Cognitive load assessment method, device and equipment and readable storage medium

Abstract

The invention discloses a cognitive load assessment method, device and equipment and a readable storage medium. The cognitive load assessment method comprises the steps of obtaining a cognitive load subjective score of a to-be-assessed interaction task; determining a driving behavior score of the to-be-evaluated interaction task; determining an electroencephalogram index score of the to-be-evaluated interaction task; determining an eye movement index score of the to-be-evaluated interaction task; determining respective weights of the cognitive load subjective score, the driving behavior score, the electroencephalogram index score and the eye movement index score of the to-be-evaluated interaction task by adopting an analytic hierarchy process; the cognitive load subjective score, the driving behavior score, the electroencephalogram index score and the eye movement index score of the to-be-evaluated interaction task are multiplied by respective weights and then summed, and a cognitive load comprehensive score of the to-be-evaluated interaction task is obtained through calculation. According to the method and the device, the calculated cognitive load comprehensive score of the to-be-evaluated interaction task can be considered more comprehensively, and evaluation is more accurate.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle human-computer interaction evaluation, and in particular to a cognitive load evaluation method, device, equipment and readable storage medium. Background Art

[0002] With the development of 5G (5th Generation Mobile Communication Technology, the fifth generation of mobile communication technology, referred to as 5G) and the popularization of smart cars, new technologies, new scenarios and new modes in smart cockpits continue to emerge. In order to meet the driver's safe, efficient and comfortable human-computer interaction experience during driving, multimodal interaction will become the mainstream of human-computer interaction in the future. Interaction methods include touch, voice and gesture interaction, and interaction objects include vehicle information systems, navigation systems and entertainment systems. However, while multimodal interaction improves the efficiency of interaction, it will also increase the driver's cognitive load, thereby affecting driving safety. Therefore, it is very necessary to accurately evaluate the driver's cognitive load in order to improve the multimodal interaction design experience.

[0003] The evaluation of driver cognitive load in the existing technology mainly includes subjective evaluation method and performance measurement method. The subjective evaluation method is highly subjective and may be affected by factors such as the driver's emotions and fatigue status, resulting in inaccurate evaluation results. The performance measurement method may be affected by factors such as task difficulty and vehicle performance, and cannot directly reflect the driver's psychological state.

[0004] In summary, the existing technology for evaluating driver cognitive load is not accurate enough. Summary of the invention

[0005] The present application provides a cognitive load assessment method, device, equipment and readable storage medium, aiming to solve the technical problem that the prior art is not accurate enough in assessing the cognitive load of drivers.

[0006] In a first aspect, an embodiment of the present application provides a cognitive load assessment method, the cognitive load assessment method comprising:

[0007] Obtaining subjective scores of cognitive load of the interactive tasks to be evaluated;

[0008] Determine a driving behavior score for the interactive task to be evaluated according to a normal distribution interval of historical statistical data of a driving behavior indicator for the interactive task to be evaluated;

[0009] Determine the EEG index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the EEG index of the interactive task to be evaluated;

[0010] Determine the eye movement index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the eye movement index of the interactive task to be evaluated;

[0011] The analytic hierarchy process was used to determine the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated.

[0012] The subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated are multiplied by their respective weights and then summed up to calculate the comprehensive score of cognitive load of the interactive task to be evaluated.

[0013] Optionally, before determining the driving behavior score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data in which the driving behavior indicator of the interactive task to be evaluated is located, the method includes:

[0014] By statistics, the historical statistical data of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated are obtained;

[0015] According to the historical statistical data of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated, the mean and standard deviation of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated are calculated;

[0016] According to the means and standard deviations of the driving behavior indicators, EEG indicators and eye movement indicators of the interactive task to be evaluated, the historical statistical data of the driving behavior indicators, EEG indicators and eye movement indicators of the interactive task to be evaluated are divided into multiple normal distribution intervals.

[0017] Optionally, the driving behavior indicators include reaction time, operation accuracy and driver emotion, and determining the driving behavior score of the interactive task to be evaluated according to the normal distribution interval of historical statistical data in which the driving behavior indicators of the interactive task to be evaluated are located includes:

[0018] Determine the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the reaction time, operation accuracy and driver emotion of the interactive task to be evaluated;

[0019] The analytic hierarchy process is used to determine the weights of the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated.

[0020] The driving behavior score of the interactive task to be evaluated is calculated by multiplying the reaction time score, operation accuracy score, and driver emotion score of the interactive task to be evaluated by their respective weights and summing them up.

[0021] Optionally, the EEG index includes time domain characteristics and frequency domain characteristics of Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave, and determining the EEG index score of the interactive task to be evaluated according to the normal distribution interval of historical statistical data of the EEG index of the interactive task to be evaluated includes:

[0022] Determine the time domain characteristic scores and frequency domain characteristic scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data in which the time domain characteristics and frequency domain characteristics of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are located;

[0023] The analytic hierarchy process was used to determine the weights of the time domain characteristic scores and frequency domain characteristic scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated;

[0024] The time domain feature scores and frequency domain feature scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are multiplied by their respective weights and then summed up to calculate the EEG index score of the interactive task to be evaluated.

[0025] Optionally, the eye movement indicators include gaze duration, gaze times, gaze hotspots, eye movement trajectories, and pupil diameters. Determining the eye movement indicator score of the interactive task to be evaluated according to the normal distribution interval of historical statistical data of the eye movement indicators of the interactive task to be evaluated includes:

[0026] Determine the gaze duration score, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the gaze duration, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter of the interactive task to be evaluated;

[0027] The analytic hierarchy process was used to determine the weights of the gaze duration score, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated.

[0028] The eye movement index score of the interactive task to be evaluated is calculated by multiplying the gaze duration score, gaze number score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated by their respective weights.

[0029] Optionally, the method of using the hierarchical analysis method to determine the weights of the subjective score of cognitive load, the driving behavior score, the EEG index score and the eye movement index score of the interactive task to be evaluated includes:

[0030] Construct a judgment matrix of subjective cognitive load scores, driving behavior scores, EEG index scores, and eye movement index scores for the interactive task to be evaluated;

[0031] For each row of the judgment matrix, take the average value of each element in each row and normalize it to obtain the weight of each row;

[0032] The maximum characteristic root is calculated based on the judgment matrix and the weight of each row;

[0033] The consistency check index is calculated based on the maximum characteristic root;

[0034] The consistency ratio is calculated based on the consistency check index and the preset random consistency index;

[0035] If the consistency ratio is less than the preset ratio, the weights of the corresponding rows are used as the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated; otherwise, the judgment matrix is ​​adjusted, and the step of averaging and normalizing the elements in each row of the judgment matrix for each row is returned to obtain the weight of each row.

[0036] Optionally, after the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated are multiplied by their respective weights and then summed to obtain a comprehensive score of cognitive load of the interactive task to be evaluated, the following steps are included:

[0037] According to the comprehensive cognitive load score of the interactive task to be evaluated, the cognitive load level of the interactive task to be evaluated is determined.

[0038] In a second aspect, an embodiment of the present application provides a cognitive load assessment device, the cognitive load assessment device comprising:

[0039] An acquisition module, used to obtain the subjective score of cognitive load of the interactive task to be evaluated;

[0040] A first determination module is used to determine the driving behavior score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the driving behavior index of the interactive task to be evaluated;

[0041] A second determination module is used to determine the EEG index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the EEG index of the interactive task to be evaluated;

[0042] A third determination module is used to determine the eye movement index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the eye movement index of the interactive task to be evaluated;

[0043] The fourth determination module is used to determine the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated by using the hierarchical analysis method;

[0044] The calculation module is used to calculate the comprehensive cognitive load score of the interactive task to be evaluated by multiplying the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated by their respective weights.

[0045] In a third aspect, an embodiment of the present application provides a cognitive load assessment device, which includes a processor, a memory, and a cognitive load assessment program stored in the memory and executable by the processor, wherein when the cognitive load assessment program is executed by the processor, the steps of the cognitive load assessment method described above are implemented.

[0046] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a cognitive load assessment program is stored, wherein when the cognitive load assessment program is executed by a processor, the steps of the cognitive load assessment method as described above are implemented.

[0047] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:

[0048] In an embodiment of the present application, a subjective score of cognitive load of an interactive task to be evaluated is obtained; a driving behavior score of the interactive task to be evaluated is determined according to a normal distribution interval of historical statistical data in which a driving behavior index of the interactive task to be evaluated is located; an EEG index score of the interactive task to be evaluated is determined according to a normal distribution interval of historical statistical data in which an EEG index of the interactive task to be evaluated is located; an eye movement index score of the interactive task to be evaluated is determined according to a normal distribution interval of historical statistical data in which an eye movement index of the interactive task to be evaluated is located; a hierarchical analysis method is used to determine the respective weights of the subjective score of cognitive load, the driving behavior score, the EEG index score, and the eye movement index score of the interactive task to be evaluated; and the subjective score of cognitive load, the driving behavior score, the EEG index score, and the eye movement index score of the interactive task to be evaluated are multiplied by their respective weights and then summed up to obtain a comprehensive score of cognitive load of the interactive task to be evaluated. The embodiment of the present application comprehensively considers the subjective score and objective score of the cognitive load of the interactive task to be evaluated, the objective score includes the driving behavior score, the EEG index score and the eye movement index score, and the driving behavior score, the EEG index score and the eye movement index score are determined according to the normal distribution interval of the historical statistical data of the driving behavior index, the EEG index and the eye movement index of the interactive task to be evaluated, and the weights of the subjective score of cognitive load, the driving behavior score, the EEG index score and the eye movement index score are determined by the hierarchical analysis method, so that the calculated comprehensive score of the cognitive load of the interactive task to be evaluated is more comprehensive and the evaluation is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a flow chart of an embodiment of a cognitive load assessment method of the present application;

[0050] Figure 2 This is a schematic diagram of the NASA-TLX measurement of an embodiment of the cognitive load assessment method of the present application;

[0051] Figure 3 A schematic diagram of the system architecture of an embodiment of the cognitive load assessment method of the present application;

[0052] Figure 4 A schematic diagram of a normal distribution interval of an embodiment of a cognitive load assessment method of the present application;

[0053] Figure 5 This is a schematic diagram of the functional modules of an embodiment of a cognitive load assessment device of the present application;

[0054] Figure 6 Schematic diagram of the hardware structure of the cognitive load assessment device involved in the embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0057] In a first aspect, an embodiment of the present application provides a cognitive load assessment method.

[0058] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of an embodiment of the cognitive load assessment method of the present application. Figure 1 As shown, cognitive load assessment methods include:

[0059] Step S10, obtaining a subjective score of cognitive load of the interactive task to be evaluated.

[0060] In this embodiment, the driver performs a certain interactive task to be evaluated, such as making a phone call and playing music while the vehicle is driving, and obtains the subjective score of the cognitive load of the driver performing the interactive task to be evaluated. Figure 2 , Figure 2 This is a schematic diagram of the NASA-TLX scale of an embodiment of the cognitive load assessment method of the present application. The NASA-TLX scale is the National Aeronautics and Space Administration's task load index scale, such as Figure 2 As shown in the figure, the NASA-TLX scale mainly divides cognitive load into six indicators, namely mental demand, physical demand, time demand, effort, work performance and frustration. First, the relative importance of the six indicators in the formation of cognitive load can be compared in pairs. For example, compared with physical demand, mental demand is more important, so the weight of mental demand is higher than that of physical demand. Based on this, the relative importance of each indicator in the formation of cognitive load is determined, and the sum of the weights of the six indicators is equal to 1. Secondly, according to the actual operation situation, the six indicators are scored, and the scores are between 0-100. Except for the indicator of work performance, the other five indicators are higher in importance, the higher the score, and the higher the importance of work performance, the lower the score. Finally, the weight and score of each indicator are weighted averaged to obtain the subjective score of cognitive load of the interactive task to be evaluated. The weighted average calculation formula can be used: Where T is the subjective score of cognitive load of the interactive task to be evaluated, M iis the scale score of the six evaluation indicators, P i is the weight of the six evaluation indicators.

[0061] Step S20 , determining a driving behavior score of the interactive task to be evaluated according to a normal distribution interval of the historical statistical data where the driving behavior index of the interactive task to be evaluated is located.

[0062] In this embodiment, the driving behavior indicators include, for example, reaction time, operation accuracy, and driver emotions, etc. These indicators can reflect the driver's attention allocation and emotional state, and can more comprehensively reflect the driver's cognitive load level and behavioral performance during driving. First, the historical data of the driving behavior indicators for the interactive task to be evaluated can be statistically analyzed and divided into normal distribution intervals. Then, the driving behavior score of the interactive task to be evaluated is determined according to the normal distribution interval of the historical statistical data of the driving behavior indicators of the interactive task to be evaluated.

[0063] Step S30, determining the EEG index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the EEG index of the interactive task to be evaluated.

[0064] In this embodiment, the EEG indicators include, for example, the time domain characteristics and frequency domain characteristics of Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave, wherein the EEG signal is a weak electromagnetic signal generated by the human brain, which can reflect the activity state of brain neurons. By analyzing the EEG signal, the cognitive load level of an individual can be evaluated. The EEG signal can be decomposed into signals of five different frequency bands after filtering, namely Delta wave (0.5-4Hz), Theta wave (4-7Hz), Alpha wave (8-12Hz), Beta wave (13-30Hz), Gamma wave (>30Hz). Delta wave is more active when a person is in deep sleep, Theta wave often appears when dreaming, tired, deeply relaxed or meditating, Alpha wave (>12Hz), Beta wave (13-30Hz), Gamma wave (>30Hz). The ha wave often appears when people are awake and relaxed, the beta wave is more active when people concentrate, and the gamma wave appears when the brain performs advanced cognitive activities. The EEG signal can be decomposed into five different frequency bands: Delta wave, Theta wave, Alpha wave, Beta wave, and Gamma wave. The time domain features and frequency domain features are extracted respectively as EEG data indicators. The time domain features are statistical features calculated for EEG signals, mainly including mean, standard deviation, maximum value, minimum value, mean of the absolute value of the first-order difference, and mean of the absolute value of the second-order difference. The frequency domain features are the original time series information converted into information in the frequency domain using the Welch method (a signal processing method based on the Welch method), mainly including absolute power spectral density and relative power spectral density. Similarly, the historical data of the EEG indicators of the interactive task to be evaluated can be firstly counted, and the normal distribution interval can be divided. Then, according to the normal distribution interval of the historical statistical data of the EEG indicators of the interactive task to be evaluated, the EEG indicator score of the interactive task to be evaluated can be determined.

[0065] Step S40, determining the eye movement index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the eye movement index of the interactive task to be evaluated.

[0066] In this embodiment, the eye movement indicators include, for example, gaze duration, gaze times, gaze hotspots, eye movement trajectories, and pupil diameter. The extraction of eye movement indicators is crucial for understanding and evaluating the driver's cognitive state. The driver's eye movement tracking data can be collected through an eye tracker, and different interest areas can be divided according to the cockpit layout in the interactive task to be evaluated, such as instruments, central control, and steering wheel. Then, the eye movement indicators are calculated in different interest areas to obtain the driver's attention distribution in different areas. Similarly, the historical data of the eye movement indicators for the interactive task to be evaluated can be first counted, and the normal distribution interval can be divided. Then, the eye movement indicator score of the interactive task to be evaluated can be determined according to the normal distribution interval of the historical statistical data of the eye movement indicators of the interactive task to be evaluated.

[0067] Step S50, using the hierarchical analysis method to determine the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated.

[0068] In this embodiment, the hierarchical analysis method mainly decomposes the decision-making problem into different hierarchical structures in the order of the overall goal, the sub-goals of each layer, the evaluation criteria and the specific backup plan, and then solves the eigenvector of the judgment matrix to obtain the weights of the subjective score of cognitive load, the driving behavior score, the EEG index score and the eye movement index score of the interactive task to be evaluated. The weights of the subjective score of cognitive load, the driving behavior score, the EEG index score and the eye movement index score of the interactive task to be evaluated determined by the hierarchical analysis method can be seen in Table 1.

[0069] Table 1.

[0070] index Weight Driving behavior score 20％ EEG index score 35％ Eye movement index evaluation 25％ Subjective rating of cognitive load 20％

[0071] Step S60, the subjective score of cognitive load, the driving behavior score, the EEG index score and the eye movement index score of the interactive task to be evaluated are multiplied by their respective weights and then summed up to calculate the comprehensive score of cognitive load of the interactive task to be evaluated.

[0072] In this embodiment, after the hierarchical analysis method is used to obtain the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated in step S50, the respective weights are multiplied by the respective scores, and then the sum is calculated to obtain the comprehensive score of cognitive load of the interactive task to be evaluated.

[0073] In this embodiment, refer to Figure 3 , Figure 3 Schematic diagram of the system architecture of an embodiment of the cognitive load assessment method of the present application. Figure 3 As shown in the figure, the system architecture, i.e. the structure of the cognitive load evaluation model, is mainly divided into three parts: multimodal basic data collection, multimodal feature extraction and evaluation model construction. By comprehensively considering the subjective score and objective score of the cognitive load of the interactive task to be evaluated, the objective score includes the driving behavior score, the EEG index score and the eye movement index score, and the driving behavior score, the EEG index score and the eye movement index score are determined according to the normal distribution interval of the historical statistical data of the driving behavior index, the EEG index and the eye movement index of the interactive task to be evaluated. The weights of the subjective score of cognitive load, the driving behavior score, the EEG index score and the eye movement index score are determined by the hierarchical analysis method, so that the calculated comprehensive score of the cognitive load of the interactive task to be evaluated is more comprehensive and the evaluation is more accurate.

[0074] Furthermore, in one embodiment, before step S20, the following steps are included:

[0075] By statistics, the historical statistical data of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated are obtained;

[0076] According to the historical statistical data of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated, the mean and standard deviation of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated are calculated;

[0077] According to the means and standard deviations of the driving behavior indicators, EEG indicators and eye movement indicators of the interactive task to be evaluated, the historical statistical data of the driving behavior indicators, EEG indicators and eye movement indicators of the interactive task to be evaluated are divided into multiple normal distribution intervals.

[0078] In this embodiment, for the interactive task to be evaluated, historical statistical data of the driving behavior index, the EEG index, and the eye movement index are collected, and based on the historical statistical data of the driving behavior index, the EEG index, and the eye movement index of the interactive task to be evaluated, the mean and standard deviation of the driving behavior index, the EEG index, and the eye movement index of the interactive task to be evaluated are calculated. According to the mean and standard deviation of the driving behavior index, the EEG index, and the eye movement index of the interactive task to be evaluated, the historical statistical data of the driving behavior index, the EEG index, and the eye movement index of the interactive task to be evaluated are divided into multiple normal distribution intervals, and the reference is made to the above. Figure 4 , Figure 4 This is a schematic diagram of a normal distribution interval of an embodiment of the cognitive load assessment method of the present application. Figure 4 As shown, according to the 3σ criterion of normal distribution, the probability that the historical data of various statistical indicators are distributed within the range of the mean μ plus or minus three standard deviations σ is about 99.7%, the probability that they are distributed within the range of the mean μ plus or minus one standard deviation σ is about 68.27%, and the probability that they are distributed within the range of the mean μ plus or minus two standard deviations σ is about 95.45%.

[0079] Furthermore, in one embodiment, the driving behavior indicators include reaction time, operation accuracy and driver emotion, and step S20 includes:

[0080] Determine the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the reaction time, operation accuracy and driver emotion of the interactive task to be evaluated;

[0081] The analytic hierarchy process is used to determine the weights of the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated.

[0082] The driving behavior score of the interactive task to be evaluated is calculated by multiplying the reaction time score, operation accuracy score, and driver emotion score of the interactive task to be evaluated by their respective weights and summing them up.

[0083] In this embodiment, according to the normal distribution interval of the historical statistical data of the reaction time, operation accuracy and driver emotion of the interactive task to be evaluated, the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated can be determined by formula 1, and the formula 1 is:

[0084]

[0085] Among them, x represents the specific value of a driving behavior indicator of the interactive task to be evaluated, such as reaction time, operation accuracy and driver emotion, and μ and σ respectively represent the mean and standard deviation of the historical statistical data of the driving behavior indicator. It should be noted that the scores in the above formula 1 and the corresponding relationship with the normal distribution interval are only examples, and can be adjusted according to actual needs. Since the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated are determined based on historical statistical data combined with formula 1, human subjectivity in the scoring process is avoided, and the accuracy of the reaction time score, operation accuracy score and driver emotion score can be improved.

[0086] Furthermore, in one embodiment, the EEG index includes the time domain characteristics and frequency domain characteristics of Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave, and step S30 includes:

[0087] Determine the time domain characteristic scores and frequency domain characteristic scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data in which the time domain characteristics and frequency domain characteristics of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are located;

[0088] The analytic hierarchy process was used to determine the weights of the time domain characteristic scores and frequency domain characteristic scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated;

[0089] The time domain feature scores and frequency domain feature scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are multiplied by their respective weights and then summed up to calculate the EEG index score of the interactive task to be evaluated.

[0090] In this embodiment, similarly, according to the normal distribution interval of the historical statistical data in which the time domain characteristics and frequency domain characteristics of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are located, the time domain characteristic score and frequency domain characteristic score of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated can be determined by Formula 1, and similarly, the score in Formula 1 and the corresponding relationship with the normal distribution interval can be adjusted according to actual needs. Since the time domain characteristic score and frequency domain characteristic score of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are determined based on historical statistical data combined with Formula 1, human subjectivity in the scoring process is avoided, and the accuracy of the time domain characteristic score and frequency domain characteristic score of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave can be improved.

[0091] Further, in one embodiment, the eye movement indicators include fixation duration, fixation times, fixation hotspots, eye movement trajectories, and pupil diameter, and step S40 includes:

[0092] Determine the gaze duration score, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the gaze duration, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter of the interactive task to be evaluated;

[0093] The analytic hierarchy process was used to determine the weights of the gaze duration score, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated.

[0094] The eye movement index score of the interactive task to be evaluated is calculated by multiplying the gaze duration score, gaze number score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated by their respective weights.

[0095] In this embodiment, similarly, according to the normal distribution interval of the historical statistical data of the gaze duration, gaze times, gaze hotspot, eye movement trajectory and pupil diameter of the interactive task to be evaluated, the gaze duration score, gaze times score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated can be determined by Formula 1. Similarly, the score in Formula 1 and the corresponding relationship with the normal distribution interval can be adjusted according to actual needs. Since the gaze duration score, gaze times score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated are determined based on historical statistical data combined with Formula 1, human subjectivity in the scoring process is avoided, and the accuracy of the gaze duration score, gaze times score, gaze hotspot score, eye movement trajectory score and pupil diameter score can be improved.

[0096] Furthermore, in one embodiment, step S50 includes:

[0097] Construct a judgment matrix of subjective cognitive load scores, driving behavior scores, EEG index scores, and eye movement index scores for the interactive task to be evaluated;

[0098] For each row of the judgment matrix, take the average value of each element in each row and normalize it to obtain the weight of each row;

[0099] The maximum characteristic root is calculated based on the judgment matrix and the weight of each row;

[0100] The consistency check index is calculated based on the maximum characteristic root;

[0101] The consistency ratio is calculated based on the consistency check index and the preset random consistency index;

[0102] If the consistency ratio is less than the preset ratio, the weights of the corresponding rows are used as the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated; otherwise, the judgment matrix is ​​adjusted, and the step of averaging and normalizing the elements in each row of the judgment matrix for each row is returned to obtain the weight of each row.

[0103] In this embodiment, a hierarchical analysis model of subjective scores of cognitive load, driving behavior scores, EEG index scores and eye movement index scores can be first constructed, that is, the decision-making goals, factors to be considered (decision criteria) and decision objects are divided into the highest level, the middle level and the lowest level according to the relationship between them, and a hierarchical structure diagram is drawn; then a judgment matrix of subjective scores of cognitive load, driving behavior scores, EEG index scores and eye movement index scores of the interactive task to be evaluated is constructed, that is, a pairwise comparison is performed in combination with a preset scale table to obtain the score of each factor in the judgment matrix, and the relative importance ratio scale is between 1-9. The preset scale table is shown in Table 2.

[0104] Table 2.

[0105]

[0106]

[0107] For example, the constructed judgment matrix is ​​an orthogonal matrix A, with a ij represents the comparison result of the i-th factor relative to the j-th factor, then the judgment matrix A can be expressed as: For each row of the judgment matrix A, take the average value of each element in each row and normalize it to get the weight of each row The weight of each row can be expressed as Calculate the maximum eigenvalue based on the judgment matrix A and the weight W of each row According to the largest characteristic root λ max Calculate consistency check index

[0109] In order to measure the size of the consistency check index CI, a preset random consistency index RI is introduced. The preset random consistency index is shown in Table 3.

[0110] Table 3.

[0111] n 1 2 3 4 5 6 7 8 9 10 11 RI 0 0 0.58 0.90 1.12 1.24 1.32 1.41 1.45 1.49 1.51

[0112] For example, if n is 4, the preset random consistency index RI is 0.90. According to the consistency verification index CI and the preset random consistency index RI, the consistency ratio is calculated. If the consistency ratio CR is less than the preset ratio, such as <0.1, it is considered that the inconsistency of the constructed judgment matrix A is within the allowable range and has satisfactory consistency. After the consistency check, the weights of the corresponding rows are used as the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated. Otherwise, the judgment matrix A is considered to be inconsistent with the established judgment matrix A. ij Adjust the judgment matrix, and continue to perform consistency check on the adjusted judgment matrix until it passes the consistency check.

[0113] Furthermore, in one embodiment, after step S60, the following steps are included:

[0114] According to the comprehensive cognitive load score of the interactive task to be evaluated, the cognitive load level of the interactive task to be evaluated is determined.

[0115] In this embodiment, a plurality of cognitive load levels may be pre-divided based on the numerical range of the cognitive load score, for example, divided into level one, level two, and level three from low to high. A higher cognitive load level represents a heavier cognitive load burden on the driver in multimodal interaction. The cognitive load level of the interactive task to be evaluated is determined according to the comprehensive cognitive load score of the interactive task to be evaluated and the plurality of pre-divided cognitive load levels, so as to more intuitively evaluate the cognitive load.

[0116] In a second aspect, an embodiment of the present application also provides a cognitive load assessment device.

[0117] In one embodiment, referring to Figure 5 , Figure 5 This is a functional module diagram of an embodiment of a cognitive load assessment device of the present application. Figure 5 As shown, the cognitive load assessment device includes:

[0118] An acquisition module 10 is used to obtain a subjective score of cognitive load of the interactive task to be evaluated;

[0119] A first determination module 20, configured to determine a driving behavior score of the interactive task to be evaluated according to a normal distribution interval of historical statistical data of the driving behavior index of the interactive task to be evaluated;

[0120] A second determination module 30 is used to determine the EEG index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the EEG index of the interactive task to be evaluated;

[0121] A third determination module 40 is used to determine the eye movement index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the eye movement index of the interactive task to be evaluated;

[0122] A fourth determination module 50 is used to determine the weights of the subjective score of cognitive load, the driving behavior score, the EEG index score and the eye movement index score of the interactive task to be evaluated by using a hierarchical analysis method;

[0123] The calculation module 60 is used to calculate the comprehensive cognitive load score of the interactive task to be evaluated by multiplying the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated by their respective weights.

[0124] Furthermore, in one embodiment, the cognitive load assessment device further includes a statistical module, which is used to:

[0125] By statistics, the historical statistical data of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated are obtained;

[0126] According to the historical statistical data of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated, the mean and standard deviation of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated are calculated;

[0127] According to the means and standard deviations of the driving behavior indicators, EEG indicators and eye movement indicators of the interactive task to be evaluated, the historical statistical data of the driving behavior indicators, EEG indicators and eye movement indicators of the interactive task to be evaluated are divided into multiple normal distribution intervals.

[0128] Furthermore, in one embodiment, the driving behavior indicators include reaction time, operation accuracy and driver emotion, and the first determination module 20 is used to:

[0129] Determine the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the reaction time, operation accuracy and driver emotion of the interactive task to be evaluated;

[0130] The analytic hierarchy process is used to determine the weights of the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated.

[0131] The driving behavior score of the interactive task to be evaluated is calculated by multiplying the reaction time score, operation accuracy score, and driver emotion score of the interactive task to be evaluated by their respective weights and summing them up.

[0132] Furthermore, in one embodiment, the EEG index includes time domain characteristics and frequency domain characteristics of Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave, and the second determination module 30 is used to:

[0133] Determine the time domain characteristic scores and frequency domain characteristic scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data in which the time domain characteristics and frequency domain characteristics of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are located;

[0134] The analytic hierarchy process was used to determine the weights of the time domain characteristic scores and frequency domain characteristic scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated;

[0135] The time domain feature scores and frequency domain feature scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are multiplied by their respective weights and then summed up to calculate the EEG index score of the interactive task to be evaluated.

[0136] Furthermore, in one embodiment, the eye movement index includes gaze duration, gaze times, gaze hotspots, eye movement trajectories, and pupil diameter. The third determination module 40 is used to:

[0137] Determine the gaze duration score, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the gaze duration, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter of the interactive task to be evaluated;

[0138] The analytic hierarchy process was used to determine the weights of the gaze duration score, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated.

[0139] The eye movement index score of the interactive task to be evaluated is calculated by multiplying the gaze duration score, gaze number score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated by their respective weights.

[0140] Furthermore, in one embodiment, the fourth determining module 50 is configured to:

[0141] Construct a judgment matrix of subjective cognitive load scores, driving behavior scores, EEG index scores, and eye movement index scores for the interactive task to be evaluated;

[0142] For each row of the judgment matrix, take the average value of each element in each row and normalize it to obtain the weight of each row;

[0143] The maximum characteristic root is calculated based on the judgment matrix and the weight of each row;

[0144] The consistency check index is calculated based on the maximum characteristic root;

[0145] The consistency ratio is calculated based on the consistency check index and the preset random consistency index;

[0146] If the consistency ratio is less than the preset ratio, the weights of the corresponding rows are used as the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated; otherwise, the judgment matrix is ​​adjusted, and the step of averaging and normalizing the elements in each row of the judgment matrix for each row is returned to obtain the weight of each row.

[0147] Furthermore, in one embodiment, the cognitive load assessment device further includes a level determination module, which is used to:

[0148] According to the comprehensive cognitive load score of the interactive task to be evaluated, the cognitive load level of the interactive task to be evaluated is determined.

[0149] The functional implementation of each module in the above-mentioned cognitive load assessment device corresponds to each step in the above-mentioned cognitive load assessment method embodiment, and its functions and implementation processes are not described one by one here.

[0150] In a third aspect, an embodiment of the present application provides a cognitive load assessment device.

[0151] Reference Figure 6 , Figure 6 Schematic diagram of the hardware structure of the cognitive load assessment device involved in the embodiment of the present application. In the embodiment of the present application, the cognitive load assessment device may include a processor, a memory, a communication interface and a communication bus.

[0152] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0153] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces, which are used to interconnect the devices inside the cognitive load assessment device, and interfaces used to interconnect the cognitive load assessment device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0154] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0155] The processor may be a general-purpose processor, and the general-purpose processor may call the cognitive load assessment program stored in the memory and execute the cognitive load assessment method provided by the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the cognitive load assessment program is called may refer to the various embodiments of the cognitive load assessment method of the present application, which will not be repeated here.

[0156] Those skilled in the art will understand that Figure 6 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0157] In a fourth aspect, an embodiment of the present application also provides a readable storage medium.

[0158] The readable storage medium of the present application stores a cognitive load assessment program, wherein when the cognitive load assessment program is executed by a processor, the steps of the cognitive load assessment method described above are implemented.

[0159] Among them, the method implemented when the cognitive load assessment program is executed can refer to the various embodiments of the cognitive load assessment method of the present application, and will not be repeated here.

[0160] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0161] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0162] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0163] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0164] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0165] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0166] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A cognitive load assessment method, characterized in that: The cognitive load assessment method includes: Obtaining subjective scores of cognitive load of the interactive tasks to be evaluated; Determine a driving behavior score for the interactive task to be evaluated according to a normal distribution interval of historical statistical data of a driving behavior indicator for the interactive task to be evaluated; Determine the EEG index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the EEG index of the interactive task to be evaluated; Determine the eye movement index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the eye movement index of the interactive task to be evaluated; The analytic hierarchy process was used to determine the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated. The subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated are multiplied by their respective weights and then summed up to calculate the comprehensive score of cognitive load of the interactive task to be evaluated.

2. The cognitive load assessment method according to claim 1, characterized in that: Before determining the driving behavior score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the driving behavior indicator of the interactive task to be evaluated, the method includes: By statistics, the historical statistical data of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated are obtained; According to the historical statistical data of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated, the mean and standard deviation of the driving behavior index, EEG index and eye movement index of the interactive task to be evaluated are calculated; According to the means and standard deviations of the driving behavior indicators, EEG indicators and eye movement indicators of the interactive task to be evaluated, the historical statistical data of the driving behavior indicators, EEG indicators and eye movement indicators of the interactive task to be evaluated are divided into multiple normal distribution intervals.

3. The cognitive load assessment method according to claim 1, wherein: The driving behavior indicators include reaction time, operation accuracy and driver emotion. The determining of the driving behavior score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data in which the driving behavior indicators of the interactive task to be evaluated are: Determine the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the reaction time, operation accuracy and driver emotion of the interactive task to be evaluated; The analytic hierarchy process is used to determine the weights of the reaction time score, operation accuracy score and driver emotion score of the interactive task to be evaluated. The driving behavior score of the interactive task to be evaluated is calculated by multiplying the reaction time score, operation accuracy score, and driver emotion score of the interactive task to be evaluated by their respective weights and summing them up.

4. The cognitive load assessment method according to claim 1, wherein: The EEG index includes the time domain characteristics and frequency domain characteristics of Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave. The EEG index score of the interactive task to be evaluated is determined according to the normal distribution interval of the historical statistical data of the EEG index of the interactive task to be evaluated, including: Determine the time domain characteristic scores and frequency domain characteristic scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data in which the time domain characteristics and frequency domain characteristics of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are located; The analytic hierarchy process was used to determine the weights of the time domain characteristic scores and frequency domain characteristic scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated; The time domain feature scores and frequency domain feature scores of the Delta wave, Theta wave, Alpha wave, Beta wave and Gamma wave of the interactive task to be evaluated are multiplied by their respective weights and then summed up to calculate the EEG index score of the interactive task to be evaluated.

5. The cognitive load assessment method according to claim 1, wherein: The eye movement indicators include fixation duration, fixation times, fixation hotspots, eye movement trajectories, and pupil diameter. The eye movement indicator score of the interactive task to be evaluated is determined according to the normal distribution interval of the historical statistical data of the eye movement indicator of the interactive task to be evaluated, including: Determine the gaze duration score, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the gaze duration, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter of the interactive task to be evaluated; The analytic hierarchy process was used to determine the weights of the gaze duration score, gaze frequency score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated. The eye movement index score of the interactive task to be evaluated is calculated by multiplying the gaze duration score, gaze number score, gaze hotspot score, eye movement trajectory score and pupil diameter score of the interactive task to be evaluated by their respective weights.

6. The cognitive load assessment method according to claim 1, wherein: The method of using the hierarchical analysis method to determine the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated includes: Construct a judgment matrix of subjective cognitive load scores, driving behavior scores, EEG index scores, and eye movement index scores for the interactive task to be evaluated; For each row of the judgment matrix, take the average value of each element in each row and normalize it to get the weight of each row; The maximum characteristic root is calculated based on the judgment matrix and the weight of each row; The consistency check index is calculated based on the maximum characteristic root; The consistency ratio is calculated based on the consistency check index and the preset random consistency index; If the consistency ratio is less than the preset ratio, the weights of the corresponding rows are used as the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated; otherwise, the judgment matrix is ​​adjusted, and the step of averaging and normalizing the elements in each row of the judgment matrix for each row is returned to obtain the weight of each row.

7. The cognitive load assessment method according to claim 1, wherein: After the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated are multiplied by their respective weights and then summed to calculate the comprehensive score of cognitive load of the interactive task to be evaluated, it includes: According to the comprehensive cognitive load score of the interactive task to be evaluated, the cognitive load level of the interactive task to be evaluated is determined.

8. A cognitive load assessment device, characterized in that: The cognitive load assessment device comprises: An acquisition module, used to obtain the subjective score of cognitive load of the interactive task to be evaluated; A first determination module is used to determine the driving behavior score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the driving behavior index of the interactive task to be evaluated; A second determination module is used to determine the EEG index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the EEG index of the interactive task to be evaluated; A third determination module is used to determine the eye movement index score of the interactive task to be evaluated according to the normal distribution interval of the historical statistical data of the eye movement index of the interactive task to be evaluated; The fourth determination module is used to determine the weights of the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated by using the hierarchical analysis method; The calculation module is used to calculate the comprehensive cognitive load score of the interactive task to be evaluated by multiplying the subjective score of cognitive load, driving behavior score, EEG index score and eye movement index score of the interactive task to be evaluated by their respective weights.

9. A cognitive load assessment device, characterized in that: The cognitive load assessment device includes a processor, a memory, and a cognitive load assessment program stored in the memory and executable by the processor, wherein when the cognitive load assessment program is executed by the processor, the steps of the cognitive load assessment method according to any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a cognitive load assessment program, wherein when the cognitive load assessment program is executed by a processor, the steps of the cognitive load assessment method according to any one of claims 1 to 7 are implemented.

Images