A crew workload self-adaptive prediction method based on multi-source heterogeneous data fusion

Abstract

The application discloses a kind of crew workload self-adaptive prediction methods based on multi-source heterogeneous data fusion, the method includes: the physiological characteristic data of crew is collected to obtain the current physiological load of the individual;Based on the current physiological load of individual and the physiological load parameter of historical time, the individual physiological load prediction value of next time period is obtained;Obtain the navigation environment data of the ship where the crew is in next time period, and obtain the comprehensive stress level of the navigation environment where the crew is in next time period;Based on the comprehensive stress level of the navigation environment where the crew is in next time period and the individual physiological load prediction value of the next time period, input causal reasoning graph model, predict the workload level of crew.The application comprehensively, multidimensionally reflects the working state of crew by collecting and fusing the physiological characteristic data of crew, historical physiological load parameter and navigation environment data, improves the information quantity and comprehensive analysis ability of prediction model.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of computer, and particularly relates to a crew workload adaptive prediction method based on multi-source heterogeneous data fusion. BACKGROUND

[0002] The crew undertakes complex and variable work tasks during the operation of the ship, and the reasonable management of their work load is of great significance to ensure the safe and efficient operation of the ship. The traditional crew workload evaluation method mainly relies on a single data source or a static evaluation model, but these methods have many shortcomings.

[0003] Firstly, it cannot fully reflect the real workload state of the crew in different working environments. During the ship navigation process, the workload of the crew is not only affected by their own physiological state, but also by the dynamic changes of the navigation environment, multi-task parallel and other factors. A single data source cannot capture these complex influencing factors.

[0004] In addition, there are significant differences among the crews in physiological characteristics, work habits and ability to cope with stress, and the traditional method often uses a unified evaluation standard, which cannot accurately evaluate different individuals.

[0005] To solve the above problems, there is an urgent need for a crew workload prediction method that can fuse multi-source heterogeneous data and achieve individualization and dynamic adaptation, in order to improve the comprehensiveness, accuracy and practicality of the prediction, and effectively support the ship operation management and protect the health and safety of the crew. SUMMARY

[0006] In view of the defects in the prior art, the present application provides a crew workload adaptive prediction method based on multi-source heterogeneous data fusion, comprising:

[0007] Collecting the physiological characteristic data of the crew and inputting it into the individual physiological load model P to obtain the current physiological load of the individual;

[0008] Based on the current physiological load of the individual and the physiological load parameters at the historical time, inputting into the time series prediction model to obtain the individual physiological load prediction value of the next time period;

[0009] Obtaining the navigation environment data of the ship where the crew is located in the next time period;

[0010] Based on the navigation environment data of the next time period, inputting into the environment evaluation model E to obtain the comprehensive stress level of the navigation environment where the crew is located in the next time period;

[0011] Based on the comprehensive stress level of the sailing environment of the crew in the next time period and the individual physiological load prediction value of the next time period, input the causal inference graph model C to predict the work load level of the crew.

[0012] Wherein, the physiological characteristic data of the crew is collected in real time by using a wearable device, including:

[0013] Heart rate HR(t), heart rate variability HRV(t), activity amount Activity(t) measured by an accelerometer, skin temperature Temp(t), skin conductivity EDA(t).

[0014] Wherein, the individual physiological load model P is defined, which is used to calculate the physiological load L(t) of the crew at the current time t; the model considers the nonlinear accumulation of fatigue and the physiological dynamic recovery process, and the formula is as follows:

[0015]

[0016] Wherein,

[0017] Lt(t): physiological load level at the current time t;

[0018] L(t-Δt): physiological load level at the last time t-Δt;

[0019] HR(t): heart rate measured at the current time t;

[0020] HR rest : individual resting heart rate;

[0021] HRV(t): heart rate variability measured at the current time t;

[0022] HRV rest : individual resting heart rate variability;

[0023] Activity(t): activity amount at the current time t;

[0024] Δt: time interval;

[0025] α1,α2,α3: individualized weight coefficients;

[0026] n1,n2,n3: nonlinear index;

[0027] γ: physiological load recovery rate parameter.

[0028] Wherein, based on the current physiological load and the physiological load parameters of the individual at the historical time, the individual physiological load in the next time period is predicted, including:

[0029] In predicting the physiological load value of the next time period, the current and historical physiological load data, as well as the model parameters, are used to predict the physiological load of the time period (t+Δt) Wherein, the sailing environment data of the ship where the crew is located in the next time period is obtained through the AIS system or the meteorological sea state service channel, and based on this, the environment assessment model E is input to obtain the comprehensive stress level of the sailing environment where the crew is located in the next time period.

[0030] Wherein, the environment assessment model E is defined, and the environment assessment model E is used to convert the sailing environment data obtained above into the comprehensive stress level S of the sailing environment where the crew is located env :

[0031] S env =E(environment parameters)=β1S weather +β2S sea +β3S nav +β4S traffic ;

[0032] Wherein,

[0033] S env : comprehensive environmental stress level;

[0034] Weight coefficient β i : represents the influence weight of each environmental factor on the comprehensive stress, satisfies β1+β2+β3+β4=1, and β i ≥0;

[0035] Wherein, the environmental stress sub-index includes:

[0036] Weather stress index S weather :S weather =w1f wind (V w )+w2f visibibity (Vis)+w3f rain (Rain)+w4f temp (Temp);

[0037] Sea state stress index S sea :S sea =w5f wave (H wave )+w6f current (V c );

[0038] Navigation stress index

[0039] S nav :S nav =w7f route (R complexity )+w8f maneuver(M frequency );

[0040] Traffic stress index

[0041] S traffic :S traffic = w9f vesseldensity (D vessel ) + w 10 f collisionrisk (C risk );

[0042] wherein,

[0043] weighting coefficient w i : represents the influence weight of each specific factor on the corresponding stress index, and the sum of the weighting coefficients in the corresponding stress index is 1, and w i ≥ 0;

[0044] The function f converts the environmental variables into a standardized stress score, with a value between 0 and 1.

[0045] wherein, based on the comprehensive stress level of the sailing environment and the individual physiological load prediction value of the crew in the next time period, the causal inference graph model C is input, to predict the work load level of the crew in the future period, including:

[0046] The causal inference graph model C is constructed to describe the causal relationship between variables;

[0047] Based on the regression model, the influence of physiological load and environmental stress on work load and the interaction therebetween are captured;

[0048] A parameter estimation method is used to estimate the model parameters.

[0049] wherein, the causal inference graph model C is constructed, including the following processes:

[0050] First, variable definition:

[0051] : individual physiological load prediction value in the next time period t+Δt;

[0052] S env (t+Δt): comprehensive stress level of the sailing environment in the next time period t+Δt;

[0053] W(t+Δt): work load level of the crew in the future period;

[0054] Determine the causal relationship, including defining that the individual physiological load and the comprehensive stress S env (t+Δt) of the sailing environment have a direct impact on the work load level W(t+Δt) of the crew.

[0055] The regression model can be expressed as:

[0056]

[0057] Wherein:

[0058] W(t+Δt): predicted value of workload level;

[0059] β0: bias term, representing the basic workload level;

[0060] β1, β2, β3: model coefficients, representing the degree of influence of corresponding variables on workload level;

[0061] : individual physiological load prediction value;

[0062] S env (t+Δt): comprehensive stress level of navigation environment;

[0063] n1, n2, n3: nonlinear index, controlling the degree of nonlinearity of variables;

[0064] In order to estimate the model parameters θ={β0, β1, β2, β3, n1, n2, n3}, a nonlinear least squares method is used to minimize the error by iterative optimization algorithm.

[0065] Wherein, based on the predicted rest time of the next time period obtained from the work-rest schedule, the first correction is made to the preliminary predicted workload level;

[0066] Based on the environmental factors of the route and the personnel situation in the next time period work-rest arrangement, the second correction is made to the workload level after the first correction;

[0067] The intermediate values in the two correction processes are recorded, as well as the workload level before each correction, so that the relationship between the multi-stage, multi-factor load and the corrected load and the reasons is fed back to the control center.

[0068] The present application utilizes the individual physiological load model P to model according to the physiological data of each crew member, realizes the accurate evaluation of the workload of different individuals, and enhances the individual adaptability and prediction accuracy of the model.

[0069] The present application dynamically predicts the physiological load of an individual in a future time period based on current and historical physiological load data through a time series prediction model, ensuring the real-time and forward-looking nature of the prediction results.

[0070] The application introduces an environment evaluation model E to systematically evaluate the comprehensive stress level of the navigation environment in the next time period, quantifies the environmental factors into the workload prediction, and improves the sensitivity and response capability of the model to external environment changes.

[0071] The application combines the individual physiological load prediction value with the environmental stress level through a causal reasoning graph model C, deeply mines the causal relationship between factors, and improves the interpretability and accuracy of the workload prediction.

[0072] The application comprehensively utilizes the synergistic effect of multi-source data and multi-model to realize adaptive prediction of the workload of the crew, can dynamically adjust the prediction result according to real-time data and environmental changes, and ensures that the workload of the crew under various complex navigation conditions is always within a controllable range.

[0073] The application collects and fuses physiological characteristic data, historical physiological load parameters and navigation environment data of the crew, comprehensively and multi-dimensionally reflects the working state of the crew, and improves the information quantity and comprehensive analysis capability of the prediction model. BRIEF DESCRIPTION OF DRAWINGS

[0074] The above and other objects, features and advantages of the disclosed example embodiments will become more apparent from the following detailed description, taken in conjunction with the accompanying drawings, in which several embodiments of the disclosure are illustrated by way of example and not limitation, in which like references indicate like or corresponding parts, wherein:

[0075] Figure 1 is a flow chart showing a crew workload adaptive prediction method based on multi-source heterogeneous data fusion according to an embodiment of the application. DETAILED DESCRIPTION

[0076] In order to make the objects, technical solutions and advantages of the present application clearer, the following will further describe the present application with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0077] The terms used in the embodiments of the present application are only for the purpose of describing the specific embodiments, and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Multiple" generally includes at least two.

[0078] It should be understood that although the terms first, second, third, etc., may be used to describe... in the embodiments of the present invention, these... should not be limited to these terms. These terms are only used to distinguish... For example, first... may also be referred to as second... without departing from the scope of the embodiments of the present invention, and similarly, second... may also be referred to as first...

[0079] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0080] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0081] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0082] Existing methods fail to adequately consider the physiological differences and dynamic changes among individual crew members, resulting in predictions that lack individualization and real-time adaptability, and cannot reflect real-time changes in crew status. During ship navigation, environmental factors (such as weather and sea conditions) have a significant impact on crew workload, and existing methods fail to systematically and comprehensively assess the combined impact of environmental pressures on workload in predictions. Existing prediction models often lack in-depth modeling of the causal relationships between various influencing factors, leading to insufficient interpretability and accuracy of prediction results.

[0083] like Figure 1 As shown, this invention discloses an adaptive prediction method for crew workload based on multi-source heterogeneous data fusion, comprising the following steps:

[0084] The physiological characteristic data of the crew members are collected using wearable devices such as smartwatches and input into the individual physiological load model P to obtain the current physiological load of the individual.

[0085] Based on the individual's current physiological load and physiological load parameters at historical moments, the data are input into a time series prediction model to obtain the predicted physiological load value for the next time period.

[0086] Obtain navigation environment data for the individual's vessel in the next time period through the AIS system or meteorological and sea condition service channels;

[0087] Based on the navigation environment data for the next time period, input the environmental assessment model E to obtain the comprehensive pressure level of the navigation environment in which the crew is located in the next time period.

[0088] Based on the overall pressure level of the crew's navigation environment in the next time period and the predicted value of individual physiological load in the next time period, the causal inference graph model C is input to predict the crew's workload level in the future period.

[0089] This invention utilizes an individual physiological workload model P, which models each crew member based on their physiological data, to accurately assess the workload of different individuals, thereby enhancing the model's individual adaptability and predictive accuracy.

[0090] This invention uses current and historical physiological load data to dynamically predict an individual's physiological load over a future period through a time series prediction model, ensuring the real-time nature and forward-looking nature of the prediction results. This invention introduces an environmental assessment model E to systematically evaluate the comprehensive stress level of the navigation environment in the next period, quantifying environmental factors and incorporating them into workload prediction, thereby improving the model's sensitivity and responsiveness to changes in the external environment.

[0091] This invention uses a causal reasoning graph model C to organically combine individual physiological load predictions with environmental stress levels, deeply exploring the causal relationships between various factors and improving the interpretability and accuracy of workload prediction.

[0092] This invention comprehensively utilizes the synergistic effect of multi-source data and multiple models to achieve adaptive prediction of crew workload. It can dynamically adjust the prediction results according to real-time data and environmental changes, ensuring that the crew's workload is always within a controllable range under various complex navigation conditions.

[0093] In one embodiment, wearable devices such as smartwatches are used to collect the physiological characteristic data of crew members, which is then input into an individual physiological load model P to obtain the individual's current physiological load, including the dynamic physiological accumulation process of fatigue based on a fatigue accumulation formula. The specific implementation method is as follows: In one embodiment, wearable devices such as smartwatches are used to collect the physiological characteristic data of crew members in real time, including:

[0094] Heart rate (HR(t))

[0095] Heart rate variability (HRV(t))

[0096] Activity level (measured by an accelerometer, Activity(t))

[0097] Skin temperature (Temp(t))

[0098] Skin conductivity (EDA(t))

[0099] An individual physiological load model P is defined, which is used to calculate the physiological load L(t) of the crew member at the current time t. The model considers the nonlinear accumulation of fatigue and the dynamic physiological recovery process, and the formula is as follows:

[0100]

[0101] in,

[0102] L(t): Physiological load level (fatigue level) at the current time t.

[0103] L(t-Δt): The physiological load level at the previous time t-Δt.

[0104] HR(t): Heart rate measured at the current time t.

[0105] HR rest An individual's resting heart rate (baseline heart rate).

[0106] HRV(t): Heart rate variability measured at the current time t.

[0107] HRV rest Individual resting heart rate variability (baseline HRV).

[0108] Activity(t): The amount of activity at the current time t (obtained via accelerometer).

[0109] Δt: Time interval (the time difference between two sampling moments).

[0110] α1, α2, α3: Individualized weighting coefficients reflecting the degree of influence of each physiological indicator on fatigue accumulation. n1, n2, n3: Nonlinear exponents used to describe the nonlinear relationship between physiological indicators and fatigue accumulation. γ: Physiological load recovery rate parameter, reflecting the speed at which fatigue recovers over time.

[0111] Among them, sub-items In the meantime, heart rate contribution: This represents the contribution of the current heart rate above the resting heart rate to fatigue, with the exponent n1 reflecting non-linearity. Heart rate variability contribution. This indicates the contribution of decreased heart rate variability (HRV) to fatigue; the lower the HRV, the higher the fatigue. (Activity level contribution) This represents the contribution of physical activity to fatigue. The fatigue recovery portion is L(t-Δt)×e -γΔt Using the exponential decay function e -γΔt The fatigue recovery process over time is simulated; the larger the γ value, the faster the fatigue recovery.

[0112] Among them, the baseline parameter HRR rest and HRV rest This data needs to be obtained through multiple measurements under resting conditions to reflect an individual's physiological baseline level. Weighting coefficients and indices α1, α2, α3, n1, n2, n3 can be individually fitted using regression analysis of historical data or machine learning methods to accurately reflect each crew member's sensitivity to different physiological indicators. The recovery rate parameter γ can be adjusted according to the individual's fatigue recovery characteristics.

[0113] For example, the model parameters are as follows: α1 = 0.5, n1 = 2; α2 = 0.3, n2 = 1;

[0114] α3=0.2, n3=1.5; γ=0.1.

[0115] By setting exponents n1, n2, and n3, the model can reflect the nonlinear influence of physiological indicators on fatigue accumulation. For example, once the heart rate exceeds a certain threshold, the rate of fatigue accumulation accelerates. The model parameters are adjusted based on individual historical data, reflecting the physiological characteristics and fatigue sensitivity of each crew member. The model simultaneously considers the fatigue accumulation and recovery process, enabling it to reflect the crew member's physiological workload status in real time.

[0116] In one embodiment, an initial fatigue level L(0) = L0 is set, which can typically be zero or a baseline value. At each time interval Δt, a new physiological load L(t) is calculated based on the latest physiological characteristic data. The model continuously accumulates fatigue over time, while also considering the fatigue recovery process.

[0117] In one embodiment, the individual's physiological load for the next time period is predicted based on the individual's current physiological load and physiological load parameters at historical moments. This includes using the physiological load L(t-iΔt) from the past p moments to predict the current physiological load L(t), and using the error term ∈(t-jΔt) from the past q moments to correct the prediction.

[0118]

[0119] Specifically, when predicting the physiological load value for the next time period, current and historical physiological load data, along with model parameters, are used to predict the physiological load for the next time period (t+Δt). The specific prediction method is as follows:

[0120]

[0121] Since t+Δt-iΔt=t-(i-1)Δt, therefore

[0122]

[0123] The parameters are defined as follows:

[0124] L(t): The physiological load of an individual at time t.

[0125] Δt: Time interval, the time difference between two sampling moments.

[0126] p: indicates how many past physiological load data points are used.

[0127] q: indicates how many past error terms to use.

[0128] Autoregressive coefficients, i = 1, 2, ..., p, represent the degree of influence of past physiological load on the current value. θ j The moving average coefficient, j = 1, 2, ..., q, represents the degree of influence of past errors on the current value.

[0129] ∈(t): Random error term (noise), assumed to be white noise with zero mean.

[0130] The future error term ∈ (t+Δt) is unknown, and it is usually assumed that its expectation is zero. Therefore, the future error term is not included in the prediction.

[0131] In one embodiment, model parameter estimation includes the following process: acquiring sufficient length of physiological load time series data L(t) and calculating the corresponding error term ∈(t), wherein the error term calculation is as follows: Using historical data, the model coefficients are estimated using methods such as least squares or maximum likelihood estimation. and θ j .

[0132] In one embodiment, the collected historical data includes physiological load data from the past p time points: L(t), L(t-Δt), L(t-2Δt), ..., L(t-(p-1)Δt), and error terms from the past q time points: ∈(t), ∈(t-Δt), ∈(t-2Δt), ..., ∈(t-(q-1)Δt).

[0133] Calculate the predicted value and Predicting the physiological load at the next moment:

[0134] In one embodiment, it is assumed that the model order is p = 2 and q = 1.

[0135] Estimated model coefficients: θ1 = 0.5.

[0136] Time interval: Δt = 1 (unit of time, e.g., 1 hour)

[0137] Time interval: Δt = 1 (unit of time, e.g., 1 hour)

[0138] Physiological load: L(t) = 25, L(t-1) = 23.

[0139] Error terms: ∈(t)=0.8, ∈(t-1)=-0.5.

[0140] Prediction calculation: θ j ∈(t-(j-1)Δt)=0.5×0.8=0.4.

[0141] Predicting the physiological load at the next moment: Therefore, the predicted physiological load for the next time period (t+Δt) is 22.5.

[0142] By inputting an individual's current physiological load L(t), its historical physiological load data, and error terms into a prediction model, the individual's physiological load for the next time period can be predicted. In one embodiment, the navigation environment data of the individual's vessel in the next time period is obtained through the AIS system or the meteorological and sea condition service channel, and based on this, the comprehensive pressure level of the navigation environment in the next time period is obtained by inputting the environmental assessment model E.

[0143] In one embodiment, acquiring navigation environment data includes:

[0144] Obtain navigation-related data through the AIS system:

[0145] AIS (Automatic Identification System) provides real-time dynamic information about vessels at sea, including the vessel's own information: vessel position (latitude and longitude) (Lat, Lon).

[0146] Ship speed (speed over land) V s

[0147] Ship heading (relative to true north) H s

[0148] Ship status (underway, at anchor, etc.)

[0149] Other vessel information: • Number of nearby vessels N v

[0150] Distance D of nearby ships i (i = 1, 2, ..., N) v • The course and speed of other vessels, and environmental data obtained through meteorological and sea state services, including meteorological and sea state data:

[0151] Wind speed V w

[0152] Wind direction H w

[0153] Visibility

[0154] Rainfall

[0155] Temperature

[0156] Wave height H wave

[0157] Wave direction (direction of wave propagation) D wave

[0158] Flow velocity V c

[0159] Flow to D c

[0160] All the data acquired should be for the next time period, that is, the forecast data within the time interval Δt starting from the current time t.

[0161] In one embodiment, an environmental assessment model E is defined, which is used to transform the acquired navigation environment data into a comprehensive pressure level S of the navigation environment in which the crew is located. env .

[0162] The model reflects the impact of various environmental factors on crew stress:

[0163] S env =E (environmental parameter) =β1S weather +β2S sea +β3s nav +β4S traffic .

[0164] in,

[0165] S env Overall environmental stress level (numerical stress indicators).

[0166] Weighting coefficient β i : Represents the weight of each environmental factor on the overall stress, satisfying β1+β2+β3+β4=1, and β i ≥0.

[0167] Among them, the environmental stress sub-indicators include:

[0168] Weather Stress Index S weather :S weather =w1f wind (V w )+w2f visibibity (Vis)+w3f rain (Rain)+w4f temp (Temp).

[0169] Sea pressure index S sea :S sea =w5f wave (H wave )+w6f current (V c ).

[0170] Navigation pressure index

[0171] S nav :S nav =w7f route (R complexity )+w8f maneuver (M frequency ).

[0172] Traffic Pressure Index

[0173] S traffic :S traffic =w9f vesseldensity (D vessel )+w 10 f collisionrisk (C risk ).

[0174] in,

[0175] Weighting coefficient w i : Represents the weight of each specific factor on the corresponding stress index, satisfying that the sum of the weight coefficients within the corresponding stress index is 1, and w i ≥0.

[0176] Function f: Converts specific environmental variables into standardized stress scores (0 to 1).

[0177] Among them, the weather stress index S weather ,include:

[0178] Wind speed influence function f wind (V w As wind speed increases, pressure increases, which can be defined as:

[0179]

[0180] in:

[0181] V w Wind speed (unit: m / s).

[0182] : Maximum wind speed, the wind speed threshold with a pressure score of 1.

[0183] Visibility influence function f visibility (Vis): The lower the visibility, the greater the pressure, which can be defined as:

[0184] in:

[0185] Vis: Visibility (unit: km).

[0186] Vis max Ideal visibility, minimum pressure.

[0187] Viss min Lowest visibility, highest pressure.

[0188] Rainfall influence function f rain (Rain): The greater the rainfall, the greater the pressure. The function can be defined as:

[0189]

[0190] in:

[0191] Rain: Rainfall amount (unit: mm / h).

[0192] Rain max : Maximum rainfall, corresponding to the rainfall threshold with a pressure score of 1.

[0193] Temperature influence function f temp (Temp): Both excessively high and low temperatures increase stress, which can be represented as:

[0194] in:

[0195] Temp: Temperature.

[0196] Temp opt The optimal temperature and the lowest pressure.

[0197] Temp range Half the width of the temperature range, used for standardization.

[0198] Among them, the sea state pressure index S sea ,include:

[0199] Wave height influence function fwave (H wave The higher the wave height, the greater the pressure, which can be defined as:

[0200] in:

[0201] H wave Wave height (unit: m).

[0202] : Maximum wave height, corresponding to a pressure score of 1.

[0203] Flow velocity influence function f current (V c The higher the flow rate, the greater the pressure, expressed as:

[0204]

[0205] in:

[0206] V c Flow velocity (unit: m / s).

[0207] : Maximum flow rate, corresponding to the threshold with a pressure score of 1.

[0208] Among them, the navigation pressure index S nav include:

[0209] The function f of route complexity route (R complexity The more complex the flight path, the greater the pressure, which is expressed as:

[0210]

[0211] in:

[0212] R complexity Rate the route complexity (0 to R) max ).

[0213] R max : The maximum value of the route complexity score.

[0214] Manipulating the frequency influence function f maneuver (M frequency When frequent manipulation is required, the pressure increases, which is represented as:

[0215] in:

[0216] M frequency : The number of manipulations expected in the next time period.

[0217] M maxMaximum expected number of manipulations.

[0218] Among them, the manipulation frequency M frequency Maneuvering types include all operations that require the crew to actively control the vessel to change its course, speed, or position, such as turning, decelerating or accelerating, changing course, avoiding other vessels, and emergency maneuvering in response to unforeseen circumstances.

[0219] M frequency The determination is usually based on the following factors:

[0220] Route complexity: The number of times the route requires maneuvering, such as turning, crossing channels, narrow waterways, and shallow water areas.

[0221] Traffic flow: When the density of surrounding vessels is high, the maneuvering required to avoid other vessels increases.

[0222] Weather and sea conditions: In adverse weather conditions, more maneuvering may be required to maintain safe navigation.

[0223] Navigation plan: Based on the predetermined route and plan, the number of maneuvers required is estimated.

[0224] Determine M frequency The process includes the following:

[0225] Step 1: Assess route complexity

[0226] Obtain route information, including flight distance, channel type, number of turning points, etc.

[0227] Calculate the number of turns N on the flight path turns : Count the number of turning points in the flight path.

[0228] Step 2: Assess traffic conditions

[0229] Obtain AIS data: Obtain the number and distribution of other vessels in the navigation area within the next time period.

[0230] Calculate the number of times N needs to avoid obstacles. avoid Based on the number of other vessels and the anticipated situation, estimate the number of times you will need to avoid them.

[0231] Step 3: Assess the impact of meteorological and sea state conditions

[0232] Obtain weather and sea condition forecasts, including information on wind, waves, and currents.

[0233] Assess the incremental demand ΔN for manipulation weather Under adverse conditions, the number of operations may need to be increased. Step 4: Calculate the total number of operations M. frequency =N turns +N avoid +ΔN weather , where N turnsNumber of turns in the flight path; N avoid : The estimated number of times it will be necessary to avoid other ships; ΔN weather Increased number of operations due to weather and sea conditions.

[0234] For example, suppose: Route information: • The route is 100 nautical miles long and contains 5 turning points.

[0235] Traffic conditions: It is expected that there will be 3 other vessels that need to be avoided in the next time period.

[0236] Weather and Sea Conditions: The weather forecast indicates high winds and waves, requiring two additional maneuvers to maintain course and speed.

[0237] Calculate: N turns =5; N avoid =3; ΔN weather =2. Total number of operations

[0238] Number: M frequency =5+3+2=10.

[0239] Traffic Pressure Index S traffic ,include:

[0240] Ship density influence function f vesseldensity (D vessel The higher the density of nearby ships, the greater the pressure.

[0241] Represented as:

[0242] in:

[0243] D vessel Number of ships per unit area.

[0244] D max : The maximum value of ship density.

[0245] Collision risk impact function f collisionrisk (C risk The higher the risk of collision with other vessels, the greater the pressure, denoted as f. collisionrisk (C risk )=min(C risk ,1),

[0246] in:

[0247] C risk Collision risk value is calculated based on indicators such as time to closest encounter (TCPA) and distance to closest encounter (DCPA).

[0248] The above-mentioned function f is used to convert the original environmental variables into standardized stress scores, ranging from 0 to 1.

[0249] Among them, the collision risk value C is determined. risk It is used to quantify the risk of a ship colliding with another ship during navigation.

[0250] Commonly used collision risk assessment indicators include:

[0251] Distance at Closest Point of Approach (DCPA): The closest distance between a vessel and another vessel that are predicted to reach each other in a track forecast.

[0252] Time to Closest Point of Approach (TCPA): The time required for a vessel to reach the DCPA with another vessel.

[0253] Rate of Turn Angle (ROTA): The rate at which the bearing of another vessel changes relative to the vessel itself.

[0254] Collision Risk Index (CRI): A risk value assessed by combining multiple indicators.

[0255] Collision risk value C risk The calculation method includes the following steps:

[0256] Step 1: Obtain information about other ships

[0257] Obtain navigation data of surrounding vessels through the AIS system:

[0258] His ship's heading θ i Speed ​​V i Location (x) i ,y i ).

[0259] Step 2: Predict the movement of other ships

[0260] Calculate the motion parameters of the other ship relative to this ship:

[0261] relative speed

[0262] Where: V0, θ0: the ship's speed and course.

[0263] Step 3: Calculate DCPA and TCPA

[0264] DCPA calculation:

[0265] TCPA calculation:

[0266] in,

[0267] x0, y0: The horizontal and vertical coordinates of the ship's current position.

[0268] x i ,y i : The x and y coordinates of the current position of the i-th ship.

[0269] V rel,x The relative velocity component of this ship with respect to other ships in the x-direction.

[0270] Calculation formula: V rel,x =V i cosθ i -V0cosθ0.

[0271] V rel,y The relative velocity component of this ship with respect to other ships in the y-direction.

[0272] Calculation formula: V rel,y =V i sinθ i -V0sinθ0.

[0273] V0: The speed of this ship.

[0274] θ0: The heading angle of this ship, calculated clockwise relative to true north.

[0275] V i : The speed of the i-th ship.

[0276] θ i The heading angle of the i-th other ship is calculated clockwise relative to due north.

[0277] TCPA: Time to the nearest meeting point, which is the time required for this vessel to reach the nearest meeting point with another vessel.

[0278] DCPA: Closest Encounter Distance, which is the minimum distance between this vessel and another vessel at the nearest encounter point.

[0279] The squares of the velocity components in the x and y directions of the relative velocity.

[0280] (x i -x0),(y i -y0): The positional difference between this ship and other ships in the x and y directions.

[0281] When TCPA < 0, it means that the other vessel has already passed by, and the risk of collision is not considered.

[0282] Step 4: Calculate the collision risk value C risk

[0283] Using the collision risk model: C risk =e -a·DCPA ·e -b·|TCPA| ,

[0284] in,

[0285] a,b: Model parameters that determine the degree of influence of DCPA and TCPA on the risk value; a,b>0.

[0286] Step 5: Accumulate collision risk values ​​for multiple other vessels

[0287] When there are multiple other vessels nearby, the risks of each vessel should be considered comprehensively:

[0288] Where N: the number of other ships in the vicinity; C risk,i Collision risk value of the i-th other ship.

[0289] C risk The calculation is based on AIS data from other vessels, using indicators such as TCPA and DCPA, and is derived through a collision risk model.

[0290] For example, suppose the ship's data is as follows:

[0291] Position (x0, y0) = (0, 0)

[0292] Heading θ0 = 0° (due north)

[0293] Speed ​​V0 = 10 knots

[0294] Data on other ships (other ship 1):

[0295] Location (x1, y1) = (1, -5) nautical miles

[0296] Heading θ1 = 90° (due east)

[0297] Speed ​​V1 = 12 knots

[0298] Model parameters:

[0299] a = 0.5

[0300] b = 0.1

[0301] Calculate relative velocity:

[0302] V rel,x =V1cosθ1-V0cosθ0=12cos90°-10cos0°=0-10=-10,

[0303] V rel,y=V1sinθ1-V0sinθ0=12sin90°-10sin0°=12-0=12,

[0304] Calculate TCPA:

[0305]

[0306] Calculate DCPA:

[0307]

[0308] Calculate the collision risk value C risk,1 :

[0309] C risk,1 =e -0.5×2.434 ·e -0.1×0.2877 ≈0.2885.

[0310] If there is only one other ship, then C risk =C risk,1 =0.2885.

[0311] C risk The calculation is based on AIS data from other vessels, using indicators such as TCPA and DCPA, and is derived through a collision risk model.

[0312] Calculate each sub-pressure index, including using its respective weighting coefficient w. i It calculates the pressure index of weather, sea conditions, navigation, and traffic.

[0313] Calculate the comprehensive environmental pressure level S env Using environmental assessment model E, the sub-pressure indices are weighted according to β. i We perform a weighted summation to obtain the overall environmental stress level: S env =β1S weather +

[0314] β2S sea +β3S nav +β4S traffic .

[0315] For example, in one embodiment, the parameter weighting coefficients are assumed to be: β1 = 0.3, β2 = 0.2, β3 = 0.25, β4 = 0.25.

[0316] Weighting coefficients of the sub-pressure index:

[0317] Weather stress index: w1 = 0.4, w2 = 0.3, w3 = 0.2, w4 = 0.1.

[0318] Sea pressure index: w5 = 0.6, w6 = 0.4

[0319] Navigation pressure index: w7 = 0.7, w8 = 0.3.

[0320] Traffic pressure index: w9 = 0.5, w 10 =0.5,

[0321] First, it is necessary to collect environmental data for the next time period, including:

[0322] Wind speed V w =15m / s, maximum wind speed

[0323] Viss = 5km max =10km,Vis min =0km,

[0324] Rainfall = 5 mm / h max =10mm / h,

[0325] Temperature Temp = 35℃, Temp opt =25℃,Temp range =10℃,

[0326] Wave height H wave =3m,

[0327] Flow velocity V c =1m / s,

[0328] Route complexity score R complexity =70,R max =100,

[0329] Expected number of manipulations M frequency =5,M mdx =10,

[0330] Ship density D vessel =20,D max =30,

[0331] Collision risk value C rusk = 0.6 (standardized).

[0332] In the next phase, standardized stress scores will be calculated, including:

[0333]

[0334]

[0335]

[0336]

[0337]

[0338]

[0339]

[0340]

[0341]

[0342]

[0343] In the next phase, the sub-pressure indices will be calculated, including:

[0344] Weather Stress Index S weather :S weather =0.4×0.75+0.3×0.5+0.2×0.5+0.1×1=0.65.

[0345] Sea pressure index S sea :S sea =0.6×0.6+0.4×0.5=0.36+0.2=0.56.

[0346] Navigation pressure index S nav :S nav =0.7×0.7+0.3×0.5=0.49+0.15=0.64.

[0347] Traffic Pressure Index S traffic :S traffic =0.5×0.6667+0.5×0.6=0.3333+0.3=0.6333.

[0348] Finally, the comprehensive environmental pressure level S is calculated. env :

[0349] S env =0.3×S weather +0.2×S sea +0.25×S nav +0.25×S traffic =0.6253.

[0350] Therefore, the overall environmental pressure level S in the next time period env =0.6253.

[0351] The ship's navigation environment data for the next time period is obtained through the AIS system and weather and sea state services. This data is then processed using environmental assessment model E to calculate the comprehensive pressure level S of the navigation environment in which the crew is located. env This model considers the impact of various environmental factors and transforms complex environmental data into a quantifiable stress index through standardization and weighted summation, providing an important basis for subsequent crew workload prediction and management.

[0352] In one embodiment, based on the overall stress level of the crew's navigation environment and the predicted value of individual physiological load in the next time period, the causal inference graph model C is input to predict the crew's workload level in the future, including:

[0353] Construct a causal reasoning graph model E to describe the causal relationships between the variables.

[0354] The study uses regression models to capture the impact of physiological load and environmental stress on workload, and the interaction between them.

[0355] Use parameter estimation methods to estimate model parameters.

[0356] In one embodiment, constructing a causal reasoning graph model C includes the following process:

[0357] First, variable definition:

[0358] : Predicted individual physiological load for the next time period t+Δt.

[0359] S env (t+Δt): The overall pressure level of the navigation environment in the next time period t+Δt.

[0360] W(t+Δt): Crew workload level over a future period (target variable).

[0361] Determining causality includes defining individual physiological load. Combined pressure of the navigation environment S env (t+Δt) has a direct impact on the crew's workload level W(t+Δt).

[0362] In one embodiment, the combined effects of individual physiological load and the combined stress of the navigation environment may interact, resulting in a non-linear summation of their influence on workload. To capture the non-linear effects of physiological load and environmental stress on workload levels, as well as their interaction, the following regression model is established:

[0363]

[0364] in:

[0365] W(t+Δt): The crew's workload level over a future period of time.

[0366] f(·): represents a non-linear function relating the input variable to the workload.

[0367] Predicted individual physiological load for the next time period.

[0368] S env (t+Δt): The overall pressure level of the navigation environment in the next time period.

[0369] θ: The set of model parameters, including weight coefficients and nonlinear exponents.

[0370] ∈: Error term, representing the random error not explained by the model, assumed to have a mean of zero.

[0371] In one embodiment, the regression model can be expressed as:

[0372]

[0373] in:

[0374] W(t+Δt): Predicted value of workload level.

[0375] β0: Bias term, representing the basic workload level.

[0376] β1, β2, β3: Model coefficients, representing the degree of influence of the corresponding variable on the workload level.

[0377] : Individual physiological load prediction value.

[0378] S env (t+Δt): Overall pressure level of the navigation environment.

[0379] n1, n2, n3: Nonlinear exponents, controlling the degree of nonlinearity of the variables.

[0380] To estimate the model parameters θ = {β0, β1, β2, β3, n1, n2, n3}, a nonlinear least squares method can be used, and the error can be minimized through an iterative optimization algorithm (such as the Levenberg-Marquardt algorithm). In one embodiment, the causal inference graph model C is constructed, including the following process:

[0381] Step 1: Obtain a sufficient amount of historical data, including:

[0382] Individual physiological load prediction value

[0383] Comprehensive pressure level of the navigation environment Senv (t+Δt).

[0384] The corresponding crew workload level W(t+Δt).

[0385] Data should be cleaned, standardized, or normalized to improve the stability and convergence of the model.

[0386] Step 2: Model training.

[0387] Set initial values ​​for the model parameters θ.

[0388] When choosing a loss function, the commonly used loss function is mean squared error (MSE):

[0389] in,

[0390] N: Number of samples.

[0391] W i : The actual workload level of the i-th sample.

[0392] : The workload level predicted by the model for the i-th sample.

[0393] Minimize the loss function using an optimization algorithm, update the parameter θ, and follow the update rule:

[0394] in:

[0395] θ (k) : The parameter value in the kth iteration.

[0396] η: Learning rate, the step size for updating control parameters.

[0397] : The gradient of the loss function with respect to the parameter θ.

[0398] Step 3: Divide the dataset into training and validation sets. Evaluate the model's predictive performance on the validation set, calculating metrics such as MSE and Root Mean Square Error (RMSE). Based on the model's performance on the validation set, adjust the model structure or retrain the model.

[0399] In one embodiment, predicting workload levels includes:

[0400] Determine the parameters of the trained model θ = {β0,β1,β2,β3,n1,n2,n3}.

[0401] Predicted individual physiological load for the next time period

[0402] The overall pressure level of the navigation environment in the next time period (S) env (t+Δt).

[0403] Calculating workload levels includes the following steps:

[0404] Step 1: Calculate each nonlinear term

[0405]

[0406]

[0407]

[0408] Step 2: Substitute into the model formula to calculate the predicted workload value W(t+Δt)=β0+β1h1+β2h2+β3h3.

[0409] For example, assume the model parameters are: β0 = -0.5, β1 = 0.8, β2 = 0.6, β3 = 0.4, n1 = 1.5, n2 = 2.0, n3 = 1.0.

[0410] Input variables: (Standardization processing, such as dividing by the maximum value of 30, yields...) S env (t+Δt)=0.6253.

[0411] Calculating workload levels includes:

[0412] Calculate nonlinear terms

[0413] h1 = (0.75) 1.5 =0.6495,

[0414] h2 = (0.6253) 2.0 =0.3909,

[0415] h3 = (0.75 × 0.6253) 1.0 =0.4690;

[0416] Calculate the predicted workload:

[0417] W(t+Δt)=-0.5+0.8×0.6495+0.6×0.3909+0.4×0.4690=0.4417.

[0418] The predicted workload level is 0.4417.

[0419] In one embodiment, the initially predicted workload level is first revised based on the expected rest time for the next time period obtained from the work-rest schedule.

[0420] Based on environmental factors along the flight route and the personnel situation in the work and rest arrangements for the next period, the workload level after the first revision will be revised a second time.

[0421] Record intermediate values ​​and values ​​before correction: Record the intermediate values ​​during the two correction processes, as well as the workload level before each correction, to obtain the relationship between multi-stage, multi-factor loads and corrected loads and causes.

[0422] The aforementioned relationships and data are fed back to the control center for decision support and management optimization. In one embodiment, obtaining the personnel work / rest schedule for the next time period includes retrieving the work and rest schedules of all crew members for the next time period from the work schedule table, calculating the personnel availability coefficient, and determining individual rest time.

[0423] For the personnel availability coefficient P avail :

[0424]

[0425] in,

[0426] P avail Personnel availability coefficient: This represents the proportion of personnel currently working in the next time period.

[0427] N working The number of crew members currently working in the next time period.

[0428] N total Total number of crew members on board.

[0429] Individual rest time R:

[0430] R i : The expected rest time (in hours) for the i-th crew member in the next time period.

[0431] The impact of individual rest time on individual workload is reflected in the fact that crew members with insufficient rest time may experience increased fatigue and a higher workload level (W); while crew members with sufficient rest time may experience a lower workload level (W).

[0432] The impact of the personnel availability factor on individual workload is reflected in the fact that when the personnel availability factor is low, there are fewer people actually working, and the workload of each person increases.

[0433] The impact of environmental factors on overall workload is reflected in environmental pressure S. env At higher levels, more work is needed to meet environmental challenges, and staff shortages can exacerbate individual workloads.

[0434] In one embodiment, W is obtained by adjusting the estimated rest time for the next time period based on the work-rest schedule obtained from the work-rest schedule, and by adjusting the rest time based on environmental factors of the flight route and the personnel situation in the work-rest schedule for the next time period. adjusted include:

[0435] W adjusted =W×F(R)×G(P) avail ,S env ),

[0436] in:

[0437] W adjusted Adjusted individual workload level.

[0438] W: Uncorrected individual workload level (calculated from the aforementioned model).

[0439] F(R): A correction factor based on individual rest time.

[0440] G(P avail ,S env ): A correction factor based on personnel availability coefficient and environmental pressure.

[0441] In one embodiment, the correction factor F(R) can be expressed as:

[0442] F(R): Individual rest time correction factor.

[0443] λ1: Rest time influence coefficient, reflecting the intensity of the impact of rest time on workload, λ1>0.

[0444] R: Individual's expected rest time in the next time period (in hours).

[0445] R opt Ideal optimal rest time (unit: hours).

[0446] Where R <R opt When F(R) > 1, it indicates insufficient rest and increased workload.

[0447] When R>R opt When F(R) < 1, it indicates that the person has had sufficient rest and the workload level has decreased.

[0448] In one embodiment, the correction factor G(P) avail ,S env This can be represented as:

[0449] G(P avail ,S env): A comprehensive correction factor that takes into account the impact of personnel availability and environmental pressure.

[0450] λ2: The coefficient of influence of personnel availability and environmental pressure, λ2>0.

[0451] P avail Personnel availability coefficient, 0 <P avail ≤1.

[0452] P opt The ideal personnel availability factor is usually 1.

[0453] S env Overall environmental pressure level, 0≤S env ≤1.

[0454] μ: Environmental stress impact index, μ≥0.

[0455] Where, when P avail <P opt At that time, G(P) avail ,S env If P > 1, it indicates insufficient personnel and an increased workload; when P avail >P opt At that time, G(P) avail ,S env If S < 1, it indicates a surplus of personnel and a reduced workload level; environmental pressure S env The higher the value, the greater the impact of the correction factor on workload levels. In one embodiment, W is obtained by adjusting the expected rest time for the next time period based on the work-rest schedule, and by adjusting for environmental factors along the flight route and personnel availability in the next time period's work-rest arrangement. adjusted include:

[0456]

[0457] in:

[0458] W adjusted : Adjusted individual workload level.

[0459] W: Uncorrected individual workload level.

[0460] R: The individual's expected rest time in the next time period.

[0461] R opt The ideal optimal rest time.

[0462] λ1: Influence coefficient of rest time.

[0463] P avail Personnel availability coefficient.

[0464] Popt Ideal personnel availability coefficient.

[0465] λ2: The coefficient of influence of personnel availability and environmental stress.

[0466] S env Overall environmental stress level.

[0467] μ: Environmental stress impact index.

[0468] This model takes into account the nonlinear relationships of multiple influencing factors, enabling it to predict workload levels more accurately.

[0469] For example, the uncorrected individual workload level is known to be: W = 0.5; the individual rest time is: R = 1.5 hours; and the ideal optimal rest time is: R opt =2 hours; Rest time impact coefficient: λ1 = 0.3; Personnel availability coefficient: Ideal personnel availability factor: P opt =1; Personnel and environmental impact coefficient: λ2 = 0.5; Overall environmental pressure level: S env =0.7;

[0470] Environmental stress impact index: μ=2.

[0471] After correction, W is obtained. adjusted include:

[0472] Calculate F(R):

[0473] Calculate G(P) avail ,S env ): Calculate the corrected workload level: W adjusted =W×F(R)×G(P) avail ,S env = 0.5655.

[0474] The above process shows that because the rest time is less than the ideal rest time, the correction factor F(R) > 1, and the workload level increases by about 7.79%.

[0475] Personnel and Environmental Corrections: Personnel availability is lower than ideal, and environmental stress is high, leading to a correction factor G(P) of higher than ideal. avail ,S env If the value is greater than 1, the workload level increases by approximately 5.02%.

[0476] The revised workload level is approximately 13.1% higher than the unrevised level.

[0477] In one embodiment, recording the intermediate values ​​between two correction processes, as well as the workload level before each correction, includes:

[0478] Record the values ​​of the workload level at each stage, including:

[0479] The uncorrected individual workload level W calculated from the model, recorded as: W initial =W.

[0480] The first revised workload level W adjusted1 ,include:

[0481] The workload level after the first correction is calculated based on the correction factor F(R) for individual rest time: W adjusted1 =W initial ×F(R).

[0482] Recorded variables: F(R): Individual rest time correction factor; W adjusted1 The workload level after the first revision.

[0483] The second revised workload level W adjusted This includes a correction factor G(P) based on personnel availability and environmental pressure. avail ,S env ), calculate the second revised workload level: W asjusted =W adjusted1 ×G(P avail ,S env ).

[0484] Record variable: G(P) avail ,S env ): Comprehensive correction factor, W adiusted Final revised workload level.

[0485] In one embodiment, multi-stage, multi-factor loads and corrective loads, along with their causes, are fed back to the control center, including:

[0486] For each correction phase, record: workload level value, correction factor value, correction increment and percentage of impact, and a detailed explanation of the reason for the correction.

[0487] For example, create a data record table as follows:

[0488]

[0489] This invention utilizes an individual physiological workload model P, which models each crew member based on their physiological data, to accurately assess the workload of different individuals, thereby enhancing the model's individual adaptability and predictive accuracy.

[0490] This invention uses a time series prediction model to dynamically predict an individual's physiological load over a future period based on current and historical physiological load data, ensuring the real-time and forward-looking nature of the prediction results.

[0491] This invention introduces an environmental assessment model E to systematically assess the overall pressure level of the navigation environment in the next time period, quantifies environmental factors and incorporates them into workload prediction, thereby improving the model's sensitivity and responsiveness to changes in the external environment.

[0492] This invention uses a causal reasoning graph model C to organically combine individual physiological load predictions with environmental stress levels, deeply exploring the causal relationships between various factors and improving the interpretability and accuracy of workload prediction.

[0493] This invention comprehensively utilizes the synergistic effect of multi-source data and multiple models to achieve adaptive prediction of crew workload. It can dynamically adjust the prediction results according to real-time data and environmental changes, ensuring that the crew's workload is always within a controllable range under various complex navigation conditions.

[0494] This invention comprehensively and multidimensionally reflects the working status of crew members by collecting and integrating their physiological characteristic data, historical physiological load parameters, and navigation environment data, thereby improving the information content and comprehensive analysis capabilities of the prediction model.

[0495] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0496] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0497] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0498] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0499] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0500] The preferred embodiments of the present invention have been described above to make the spirit of the present invention clearer and easier to understand, and are not intended to limit the present invention. All modifications, substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope summarized by the appended claims.

Claims

1. An adaptive prediction method for crew workload based on multi-source heterogeneous data fusion, comprising: Collect physiological characteristic data of crew members and input them into the individual physiological load model P to obtain the individual's current physiological load; Based on an individual's current physiological load and physiological load parameters at historical moments, the data are input into a time series prediction model to obtain the predicted physiological load value for the next time period. Obtain navigation environment forecast data for the next time period through the AIS system or meteorological and sea condition service channels; Based on the navigation environment forecast data for the next time period, input the environmental assessment model E to conduct a sub-item pressure assessment of the navigation environment for the next time period and summarize it to obtain the comprehensive pressure level of the navigation environment in which the crew is located in the next time period. Based on the overall pressure level of the crew's navigation environment in the next time period and the predicted value of individual physiological load in the next time period, input the causal inference graph model C to predict the crew's workload level in the next time period. The first revision is made to the predicted workload level of the crew for the next time period based on the rest time expected in the next time period obtained from the work and rest schedule; the second revision is made to the workload level after the first revision based on the environmental factors of the route and the personnel situation in the work and rest schedule for the next time period. Record the intermediate values ​​during the two correction processes, as well as the workload level before each correction, and feed back each intermediate value and the corresponding correction reason to the control center. This includes using wearable devices to collect real-time physiological characteristic data of crew members, including: Heart rate, heart rate variability, and activity levels measured by an accelerometer; Define individual physiological load model Individual physiological load model Used to calculate the current time physiological load on crew members The model considers the nonlinear accumulation of fatigue and the dynamic physiological recovery process, and the formula is as follows: ， in, Current moment Physiological load level; Previous moment Physiological load level; Current moment Measured heart rate; An individual's resting heart rate; Current moment Measured heart rate variability; Individual resting heart rate variability; Activity Current moment The amount of activity; :Time interval; Individualized weighting coefficients; Nonlinear exponent; Physiological load recovery rate parameter.

2. The adaptive prediction method for crew workload based on multi-source heterogeneous data fusion as described in claim 1, characterized in that, Based on an individual's current physiological workload and historical physiological workload parameters, predict the individual's physiological workload for the next time period, including: When predicting physiological load values ​​for the next time period, current and historical physiological load data, along with model parameters, are used to predict the time period. physiological load .

3. The adaptive prediction method for crew workload based on multi-source heterogeneous data fusion as described in claim 2, characterized in that, Define environmental assessment model Environmental assessment model This is used to convert the acquired navigation environment data into a comprehensive pressure level of the navigation environment in which the crew is located. : ； in, Overall environmental stress level; Weighting coefficient : Represents the weight of each environmental factor on the overall stress, satisfying ; Among them, the environmental stress sub-indicators include: Weather stress index : ; Sea pressure index : ; Navigation pressure index : ; Traffic Pressure Index : ; in, Weighting coefficient : Indicates the weight of each specific factor on the corresponding stress index, satisfying that the sum of the weight coefficients within the corresponding stress index is 1; The wind speed influence function; The visibility effect function; Let the rainfall effect function be used. This is a function representing the influence of temperature. The function representing the influence of wave height; Let be the flow velocity influence function. This is a function that affects the complexity of flight routes. This is a function that manipulates the frequency effect; The function representing the influence of ship density; This is a collision risk impact function; The above function Environmental variables are converted into standardized stress scores, with values ​​between 0 and 1.

4. The adaptive prediction method for crew workload based on multi-source heterogeneous data fusion as described in claim 1, characterized in that, Based on the comprehensive stress level and individual physiological load predictions of the crew's navigation environment in the next time period, input the causal inference graph model. Predicting the workload level of crew members over a future period, including: Constructing a causal reasoning graph model Describes the causal relationships between variables; The impact of physiological load and environmental stress on workload, and the interaction between them, is captured using regression models. Use parameter estimation methods to estimate model parameters.

5. The adaptive prediction method for crew workload based on multi-source heterogeneous data fusion as described in claim 4, characterized in that, The regression model is expressed as: ， in: Forecasted workload levels; : Bias term, representing the base workload level; Model coefficients represent the degree of influence of the corresponding variable on the workload level; Individual physiological load prediction values; Overall pressure level of the navigation environment; Nonlinear index: controls the degree of nonlinearity of the variable; To estimate model parameters The nonlinear least squares method is used to minimize the error through an iterative optimization algorithm.

Images