A method and system for monitoring the workload of tugboat crew members based on AIS data

Abstract

This application discloses a method and system for monitoring the workload of tugboat crew members based on AIS data. The method includes: acquiring AIS data corresponding to the tugboat and generating a corresponding AIS time series based on the AIS data; normalizing the AIS time series to ensure that the AIS data in the AIS time series are at the same scale; determining the tugboat's operating status based on the normalized AIS time series, including berthing, cruising, and operations; determining the tugboat crew's work and rest status based on the operating status, and generating a work and rest time series for the tugboat crew, thereby determining the workload of the tugboat crew members based on the work and rest time series. This application provides a scientific basis for assessing crew workload, effectively avoiding safety hazards caused by crew overwork, and helps improve the overall efficiency and safety of tugboat operations.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to an AIS data tugboat crew work intensity monitoring method and system. BACKGROUND

[0002] The port tugboat is the core support unit of the port operation system, and the crew faces a high-intensity and high-risk operation environment for a long time. The International Maritime Organization (IMO) statistics show that about 38% of global port accidents in the past ten years involve tugboat operation errors, and fatigue is identified as one of the main causes.

[0003] Therefore, there are restrictive requirements for the "longest working time" and "shortest rest time" of the seafarers. Currently, the working time of the seafarers is recorded by a work and rest time record table, and is signed and approved by the captain or the captain's designated personnel and the seafarers. However, due to human factors, the seafarers' work and rest time record table may be fabricated or tampered with under certain circumstances, and cannot truly reflect the actual working time of the seafarers. Therefore, how to accurately evaluate the working intensity of the crew on the tugboat is a problem to be solved at present. SUMMARY

[0004] To solve the above technical problems, an embodiment of the present application provides a tugboat crew work intensity monitoring method and system based on AIS data.

[0005] According to an aspect of an embodiment of the present application, a tugboat crew work intensity monitoring method based on AIS data is provided, comprising: acquiring AIS data corresponding to a tugboat, and generating a corresponding AIS time sequence based on the AIS data; performing normalization processing on the AIS time sequence to make the AIS data in the AIS time sequence in the same scale; determining the running state of the tugboat based on the normalized AIS time sequence, the running state including parking, cruising and operation; determining the work and rest state of the tugboat crew based on the running state, and generating a work and rest time sequence of the tugboat crew based on the work and rest state, to determine the working intensity of the tugboat crew based on the work and rest time sequence.

[0006] According to an aspect of an embodiment of the present application, the determination of the running state of the tugboat based on the normalized AIS time sequence comprises: determining the speed feature of the tugboat based on the normalized AIS time sequence, and generating a corresponding speed time sequence; introducing a preset speed function, and identifying the speed pulse interval in the speed time sequence and the speed mutation point corresponding to the start point and end point of the speed pulse interval based on the preset speed function; determining the running state of the tugboat based on the speed pulse interval and the speed mutation point.

[0007] According to an aspect of some embodiments of the present application, the method further includes: taking the preset speed function as an index, the index including at least one speed threshold; dividing the speed time sequence into a plurality of speed intervals based on the speed threshold; and identifying a speed pulse interval in the speed time sequence based on the plurality of speed intervals.

[0008] According to an aspect of some embodiments of the present application, the method further includes: performing a differential calculation on the speed time sequence to obtain a differential speed time sequence; extracting extreme points in the differential speed time sequence, and taking the extreme points as speed mutation points corresponding to the speed time sequence.

[0009] According to an aspect of some embodiments of the present application, the method further includes: determining a speed mutation point type corresponding to a start point and an end point of the speed pulse interval; and determining a running state of the tugboat in the speed pulse interval based on the speed mutation point type.

[0010] According to an aspect of some embodiments of the present application, the method further includes: if the start point of the speed pulse interval is a first type mutation point and the end point is a second type mutation point, determining that the running state of the tugboat in the speed pulse interval is a cruising state; and if the start point of the speed pulse interval is the second type mutation point and the end point is the first type mutation point, obtaining an average speed change trend in the speed pulse interval to determine the running state of the tugboat in the speed pulse interval based on the average speed change trend.

[0011] According to an aspect of some embodiments of the present application, the determining the running state of the tugboat in the speed pulse interval based on the average speed change trend includes: if the average speed change trend represents that an average speed in the speed pulse interval is less than a preset speed threshold, determining that the tugboat state in the speed pulse interval is a berthing state; if the average speed change trend represents that the average speed in the speed pulse interval is greater than the preset speed threshold and the average speed in the speed pulse interval presents an increasing trend, determining that the tugboat state in the speed pulse interval is an assisting undocking state; and if the average speed change trend represents that the average speed in the speed pulse interval is greater than the preset speed threshold and the average speed in the speed pulse interval presents a decreasing trend, determining that the tugboat state in the speed pulse interval is an assisting berthing state.

[0012] According to an aspect of the embodiment of the present application, the method further comprises: if the operating state of the tugboat is the berthing state, determining that the tugboat crew is in a rest state; if the operating state of the tugboat is the cruising state or the working state, determining that the tugboat crew is in a working state; determining time periods corresponding to the rest state and the working state respectively, and determining a work-rest time sequence of the tugboat crew based on the time periods.

[0013] According to an aspect of the embodiment of the present application, the method further comprises: if the operating state of the tugboat is the berthing state, determining that the tugboat crew is in a rest state; if the operating state of the tugboat is the cruising state or the working state, determining that the tugboat crew is in a working state; determining time periods corresponding to the rest state and the working state respectively, and determining a work-rest time sequence of the tugboat crew based on the time periods.

[0014] According to an aspect of the embodiment of the present application, a system for monitoring working strength of tugboat crew based on AIS data is provided, the system comprises a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are connected with each other, wherein the memory is used for storing a computer program, the computer program comprises program instructions, the processor is configured to invoke the program instructions, and the above-mentioned method for monitoring working strength of tugboat crew based on AIS data is executed.

[0015] In the technical solutions provided in the embodiments of the present application, the AIS data corresponding to the tugboat is acquired and AIS time series is generated, so that the key information such as the position and speed of the tugboat at different times can be recorded comprehensively and accurately, and detailed and reliable data basis is provided for subsequent analysis. The AIS time series is normalized, so that the AIS data which is originally difficult to compare and analyze directly due to differences in different dimensions or data ranges is in the same scale, the magnitude difference between the data is eliminated, the consistency and comparability of the data are greatly improved, and favorable conditions are created for accurate analysis of the running state of the tugboat. The running state of the tugboat is determined based on the normalized AIS time series, covering different states such as parking, cruising and operation, and such accurate state recognition is helpful to in-depth understanding of the running characteristics and laws of the tugboat at different stages. The work and rest state of the tugboat crew is further determined based on the running state, and a work and rest time series is generated, so that the work and rest arrangement of the crew at different time periods can be clearly presented. Finally, the work intensity of the tugboat crew is determined based on the work and rest time series, which not only provides a scientific basis for evaluating the work load of the crew, but also enables reasonable arrangement of the work and rest time of the crew, effectively avoids safety hazards caused by overwork of the crew, and helps to improve the overall efficiency and safety of the tugboat operation, and ensures the smooth progress of the marine operation.

[0016] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0017] The drawings incorporated into the specification and forming a part thereof illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the application. It is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those of ordinary skill in the art without creative labor. In the drawings:

[0018] Figure 1 FIG. 1 is a flowchart of a method for monitoring the work intensity of tugboat crew based on AIS data according to an exemplary embodiment of the present application.

[0019] Figure 2 FIG. 3 is a schematic diagram of the speed characteristics and feature recognition results of the tugboat according to an exemplary embodiment of the present application.

[0020] Figure 3 FIG. 4 is a schematic diagram of the operation state recognition results of the tugboat according to an exemplary embodiment of the present application.

[0021] Figure 4 FIG. 5 is a block diagram of a system for monitoring the work intensity of tugboat crew based on AIS data according to an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0022] Detailed description will be given to the exemplary embodiments here, and examples thereof are shown in the drawings. When the following description refers to the drawings, identical numbers on different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0023] The block diagrams shown in the drawings are merely functional entities, and do not necessarily have to correspond to physically independent entities. That is, the functional entities can be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0024] The flowcharts shown in the drawings are merely exemplary illustrations, and do not necessarily include all contents and operations / steps, nor do they have to be executed in the described order. For example, some operations / steps can be further divided, and some operations / steps can be combined or partially combined, so that the actual execution order can be changed depending on the actual situation.

[0025] In the present application, "a plurality of" means two or more. The "and / or" describes the association between the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally means that the associated objects before and after are in an "or" relationship.

[0026] First of all, it is necessary to explain the ship automatic identification system (Automatic Identification System AIS) data. AIS data is a kind of maritime safety and communication system applied between ships and shores, and between ships, which automatically sends and receives static information (such as ship name, call sign, MMSI code, etc.), dynamic information (such as position, speed, heading, etc.), navigation information and short safety-related messages, etc. AIS data plays an important role in ship traffic management, maritime safety, collision avoidance, navigation monitoring and data analysis (such as identification of tugboat operation state, analysis of crew work and rest, etc.).

[0027] As the core support unit of the port operation system, tugboat crews are long-term exposed to high-intensity and high-risk working environments. According to the statistics of the International Maritime Organization (IMO), about 38% of global port accidents in the past decade are related to tugboat operation errors, and fatigue is identified as one of the main causes. Currently, the working hours of seafarers are recorded by a rest log, which is signed and approved by the captain or the designated personnel of the captain and the seafarer himself. However, due to human factors, the seafarer's rest log may be fabricated or tampered with in certain circumstances, and cannot truly reflect the actual working hours of the seafarer.

[0028] To solve the above problems, the present application proposes a tugboat crew working intensity monitoring method based on AIS data, a tugboat crew working intensity monitoring system based on AIS data, an electronic device, a computer readable storage medium and a computer program product, which will be described in detail below.

[0029] Please refer to Figure 1 , Figure 1 is an exemplary embodiment of the present application, which shows the flow chart of the tugboat crew working intensity monitoring method based on AIS data, in Figure 1 which the tugboat crew working intensity monitoring method based on AIS data at least includes steps S110 to S140, which are described in detail as follows:

[0030] Step S110, acquiring the AIS data corresponding to the tugboat, and generating the corresponding AIS time sequence based on the AIS data.

[0031] For example, by establishing a data interface with the maritime traffic management department, the port operation agency or the AIS data service provider, using satellite communication, shore-based base station or shipborne equipment, etc., the AIS data of the tugboat is acquired in real time. These data usually contain key information such as ship identification information (such as MMSI code), position (latitude and longitude), speed, heading, timestamp, etc. Then, the raw AIS data obtained is preprocessed, including data cleaning to remove duplicate, error or invalid data records, and data format conversion to ensure that all data are unified into a standard format for subsequent processing. Then, the processed AIS data is sorted in chronological order with timestamp as index, and a continuous data sequence is constructed. Considering the transmission frequency of AIS data and the actual situation, interpolation processing may be needed for missing time points to maintain the continuity of the time sequence, so as to generate the AIS time sequence corresponding to the tugboat, which can accurately reflect the motion state and position information of the tugboat at different times, providing basic data support for subsequent analysis.

[0032] Step S120, normalizing the AIS time sequence to make the AIS data in the AIS time sequence in the same scale.

[0033] For example, first, the AIS data features that need to be normalized are determined, such as common speed, latitude and longitude change, etc. For each feature, the maximum value and the minimum value in the entire time sequence are calculated. Then, a linear normalization method is used. For each data point in the time sequence, the feature value of the data point is subtracted from the minimum value of the feature, and then divided by the difference between the maximum value and the minimum value of the feature to obtain the normalized value. For latitude and longitude data, since the ranges of longitude and latitude are different, the above normalization processing can be performed on longitude and latitude respectively. Through such normalization operation, the AIS data features of different dimensions and numerical ranges are mapped into the interval [0, 1], so that the various AIS data in the AIS time sequence are in the same scale, which facilitates subsequent unified analysis and processing, such as state recognition, pattern mining, etc.

[0034] In step S130, the running state of the tugboat is determined based on the normalized AIS time sequence, and the running state includes parking, cruising and working.

[0035] For example, first, for the parking state, the normalized speed feature is observed. If the normalized value of the speed is close to 0 for a period of time, and the normalized change of the position (latitude and longitude) is very small and basically fluctuates in a small range, it can be determined that the tugboat is in the parking state. For the cruising state, the normalized value of the speed is analyzed. If the normalized value of the speed remains relatively stable within a certain range (such as 0.3 to 0.8), and the normalized change of the position is regular and continuous, it indicates that the tugboat is sailing at a relatively constant speed, and the cruising state can be determined. The working state is usually accompanied by a more complex motion pattern. On the one hand, the normalized value of the speed will change frequently, and there may be multiple accelerations, decelerations or even temporary stops (the normalized value of the speed fluctuates greatly between 0 and 1). On the other hand, the normalized change of the position will also present irregular dynamic changes, and there may be repeated movements or positioning within a certain area. Combining these features, when the speed and position changes satisfy the above complex and irregular pattern, it can be determined that the tugboat is in the working state. By comprehensively analyzing the change law of the normalized speed and position features in the time sequence, the parking, cruising and working states of the tugboat can be accurately distinguished.

[0036] In step S140, the work and rest state of the tugboat crew is determined based on the running state, and the work and rest time sequence of the tugboat crew is generated based on the work and rest state, so as to determine the working intensity of the tugboat crew based on the work and rest time sequence.

[0037] For example, according to the determined tug operating state, the judgment rule corresponding to the crew rest state is set. When the tug is in the berthing state, if the berthing time is relatively long (such as exceeding a set threshold), it can be considered that the crew is in a rest state; if the berthing time is relatively short and accompanied by some simple preparation work (such as equipment inspection, etc.), it can be determined as a short rest or work preparation state. In the cruising state, the crew is usually in a normal working state, and needs to continuously monitor the navigation situation, operate the equipment, etc. In the working state, due to the high intensity and complex operation, the crew is often in a high-intensity working state. Then, according to the time sequence, the rest state judgment result corresponding to the different operating states is marked for each time point to generate the rest time sequence of the tug crew. Finally, the working intensity is determined based on the rest time sequence, which can be quantified by counting the proportion and duration of different rest states in the rest time sequence. For example, the proportion of the duration of the high-intensity working state (the rest state corresponding to the working state) in the entire rest time sequence is counted. The higher the proportion is, the greater the working intensity of the crew is. At the same time, combined with the duration of the continuous high-intensity working state, if the continuous high-intensity working time is too long, it also indicates that the working intensity is large. By comprehensively analyzing the rest time sequence in this way, the working intensity of the tug crew can be accurately determined.

[0038] In some embodiments of the present application, the acquired tug AIS data is taken as the starting point to generate a time sequence and perform normalization processing, ensuring the consistency and comparability of the data, and laying a solid foundation for subsequent analysis; the tug operating state is determined by analyzing the normalized data, which can accurately grasp the actual operation of the tug in different periods; and then the crew rest state is derived based on the operating state and the rest time sequence is generated, and the working intensity is determined, realizing the coherent analysis from the ship data to the crew working state evaluation, which is helpful for reasonably arranging the crew work and rest, ensuring the safe operation of the ship and the physical and mental health of the crew, and improving the overall efficiency of maritime management.

[0039] Further, based on the above embodiments, in one of the example embodiments provided by the present application, the specific implementation process of determining the operating state of the tug based on the normalized AIS time sequence can further include steps S210 to S230, which are described in detail as follows:

[0040] Step S210, determining the speed characteristics of the tug based on the normalized AIS time sequence, and generating a corresponding speed time sequence;

[0041] Step S220, introducing a preset speed function, and identifying the speed pulse interval in the speed time sequence and the speed mutation points corresponding to the start and end points of the speed pulse interval based on the preset speed function;

[0042] Step S230, determining the operation state of the tugboat based on the speed pulse interval and the speed mutation point.

[0043] For example, based on the normalized AIS time series to determine the speed characteristics of the tugboat and generate the speed time series, the speed-related data can be extracted from the normalized data, with the timestamp as the horizontal axis and the normalized speed value as the vertical axis, and the data points are arranged in chronological order to form the speed time series. A preset speed function is introduced, which can be set according to the typical speed characteristics of the tugboat in different operating states, such as speed close to 0 when at anchor, speed stable fluctuation in a certain interval when cruising, and speed change complex when working. The speed time series is matched and analyzed using the preset speed function. When the speed value in the sequence matches the speed pulse characteristics (such as a sharp rise or fall in speed in a short time) in the preset function, it is determined that this section is a speed pulse interval. By calculating the speed difference of adjacent data points in the speed time series, when the difference exceeds the set threshold value, the point is the speed mutation point, and the start and end points of the speed pulse interval are determined. Finally, based on the speed pulse interval and the speed mutation point, the operating state of the tugboat is determined. If the speed fluctuation in the speed pulse interval is small and the overall value is low, it can be determined as the at-anchor state; if the speed in the speed pulse interval is relatively stable in a certain high interval, it can be determined as the cruising state; if the speed in the speed pulse interval changes frequently and greatly, it can be determined as the working state.

[0044] Optionally, a preset speed function (such as threshold method, sliding window variance detection or abnormal detection model based on machine learning) can be introduced to identify the speed pulse interval by comparing the speed time series with the function. Specifically, a dynamic threshold (such as mean ± k times standard deviation) can be set or a clustering algorithm can be used to separate normal navigation segments and pulse segments, and the start and end time points of the pulse interval are recorded as the speed mutation points; Finally, combined with the duration of the speed pulse interval, the speed change rate of the mutation point and the pulse amplitude characteristics, the operating state of the tugboat is comprehensively judged: for example, a short-time high-amplitude pulse may correspond to acceleration / deceleration, a long-time low-amplitude pulse may reflect the towing operation, and a smooth segment without pulse may be a constant-speed navigation or standby state. At the same time, the frequency distribution of the pulse interval can be further refined to classify the state.

[0045] Please refer to Figure 2 , Figure 2 The tugboat speed characteristics and feature recognition results from 00:00 to 09:00 on January 1, 2020 are shown. As Figure 2As shown in the middle blue curve, the speed curve of the tugboat during berthing, operation (including assisting berthing, assisting unberthing, and temporary berthing), and cruising has the following obvious characteristics: there are several "0-value speed intervals" with a duration of 0 or approximately 0 and not adjacent, and one or several "speed pulses" are adjacent to the 0-value speed intervals. When the 0-value speed interval and / or the speed pulse is converted, there is usually a "speed mutation point". From the above, it can be seen that the "speed mutation point" is usually distributed on both sides of the speed pulse. By applying the "pulse-mutation point" detection algorithm, the speed pulse (such as the pink interval in Figure 2 ), the first type of mutation point (such as the red triangle in Figure 2 ), and the second type of mutation point (such as the black star in Figure 2 ) in the speed time sequence can be identified. Figure 2 Figure 2 Figure 2

[0046] In some embodiments of the present application, the tugboat speed features are extracted based on the normalized AIS time sequence, and the speed time sequence is generated, which ensures the quality and uniformity of the speed data and provides a reliable basis for subsequent analysis; the preset speed function is introduced to identify the speed pulse interval and the corresponding speed mutation point, which can accurately capture the abnormal changes and key turning points of the speed and effectively distinguish the features of different running stages of the tugboat; finally, the running state of the tugboat is determined based on the speed pulse interval and the mutation point, which makes the judgment of the running state more scientific and accurate, helps to timely grasp the dynamic of the tugboat, and provides accurate information support for ship scheduling, safety monitoring, and crew work arrangement, thereby improving the fine level of shipping management.

[0047] Further, based on the above embodiments, in one of the exemplary embodiments provided by the present application, the specific implementation process of the above-mentioned tugboat crew work intensity monitoring method based on AIS data can further include steps S310 to S340, which are described in detail as follows:

[0048] Step S310, taking the preset speed function as an index, the index including at least one speed threshold value;

[0049] Step S320, dividing the speed time sequence into multiple speed intervals based on the speed threshold value;

[0050] Step S330, identifying the speed pulse interval in the speed time sequence based on the multiple speed intervals.

[0051] For example, according to the typical speed characteristics of different operating states (such as parking, cruising, and working) of the tugboat, a preset speed function is set, which includes at least one speed threshold, for example, a low speed threshold, a medium speed threshold, and a high speed threshold, to construct an index. Then, based on these speed thresholds, the generated speed time series is divided, specifically, each speed value in the speed time series is compared with the set speed threshold, if the speed value is lower than the low speed threshold, it is classified into the low speed interval; if the speed value is between the low speed threshold and the medium speed threshold, it is classified into the medium speed interval; if the speed value is higher than the medium speed threshold, it is classified into the high speed interval, thereby dividing the speed time series into multiple speed intervals. Then, the speed pulse interval is identified by analyzing the distribution of multiple speed intervals in the time series, for example, when the speed interval rapidly jumps from the low speed interval to the high speed interval in a short time, and then rapidly falls back to the low speed interval, this interval with sharp changes and relatively short duration is identified as the speed pulse interval, thereby accurately identifying the speed pulse interval in the speed time series.

[0052] For the convenience of research, it is assumed that is a sequence of discrete time points, where, is the start time of monitoring, is the end time of monitoring, and T is an ordered set. For all satisfies . Let : T to R be a speed function, where, represents the speed value at time t, with the unit of knots (knots). The speed interval S is a continuous subsequence of T, that is, there are indexes , satisfying , so that . The duration of interval S is defined as: (unit: minutes). On this basis, the definitions of "speed pulse interval" and "speed mutation point" are proposed.

[0053] In some embodiments of the present application, by taking the preset speed function as an index with speed thresholds, a clear and quantitative division standard is provided for the analysis of the speed time series; based on the speed thresholds, the speed time series is divided into multiple speed intervals, so that the speed data is structured and presented, facilitating clear observation of the change range and distribution of the speed; further, based on these speed intervals, the speed pulse interval is identified, which can accurately capture the abnormal fluctuations and specific patterns of the speed, helping to more detailed and accurate analysis of the operating characteristics of the tugboat, providing key basis for subsequent operations such as judging the operating state of the tugboat and evaluating the working intensity of the crew, and improving the efficiency and accuracy of the mining and utilization of the tugboat navigation data.

[0054] Furthermore, based on the above embodiments, in one exemplary embodiment provided in this application, the specific implementation process of the above-mentioned method for monitoring the workload of tugboat crew members based on AIS data may further include steps S410 and S420, which are described in detail below:

[0055] Step S410: Perform differential calculation on the velocity time series to obtain the differential velocity time series;

[0056] Step S420: Extract the extreme points in the differential velocity time series and use the extreme points as the velocity change points corresponding to the velocity time series.

[0057] For example, in the process of performing difference calculations on a velocity time series to extract velocity abrupt change points, it is first necessary to clarify that the goal of the difference operation is to amplify local change features by calculating the difference between velocity values ​​at adjacent time points, thereby highlighting the abrupt change in velocity. In specific implementation, assume the original velocity time series is represented as follows:

[0058]

[0059] in, For the first The velocity values ​​at each time point, where n is the sequence length, are the differencing velocity-time series. That is, perform the following operation on each element in the sequence (except for the first element):

[0060]

[0061] This generates a new sequence:

[0062]

[0063] If a higher-order difference (such as a second-order difference) is required, it can be... Repeat the above operation to obtain the differenced sequence. It reflects the instantaneous rate of velocity change, its extreme points (i.e., local maximum or minimum values).

[0064] Specifically, it can be traversed Sequence, marking all sequences that satisfy... (Local maximum) and Points with local minimum values ​​are selected as candidate extreme points. To avoid noise interference, a threshold (such as the minimum amplitude of the absolute value of the difference) or a sliding window can be set to filter significant extreme points. Since the length of the difference sequence is 1 less than that of the original sequence (in the case of first-order difference), the position of the extreme point in the original sequence needs to correspond back to the original timestamp (i.e., the first time step). The original sequence corresponding to each extreme point or Finally, these extreme points are identified as speed mutation points, representing the time when significant acceleration or deceleration occurs in the original speed sequence. If further optimization is needed, the extreme point identification conditions can be adjusted in combination with domain knowledge (such as minimum interval time), or the differential sequence can be preprocessed through smoothing processing (such as moving average) to reduce the impact of false mutation points.

[0065] In some embodiments of the present application, by performing differential calculation on the speed time sequence, the rate of change of speed can be highlighted, making the small fluctuations and trend changes of speed more obvious, so as to more sensitively capture the dynamic characteristics of speed; extracting the extreme points in the differential speed time sequence and taking them as speed mutation points can accurately locate the time when speed changes significantly, providing accurate basis for identifying key turning points of tug operation state, helping to analyze the running characteristics of tug in different periods, and further providing reliable data support for reasonably judging the running state of tug, scientifically arranging the work and rest of crew, and evaluating the work intensity, etc., improving the accuracy and effectiveness of shipping management.

[0066] Further, based on the above embodiments, in one of the exemplary embodiments provided by the present application, the specific implementation process of the above-mentioned tug crew work intensity monitoring method based on AIS data can further include steps S510 and S520, which are described in detail as follows:

[0067] Step S510, determining the speed mutation point types corresponding to the start point and end point of the speed pulse interval;

[0068] Step S520, determining the corresponding running state of the tug in the speed pulse interval based on the speed mutation point types.

[0069] For example, when determining the speed mutation point types corresponding to the start point and end point of the speed pulse interval, the extreme points of the differential speed time sequence need to be classified in combination with the characteristics of the extreme points. Assuming that the extreme points of the differential sequence AV have been marked by local maximum and local minimum , the speed mutation point types can be divided into two categories: acceleration mutation point (corresponding to local maximum, indicating that the speed starts to increase significantly) and deceleration mutation point (corresponding to local minimum, indicating that the speed starts to decrease significantly). In specific implementation, first, map the extreme points of the differential sequence back to the time stamps of the original speed sequence (for example, the first extreme point corresponds to the th time stamp of the original sequence the interval between the first type of mutation point and the second type of mutation point is the potential speed pulse interval (indicating that the speed changes from increasing to decreasing), and vice versa. It should be noted that the boundary conditions are handled (such as discarding when there is no paired extreme point at the beginning and end of the sequence). When determining the tugboat running state based on the type of speed mutation point, the dynamic characteristics in the speed pulse interval need to be analyzed. If the start of the interval is an acceleration mutation point and the end is a deceleration mutation point, the speed in the interval first increases and then decreases, which may correspond to the acceleration-deceleration working condition of the tugboat (such as avoiding obstacles or adjusting the heading); if the start is a deceleration mutation point and the end is an acceleration mutation point, the speed first decreases and then increases, which may correspond to the deceleration to recovery working condition (such as entering the shallow water area to restore the speed). Further, in combination with the duration of the pulse interval, the speed change amplitude and the characteristics of the adjacent interval, the running state classification can be refined: for example, a short-time high-frequency pulse may correspond to the dynamic positioning system adjustment, and a long-time low-frequency pulse may reflect the periodic start-stop of the tugboat in the push-barge operation. In addition, by setting a speed change threshold (such as > 0.5 m / s) to filter minor fluctuations, or in combination with the acceleration second-order difference to verify the significance of the mutation point, the robustness of state recognition can be improved. Finally, according to the mutation point type and interval characteristics, the tugboat running state is divided into "acceleration to deceleration", "deceleration to recovery", "uniform speed running" or "static" modes, providing a basis for navigation behavior analysis.

[0070] In some embodiments of the present application, by explicitly determining the type of speed mutation point corresponding to the start and end of the speed pulse interval, the nature of the speed change can be accurately classified, such as distinguishing between acceleration mutation and deceleration mutation; based on these specific speed mutation point types, the running state of the tugboat in the speed pulse interval is determined, making the running state judgment more in line with the actual dynamic changes, and more detailedly reflecting the specific behavior of the tugboat in different speed change stages, such as the transition from parking to cruising, acceleration adjustment in cruising, or transition from working state to parking, etc., thereby providing more targeted and reliable basis for accurately evaluating the running condition of the tugboat, reasonably arranging the work of the crew, and ensuring the safety of maritime transportation.

[0071] Further, based on the above embodiments, in one of the exemplary embodiments provided in the present application, the specific implementation process of the above-mentioned tugboat crew work intensity monitoring method based on AIS data can further include steps S610 and S620, which are described in detail as follows:

[0072] Step S610: If the start of the speed pulse interval is a first type of mutation point and the end is a second type of mutation point, the running state of the tugboat in the speed pulse interval is determined to be a cruising state;

[0073] In step S620, if the start point of the speed pulse interval is the second type mutation point and the end point is the first type mutation point, the average speed change trend in the speed pulse interval is obtained to determine the corresponding running state of the tugboat in the speed pulse interval based on the average speed change trend.

[0074] For example, first, the type definition of the speed mutation point is determined. It is assumed that the first type mutation point is an acceleration mutation point (local maximum value of the difference sequence, indicating that the speed starts to significantly increase), and the second type mutation point is a deceleration mutation point (local minimum value of the difference sequence, indicating that the speed starts to significantly decrease). When the start point of the speed pulse interval is the first type mutation point and the end point is the second type mutation point, it indicates that the speed of the tugboat experiences the process of first acceleration and then deceleration in the interval, which is consistent with the characteristics of the typical cruising state (such as dynamic adjustment when maintaining the target speed). At this time, the tugboat in the interval can be directly determined to be in the cruising state without further analyzing the speed change details in the interval. If the start point of the speed pulse interval is the second type mutation point and the end point is the first type mutation point, it indicates that the speed of the tugboat first decelerates and then accelerates, which may correspond to a non-cruising working condition (such as avoidance, turning or recovery process under external interference). At this time, the original speed sequence segment in the interval needs to be extracted, and the average speed change trend is calculated to refine the state classification. The specific implementation steps are as follows: first, the speed values in the interval are linearly fitted or averaged by a sliding window to obtain the slope of the speed change with time; if the slope is negative and the absolute value is large, it indicates that the tugboat is in a deceleration working condition (such as active braking or increased environmental resistance); if the slope is positive and the absolute value is large, it indicates that the tugboat is in an acceleration working condition (such as recovering the speed or starting the pusher operation); if the slope is close to zero, it may be a low-speed maneuvering state (such as fine-tuning the heading). Further, the classification logic can be optimized by combining the interval duration (such as short-time deceleration followed by acceleration may be a collision avoidance operation, and long-time deceleration may be a port approach) and the speed amplitude (such as deceleration to near zero is determined as a stop state). In addition, to avoid noise interference, the speed sequence can be filtered (such as Savitzky-Golay smoothing) before calculating the trend, or a slope threshold (such as zero is considered as uniform speed). Finally, according to the slope of the average speed change trend and the interval characteristics, the running state of the tugboat is divided into “deceleration working condition”, “acceleration working condition”, “low-speed maneuvering” or “other abnormal state”, thereby realizing accurate identification of complex navigation behaviors.

[0075] In some embodiments of the present application, the running state of the tugboat is flexibly determined according to different combinations of the types of the start point and end point mutation points of the speed pulse interval. The judgment efficiency of part of the cases is improved by direct determination, and the judgment accuracy in complex cases is ensured by the average speed change trend analysis, so that the identification of the running state of the tugboat is more scientific and reasonable.

[0076] Further, based on the above embodiments, in one of the example embodiments provided in the present application, the specific implementation process of determining the corresponding running state of the tugboat in the speed pulse interval based on the average speed change trend can further include steps S710 to S730, which are described in detail as follows:

[0077] Step S710, if the average speed change trend represents that the average speed in the speed pulse interval is less than the preset speed threshold, it is determined that the state of the tugboat in the speed pulse interval is the berthing state;

[0078] Step S720, if the average speed change trend represents that the average speed in the speed pulse interval is greater than the preset speed threshold, and the average speed in the speed pulse interval shows a growth trend, it is determined that the state of the tugboat in the speed pulse interval is the assisting undocking state;

[0079] Step S730, if the average speed change trend represents that the average speed in the speed pulse interval is greater than the preset speed threshold, and the average speed in the speed pulse interval shows a decay trend, it is determined that the state of the tugboat in the speed pulse interval is the assisting berthing state.

[0080] For example, the average speed change trend in the speed pulse interval and the preset speed threshold are comprehensively judged. First, the arithmetic mean of the original speed sequence in the speed pulse interval is calculated as the average speed, and an empirical speed threshold (such as 0.5 m / s, the specific value can be adjusted according to the working scene of the tugboat) is set. If the average speed is less than the threshold, it indicates that the tugboat is in a low speed or static state in the interval, and is directly determined as the berthing state (such as waiting for instructions or anchoring). If the average speed is greater than the threshold, the speed change trend in the interval is further analyzed: the slope of the speed change with time is calculated through linear regression or difference, if the slope is positive (i.e. the average speed shows a growth trend), it indicates that the tugboat is continuously accelerating in the interval, and combined with the working logic of the tugboat, it can be determined as the assisting undocking state (such as the active acceleration when the tugboat leaves the wharf); if the slope is negative (i.e. the average speed shows a decay trend), it indicates that the tugboat is continuously decelerating in the interval, and is determined as the assisting berthing state (such as the braking process when the tugboat approaches the wharf). In order to improve the judgment accuracy, the following optimization measures can be introduced: the speed sequence is filtered by a sliding window to eliminate transient noise and avoid misjudgment of the trend due to local fluctuations; a slope threshold (such as is considered as no significant trend) is set to prevent small changes from causing state misclassification; the interval duration is combined (such as short-time acceleration may be a fine-tuning operation, and long-time acceleration is more consistent with the undocking characteristics); and the threshold rationality is verified through historical data (such as the speed distribution under different working conditions is counted). Finally, through the comparison of the average speed and the threshold and the trend analysis, the tugboat state is accurately divided into “berthing”, “assisting undocking” or “assisting berthing”, providing a reliable basis for the modeling of the navigation behavior.

[0081] Specifically, if the start point s of the interval is the "second type mutation point M2" and the end point s is the "first type mutation point M1", the average speed v in the interval is less than 0.25 knots, then the interval is in the "parking" state; if the start point s of the interval is the "second type mutation point M2" and the end point s is the "first type mutation point M1", the average speed v in the interval is greater than 0.25 knots, and the average speed v of the first half of the interval is less than the average speed v of the second half of the interval, then the interval is in the "assisted unberthing" state; if the start point s of the interval is the "second type mutation point M2" and the end point s is the "first type mutation point M1", the average speed v in the interval is greater than 0.25 knots, and the average speed v of the first half of the interval is greater than the average speed v of the second half of the interval, then the interval is in the "assisted berthing" state; if the start point s of the interval is the "first type mutation point M1" and the end point s is the "first type mutation point M1", then the interval is in the "assisted berthing" state; if the start point s of the interval is the "second type mutation point M2" and the end point s is the "second type mutation point M2", then the interval is in the "assisted unberthing" state.

[0082] In some embodiments of the present application, by comprehensively considering the comparison relationship between the average speed in the speed pulse interval and the preset speed threshold, and the change trend of the average speed, a scientific and detailed tug running state judgment system is constructed. It not only can accurately identify the static parking state of the tug, but also can clearly distinguish the unberthing state of the tug assisting the ship to leave the berth and the berthing state of the tug assisting the ship to approach the berth according to the growth or decay trend of the average speed. This comprehensive and accurate state judgment method provides strong data support for shipping management personnel to master the real-time tug dynamic, reasonably schedule tug resources and ensure the safety and efficiency of port operation, which helps to improve the operation efficiency and safety of the entire shipping system.

[0083] Further, based on the above embodiments, in one of the exemplary embodiments provided by the present application, the specific implementation process of the above-mentioned tug crew work intensity monitoring method based on AIS data can further include steps S810 to S830, which are described in detail as follows:

[0084] Step S810, if the running state of the tug is the parking state, it is determined that the tug crew is in the rest state; ​​​​​​​​​​​​​​​

[0085] Step S820, if the operating state of the tugboat is in the cruising state or the working state, it is determined that the tugboat crew is in the working state;

[0086] Step S830, the time period corresponding to the rest state and the working state is determined, and the rest and work time sequence of the tugboat crew is determined based on the time period.

[0087] For example, first, according to the operating state of the tugboat (such as the berthing state, the cruising state, the assisting unberthing / berthing state, etc.) determined in the preceding steps, a mapping rule of state and crew activity state is established, that is, when the tugboat is in the berthing state (the average speed is lower than the preset threshold value and there is no significant speed change), the crew is in the rest state by default; when the tugboat is in the cruising state (pulse interval of accelerating first and then decelerating) or the working state (such as assisting unberthing / berthing, speed continuously changing and higher than the threshold value), it is determined that the crew is in the working state. It should be noted that if there is a high-frequency short-time pulse (such as dynamic positioning system fine tuning) during the berthing of the tugboat, invalid rest state can be filtered by setting a minimum continuous time threshold (such as 5 minutes). Next, the speed time sequence of the tugboat is traversed, and the crew state (rest or work) at each time point is marked according to the above rule to generate an initial state label sequence. In order to improve accuracy, auxiliary information (such as heading stability in AIS data, main engine power output) can be combined to verify the reasonableness of state classification, for example: if the main engine power is continuously zero and the heading angle fluctuation is less than 5 degrees during berthing, the rest state determination is strengthened; if the cruising or working state is accompanied by high power output of the main engine or frequent turning, the working state is confirmed. Then, the same continuous state labels are merged into time periods to form a rest time period set and a working time period set, for example: , , the working time period is , .

[0088] Finally, based on the merged time period set, the rest and work time sequence of the tugboat crew is constructed. The sequence is indexed by time stamp, sequentially records the start and end time of each time period and the corresponding state (such as "08:00-12:00 work" "12:00-14:00 rest"), and can be directly displayed through visualization tools (such as Gantt chart). In order to optimize the results, fatigue management rules (such as single continuous work not more than 4 hours need to arrange rest) can be introduced to verify the compliance of the rest and work sequence and mark the potential fatigue risk period. In addition, if long-term rest and work rules need to be analyzed, the time sequences of multiple voyages can be counted (such as calculating the average rest time per day, the distribution of working time period), which can provide data support for crew scheduling optimization. The final output rest and work time sequence reflects the real-time state and supports the macro management needs.

[0089] Please refer to Figure 3 ,Figure 3 is shown is the identification result of a tugboat operation state from 00:00 to 09:00 on January 1, 2020, in which Figure 3 The navigation data of the tugboat is comprehensively displayed in the figure, which includes heading, SOG (speed over ground), identification state, displacement, and total displacement. The top curve chart presents the change of the heading over time, which fluctuates greatly and has multiple mutations. The middle speed-time chart distinguishes the auxiliary, cruising, mooring, and temporary mooring states of the tugboat with different colors, and marks the cruising and mooring threshold lines, showing the frequent switching of the speed between different states. The lower column chart intuitively displays the time distribution of each state, and the colors correspond to the middle chart. The displacement curve chart at the bottom reflects the change trend of the displacement and total displacement, in which the total displacement is represented by a dashed line, showing the accumulation process of the displacement. Overall, the image presents the complex navigation state and dynamic change of the tugboat in this period through multi-dimensional data.

[0090] In some embodiments of the present application, the rest and work states of the crew are accurately defined according to the explicit operation states (parking, cruising, and operation) of the tugboat, making the crew state judgment simple and practical. By further determining the time period corresponding to different states and generating the work-rest time sequence, the regular distribution of the crew's work and rest can be intuitively presented, providing a clear basis for reasonably arranging the crew's shift and ensuring their reasonable rest time, which helps to improve the crew's work efficiency, ensure the safety of maritime operations, and also helps maritime enterprises to optimize human resource management and realize scientific and humanized ship operation.

[0091] Further, based on the above embodiments, in one of the exemplary embodiments provided by the present application, the specific implementation process of determining the work intensity of the tugboat crew based on the work-rest time sequence can further include steps S910 to S930, which are described in detail as follows:

[0092] Step S910, determining the rest time and work time of the tugboat crew based on the work-rest time sequence;

[0093] Step S920, if the preset evaluation strategy is the longest work time evaluation strategy, calculating the cumulative work time of the tugboat crew within a preset time period based on the work time, and determining the work intensity of the tugboat crew based on the cumulative work time;

[0094] Step S930, if the preset evaluation strategy is the shortest rest time evaluation strategy, calculating the continuous rest time of the tugboat crew within a preset time period based on the rest time, and determining the work intensity of the tugboat crew based on the continuous rest time.

[0095] For example, the total length of time periods marked as "rest state" and "work state" is calculated respectively by traversing each time period in the work-rest time sequence, to obtain the absolute values of rest time and work time in a single day or multi-day cycle. To adapt to the needs of different evaluation strategies, further normalization processing is required in combination with the preset time length (such as 24 hours or voyage cycle), for example, to calculate the daily average rest time and daily average work time. The calculation method of work intensity differs for different preset evaluation strategies: if the longest work time evaluation strategy is adopted, the focus is on the extreme case in the work period. The specific operation is: identify the continuous work time period in the work-rest time sequence, calculate the length of each continuous work interval, and take the maximum value as the longest continuous work time. Then, the cumulative length of all work intervals in the preset time length (such as 24 hours) is calculated, combined with the longest continuous work time, and the work intensity is evaluated by a weighting strategy. This strategy focuses on preventing fatigue accumulation caused by long-term continuous work of the crew. If the shortest rest time evaluation strategy is adopted, the focus is on the continuity of the rest period. The specific operation is: identify the continuous rest time period in the work-rest time sequence, calculate the length of each continuous rest interval, and take the minimum value as the shortest continuous rest time. At the same time, the cumulative length of all rest intervals in the preset time length is calculated. Based on the shortest continuous rest time, the work intensity is determined by threshold comparison (such as if the minimum rest time < 1 hour, it is determined as high risk) or normalized score (such as rest adequacy). This strategy aims to ensure that the crew obtains sufficient intermittent recovery time.

[0096] To improve the practicality of the evaluation, industry standards can be combined, for example, according to the Maritime Labour Convention, the International Convention on Standards of Training, Certification and Watchkeeping for Seafarers, and other rules for seafarer rest time compliance. The rules can be summarized as follows: no less than 10 hours in any 24-hour period, and no less than 77 hours in any 7-day period. In addition, the rest time can be divided into two segments at most, one of which must be at least 6 hours long, and the interval between the two consecutive rest time segments must not exceed 14 hours. Then the convention rules can be formalized as follows:

[0097] For example, the 24-hour rest rule can be expressed as:

[0098]

[0099] where, is an indicator function (rest = 1, work = 0), is a segmented rule verification function.

[0100] For example, the 7-day rest rule can be expressed as:

[0101]

[0102] The segmentation rules can be represented as:

[0103]

[0104] wherein, is the combined set of rest segments, is the segment interval ( = ). Then the corresponding compliance measure function is constructed, assuming that the berthing time segments represent crew rest time (i.e., when the ship is at berth, the crew is not on duty). Then the 24h window compliance measure function is represented as:

[0105]

[0106] wherein, represents the kth 24-hour sliding window, defined as the time interval starting at time point and lasting 24 hours, i.e., . Typically, we set a sliding step size (e.g., 1 hour), then , where is the starting time point (e.g., the start time of the voyage). The number of sliding windows is determined by the total time length and the step size.

[0107] Similarly, the 7-day window compliance measure function can be represented as:

[0108]

[0109] wherein, represents the kth 168-hour (7-day) sliding window, defined as the time interval starting at time point and lasting 168 hours, i.e., .

[0110] Next, the compliance measure function can be constructed as:

[0111]

[0112] Further, the overall compliance index is obtained as:

[0113]

[0114] wherein, , . represents the final compliance index of the entire voyage, expressed in percentage form. It is the minimum value of the 24-hour window compliance rate and the 7-day (168-hour) window compliance rate (the bucket principle, i.e., the worst compliance rate determines the overall compliance level).

[0115] In some embodiments of the present application, the rest duration and work duration of the tugboat crew are accurately extracted from the work-rest time sequence, laying a data foundation for subsequent evaluation. Then, according to different preset evaluation strategies, the relevant duration indicators are flexibly calculated. The longest work duration evaluation strategy focuses on the cumulative work duration within the preset duration, which can intuitively reflect the overall load of the crew. The shortest rest duration evaluation strategy focuses on the continuous rest duration, which can effectively evaluate the sufficiency of the crew's rest. These two strategies scientifically determine the work intensity of the crew from different dimensions, which helps shipping enterprises to comprehensively and reasonably arrange the work and rest of the crew, protect the physical and mental health of the crew, and improve the safety and efficiency of shipping operations.

[0116] Please refer to Figure 4 , provides a tugboat crew work intensity monitoring system based on AIS data, the system includes a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory are connected with each other, wherein the memory is used for storing computer programs, the computer programs include program instructions, the processor is configured to call the program instructions, and the tugboat crew work intensity monitoring method based on AIS data in any one of the above embodiments is executed.

[0117] The flowcharts and block diagrams in the drawings illustrate the possible implementation architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In the flowchart or block diagram, each block can represent a module, a program segment or a part of code, which contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks can also occur in different order from that marked in the drawings. For example, two blocks represented in succession can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be realized by a special hardware-based system for executing the specified functions or operations, or can be realized by a combination of special hardware and computer instructions.

[0118] The units involved in the embodiments of the present application can be realized in the form of software or in the form of hardware, and the described units can also be arranged in a processor. In some cases, the names of these units do not constitute a limitation on the units themselves.

[0119] Another aspect of the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method for monitoring working intensity of tugboat crew based on AIS data as described above. The computer readable storage medium can be included in the electronic device described in the above embodiments, or can exist separately without being assembled into the electronic device.

[0120] Another aspect of the present application also provides a computer program product or computer program, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to make the computer device execute the method for monitoring working intensity of tugboat crew based on AIS data provided in the above embodiments.

[0121] The above merely describes preferred exemplary embodiments of the present application, and is not intended to limit the implementation of the present application. Based on the main concept and spirit of the present application, those skilled in the art can easily make corresponding modifications or changes, and therefore the protection scope of the present application should be subject to the protection scope required by the claims.

Claims

1. A tugboat crew work intensity monitoring method based on AIS data, characterized by, The method comprises: obtaining AIS data corresponding to the tugboat, and generating an AIS time sequence corresponding to the AIS data based on the AIS data; normalizing the AIS time sequence so that the AIS data in the AIS time sequence is in the same scale; determining the running state of the tugboat based on the normalized AIS time sequence, wherein the running state comprises parking, cruising and working; determining the work-rest state of the tugboat crew based on the running state, and generating a work-rest time sequence of the tugboat crew based on the work-rest state, so as to determine the working intensity of the tugboat crew based on the work-rest time sequence; the method further comprises: determining the speed feature of the tugboat based on the normalized AIS time sequence, and generating a speed time sequence corresponding thereto; introducing a preset speed function, and identifying a speed pulse interval in the speed time sequence and a speed mutation point corresponding to the start point and the end point of the speed pulse interval based on the preset speed function; determining the running state of the tugboat based on the speed pulse interval and the speed mutation point; the method further comprises: taking the preset speed function as an index, wherein the index comprises at least one speed threshold; dividing the speed time sequence into a plurality of speed intervals based on the speed threshold; identifying the speed pulse interval in the speed time sequence based on the plurality of speed intervals; the method further comprises: performing difference calculation on the speed time sequence to obtain a differential speed time sequence; extracting extreme points in the differential speed time sequence, and taking the extreme points as the speed mutation points corresponding to the speed time sequence; the method further comprises: determining the type of the speed mutation point corresponding to the start point and the end point of the speed pulse interval, wherein the speed mutation point comprises an acceleration mutation point and a deceleration mutation point; determining the running state of the tugboat corresponding to the speed pulse interval based on the type of the speed mutation point.

2. The method of claim 1, wherein, the method further comprises: if the start point of the speed pulse interval is a first type mutation point, and the end point is a second type mutation point, it is determined that the running state of the tugboat corresponding to the speed pulse interval is a cruising state; if the start point of the speed pulse interval is a second type mutation point, and the end point is a first type mutation point, an average speed change trend in the speed pulse interval is obtained, so as to determine the running state of the tugboat corresponding to the speed pulse interval based on the average speed change trend.

3. The method of claim 2, wherein, the method further comprises: if the average speed change trend represents that the average speed in the speed pulse interval is less than a preset speed threshold, it is determined that the state of the tugboat in the speed pulse interval is a parking state; if the average speed change trend represents that the average speed in the speed pulse interval is greater than a preset speed threshold, and the average speed in the speed pulse interval shows a growth trend, it is determined that the state of the tugboat in the speed pulse interval is an assisting undocking state. If the average speed variation trend represents that the average speed in the speed pulse interval is greater than a preset speed threshold, and the average speed in the speed pulse interval presents a decaying trend, it is determined that the tugboat state in the speed pulse interval is a berthing assisting state.

4. The method of claim 1, wherein, The method further comprises: If the running state of the tugboat is a berthing state, it is determined that the tugboat crew is in a rest state; If the running state of the tugboat is a cruising state or a working state, it is determined that the tugboat crew is in a working state; Time periods corresponding to the rest state and the working state are determined, and a work-rest time sequence of the tugboat crew is determined based on the time periods.

5. The method of claim 4, wherein, The determination of the working intensity of the tugboat crew based on the work-rest time sequence comprises: The rest duration and the working duration of the tugboat crew are determined based on the work-rest time sequence; if a preset evaluation strategy is a longest working duration evaluation strategy, the cumulative working duration of the tugboat crew within a preset time duration is calculated based on the working duration, so as to determine the working intensity of the tugboat crew based on the cumulative working duration; If a preset evaluation strategy is a shortest rest duration evaluation strategy, the continuous rest duration of the tugboat crew within a preset time duration is calculated based on the rest duration, so as to determine the working intensity of the tugboat crew based on the continuous rest duration.

6. A tugboat crew work intensity monitoring system based on AIS data, characterized by, The system comprises a processor, an input device, an output device and a memory, which are connected to each other, wherein the memory is used to store a computer program, the computer program comprises program instructions, the processor is configured to invoke the program instructions, and execute the method for monitoring the working intensity of a tugboat crew based on AIS data according to any one of claims 1 to 5.

Images