time domain segments {W j ,W j+1 ,...,W j+l }, and obtain the contribution ratio of different functional channels to workload {β1,β2,...,β N }; Among them, W j UW j+1 U...UW j+l =T, where T is the length of the time series.

2. The method for evaluating the contribution rate of functional channels to pilot workload according to claim 1, characterized in that: The multi-dimensional physiological data in step S1 includes eye movement data, respiratory rate data, heart rate data, pilot's motion control input data measured by a cockpit data recorder, and pilot's control command data for instruments in the cockpit.

3. The method for evaluating the contribution rate of functional channels to pilot workload according to claim 1, characterized in that: The step S1 specifically includes: collecting multi-dimensional physiological data of the pilot in the aircraft cockpit when completing the task, fitting and extracting visual features, dynamic features and breathing frequency features respectively to obtain workload.

4. The method for evaluating the contribution rate of functional channels to pilot workload according to claim 1, characterized in that: The subtask function categories in step S2 include collision avoidance, track control, navigation, communication, equipment monitoring and command decision-making.

5. A system for evaluating the contribution of functional channels to pilot workload, characterized in that: The method according to any one of claims 1 to 4 is adopted, wherein the system comprises: A multi-dimensional physiological data acquisition and processing module is used to collect multi-dimensional physiological data of the test pilot in the aircraft cockpit when completing the task and obtain the workload after processing; A multi-dimensional functional channel execution sequence calculation module is used to classify the pilot's aircraft mission into different sub-task function categories based on the attention shift information during the interaction between the pilot and the aircraft, and obtain the multi-dimensional functional channel execution sequence; The workload dynamic assessment module is used to dynamically adjust the length of the pilot's cognitive time domain segment for different sub-task functions, correct the workload, build a data regression model to perform data regression on the multi-dimensional functional channel execution sequence and the corrected workload, and perform inverse solution to obtain the contribution rate of the functional channel to the pilot's workload.

6. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images