Ship driver navigation task planning method, system and equipment and storage medium

Abstract

The embodiment of the invention provides a ship driver navigation task planning method, system and device and a storage medium, and belongs to the technical field of artificial intelligence. According to the method, driver monitoring data of a ship driver under a current navigation task are obtained through a data acquisition device, and the driver monitoring data comprise monitoring index data of heart rate variability, skin electrical activity, skin temperature and activity state; determining a comprehensive psychological load index according to the monitoring data of the driver, then judging whether the comprehensive psychological load index of the navigation task is greater than a load threshold value or not, and re-planning the navigation task when the comprehensive psychological load index is greater than the load threshold value. The psychological load of the driver in the navigation process is analyzed in real time, and the navigation task is adjusted when the psychological load is too large, so that the navigation task is reasonably planned according to the psychological load, the psychological load of the driver is reduced, and the navigation safety is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method, system, device and storage medium for planning a navigation task for a ship driver. Background Art

[0002] In actual navigation, the ship driver faces different states when facing different navigation tasks. For example, when facing a monitoring task that requires high mental concentration, the ship driver may have a higher navigation risk due to poor state compared to a physical task. For example, when facing a driving scenario with a high speed requirement, the ship driver is not proficient in driving at high speed and the driving process is tense, which leads to an increased error rate. Therefore, the ship driver faces different states when facing different navigation tasks, and tasks with too poor a state will increase the accident rate. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose a method, system, device and storage medium for planning the navigation tasks of ship drivers, aiming to reasonably plan the navigation tasks of ship drivers and reduce the risk of accidents.

[0004] To achieve the above purpose, one aspect of an embodiment of the present application proposes a method for planning a navigation task for a ship driver, comprising the following steps:

[0005] Acquiring the driver monitoring data of the ship driver under the current navigation task through the data acquisition device, wherein the driver monitoring data includes monitoring index data of heart rate variability, skin electrode activity, skin temperature and activity status;

[0006] Determining a comprehensive mental load index according to the driver monitoring data by using a trained mental load analysis model;

[0007] Determining whether the comprehensive psychological load index of the navigation task is greater than a load threshold;

[0008] When the comprehensive mental load index is greater than the load threshold, the navigation task is replanned.

[0009] In some embodiments, the data acquisition device is a portable wearable device, and the portable wearable device includes a photoelectric volumetric pulse wave sensor, a skin charge sensor, a body temperature sensor, and an acceleration sensor.

[0010] In some embodiments, the step of acquiring the driver monitoring data of the ship driver under the current navigation task through the data acquisition device includes the following steps:

[0011] Collecting heart rate data through the photoplethysmography sensor, and performing feature analysis on the heart rate data using a fast Fourier transform and a time domain analysis method to obtain heart rate variability in the driver monitoring data, wherein the heart rate variability includes time domain features and frequency domain features;

[0012] Collecting skin conductivity through the galvanic skin sensor, and performing feature analysis on the skin conductivity to obtain skin electrical activity in the driver monitoring data, wherein the skin electrical activity includes skin conductivity and galvanic skin response;

[0013] The skin surface temperature is collected by the body temperature sensor, and the skin temperature in the driver monitoring data is obtained by calculating the average skin temperature within a preset time interval according to the skin surface temperature;

[0014] The three-axis acceleration data is collected by the acceleration sensor, the three-axis acceleration data is integrated to obtain the total acceleration, and the total acceleration is classified by using a machine learning algorithm to obtain the activity state in the driver monitoring data.

[0015] In some embodiments, determining the comprehensive mental load index according to the driver monitoring data using the trained mental load analysis model comprises the following steps:

[0016] After performing data preprocessing on each monitoring indicator data in the driver monitoring data, constructing a feature vector according to each monitoring indicator data;

[0017] Inputting the characteristic vector into a trained mental load analysis model to obtain a basic mental load index;

[0018] A comprehensive mental load index is determined according to the basic mental load index.

[0019] In some embodiments, the mental load analysis model is trained by the following steps:

[0020] Acquire a plurality of sample data, wherein the plurality of sample data include feature vectors and mental load index labels of historical monitoring data of different ship drivers;

[0021] Divide multiple sample data into training data sets and test data sets;

[0022] Optimizing the mental workload analysis model based on the support vector machine algorithm using the training data set, and evaluating the optimized mental workload analysis model using the test data set to obtain a model evaluation result, wherein the evaluation result includes a mean square error and a determination coefficient;

[0023] When the evaluation results meet the preset requirements, the trained mental load analysis model is output.

[0024] In some embodiments, determining the comprehensive mental load index according to the basic mental load index comprises the following steps:

[0025] Determine the personalized benchmark value of each monitoring indicator based on the user's historical monitoring data of the ship driver;

[0026] Determining a personalized adjustment coefficient according to the currently collected driver monitoring data and the personalized reference value;

[0027] The personalized adjustment coefficient and the basic mental load index are input into a mental load correction model to obtain a comprehensive mental load index.

[0028] In some embodiments, re-planning the navigation mission comprises the following steps:

[0029] determining a plurality of first candidate flight segments according to the position information of the navigation pilot;

[0030] Querying the comprehensive psychological load index of the ship driver corresponding to each of the first candidate segments from the database;

[0031] The navigation task is re-determined according to the first candidate segment in which the comprehensive psychological load index of the ship driver is less than the load threshold.

[0032] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application provides a navigation task planning system for a ship driver, comprising:

[0033] The first module is used to obtain the driver monitoring data of the ship driver under the current navigation task through the data acquisition device, wherein the driver monitoring data includes monitoring index data of heart rate variability, skin electrode activity, skin temperature and activity state;

[0034] The second module is used to determine the comprehensive mental load index according to the driver monitoring data by using the trained mental load analysis model;

[0035] The third module is used to determine whether the comprehensive psychological load index of the navigation task is greater than the load threshold;

[0036] The fourth module is used to re-plan the navigation task when the comprehensive psychological load index is greater than the load threshold.

[0037] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program, when executed by the processor, implements the method described in the above embodiment.

[0038] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes a storage medium, which is a computer-readable storage medium used for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method described in the above embodiment.

[0039] The method, system, device and storage medium for planning the navigation task of the ship driver proposed in the present application obtain the driver monitoring data of the ship driver under the current navigation task through the data acquisition device. The driver monitoring data includes the monitoring index data of heart rate variability, skin electrode activity, skin temperature and activity status. Through the trained psychological load analysis model, the comprehensive psychological load index is determined according to the driver monitoring data, and then it is judged whether the comprehensive psychological load index of the navigation task is greater than the load threshold. When the comprehensive psychological load index is greater than the load threshold, the navigation task is re-planned. The present application analyzes the psychological load of the driver during the navigation process in real time, adjusts the navigation task when the psychological load is too large, so as to reasonably plan the navigation task according to the psychological load, reduce the psychological load of the driver, and thus improve the navigation safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flow chart of a method for planning a navigation task for a ship driver provided in an embodiment of the present application;

[0041] Figure 2 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] It should be noted that, although the functional modules are divided in the system and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0045] The embodiments of the present application provide a method, system, device and storage medium for planning the navigation mission of a ship driver, aiming to reasonably plan the navigation mission of the ship driver and reduce the risk of accidents.

[0046] The method, system, device and storage medium for planning the navigation mission of a ship driver provided in the embodiments of the present application are specifically described through the following embodiments. First, the method for planning the navigation mission of a ship driver in the embodiments of the present application is described.

[0047] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0048] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0049] The method for planning the navigation task of a ship driver provided in an embodiment of the present application relates to the field of artificial intelligence technology. The method for planning the navigation task of a ship driver provided in an embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the method for planning the navigation task of a ship driver, etc., but is not limited to the above forms.

[0050] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0051] Figure 1 is an optional flow chart of the method for planning a navigation task for a ship driver provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S104.

[0052] Step S101, obtaining the driver monitoring data of the ship driver under the current navigation task through the data acquisition device, wherein the driver monitoring data includes monitoring index data of heart rate variability, skin electrode activity, skin temperature and activity state;

[0053] Step S102, determining a comprehensive mental load index according to the driver monitoring data by using the trained mental load analysis model;

[0054] Step S103, determining whether the comprehensive mental load index of the navigation task is greater than the load threshold;

[0055] Step S104: when the comprehensive mental load index is greater than the load threshold, the navigation task is replanned.

[0056] In step S101 of some embodiments, the data acquisition device is provided with various sensors for collecting physiological state data required for analyzing the driver's psychological load. The data acquisition device may be a portable wearable device, and illustratively, the portable wearable device may be in the form of a wristband, which includes a wristband, a sensor component, a display screen, and a processing chip. The wristband may be made of comfortable materials for long-term wear.

[0057] The sensor components include a photoplethysmography sensor, a skin charge sensor, a body temperature sensor, and an accelerometer. Specifically, the accelerometer is used to monitor the driver's activity status. By analyzing the changes in movement, the driver's tension and fatigue level at work can be evaluated. The skin temperature sensor can reflect the driver's stress response and physiological state by measuring the changes in body surface temperature, helping to identify psychological stress. The photoplethysmography (PPG) sensor is used to measure blood flow changes and evaluate the driver's psychological load by calculating related indicators such as heart rate and heart rate variability (HRV).

[0058] The processing chip is responsible for collecting, processing and analyzing sensor data to obtain relevant monitoring indicator data. Each monitoring indicator data forms driver monitoring data, which includes but is not limited to heart rate variability, skin electrode activity, skin temperature and activity status.

[0059] It is understandable that, according to the monitoring index requirements of the psychological load index, more sensors can be set on the data acquisition device to obtain more types of monitoring index data. For example, a blood oxygen sensor and a blood pressure sensor can also be set on the data acquisition device to further improve the accuracy of psychological load detection. The blood oxygen sensor can monitor the driver's blood oxygen saturation index data in real time and identify physiological changes caused by fatigue or stress; the blood pressure sensor can detect the driver's blood pressure change index data, and combine it with other physiological data to provide a more comprehensive and accurate psychological load assessment.

[0060] The data acquisition device is also equipped with a wireless communication module that supports Bluetooth and Wi-Fi communications, transmitting data in real time to a central monitoring system (i.e., a remote server) or a mobile device. Furthermore, the data acquisition device is also equipped with a built-in storage chip for local storage of sensor data and processing results, ensuring that data can still be recorded and saved when the network connection is interrupted.

[0061] The central monitoring system is provided with a database for centralized management and analysis of the received data. Considering the real-time nature, high concurrency and subsequent analysis requirements of the data, the central monitoring system of the embodiment of the present application uses the following two databases:

[0062] Time Series Database (TSDB): used to store sensor data. Time Series Database is good at processing time series data and supports efficient read and write operations and queries, such as InfluxDB.

[0063] Relational Database (RDBMS): used to store user information, device information and comprehensive analysis results (such as comprehensive mental stress index). Relational databases support complex queries and transaction processing, such as PostgreSQL.

[0064] For example, the structure of the time series database (InfluxDB) is designed as follows:

[0065]

[0066] The relational database (PostgreSQL) structure is designed as follows:

[0067]

[0068]

[0069] The data collection device (such as a wristband) transmits data to the central monitoring system through a wireless communication module. The central monitoring system uses InfluxDB to store real-time sensor data and uses PostgreSQL to store user information, device information, and comprehensive analysis results. The central monitoring system reads real-time data from InfluxDB, combines user and device information, calculates the comprehensive mental load index, and stores the results in PostgreSQL.

[0070] In some embodiments, step S101 may include but is not limited to steps S201 to S204:

[0071] Step S201, collecting heart rate data through a photoplethysmography sensor, and performing feature analysis on the heart rate data using a fast Fourier transform and a time domain analysis method to obtain heart rate variability in the driver monitoring data, wherein the heart rate variability includes time domain features and frequency domain features;

[0072] Step S202, collecting skin conductivity through a skin conductivity sensor, and performing feature analysis on the skin conductivity to obtain skin electrical activity in the driver monitoring data, wherein the skin electrical activity includes skin conductivity and skin electrical response;

[0073] Step S203, collecting the skin surface temperature through the body temperature sensor, and calculating the average skin temperature within a preset time interval based on the skin surface temperature to obtain the skin temperature in the driver monitoring data;

[0074] Step S204, collecting three-axis acceleration data through an acceleration sensor, integrating the three-axis acceleration data to obtain a total acceleration, and classifying the total acceleration using a machine learning algorithm to obtain an activity state in the driver monitoring data.

[0075] In this embodiment, after the data acquisition device collects heart rate data, skin conductivity, skin surface temperature and three-axis acceleration data through the sensor assembly, the data collected by the sensor can be analyzed locally to obtain monitoring index data such as heart rate variability, skin electrical activity, skin temperature and activity status. Each monitoring index data forms a driver monitoring and is sent to a remote service for psychological load analysis. The data acquisition device can also collect sensor data and send the data to a remote server, which analyzes the monitoring index data and calculates the psychological load. After the sensor data is collected at a certain sampling frequency, the interpolation method can be used to process missing values ​​and outliers, and then the monitoring index data can be analyzed based on the processed sensor data.

[0076] In step S201 of some embodiments, heart rate data is collected by a PPG sensor with a sampling rate of 250 Hz. Fast Fourier transform (FFT) and time domain analysis methods are used to calculate the heart rate interval (RR), and then the standard deviation (SDNN) and root mean square deviation (RMSSD) of the time domain index, as well as the ratio (LF / HF) of the low frequency (LF) and high frequency (HF) of the frequency domain index are calculated based on the heart rate interval. The monitoring index data of SDNN, RMSSD and LF / HF jointly represent the heart rate variability (HRV), as shown in the following formula:

[0077]

[0078]

[0079]

[0080] Where P represents the power of the frequency and N represents the number of samples.

[0081] In step S202 of some embodiments, a skin electrical signal (EDA), i.e., skin conductivity, is detected by a skin electrical sensor with a sampling rate of 50 Hz. The amplitude and frequency of the EDA signal are analyzed to determine the amplitude and frequency changes, skin conductivity (SCL) and skin electrical response (SCR), and the monitoring indicator data of skin conductivity (SCL) and skin electrical response (SCR) together represent skin electrical activity.

[0082] Among them, skin conductivity (SCL) represents the average value of skin conductivity over a period of time, reflecting the baseline level, and the calculation formula is as follows:

[0083]

[0084] The skin galvanic response (SCR) represents the instantaneous change in skin conductivity when a stressful event occurs. The calculation formula is as follows:

[0085] ΔSCR=EDA peak-EDA baseline ;

[0086] Among them, EDA peak Indicates the peak value of skin conductivity, EDA baseline Indicates the baseline value of skin conductivity.

[0087] In step S203 of some embodiments, the skin surface temperature is detected by a body temperature sensor with a sampling rate of 1 Hz, the skin temperature change trend is analyzed, and the average skin temperature is calculated using the following calculation formula:

[0088]

[0089] Where T represents skin temperature, N represents the total number of skin temperature measurements (the number of data points), and T i represents the skin surface temperature measured at the ith time. The skin temperature can be represented by the skin average temperature value and the skin temperature change rate.

[0090] In step S204 of some embodiments, the three-dimensional acceleration sensor continuously collects acceleration data in the three directions of X, Y, and Z, with a sampling rate of 100 Hz. It is expressed as follows:

[0091] a(t)=[a x (t), a y (t), a z (t)];

[0092] Among them, a x (t), a y (t), a z (t) represents the acceleration values ​​in the X, Y, and Z directions at time t, respectively.

[0093] Then the raw acceleration data is denoised. A low-pass filter can be used to remove high-frequency noise. The low-pass filter is expressed as follows:

[0094] a filtered (t) = LowPassFilter(a(t));

[0095] Calculate the magnitude of the total acceleration, expressed as follows:

[0096]

[0097] The acceleration data is classified using a machine learning algorithm (such as K-means, support vector machine, etc.) to divide the activity states into different categories (such as still, walking, running, etc.). The activity state ActivityState is represented as follows.

[0098] ActivityState = Classifier(a magnitude(t))

[0099] Here, Classifier represents a classifier obtained based on a machine learning algorithm.

[0100] In step S102 of some embodiments, the mental load analysis model can be obtained based on training of a machine learning algorithm or a deep learning algorithm. The machine learning algorithm can be a decision tree, a random forest, a support vector machine (SVM), etc. The deep learning algorithm can be a neural network, and the embodiments of the present application are not specifically limited. After the mental load model is obtained by training with historical sample data, the driver monitoring data can be calculated using the mental load model to obtain the driver's mental load index. Specifically, the driver monitoring data can be input into the mental load analysis model to obtain the output mental load index, which is the comprehensive mental load index; the driver monitoring data can also be input into the mental load analysis model to obtain the output mental load index. The comprehensive mental load index is obtained after the mental load index is personalized.

[0101] In some embodiments, step S102 may include but is not limited to steps S301 to S303:

[0102] Step S301, after performing data preprocessing on each monitoring indicator data in the driver monitoring data, constructing a feature vector according to each monitoring indicator data;

[0103] Step S302, inputting the feature vector into the trained mental load analysis model to obtain a basic mental load index;

[0104] Step S303: determining a comprehensive mental load index according to the basic mental load index.

[0105] In this embodiment, before the driver monitoring data is input into the mental load analysis model, the driver monitoring data can be pre-processed to form a feature vector, and then the feature vector is input into the mental load analysis model for analysis and calculation, as follows:

[0106] The data of each monitoring indicator is standardized so that it is in the same dimension for easy fusion calculation. The formula is as follows:

[0107]

[0108] Among them, X standard represents the standardized monitoring indicator data, X represents the original monitoring indicator data, μ represents the mean, and σ represents the standard deviation.

[0109] According to the SDNN, RMSSD, LF / HF in heart rate variability, SCL and SCR of skin electrical activity, and the average skin temperature ST of skin temperature meanand skin temperature change rate ST delta , Active Status ACC activitysituation Together we construct a feature vector, which is represented as follows:

[0110] F=[HRV SDNN , HRV RMSSD , HRV LF / HF , EDA SCL , EDA SCR ,ST mean ,ST delta , ACC activitysituation ];

[0111] The characteristic vector is input into the trained mental load analysis model to obtain the basic mental load index, and then the basic mental load index is personalized modified to obtain the current comprehensive mental load index of the ship driver.

[0112] In some embodiments, the mental load analysis model in step S302 can be obtained through but not limited to steps S401 to S404:

[0113] Step S401, obtaining a plurality of sample data, wherein the plurality of sample data includes feature vectors and mental load index labels of historical monitoring data of different ship drivers;

[0114] Step S402, dividing the plurality of sample data into a training data set and a test data set;

[0115] Step S403, optimizing the mental load analysis model based on the support vector machine algorithm using the training data set, and evaluating the optimized mental load analysis model using the test data set to obtain a model evaluation result, wherein the evaluation result includes a mean square error and a determination coefficient;

[0116] Step S404: when the evaluation result meets the preset requirements, the trained mental load analysis model is output.

[0117] In this embodiment, a large amount of historical monitoring data (including heart rate variability, skin temperature, activity status and skin electrical activity) of different users and corresponding mental load index labels are first obtained. The mental load index label can be obtained by scoring the user in the corresponding historical environment. The corresponding feature vector is constructed according to the user's historical monitoring data to obtain sample data. The obtained sample data is divided into a training data set and a test data set, for example, divided according to the ratio of 70% training data set and 30% test data set. The training data set is used to train the mental load analysis model (i.e., SVM regression model) of the support vector machine algorithm (SVM) so that the model can output the mental load index according to the input feature vector. The support vector machine algorithm is suitable for classification and regression tasks, and SVM regression can be used to fuse multiple physiological indicators according to the indicator weights to calculate the basic mental load index.

[0118] In the process of updating the model weight parameters, kernel functions (such as RBF kernel functions) can be used to handle nonlinear relationships. The kernel functions are as follows:

[0119] K(X i , X j ) = exp(-γ||X i -X j || 2 );

[0120] Use the cross-validation method to tune the model's hyperparameters (such as the penalty parameter C and the kernel function parameter γ) and select the optimal parameter combination. Use the test data set to evaluate the performance of the SVM regression model, calculate the mean square error (MSE), determination coefficient (R) and other indicators, and when the model performance (i.e., the evaluation result) meets certain requirements, obtain the trained mental load analysis model, and use the mental load analysis model to calculate the real-time basic mental load index CMWI real-time , which is expressed as follows

[0121] CMWI real-time =SVM model (F real-time ).

[0122] In some embodiments, step S303 includes but is not limited to steps S501 to S503:

[0123] Step S501, determining personalized reference values ​​of various monitoring indicators according to the user historical monitoring data of the ship driver;

[0124] Step S502, determining a personalized adjustment coefficient according to currently collected driver monitoring data and a personalized reference value;

[0125] Step S503: input the personalized adjustment coefficient and the basic mental load index into the mental load correction model to obtain the comprehensive mental load index.

[0126] In this embodiment, the personalized baseline values ​​of monitoring indicators such as the heart rate variability (HRV), skin temperature, and motion status of the driver in a resting state can be determined based on the user's historical monitoring data of the ship driver. i represents time.

[0127] The user's personalized benchmark value and the currently collected driver monitoring data are input into a pre-constructed relationship function to obtain a personalized adjustment coefficient for compensating the indicator weight in the psychological analysis model.

[0128] Based on the historical monitoring data of the user, a personalized adjustment model (i.e., a mental load correction model) is trained, which can combine the basic mental load index and the personalized adjustment coefficient to calculate the final comprehensive mental load index. This embodiment introduces a personalized adjustment coefficient and establishes a suitable calculation model for different drivers to enhance the accuracy of mental load prediction.

[0129] According to some embodiments of the present application, the driver's historical mental load index and monitoring data can be combined to predict the trend of mental load changes in the future, so as to take measures in advance to reduce the operating error rate.

[0130] In steps S103 to S104 of some embodiments, by measuring the comprehensive psychological load index in different difficulty navigation task scenarios, a load threshold is set for each driver. When the comprehensive psychological load index rises to the load threshold, an early warning can be initiated at the user side terminal and the monitoring side terminal at the same time. The alarm mode includes visual alarm (screen prompt), sound alarm (alarm sound) and notification alarm (text message, email, etc.), so that abnormal psychological load conditions can be discovered and intervened in time, the driver's psychological state can be improved, and navigation safety can be improved. This embodiment sets different load thresholds according to the performance of different drivers in different navigation tasks, so as to improve the rationality of subsequent navigation task planning.

[0131] In some embodiments, the navigation task may refer to the route given by the system, the specified navigation time and navigation speed, etc. When the driver has a psychological load index during the execution of the navigation task, the navigation task can be replanned by obtaining the factors that cause the driver's psychological load to increase. Exemplarily, when the central monitoring system detects that the driver's psychological load index exceeds the load threshold, a user interface can be displayed through a terminal (such as a bracelet or a ship central controller), and the driver inputs the factors that cause the driver's psychological load to increase on the user interface, such as the factors that make the current segment difficult to operate. The system replans the segment in the navigation task based on the driver's feedback, thereby improving navigation safety.

[0132] In some embodiments, the re-planning of the navigation task in step S104 may include but is not limited to steps S601 to S603:

[0133] Step S601, determining a plurality of first candidate flight segments according to the position information of the navigation pilot;

[0134] Step S602, querying the comprehensive psychological load index of the ship driver corresponding to each first candidate segment from the database;

[0135] Step S603, re-determining the navigation task according to the first candidate segment whose comprehensive psychological load index of the ship driver is less than the load threshold.

[0136] In some embodiments, step S603 includes but is not limited to steps S701 to S703:

[0137] Step S701, selecting a first candidate segment whose comprehensive psychological load index of the ship driver is less than a load threshold as a second candidate segment;

[0138] Step S702, screening multiple second candidate flight segments according to the desired screening condition to obtain a target flight segment;

[0139] Step S703, modifying the current segment in the navigation task into the target segment.

[0140] In this embodiment, a GPS data transmission module is added to the data acquisition device to record the geographical location and navigation path of the ship. Combined with real-time psychological load index analysis, the changes in psychological load on each navigation path driven can be recorded in the database, and possible high-risk areas or sections with greater operating difficulty can be identified, so as to reasonably plan the driver's navigation tasks. Specifically, the psychological load data of the crew can be superimposed and displayed with the navigation path through the geographic information system (GIS) to provide a visual psychological load map. At the same time, the changes in key physiological indicators and psychological load index are displayed through data dashboards and real-time charts, helping managers to quickly identify abnormal situations and take corresponding measures.

[0141] In this embodiment, the change in the driver's psychological load is usually caused by the difficulty of executing the segment, such as too many obstacles in the segment, fierce water flow in the segment, etc. When the system detects that the driver's psychological load is too high, it determines multiple first candidate segments that are located within a certain range of the current position and can reach the destination according to the location information of the navigation driver, queries the comprehensive psychological load index of the ship driver corresponding to each first candidate segment from the database, selects the first candidate segment whose comprehensive psychological load index of the ship driver is less than the load threshold as the second candidate segment, and then screens the multiple second candidate segments according to expected screening conditions such as low operating difficulty or short driving time to obtain the target segment, and switches the current segment to the target segment to achieve re-planning of the navigation task, so as to reduce the driver's psychological load while meeting certain task expectations and improve driving safety.

[0142] The present application also provides a navigation task planning system for ship drivers, including:

[0143] The first module is used to obtain the driver monitoring data of the ship driver under the current navigation task through the data acquisition device, wherein the driver monitoring data includes monitoring index data of heart rate variability, skin electrode activity, skin temperature and activity status;

[0144] The second module is used to determine the comprehensive mental load index based on the driver monitoring data through the trained mental load analysis model;

[0145] The third module is used to determine whether the comprehensive psychological load index of the navigation task is greater than the load threshold;

[0146] The fourth module is used to re-plan the navigation task when the comprehensive mental load index is greater than the load threshold.

[0147] It can be understood that the contents of the above-mentioned ship pilot navigation mission planning method embodiment are all applicable to the present system embodiment, the functions specifically implemented by the present system embodiment are the same as those in the above-mentioned ship pilot navigation mission planning method embodiment, and the beneficial effects achieved are also the same as the beneficial effects achieved by the above-mentioned ship pilot navigation mission planning method embodiment.

[0148] The embodiment of the present application also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned ship driver navigation task planning method. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0149] See also Figure 2 , Figure 2The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0150] The processor 201 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0151] The memory 202 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 202 can store an operating system and other applications. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 202, and the processor 201 calls and executes the navigation task planning method for the ship driver in the embodiment of this application;

[0152] Input / output interface 203, used to implement information input and output;

[0153] The communication interface 204 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0154] Bus 205 , which transmits information between various components of the device (e.g., processor 201 , memory 202 , input / output interface 203 , and communication interface 204 );

[0155] The processor 201 , the memory 202 , the input / output interface 203 and the communication interface 204 are connected to each other in communication within the device via the bus 205 .

[0156] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned ship driver navigation task planning method.

[0157] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0158] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0159] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0160] The system embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0161] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0162] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0163] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0164] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0165] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0166] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0167] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0168] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for planning a navigation task for a ship driver, characterized in that: The following steps are involved: Acquiring the driver monitoring data of the ship driver under the current navigation task through the data acquisition device, wherein the driver monitoring data includes monitoring index data of heart rate variability, skin electrode activity, skin temperature and activity status; Determining a comprehensive mental load index according to the driver monitoring data by using a trained mental load analysis model; Determining whether the comprehensive psychological load index of the navigation task is greater than a load threshold; When the comprehensive mental load index is greater than the load threshold, the navigation task is replanned.

2. The method for planning a navigation task for a ship driver according to claim 1, characterized in that: The data acquisition device is a portable wearable device, which includes a photoelectric volumetric pulse wave sensor, a skin charge sensor, a body temperature sensor and an acceleration sensor.

3. The method for planning a navigation task for a ship driver according to claim 2, characterized in that: The method of obtaining the driver monitoring data of the ship driver under the current navigation task by the data acquisition device includes the following steps: Collecting heart rate data through the photoplethysmography sensor, and performing feature analysis on the heart rate data using a fast Fourier transform and a time domain analysis method to obtain heart rate variability in the driver monitoring data, wherein the heart rate variability includes time domain features and frequency domain features; Collecting skin conductivity through the galvanic skin sensor, and performing feature analysis on the skin conductivity to obtain skin electrical activity in the driver monitoring data, wherein the skin electrical activity includes skin conductivity and galvanic skin response; The skin surface temperature is collected by the body temperature sensor, and the skin temperature in the driver monitoring data is obtained by calculating the average skin temperature within a preset time interval according to the skin surface temperature; The three-axis acceleration data is collected by the acceleration sensor, the three-axis acceleration data is integrated to obtain the total acceleration, and the total acceleration is classified by using a machine learning algorithm to obtain the activity state in the driver monitoring data.

4. The method for planning a navigation task for a ship driver according to claim 1, characterized in that: The method of determining the comprehensive mental load index according to the driver monitoring data by using the trained mental load analysis model comprises the following steps: After performing data preprocessing on each monitoring indicator data in the driver monitoring data, constructing a feature vector according to each monitoring indicator data; Inputting the characteristic vector into a trained mental load analysis model to obtain a basic mental load index; A comprehensive mental load index is determined according to the basic mental load index.

5. The method for planning a navigation task for a ship driver according to claim 4, characterized in that: The mental load analysis model is trained by the following steps: Acquire a plurality of sample data, wherein the plurality of sample data include feature vectors and mental load index labels of historical monitoring data of different ship drivers; Divide multiple sample data into training data sets and test data sets; The training data set is used to optimize the mental workload analysis model based on the support vector machine algorithm, and the test data set is used to evaluate the optimized mental workload analysis model to obtain a model evaluation result, wherein the evaluation result includes a mean square error and a determination coefficient; When the evaluation results meet the preset requirements, the trained mental load analysis model is output.

6. The method for planning a navigation task for a ship driver according to claim 4, characterized in that: Determining the comprehensive mental load index according to the basic mental load index comprises the following steps: Determine the personalized benchmark value of each monitoring indicator based on the user's historical monitoring data of the ship driver; Determining a personalized adjustment coefficient according to the currently collected driver monitoring data and the personalized reference value; The personalized adjustment coefficient and the basic mental load index are input into a mental load correction model to obtain a comprehensive mental load index.

7. The method for planning a navigation task for a ship driver according to claim 1, characterized in that: The re-planning of the navigation mission comprises the following steps: determining a plurality of first candidate flight segments according to the position information of the navigation pilot; Querying the comprehensive psychological load index of the ship driver corresponding to each of the first candidate segments from the database; The navigation task is re-determined according to the first candidate segment in which the comprehensive psychological load index of the ship driver is less than the load threshold.

8. A navigation mission planning system for ship drivers, characterized in that: include: The first module is used to obtain the driver monitoring data of the ship driver under the current navigation task through the data acquisition device, wherein the driver monitoring data includes monitoring index data of heart rate variability, skin electrode activity, skin temperature and activity state; The second module is used to determine the comprehensive mental load index according to the driver monitoring data by using the trained mental load analysis model; The third module is used to determine whether the comprehensive psychological load index of the navigation task is greater than the load threshold; The fourth module is used to re-plan the navigation task when the comprehensive psychological load index is greater than the load threshold.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the method described in any one of claims 1 to 7 are realized.

10. A storage medium, the storage medium being a computer-readable storage medium, used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of claims 1 to 7.

Images