Ship arrival status determination method, device and readable storage medium

Abstract

The application provides a ship arrival state determination method, device and readable storage medium. The ship arrival state determination method comprises the following steps: acquiring sailing dynamic data and ship static attribute data of a target ship; determining target port coordinate data of the target ship according to the ship static attribute data; determining a distance change rate between the target ship and the target port based on a spherical distance calculation formula, the target port coordinate data and position data; determining a heading change trend of the target ship relative to the target port according to the heading data and the target port coordinate data; acquiring a speed change rate according to the speed data; determining a dynamic approaching degree according to the distance change rate, the speed change rate and the heading change trend; acquiring a time sequence feature of the dynamic approaching degree according to a preset time window; and determining an arrival state of the target ship based on the time sequence feature. The application determines the arrival state based on the dynamic approaching degree, thereby improving the prediction accuracy.

Description

Technical Field

[0001] This application relates to the field of shipping and maritime monitoring technology, and more specifically, to a method, apparatus and readable storage medium for determining the arrival status of a ship. Background Technology

[0002] In related technologies, with the accelerated digital transformation of the global shipping industry and port logistics, the automatic identification and prediction of ship operating status has become an important support for smart ports and intelligent shipping management. Ship owners, cargo owners, port dispatchers, and maritime regulators all hope to have real-time access to ship dynamic information, especially the departure, arrival, and occupancy status of ships.

[0003] Therefore, accurate and timely arrival determination is required. However, common methods for determining ship arrival rely on static threshold rules such as speed dropping to zero and ship position being fixed, lacking dynamic trend analysis of ships approaching the port, which leads to low accuracy and large delays in judgment. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art or related technologies.

[0005] Therefore, the first aspect of this application proposes a method for determining the arrival status of a ship.

[0006] The second aspect of this application proposes a device for determining the arrival status of a ship.

[0007] The third aspect of this application proposes another device for determining the arrival status of a ship.

[0008] The fourth aspect of this application proposes a readable storage medium.

[0009] In view of this, the first aspect of this application provides a method for determining the arrival status of a vessel, comprising: acquiring navigation dynamic data and static attribute data of a target vessel, wherein the navigation dynamic data includes at least heading data, speed data, and position data; determining the target port coordinate data of the target vessel based on the static attribute data; determining the distance change rate between the target vessel and the target port based on the spherical distance calculation formula, the target port coordinate data, and the position data; determining the heading change trend of the target vessel relative to the target port based on the heading data and the target port coordinate data; obtaining the speed change rate based on the speed data; determining the dynamic approach degree based on the distance change rate, the speed change rate, and the heading change trend, wherein the dynamic approach degree is used to characterize the degree to which the target vessel approaches the target port; acquiring the temporal characteristics of the dynamic approach degree according to a preset time window; and determining the arrival status of the target vessel based on the temporal characteristics.

[0010] The navigation dynamic data in this application refers to the relevant data that changes in real time during the navigation of a ship. The core data includes heading data (the direction of the ship's navigation, such as Course Over Ground, COG), speed data (the speed of the ship's navigation, such as Speed ​​Over Ground, SOG), and position data (the spatial coordinates of the ship in real time, such as latitude and longitude). It may also include auxiliary data such as time series, which mainly comes from the Automatic Identification System (AIS).

[0011] Ship static attribute data refers to the inherent attribute information of a ship that does not change dynamically during navigation, including ship type, length, tonnage, destination port coordinates, etc., and is the basic characteristic data of a ship.

[0012] Target port coordinate data refers to the precise spatial coordinates (usually latitude and longitude) of the target port, which are obtained by associating with the destination port information in the ship's static attribute data. It is the core benchmark data for calculating the distance and course relationship between the ship and the port.

[0013] The spherical distance calculation formula is a mathematical formula used to calculate the shortest distance (great circle distance) between two points on a sphere. It is adapted to the Earth's spherical model. In this application, the Haversine formula is specifically used, which can accurately calculate the spatial distance between ships and ports.

[0014] The rate of change of distance is the ratio of the difference in spherical distance between a ship and a target port within a continuous time period to the corresponding time difference. It is used to quantify the rate at which a ship approaches or moves away from the port, with a positive value indicating that the ship is approaching the port.

[0015] The course change trend refers to the deviation of a ship's current course from its ideal course toward the target port. It reflects the consistency trend between the ship's sailing direction and the port, including states such as heading toward the port and deviating from the port.

[0016] The rate of change of speed is the ratio of the difference in ship speed over a continuous period of time to the corresponding time difference. It is used to characterize the dynamic changes in ship speed and can reflect whether the ship is slowing down before berthing.

[0017] Dynamic approach is a normalized index (range [0, 1]) obtained by weighted fusion of three dimensions: distance change rate, speed change rate, and heading change trend. It is used to quantitatively characterize the degree to which a ship approaches the target port. The larger the value, the higher the degree of approach.

[0018] The preset time window refers to a fixed time interval (such as 10 AIS message cycles) that is set in advance to perform time series analysis on dynamic convergence and extract features within a continuous time period, rather than instantaneous features at a single point in time.

[0019] Time-series characteristics: refer to the statistical characteristics of dynamic convergence within a preset time window, including the statistical mean (the average level of dynamic convergence within the window) and fluctuation characteristics (the degree of dispersion of dynamic convergence within the window, such as standard deviation), which are used to reflect the changing pattern of dynamic convergence.

[0020] The arrival status refers to the classification of a vessel's navigation status relative to the target port, including three core statuses: not yet arrived, expected arrival, and already arrived. This is the final determination result of this application.

[0021] Based on the above data and steps, this application can overcome the limitations of static threshold judgment, realize dynamic perception and early judgment of ship arrival status, significantly reduce judgment delay, and improve the universality and accuracy of judgment, providing timely and reliable decision-making basis for port scheduling and logistics docking.

[0022] First, a complete input dataset was constructed by acquiring navigation dynamic data and ship static attribute data. This dataset encompasses both the ship's real-time motion status and its basic characteristics, as well as target port reference information, providing data support for subsequent calculations. Next, target port coordinate data was extracted from the ship's static attribute data, establishing the core benchmarks for distance and heading calculations. Subsequently, based on the spherical distance calculation formula, combined with ship position data and target port coordinate data, the distance change rate was calculated, quantifying the ship's spatial approach speed. The heading change trend was determined using heading data and target port coordinate data, clarifying the consistency of the ship's navigation direction. The speed change rate was extracted from the speed data, capturing the ship's dynamic speed adjustment characteristics. These three factors together constitute the core dynamic indicators reflecting the ship's approaching behavior. Based on this, a dynamic approach degree was constructed by fusing these three core indicators, transforming multi-dimensional dynamic information into a unified quantitative indicator, achieving a precise characterization of the ship's approach degree. Finally, the temporal characteristics of the dynamic approach degree were extracted through a preset time window, filtering out the randomness of data at a single time point and highlighting the trend-like patterns of approaching behavior. Finally, based on the time sequence characteristics, the arrival status can be determined without waiting for the ship to come to a complete stop. The arrival trend can be identified in advance during the approach of the ship, thus avoiding the problems of high determination delay and lack of dynamic perception capability. At the same time, it is adaptable to different ship types and port environments, improving the versatility of the determination.

[0023] In some technical solutions of this application, after obtaining the navigation dynamic data and static attribute data of the target vessel, the method further includes: preprocessing the navigation dynamic data, wherein the preprocessing includes at least one of removing abnormal data points, supplementing missing data, and smoothing filtering the navigation dynamic data and the static attribute data.

[0024] In this technical solution, preprocessing refers to the cleaning, correction, and optimization of navigation dynamic data before subsequent index calculations, aiming to improve data quality and reduce noise interference. Outlier removal involves identifying and deleting data that significantly deviates from the normal range (such as abrupt changes in latitude and longitude due to AIS signal obstruction or delay, or abnormal speed spikes), preventing outliers from affecting calculation results. Data supplementation addresses missing items in the navigation dynamic data (such as missing speed or heading data at specific time points) by using appropriate interpolation and fitting methods to ensure data continuity and integrity. Smoothing filtering uses specific algorithms (such as moving averages) to process navigation dynamic data (especially speed data), reducing high-frequency noise and making data changes smoother, better reflecting the true trend of ship movement.

[0025] Based on the above data and steps, the quality and reliability of input data can be further improved, reducing the interference of data noise, anomalies, and missing data on subsequent calculations. This provides a precise and continuous data source for dynamic approach calculation, temporal feature extraction, and arrival status determination, thereby improving the overall accuracy and robustness of the method. In this application, a data preprocessing step is added to the acquisition of the target vessel's navigation dynamic data and static attribute data. Because AIS data may be affected by signal obstruction, equipment failure, etc., during actual transmission, there may be abnormal data points and missing data. If used directly for calculation, it will lead to distortion of core indicators such as distance change rate and speed change rate, thus affecting the accuracy of dynamic approach and the reliability of temporal features, ultimately causing misjudgment of arrival status. By removing abnormal data points, data interference that clearly does not conform to the actual movement patterns of the vessel can be eliminated, ensuring the authenticity of the data. Supplementing missing data ensures the continuity of the data sequence, avoiding calculation interruptions or result deviations due to data breaks. Smoothing filtering of the navigation dynamic data can weaken the noise impact caused by short-term data fluctuations, making data such as speed and heading more reflective of the vessel's true movement trend. Through the above preprocessing operations, the original data that originally had quality problems was optimized into accurate, continuous, and reliable valid data, providing a high-quality data foundation for all subsequent calculation steps, reducing the risk of misjudgment from the source, and significantly improving the overall accuracy and robustness of the method.

[0026] In some technical solutions of this application, the dynamic convergence degree is determined based on the distance change rate, speed change rate, and heading change trend. This includes: setting three weight coefficients that satisfy the condition that the sum of the weights is 1, based on the importance ratio of the distance change rate, speed change rate, and heading change trend, where the set weight coefficients correspond to the distance change rate, speed change rate, and heading change trend, respectively; normalizing the indicators corresponding to the distance change rate, speed change rate, and heading change trend according to a preset normalization rule to obtain a normalized indicator set; and merging and calculating the normalized indicators in the indicator set according to their corresponding weight coefficients using a weighted summation algorithm to determine the dynamic convergence degree.

[0027] In this technical solution, the importance ratio refers to the relative importance of three indicators—distance change rate, speed change rate, and heading change trend—in characterizing the ship's approach degree. This importance ratio can be obtained through historical data modeling or big data calculations, or determined by technical personnel based on factors such as the actual application scenario, ship type characteristics, and port environment. The weighting coefficients are numerical coefficients set to reflect the importance ratio of the three indicators, ensuring that the sum of the three coefficients is 1. Each coefficient corresponds one-to-one with the distance change rate, speed change rate, and heading change trend, and is used to adjust the contribution of each indicator in the dynamic approach degree calculation. The preset normalization rule refers to a pre-defined rule for a unified data scale (such as linear normalization, maximum-minimum normalization, etc.). Its purpose is to transform the indicators corresponding to the distance change rate, speed change rate, and heading change trend into the same scale (usually [0, 1]), avoiding fusion bias caused by differences in indicator dimensions and numerical ranges. The normalized index set refers to the standardized data set formed after processing the three core indicators according to preset normalization rules. It includes the normalized distance change rate, speed change rate, and heading change trend indicators. All indicators are on the same scale and can be directly weighted and fused. The weighted summation algorithm is an algorithm that multiplies each normalized indicator by its corresponding weight coefficient and then adds the products to obtain the dynamic convergence degree. It is the core algorithm for realizing multi-indicator fusion.

[0028] Based on the aforementioned data and steps, the dynamic approach score can be further improved to accurately and comprehensively reflect the degree of a ship's approach to the port. Simultaneously, it provides flexibility in constructing the dynamic approach score, allowing for adjustments to indicator weights according to different scenarios and enhancing the method's adaptability. This application refines the steps for determining the dynamic approach score. Because the dimensions and numerical ranges of the three types of indicators—distance change rate, speed change rate, and heading change trend—differ (e.g., distance change rate is measured in meters per second, and heading change trend is represented by heading deviation in degrees), direct fusion would lead to indicators with larger numerical ranges dominating, failing to fully reflect the roles of each indicator. Furthermore, the importance of each indicator varies across different scenarios (e.g., distance change rate is more important in open waters, while heading change trend is more critical in narrow channels), requiring flexible adjustment of their contribution. By setting weight coefficients based on importance proportions, each indicator can be assigned a contribution matching its importance, making the dynamic approach score more aligned with actual scenario needs. A preset normalization rule is used to normalize the three types of indicators, transforming them into standardized indicators of the same scale, eliminating fusion bias caused by differences in dimensions and numerical ranges. By using a weighted summation algorithm to fuse the normalized indicators, the resulting dynamic approach degree can comprehensively reflect the combined effect of the three types of indicators. It not only quantifies the spatial approach rate of the ship, but also reflects the consistency of the navigation direction and the adjustment trend of the speed, thus achieving a comprehensive and accurate characterization of the ship's approach degree. At the same time, the adjustability of the weight coefficients improves the adaptability of the method in different scenarios.

[0029] In some technical solutions of this application, the location data includes the ship's latitude and longitude; based on the spherical distance calculation formula, the target port coordinate data, and the location data, the rate of change of distance between the target ship and the target port is determined, including: using the semi-versus formula as the spherical distance calculation formula, and using the ship's latitude and longitude and the target port coordinate data, calculating the spherical distance between the target ship and the target port at consecutive time points; and determining the rate of change of distance based on the ratio of the difference in spherical distance between adjacent time points to the time difference.

[0030] In this technical solution, the ship's latitude and longitude refer to the geographic coordinates of the ship's real-time location, including latitude and longitude. This is the core data characterizing the ship's position and the fundamental data for calculating the spherical distance between the ship and the target port. The Haversine formula is a mathematical formula specifically used to calculate the shortest distance (great circle distance) between two points on a sphere. It derives the central angle of the sphere from the difference in latitude and longitude between the two points, and then combines this with the Earth's radius to calculate the actual distance. Adapted to the Earth's spherical model, it offers high accuracy and low complexity, making it suitable for calculating the distance between ships and ports. Continuous time points refer to two or more adjacent time nodes arranged in chronological order (such as the time points corresponding to consecutive AIS message timestamps). These are used to obtain the ship's position data at different times and then calculate distance changes. Spherical distance refers to the shortest distance between the ship and the target port on the Earth's sphere, calculated by combining the ship's latitude and longitude with the target port's coordinate data using the Haversine formula. It is the core parameter reflecting the spatial distance between the ship and the port.

[0031] The spherical distance difference between adjacent time points refers to the difference in the spherical distance between a ship and the target port calculated at two consecutive time points. A positive difference indicates that the ship is approaching the port, while a negative difference indicates that the ship is moving away from the port. The time difference refers to the time interval between two consecutive time points (such as the time difference between two AIS messages) and is one of the key parameters for calculating the rate of change of distance.

[0032] Based on the above data and steps, we can further realize the accurate and efficient calculation of the distance between the ship and the target port and the rate of change of the distance, so as to ensure that the distance-related indicators can truly reflect the spatial positional relationship and changing trend between the ship and the port, and provide reliable spatial dimension data support for the construction of dynamic proximity.

[0033] This application details the steps for determining the rate of change of distance. Since the Earth is approximately sphere, and the positions of ships and ports are expressed in latitude and longitude, traditional planar distance formulas cannot accurately calculate the actual distance between them, leading to data distortion and affecting the reliability of the rate of change of distance. By specifying the ship's latitude and longitude as the location data, a precise foundation for distance calculation is established. The semi-versus formula is used as the spherical distance calculation formula. This formula is specifically adapted to spherical coordinates and can accurately derive the spherical distance between the ship's latitude and longitude and the target port's coordinates, avoiding the errors of planar distance formulas. By obtaining the ship's latitude and longitude at consecutive time points, the spherical distance at each time point is calculated. Then, the rate of change of distance is obtained by the ratio of the difference in spherical distance between adjacent time points to the time difference. In this process, the application of the semi-versus formula ensures the accuracy of the spherical distance calculation, and the selection of consecutive time points ensures that the rate of change of distance reflects the real-time rate of the ship approaching or moving away from the port, providing a reliable spatial dimension indicator for dynamic approach, enabling dynamic approach to truly reflect the ship's spatial approach trend.

[0034] In some technical solutions of this application, determining the course change trend of a target vessel relative to a target port based on course data and target port coordinate data includes: determining the ideal course pointing to the target port based on the target port coordinate data; calculating the course deviation between the current course and the ideal course in the navigation dynamic data; determining the course change trend by the change law of the course deviation within a continuous time window; wherein, when the course deviation continuously decreases or remains within a preset range, the course change trend toward the target port is determined.

[0035] In this technical solution, the ideal course refers to the optimal navigation direction from the ship's current position to the target port coordinates. It is the reference direction for determining whether the ship's course is heading towards the port, and is derived from the target port coordinate data and the ship's current position data. Course deviation refers to the angle (usually in degrees) between the ship's current course (course data) and the ideal course. It is used to quantify the degree of deviation between the ship's actual navigation direction and the reference direction; the smaller the angle, the closer the course is to the ideal direction. A continuous time window refers to a continuous, fixed-length time interval (consistent with the "preset time window") used to analyze the variation pattern of the course deviation over a period of time, rather than the deviation value at a single point in time. The variation pattern refers to the trend of the course deviation within the continuous time window, including continuous decrease, continuous increase, maintenance within a fixed range, and irregular fluctuations. The preset range refers to a pre-set course deviation threshold range (e.g., 0° to 30°). When the course deviation is within this range, the ship's course is considered to be basically heading towards the target port.

[0036] Specifically, this application, based on the aforementioned data and steps, accurately depicts the consistency trend between the ship's navigation direction and the target port, avoiding the accidental influence of course deviation at a single point in time, ensuring that the course change trend truly reflects the ship's navigation intention, providing reliable directional dimension data support for dynamic approach determination, and improving the accuracy of arrival status assessment. This application details the steps for determining the course change trend. During navigation, ships may experience short-term course deviations due to avoiding other vessels or adjusting their navigation attitude. Judging the course trend solely based on the course deviation at a single point in time is prone to misjudgment due to accidental deviations. By determining the ideal course based on the target port coordinate data, an objective benchmark for course judgment is established, solving the problem of which direction to use as the target. Calculating the course deviation between the current course and the ideal course quantifies the degree of deviation between the actual course and the benchmark direction. Analyzing the changing patterns of the course deviation through continuous time windows filters out the accidental nature of deviations at a single point in time, highlighting the long-term trend of course change. When the course deviation continuously decreases, it indicates that the ship is adjusting its course to approach the ideal direction. When the heading deviation remains within the preset range, it indicates that the ship's heading is stable and moving towards the port, both showing a trend of heading towards the target port. However, when the heading deviation continues to increase or fluctuates significantly, it indicates that the ship's heading has deviated from the ideal direction and is not showing a trend of approaching the port. This process can accurately capture the ship's navigational intention, providing a reliable directional dimension indicator for dynamic approach, enabling dynamic approach to comprehensively reflect the ship's approaching behavior and improving the accuracy of arrival status determination.

[0037] In some technical solutions of this application, obtaining the speed change rate based on speed data includes: determining the speed data of consecutive time points in the navigation dynamic data based on the speed data; calculating the ratio of the speed difference between adjacent time points to the time difference based on the speed data to determine the speed change rate; wherein, the speed change rate is used to characterize whether the target vessel has deceleration behavior before berthing.

[0038] In this technical solution, continuous time-point speed data refers to the ship's speed values ​​acquired at consecutive time points (such as the speed SOG recorded in continuous AIS messages). This data forms the basis for calculating the rate of change of speed, reflecting the ship's speed at different times. Speed ​​difference refers to the difference between speed data at two consecutive time points; a negative difference indicates deceleration, a positive difference indicates acceleration, and a zero difference indicates constant speed. Pre-berthing deceleration refers to the ship's deliberate reduction of speed as it approaches the port and prepares to berth. This is a key characteristic of a ship arriving at port and is typically characterized by a continuous decrease in speed.

[0039] This application details the steps for obtaining the rate of change of speed. The deceleration behavior of a ship before berthing is one of the key characteristics of arrival at port, but speed data at a single point in time cannot reflect the trend of speed change (e.g., a ship traveling at a constant speed has a fixed speed but shows no deceleration trend, clearly indicating it is not in the berthing phase). By extracting speed data from consecutive time points from the speed data, the basis for speed change analysis is established. The ratio of the speed difference between adjacent time points to the time difference is calculated to obtain the rate of change of speed, quantifying the rate of change of the ship's speed. When the rate of change of speed is negative and the absolute value is large, it indicates that the ship is rapidly decelerating. When the rate of change of speed is continuously negative and the absolute value gradually decreases (or approaches zero), it indicates that the ship is gradually stabilizing after deceleration, both consistent with the speed change characteristics before berthing. When the rate of change of speed is positive or remains near zero, it indicates that the ship is not showing a deceleration trend before berthing. This process can accurately capture the dynamic adjustment of the ship's speed, especially the deceleration behavior before berthing, providing a reliable speed dimension indicator for dynamic approach, enabling dynamic approach to comprehensively reflect the ship's approach behavior and further improving the accuracy of arrival status determination.

[0040] In some technical solutions of this application, before determining the arrival status of the target vessel based on time-series characteristics, the method further includes: determining the type level and size level of the vessel according to the vessel type, tonnage data, and size data in the vessel's static attribute data; determining the statistical mean threshold of the time-series characteristics according to the type level, wherein the type level includes a first vessel type and a second vessel type, and the statistical mean threshold corresponding to the first vessel type is higher than the statistical mean threshold corresponding to the second vessel type; determining the fluctuation characteristic threshold of the time-series characteristics according to the size level, wherein the size level includes a first size level and a second size level, and the fluctuation characteristic threshold corresponding to the first size level is lower than the fluctuation characteristic threshold corresponding to the second size level; and determining the judgment threshold of the target vessel according to the statistical mean threshold and the fluctuation characteristic threshold, wherein the judgment threshold includes the statistical mean threshold and the fluctuation characteristic threshold corresponding to the expected arrival status and the already arrived status, respectively, and the duration threshold corresponding to the already arrived status.

[0041] In this technical solution, the type level is a ship category level based on the ship type and tonnage data in the ship's static attribute data, including a first ship type and a second ship type, used to distinguish ships with different deadweights and drafts (e.g., the first ship type is a ship with a large draft and high deadweight tonnage, and the second ship type is a ship with a small draft and low deadweight tonnage). The size level is a ship category level based on the size data (mainly the ship length) in the ship's static attribute data, including a first size level (ship length ≥ 150 meters) and a second size level (ship length < 150 meters), used to distinguish ships of different sizes. The statistical mean threshold refers to a pre-set critical value for the statistical mean of dynamic approach to determine the arrival status, including thresholds corresponding to the expected arrival status and the actual arrival status. Different ship type levels correspond to different statistical mean thresholds. The fluctuation characteristic threshold refers to a pre-set critical value for the fluctuation characteristics (such as standard deviation) of dynamic approach to determine the arrival status, including thresholds corresponding to the expected arrival status and the actual arrival status. Different ship size levels correspond to different fluctuation characteristic thresholds. The duration threshold refers to the minimum duration (such as 3 consecutive time windows) that is preset to confirm the "arrived" status, ensuring the stability of the "arrived" status determination and avoiding misjudgments caused by short-term data fluctuations.

[0042] Based on the above steps and data, the proposed solution can adaptively adjust the judgment threshold, enabling the arrival status judgment to be adapted to different types and sizes of ships. This solves the problem of poor adaptability of traditional fixed thresholds and further improves the versatility, robustness and accuracy of the method.

[0043] Specifically, this application adds an adaptive adjustment step for the judgment threshold before determining the arrival status based on time-series characteristics. Different types and sizes of vessels exhibit significant differences in their berthing behavior characteristics (e.g., large cargo ships and container ships (first vessel type) require a higher dynamic approach degree to confirm their arrival status. Vessels with a length ≥150 meters (first size class) have a more stable berthing status, and their fluctuation characteristic threshold should be lower). Using a fixed threshold for judgment could lead to misjudgments of some vessels (e.g., using the threshold for small vessels to judge large vessels might prematurely determine them as "arrived"). By determining the vessel type, tonnage, and size data from the vessel's static attribute data, the corresponding type and size class of the vessel are determined, achieving accurate differentiation of vessel categories. A statistical mean threshold is determined based on the type class, ensuring that vessels with greater draft and higher deadweight tonnage correspond to a higher statistical mean threshold, guaranteeing that the determination of the target vessel's arrival status matches the actual berthing characteristics. The wave characteristic threshold is determined based on size class, so that vessels with a length ≥150 meters correspond to a lower wave characteristic threshold, adapting to the more stable state of the target vessel after berthing. Finally, the statistical mean threshold, wave characteristic threshold, and duration threshold are combined to form a judgment threshold suitable for the current vessel. This process achieves adaptive adjustment of the judgment threshold, enabling the arrival status judgment to conform to the berthing behavior characteristics of different types and sizes of vessels, solving the problem of poor adaptability of traditional fixed thresholds, and further improving the versatility, robustness, and judgment accuracy of the method.

[0044] The second aspect of this application provides a device for determining the arrival status of a vessel, comprising: a first acquisition module, a first determination module, a second determination module, a third determination module, a second acquisition module, a fourth determination module, a third acquisition module, and a fifth determination module; the first acquisition module is used to acquire the navigation dynamic data and static attribute data of the target vessel, wherein the navigation dynamic data includes at least heading data, speed data, and position data; the first determination module is used to determine the target port coordinate data of the target vessel based on the static attribute data of the vessel; the second determination module is used to determine the distance change rate between the target vessel and the target port based on the spherical distance calculation formula, the target port coordinate data, and the position data; the third determination module is used to determine the heading change trend of the target vessel relative to the target port based on the heading data and the target port coordinate data; the second acquisition module is used to acquire the speed change rate based on the speed data; the fourth determination module is used to determine the dynamic approach degree based on the distance change rate, the speed change rate, and the heading change trend, wherein the dynamic approach degree is used to characterize the degree to which the target vessel approaches the target port; the third acquisition module is used to acquire the temporal characteristics of the dynamic approach degree according to a preset time window; and the fifth determination module is used to determine the arrival status of the target vessel based on the temporal characteristics.

[0045] The vessel arrival status determination device provided by this application acquires navigation dynamic data and vessel static attribute data through a first acquisition module, locks the target port coordinate data through a first determination module, and then accurately calculates the distance change rate, course change trend, and speed change rate through a second determination module, a third determination module, and a second acquisition module, respectively. A fourth determination module integrates the three types of indicators to construct a dynamic approach degree to quantify the degree of vessel approach. Finally, the third acquisition module extracts time-series features, and the fifth determination module determines the arrival status. The device achieves dynamic perception and early determination of vessel arrival status, effectively solving the problems of traditional methods relying on static thresholds, high determination delay, and lack of dynamic trend analysis. It significantly shortens the determination delay, improves the accuracy and versatility of the determination, and provides timely and reliable decision support for port scheduling and logistics docking.

[0046] A third aspect of this application provides a vessel arrival status determination apparatus, comprising: a processor and a memory, wherein the memory stores a program or instructions, and the processor, when executing the program or instructions in the memory, implements the steps of the vessel arrival status determination method as described in any of the above-described technical solutions. Therefore, the vessel arrival status determination apparatus possesses all the beneficial effects of the vessel arrival status determination method as described in any of the above-described technical solutions.

[0047] A fourth aspect of this application provides a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the ship arrival status determination method as described in any of the above-described technical solutions. Therefore, the readable storage medium possesses all the beneficial effects of the ship arrival status determination method as described in any of the above-described technical solutions.

[0048] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0049] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0050] Figure 1 This is a flowchart illustrating a method for determining the arrival status of a ship according to an embodiment of this application;

[0051] Figure 2 This is a block diagram of a PCI model based on AIS data according to an embodiment of this application;

[0052] Figure 3 This is a graph illustrating the conditions for determining when a ship is about to arrive at port, according to one embodiment of this application.

[0053] Figure 4This is one of the schematic block diagrams of a ship arrival status determination device according to an embodiment of this application;

[0054] Figure 5 This is a second schematic block diagram of a vessel arrival status determination device according to an embodiment of this application. Detailed Implementation

[0055] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0056] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Therefore, the scope of protection of this application is not limited to the specific embodiments disclosed below.

[0057] The following reference Figures 1 to 5 This application describes a method, apparatus, and readable storage medium for determining the arrival status of a ship according to some embodiments.

[0058] like Figure 1 As shown, an embodiment of this application provides a method for determining the arrival status of a ship, the steps of which include:

[0059] Step 102: Obtain the target vessel's navigation dynamic data and static attribute data, wherein the navigation dynamic data includes at least heading data, speed data, and position data;

[0060] Step 104: Determine the target port coordinates of the target vessel based on the vessel's static attribute data;

[0061] Step 106: Based on the spherical distance calculation formula, target port coordinate data, and location data, determine the rate of change of distance between the target vessel and the target port;

[0062] Step 108: Based on the heading data and target port coordinate data, determine the heading change trend of the target vessel relative to the target port;

[0063] Step 110: Obtain the rate of change of velocity based on the velocity data;

[0064] Step 112: Determine the dynamic approach degree based on the distance change rate, speed change rate, and heading change trend. The dynamic approach degree is used to characterize the degree to which the target vessel approaches the target port.

[0065] Step 114: Obtain the temporal characteristics of dynamic convergence according to the preset time window;

[0066] Step 116: Determine the arrival status of the target vessel based on the time series characteristics.

[0067] The navigation dynamic data in this application refers to the relevant data that changes in real time during the navigation of a ship. The core data includes heading data (the direction of the ship's navigation, such as heading COG), speed data (the rate of the ship's navigation, such as speed SOG), and position data (the real-time spatial coordinates of the ship, such as latitude and longitude). It may also include auxiliary data such as time series, which mainly comes from the AIS system.

[0068] Ship static attribute data refers to the inherent attribute information of a ship that does not change dynamically during navigation, including ship type, length, tonnage, destination port coordinates, etc., and is the basic characteristic data of a ship.

[0069] Target port coordinate data refers to the precise spatial coordinates (usually latitude and longitude) of the target port, which are obtained by associating with the destination port information in the ship's static attribute data. It is the core benchmark data for calculating the distance and course relationship between the ship and the port.

[0070] The spherical distance calculation formula is a mathematical formula used to calculate the shortest distance (great circle distance) between two points on a sphere. It is adapted to the Earth's spherical model. In this application, the Haversine formula is specifically used, which can accurately calculate the spatial distance between ships and ports.

[0071] The rate of change of distance is the ratio of the difference in spherical distance between a ship and a target port within a continuous time period to the corresponding time difference. It is used to quantify the rate at which a ship approaches or moves away from the port, with a positive value indicating that the ship is approaching the port.

[0072] The course change trend refers to the deviation of a ship's current course from its ideal course toward the target port. It reflects the consistency trend between the ship's sailing direction and the port, including states such as heading toward the port and deviating from the port.

[0073] The rate of change of speed is the ratio of the difference in ship speed over a continuous period of time to the corresponding time difference. It is used to characterize the dynamic changes in ship speed and can reflect whether the ship is slowing down before berthing.

[0074] Dynamic approach is a normalized index (range [0, 1]) obtained by weighted fusion of three dimensions: distance change rate, speed change rate, and heading change trend. It is used to quantitatively characterize the degree to which a ship approaches the target port. The larger the value, the higher the degree of approach.

[0075] The preset time window refers to a fixed time interval (such as 10 AIS message cycles) that is set in advance to perform time series analysis on dynamic convergence and extract features within a continuous time period, rather than instantaneous features at a single point in time.

[0076] Time-series characteristics: refer to the statistical characteristics of dynamic convergence within a preset time window, including the statistical mean (the average level of dynamic convergence within the window) and fluctuation characteristics (the degree of dispersion of dynamic convergence within the window, such as standard deviation), which are used to reflect the changing pattern of dynamic convergence.

[0077] The arrival status refers to the classification of a vessel's navigation status relative to the target port, including three core statuses: not yet arrived, expected arrival, and already arrived. This is the final determination result of this application.

[0078] Based on the above data and steps, this application can overcome the limitations of static threshold judgment, realize dynamic perception and early judgment of ship arrival status, significantly reduce judgment delay, and improve the universality and accuracy of judgment, providing timely and reliable decision-making basis for port scheduling and logistics docking.

[0079] First, a complete input dataset was constructed by acquiring navigation dynamic data and ship static attribute data. This dataset encompasses both the ship's real-time motion status and its basic characteristics, as well as target port reference information, providing data support for subsequent calculations. Next, target port coordinate data was extracted from the ship's static attribute data, establishing the core benchmarks for distance and heading calculations. Subsequently, based on the spherical distance calculation formula, combined with ship position data and target port coordinate data, the distance change rate was calculated, quantifying the ship's spatial approach speed. The heading change trend was determined using heading data and target port coordinate data, clarifying the consistency of the ship's navigation direction. The speed change rate was extracted from the speed data, capturing the ship's dynamic speed adjustment characteristics. These three factors together constitute the core dynamic indicators reflecting the ship's approaching behavior. Based on this, a dynamic approach degree was constructed by fusing these three core indicators, transforming multi-dimensional dynamic information into a unified quantitative indicator, achieving a precise characterization of the ship's approach degree. Finally, the temporal characteristics of the dynamic approach degree were extracted through a preset time window, filtering out the randomness of data at a single time point and highlighting the trend-like patterns of approaching behavior. Finally, based on the time sequence characteristics, the arrival status can be determined without waiting for the ship to come to a complete stop. The arrival trend can be identified in advance during the approach of the ship, thus avoiding the problems of high determination delay and lack of dynamic perception capability. At the same time, it is adaptable to different ship types and port environments, improving the versatility of the determination.

[0080] In some embodiments of this application, after acquiring the navigation dynamic data and static attribute data of the target vessel, the method further includes: preprocessing the navigation dynamic data, wherein the preprocessing includes at least one of removing abnormal data points, supplementing missing data, and smoothing filtering the navigation dynamic data and the static attribute data.

[0081] In this embodiment, preprocessing refers to the cleaning, correction, and optimization of the data before using navigation dynamic data for subsequent index calculations. The aim is to improve data quality and reduce noise interference. Removing outlier data points involves identifying and deleting data in the navigation dynamic data that significantly deviates from the normal range (such as abrupt changes in latitude and longitude due to AIS signal obstruction or delay, or abnormal speed spikes), preventing outlier data from affecting the calculation results. Supplementing missing data involves addressing missing items in the navigation dynamic data (such as missing speed or heading data at specific time points) through appropriate interpolation, fitting, or other methods to ensure data continuity and integrity. Smoothing filtering involves processing the navigation dynamic data (especially speed data) using specific algorithms (such as moving averages) to reduce high-frequency noise, making data changes smoother and better reflecting the true trend of ship movement.

[0082] Based on the above data and steps, the quality and reliability of input data can be further improved, reducing the interference of data noise, anomalies, and missing data on subsequent calculations. This provides a precise and continuous data source for dynamic approach calculation, temporal feature extraction, and arrival status determination, thereby improving the overall accuracy and robustness of the method. In this application, a data preprocessing step is added to the acquisition of the target vessel's navigation dynamic data and static attribute data. Because AIS data may be affected by signal obstruction, equipment failure, etc., during actual transmission, there may be abnormal data points and missing data. If used directly for calculation, it will lead to distortion of core indicators such as distance change rate and speed change rate, thus affecting the accuracy of dynamic approach and the reliability of temporal features, ultimately causing misjudgment of arrival status. By removing abnormal data points, data interference that clearly does not conform to the actual movement patterns of the vessel can be eliminated, ensuring the authenticity of the data. Supplementing missing data ensures the continuity of the data sequence, avoiding calculation interruptions or result deviations due to data breaks. Smoothing filtering of the navigation dynamic data can weaken the noise impact caused by short-term data fluctuations, making data such as speed and heading more reflective of the vessel's true movement trend. Through the above preprocessing operations, the original data that originally had quality problems was optimized into accurate, continuous, and reliable valid data, providing a high-quality data foundation for all subsequent calculation steps, reducing the risk of misjudgment from the source, and significantly improving the overall accuracy and robustness of the method.

[0083] In some embodiments of this application, determining the dynamic convergence degree based on the distance change rate, speed change rate, and heading change trend includes: setting three weight coefficients that satisfy the condition that the sum of the weights is 1, based on the importance ratio of the distance change rate, speed change rate, and heading change trend, wherein the set weight coefficients correspond to the distance change rate, speed change rate, and heading change trend, respectively; normalizing the indicators corresponding to the distance change rate, speed change rate, and heading change trend according to a preset normalization rule to obtain a normalized indicator set; and merging and calculating the normalized indicators in the indicator set according to their corresponding weight coefficients using a weighted summation algorithm to determine the dynamic convergence degree.

[0084] In this embodiment, the importance ratio refers to the relative importance of the three indicators—distance change rate, speed change rate, and heading change trend—in characterizing the ship's approach degree. This importance ratio can be obtained through historical data modeling or big data calculations, or determined by technical personnel based on factors such as the actual application scenario, ship type characteristics, and port environment. The weighting coefficient is a numerical coefficient set to reflect the importance ratio of the three indicators, ensuring that the sum of the three coefficients is 1. Each coefficient corresponds one-to-one with the distance change rate, speed change rate, and heading change trend, and is used to adjust the contribution of each indicator in the dynamic approach degree calculation. The preset normalization rule refers to a pre-set rule for a unified data scale (such as linear normalization, maximum-minimum normalization, etc.). Its purpose is to transform the indicators corresponding to the distance change rate, speed change rate, and heading change trend into the same scale (usually [0, 1]), avoiding fusion bias caused by differences in indicator dimensions and numerical ranges. The normalized index set refers to the standardized data set formed after processing the three core indicators according to preset normalization rules. It includes the normalized distance change rate, speed change rate, and heading change trend indicators. All indicators are on the same scale and can be directly weighted and fused. The weighted summation algorithm is an algorithm that multiplies each normalized indicator by its corresponding weight coefficient and then adds the products to obtain the dynamic convergence degree. It is the core algorithm for realizing multi-indicator fusion.

[0085] Based on the aforementioned data and steps, the dynamic approach score can be further improved to accurately and comprehensively reflect the degree of a ship's approach to the port. Simultaneously, it provides flexibility in constructing the dynamic approach score, allowing for adjustments to indicator weights according to different scenarios and enhancing the method's adaptability. This application refines the steps for determining the dynamic approach score. Because the dimensions and numerical ranges of the three types of indicators—distance change rate, speed change rate, and heading change trend—differ (e.g., distance change rate is measured in meters per second, and heading change trend is represented by heading deviation in degrees), direct fusion would lead to indicators with larger numerical ranges dominating, failing to fully reflect the roles of each indicator. Furthermore, the importance of each indicator varies across different scenarios (e.g., distance change rate is more important in open waters, while heading change trend is more critical in narrow channels), requiring flexible adjustment of their contribution. By setting weight coefficients based on importance proportions, each indicator can be assigned a contribution matching its importance, making the dynamic approach score more aligned with actual scenario needs. A preset normalization rule is used to normalize the three types of indicators, transforming them into standardized indicators of the same scale, eliminating fusion bias caused by differences in dimensions and numerical ranges. By using a weighted summation algorithm to fuse the normalized indicators, the resulting dynamic approach degree can comprehensively reflect the combined effect of the three types of indicators. It not only quantifies the spatial approach rate of the ship, but also reflects the consistency of the navigation direction and the adjustment trend of the speed, thus achieving a comprehensive and accurate characterization of the ship's approach degree. At the same time, the adjustability of the weight coefficients improves the adaptability of the method in different scenarios.

[0086] In some embodiments of this application, the location data includes the ship's latitude and longitude; determining the rate of change of distance between the target ship and the target port based on the spherical distance calculation formula, the target port coordinate data, and the location data includes: using the semi-versus formula as the spherical distance calculation formula, and using the ship's latitude and longitude and the target port coordinate data to calculate the spherical distance between the target ship and the target port at consecutive time points; and determining the rate of change of distance based on the ratio of the difference in spherical distance between adjacent time points to the time difference.

[0087] In this embodiment, the ship's latitude and longitude refer to the geographic coordinates of the ship's real-time location, including latitude and longitude. This is the core data characterizing the ship's position and the fundamental data for calculating the spherical distance between the ship and the target port. The Haversine formula is a mathematical formula specifically used to calculate the shortest distance (great circle distance) between two points on a sphere. It derives the central angle of the sphere from the difference in latitude and longitude between the two points, and then combines this with the Earth's radius to calculate the actual distance. Adapted to the Earth's spherical model, it offers high accuracy and low complexity, making it suitable for calculating the distance between ships and ports. Continuous time points refer to two or more adjacent time nodes arranged in chronological order (such as the time points corresponding to consecutive AIS message timestamps). These are used to obtain the ship's position data at different times and then calculate distance changes. Spherical distance refers to the shortest distance between the ship and the target port on the Earth's sphere, calculated by combining the ship's latitude and longitude with the target port's coordinate data using the Haversine formula. It is the core parameter reflecting the spatial distance between the ship and the port.

[0088] The spherical distance difference between adjacent time points refers to the difference in the spherical distance between a ship and the target port calculated at two consecutive time points. A positive difference indicates that the ship is approaching the port, while a negative difference indicates that the ship is moving away from the port. The time difference refers to the time interval between two consecutive time points (such as the time difference between two AIS messages) and is one of the key parameters for calculating the rate of change of distance.

[0089] Based on the above data and steps, we can further realize the accurate and efficient calculation of the distance between the ship and the target port and the rate of change of the distance, so as to ensure that the distance-related indicators can truly reflect the spatial positional relationship and changing trend between the ship and the port, and provide reliable spatial dimension data support for the construction of dynamic proximity.

[0090] This application details the steps for determining the rate of change of distance. Since the Earth is approximately sphere, and the positions of ships and ports are expressed in latitude and longitude, traditional planar distance formulas cannot accurately calculate the actual distance between them, leading to data distortion and affecting the reliability of the rate of change of distance. By specifying the ship's latitude and longitude as the location data, a precise foundation for distance calculation is established. The semi-versus formula is used as the spherical distance calculation formula. This formula is specifically adapted to spherical coordinates and can accurately derive the spherical distance between the ship's latitude and longitude and the target port's coordinates, avoiding the errors of planar distance formulas. By obtaining the ship's latitude and longitude at consecutive time points, the spherical distance at each time point is calculated. Then, the rate of change of distance is obtained by the ratio of the difference in spherical distance between adjacent time points to the time difference. In this process, the application of the semi-versus formula ensures the accuracy of the spherical distance calculation, and the selection of consecutive time points ensures that the rate of change of distance reflects the real-time rate of the ship approaching or moving away from the port, providing a reliable spatial dimension indicator for dynamic approach, enabling dynamic approach to truly reflect the ship's spatial approach trend.

[0091] In some embodiments of this application, determining the course change trend of a target vessel relative to a target port based on course data and target port coordinate data includes: determining an ideal course pointing to the target port based on the target port coordinate data; calculating the course deviation between the current course and the ideal course in the navigation dynamic data; determining the course change trend by the variation law of the course deviation within a continuous time window; wherein, when the course deviation continuously decreases or remains within a preset range, the course change trend toward the target port is determined.

[0092] In this embodiment, the ideal course refers to the optimal navigation direction from the ship's current position to the target port coordinates. It is the reference direction for determining whether the ship's course is heading towards the port and is derived from the target port coordinate data and the ship's current position data. Course deviation refers to the angle (usually in degrees) between the ship's current course (course data) and the ideal course. It is used to quantify the degree of deviation between the ship's actual navigation direction and the reference direction; the smaller the angle, the closer the course is to the ideal direction. A continuous time window refers to a continuous, fixed-length time interval (consistent with the "preset time window") used to analyze the variation pattern of the course deviation over a period of time, rather than the deviation value at a single point in time. Variation pattern refers to the trend of the course deviation within the continuous time window, including continuous decrease, continuous increase, maintenance within a fixed range, and irregular fluctuations. The preset range refers to a pre-set course deviation threshold range (e.g., 0° to 30°). When the course deviation is within this range, the ship's course is considered to be basically heading towards the target port.

[0093] Specifically, this application, based on the aforementioned data and steps, accurately depicts the consistency trend between the ship's navigation direction and the target port, avoiding the accidental influence of course deviation at a single point in time, ensuring that the course change trend truly reflects the ship's navigation intention, providing reliable directional dimension data support for dynamic approach determination, and improving the accuracy of arrival status assessment. This application details the steps for determining the course change trend. During navigation, ships may experience short-term course deviations due to avoiding other vessels or adjusting their navigation attitude. Judging the course trend solely based on the course deviation at a single point in time is prone to misjudgment due to accidental deviations. By determining the ideal course based on the target port coordinate data, an objective benchmark for course judgment is established, solving the problem of which direction to use as the target. Calculating the course deviation between the current course and the ideal course quantifies the degree of deviation between the actual course and the benchmark direction. Analyzing the changing patterns of the course deviation through continuous time windows filters out the accidental nature of deviations at a single point in time, highlighting the long-term trend of course change. When the course deviation continuously decreases, it indicates that the ship is adjusting its course to approach the ideal direction. When the heading deviation remains within the preset range, it indicates that the ship's heading is stable towards the port, and both are judged as a heading change trend towards the target port. However, when the heading deviation continues to increase or fluctuates significantly, it indicates that the ship's heading has deviated from the ideal direction and does not show a trend of approaching the port. This process can accurately capture the ship's navigational intention, providing a reliable directional dimension indicator for dynamic approach, enabling dynamic approach to comprehensively reflect the ship's approaching behavior and improving the accuracy of arrival status determination.

[0094] In some embodiments of this application, obtaining the speed change rate based on speed data includes: determining the speed data of consecutive time points in the navigation dynamic data based on the speed data; calculating the ratio of the speed difference between adjacent time points to the time difference based on the speed data to determine the speed change rate; wherein, the speed change rate is used to characterize whether the target vessel has deceleration behavior before berthing.

[0095] In this embodiment, continuous time-point speed data refers to the ship's speed values ​​acquired at consecutive time points (such as the speed SOG recorded in consecutive AIS messages). This data forms the basis for calculating the rate of change of speed and reflects the ship's speed at different times. Speed ​​difference refers to the difference between speed data at two consecutive time points. A negative difference indicates deceleration, a positive difference indicates acceleration, and a zero difference indicates constant speed. Pre-berthing deceleration refers to the ship's proactive speed reduction as it approaches the port and prepares to berth. This is a key characteristic of a ship arriving at port and is typically characterized by a continuous decrease in speed.

[0096] This application details the steps for obtaining the rate of change of speed. The deceleration behavior of a ship before berthing is one of the key characteristics of arrival at port, but speed data at a single point in time cannot reflect the trend of speed change (e.g., a ship traveling at a constant speed has a fixed speed but shows no deceleration trend, clearly indicating it is not in the berthing phase). By extracting speed data from consecutive time points from the speed data, the basis for speed change analysis is established. The ratio of the speed difference between adjacent time points to the time difference is calculated to obtain the rate of change of speed, quantifying the rate of change of the ship's speed. When the rate of change of speed is negative and the absolute value is large, it indicates that the ship is rapidly decelerating. When the rate of change of speed is continuously negative and the absolute value gradually decreases (or approaches zero), it indicates that the ship is gradually stabilizing after deceleration, both consistent with the speed change characteristics before berthing. When the rate of change of speed is positive or remains near zero, it indicates that the ship is not showing a deceleration trend before berthing. This process can accurately capture the dynamic adjustment of the ship's speed, especially the deceleration behavior before berthing, providing a reliable speed dimension indicator for dynamic approach, enabling dynamic approach to comprehensively reflect the ship's approach behavior and further improving the accuracy of arrival status determination.

[0097] In some embodiments of this application, before determining the arrival status of a target vessel based on time-series characteristics, the method further includes: determining the type level and size level of the vessel based on the vessel type, tonnage data, and size data in the vessel's static attribute data; determining a statistical mean threshold for the time-series characteristics based on the type level, wherein the type level includes a first vessel type and a second vessel type, and the statistical mean threshold corresponding to the first vessel type is higher than the statistical mean threshold corresponding to the second vessel type; determining a fluctuation characteristic threshold for the time-series characteristics based on the size level, wherein the size level includes a first size level and a second size level, and the fluctuation characteristic threshold corresponding to the first size level is lower than the fluctuation characteristic threshold corresponding to the second size level; and determining a judgment threshold for the target vessel based on the statistical mean threshold and the fluctuation characteristic threshold, wherein the judgment threshold includes the statistical mean threshold and the fluctuation characteristic threshold corresponding to the expected arrival status and the already arrived status, respectively, and the duration threshold corresponding to the already arrived status.

[0098] In this embodiment, the type level is a ship category level divided according to the ship type and tonnage data in the ship's static attribute data, including a first ship type and a second ship type, used to distinguish ships with different deadweights and drafts (e.g., the first ship type is a ship with a large draft and high deadweight tonnage, and the second ship type is a ship with a small draft and low deadweight tonnage). The size level is a ship category level divided according to the size data (mainly the ship length) in the ship's static attribute data, including a first size level (ship length ≥ 150 meters) and a second size level (ship length < 150 meters), used to distinguish ships of different sizes. The statistical mean threshold refers to a pre-set critical value for the dynamic approach statistical mean used to determine the arrival status, including thresholds corresponding to the expected arrival status and the actual arrival status, with different statistical mean thresholds corresponding to different ship type levels. The fluctuation characteristic threshold refers to a pre-set critical value for the dynamic approach fluctuation characteristic (e.g., standard deviation) used to determine the arrival status, including thresholds corresponding to the expected arrival status and the actual arrival status, with different fluctuation characteristic thresholds corresponding to different ship size levels. The duration threshold refers to the minimum duration (such as 3 consecutive time windows) that is preset to confirm the "arrived" status, ensuring the stability of the "arrived" status determination and avoiding misjudgments caused by short-term data fluctuations.

[0099] Based on the above steps and data, the proposed solution can adaptively adjust the judgment threshold, enabling the arrival status judgment to be adapted to different types and sizes of ships. This solves the problem of poor adaptability of traditional fixed thresholds and further improves the versatility, robustness and accuracy of the method.

[0100] Specifically, this application adds an adaptive adjustment step for the judgment threshold before determining the arrival status based on time-series characteristics. Different types and sizes of vessels exhibit significant differences in their berthing behavior characteristics (e.g., large cargo ships and container ships (first vessel type) require a higher dynamic approach degree to confirm their arrival status. Vessels with a length ≥150 meters (first size class) have a more stable berthing status, and their fluctuation characteristic threshold should be lower). Using a fixed threshold for judgment could lead to misjudgments of some vessels (e.g., using the threshold for small vessels to judge large vessels might prematurely determine them as "arrived"). By determining the vessel type, tonnage, and size data from the vessel's static attribute data, the corresponding type and size class of the vessel are determined, achieving accurate differentiation of vessel categories. A statistical mean threshold is determined based on the type class, ensuring that vessels with greater draft and higher deadweight tonnage correspond to a higher statistical mean threshold, guaranteeing that the determination of the target vessel's arrival status matches the actual berthing characteristics. The wave characteristic threshold is determined based on size class, so that vessels with a length ≥150 meters correspond to a lower wave characteristic threshold, adapting to the more stable state of the target vessel after berthing. Finally, the statistical mean threshold, wave characteristic threshold, and duration threshold are combined to form a judgment threshold suitable for the current vessel. This process achieves adaptive adjustment of the judgment threshold, enabling the arrival status judgment to conform to the berthing behavior characteristics of different types and sizes of vessels, solving the problem of poor adaptability of traditional fixed thresholds, and further improving the versatility, robustness, and judgment accuracy of the method.

[0101] In one embodiment of this application, after acquiring AIS data, the spherical distance D(t) between the ship's current position and the target port coordinates is first calculated using the Haversine formula. This distance reflects the ship's spatial proximity. Then, the rate of change of distance, ΔD / Δt, is calculated. A positive value indicates that the ship is approaching the port, a key indicator of arrival trend.

[0102] Next, the heading deviation |H| is calculated, which is the angle between the current heading and the ideal direction toward the port, to assess the consistency of the navigation direction. A smaller heading deviation often means that the ship is heading toward the port area.

[0103] At the same time, speed-related indicators, including current speed and speed change rate ΔSOG / Δt, are extracted to determine whether there is significant deceleration behavior, which is usually a sign that the ship is preparing to dock.

[0104] Finally, by combining all the indicators and assigning them the set weights, a dynamic convergence formula is formed:

[0105] ;

[0106] Among them, the dynamic convergence is PCI (Proximity Convergence Index). , and These are the PCI index calculation weights, ΔD / Δt: distance change rate (unit: nautical miles / minute), where ΔD is the distance difference between adjacent time points and Δt is the time interval between adjacent time points; a positive value indicates that the ship is approaching the port; |H|: heading deviation (unit: degrees), the angle between the current heading and the ideal direction pointing to the port, reflecting the consistency of the sailing direction; SOG: current speed (unit: knots); SOG max : Maximum speed; |H max Maximum heading deviation.

[0107] Weights satisfy + + =1, the PCI value is normalized to the range [0, 1]. The larger the PCI, the higher the degree of approach to the port. When the PCI exceeds the set threshold (e.g., 0.8) at multiple consecutive time points, the system can preliminarily determine that the ship is in the berthing stage.

[0108] Based on this, the system calculates the mean, volatility, and trend of PCI according to a fixed time window (e.g., the most recent 10 minutes or 10 AIS message cycles), forming a continuous PCI curve. Continuous characteristics reflect the dynamic process of a vessel from "approaching – decelerating – stopping." If the curve shows a stable upward trend and exceeds a set threshold, the system can output the "expected arrival" status in advance. Time-series processing effectively filters short-term data anomalies, improves identification stability, and enables the model to have predictive capabilities rather than just passive judgment. Furthermore, after acquiring continuous dynamic approach velocity (PCI) time-series data, this application makes a comprehensive judgment based on the mean level and volatility (stability) of the PCI to determine whether the vessel has arrived at port or is approaching port. The system calculates PCI once at a fixed time interval (e.g., every minute or every AIS message); and forms a continuous PCI sequence through a sliding time window (e.g., the most recent 10 AIS points, approximately corresponding to 10 minutes of data): PCI seq ={PCI t-n+1 PCI t-n+2 ..., PCI t Within this window, statistical analysis is performed on the PCI sequences to obtain the following two core metrics:

[0109] 1. Mean Indicator ;

[0110] 2. Volatility indicator (standard deviation): ;

[0111] Based on the statistical characteristics of PCI, the multi-level decision rules are defined as follows: Table 1-1:

[0112] Table 1-1

[0113]

[0114] The above data represents: the overall degree of convergence; σPCI reflects stability (smaller fluctuations indicate smoother movement); duration rules prevent misjudgments due to temporary AIS anomalies or short-term drift. Threshold setting and adjustment strategy: PCI mean threshold setting: based on actual test samples from different port areas and ship types, a range of 0.6~0.8 can be used; higher values ​​can be used for large cargo ships and container ships, and slightly lower thresholds for small ships. Volatility threshold setting: generally between 0.05~0.2, used to filter abnormal drift. Duration judgment threshold: three consecutive time windows are empirical values, which can be adjusted according to the AIS reporting frequency. The system can use configuration parameter files to allow each port to adjust the above thresholds according to the actual environment. Judgment signal output and system integration interface: the rule judgment module output results include: Status Code: 0 = not arrived, 1 = expected to arrive, 2 = arrived; timestamp and coordinate information: used for subsequent port scheduling system integration. The output mechanism is as follows: When the "expected arrival" condition is met, the system immediately generates an arrival prediction event and sends a notification to the port operation system via API interface or message queue; when the "arrived" condition is met (≥3 consecutive checks), a formal "arrival event" is generated, written to the database, and pushed to the business platform; if the PCI is below 0.5 for three consecutive time windows, the "expected arrival" flag is canceled, and the system reverts to the "not arrived" status to correct misjudgments. This process does not rely on any machine learning model and is entirely based on real-time statistics and rule-based judgment of dynamic proximity data. It can be deployed on edge computing terminals or port monitoring servers to run in real time. Rule-based judgment process overview: Collect AIS data and calculate PCI; calculate σPCI in a sliding window; judge the status step by step according to the rule table; output the arrival status and confidence coefficient; update the window to continue judgment, realizing real-time scrolling recognition.

[0115] like Figure 2As shown, the PCI model based on AIS data comprises six key modules, arranged in the order of data processing: AIS data acquisition module, data preprocessing module, core calculation module, PCI index construction module, decision module, and output module. The functions and interconnections of each module are as follows: First, the AIS data acquisition module acquires dynamic AIS data of the vessel (latitude, longitude, speed, heading, etc.) and destination information (target port coordinates), providing raw input for subsequent calculations. Next, the data preprocessing module cleans the raw data (removing outliers and supplementing missing items), eliminating data noise interference and ensuring the accuracy of the input data. Then, the core calculation module calculates three core dynamic indicators—distance change rate, speed change rate, and heading change trend—based on the preprocessed data, providing fundamental data for PCI index construction. The PCI index construction module then integrates these three core indicators according to preset weights to form a dynamic approach index (PCI) that quantifies the vessel's approach degree. Finally, the decision module, based on the temporal characteristics of the PCI index, determines the vessel's arrival status (not yet arrived, expected to arrive, already arrived) according to preset rules. Finally, the output module synchronizes the judgment results to relevant systems such as port scheduling and logistics docking through information push, providing decision support for actual business.

[0116] like Figure 3 As shown, Figure 3 The graph shows the horizontal axis as time (from 10:00 to 10:33, with 3-minute intervals, matching the regular reporting frequency of AIS messages) and the vertical axis as the PCI volatility value (i.e., the standard deviation of the PCI sequence), used to characterize the stability of ship approach behavior. The curve shows a continuous decrease in PCI volatility over time: the value is 0.22 at 10:00, then gradually decreases to 0.05 at 10:33, with the rate of decrease gradually slowing down before stabilizing. This pattern closely matches the behavioral characteristics of ships during berthing: during the voyage away from the port, ships make frequent adjustments to their course and speed, resulting in higher PCI volatility; as they approach the port and enter the berthing process, their navigation gradually stabilizes, the magnitude of course and speed adjustments decreases, and the PCI volatility continues to decline; once the ship is fully anchored, its navigation stabilizes, and the PCI volatility drops to a low level and remains stable.

[0117] Table 1-2

[0118]

[0119] As shown in Table 1-2, the "Dynamic Approach Judgment Output Table" is a concrete representation of the core judgment logic of this application. It shows the statistical characteristics of the dynamic approach index (PCI) and the correspondence between the arrival status and the ship's status throughout the entire process from "navigation" to "stable berthing", clearly reflecting the application effect of the judgment rule.

[0120] Table 1-2 contains three columns of core information: "Time Window Start," "Average PCI," "PCI Fluctuation Value," and "Status." The "Time Window Start" column specifies the start time of each analysis period (every 3 minutes apart, consistent with the regular reporting frequency of AIS messages). The "Average PCI" column represents the mean of the dynamic approach within the corresponding time window, quantifying the overall degree of vessel approach to the port during this period. The "PCI Fluctuation Value" column represents the standard deviation of the PCI within the window, reflecting the stability of vessel approach behavior. The "Status" column is the final result derived from the first two indicators combined with the judgment rules.

[0121] The data shows a continuous upward trend in the average PCI over time, gradually climbing from 0.45 at 10:00 to 0.93 at 10:33, indicating that the proximity of ships to ports is increasing. Meanwhile, the PCI fluctuation value has been decreasing from 0.22 to 0.05, reflecting a gradual stabilization of the ship's navigation status, consistent with the behavioral characteristics of "gradual approach – deceleration and adjustment – ​​stable berthing" during berthing.

[0122] The status assessment results strictly matched the above data changes: From 10:00 to 10:09, the average PCI was below 0.6 or the fluctuation value was above 0.15, indicating a "navigating" status, meaning the vessel had not yet entered the berthing process. From 10:12 to 10:15, the average PCI rose to 0.72-0.78 and the fluctuation value was between 0.12 and 0.14 (within the 0.05-0.15 range), meeting the criteria for "expected arrival," indicating the vessel had entered the stable berthing phase. From 10:18 to 10:30, the average PCI remained above 0.8 and the fluctuation value was below 0.05, indicating an "arrival assessment," at which point the vessel had essentially completed berthing. At 10:33, the average PCI remained high at 0.93 and the fluctuation value dropped to 0.05, meeting the "continuous stability" requirement of the "arrived" status, and was assessed as "stable berthing," signifying the vessel had fully berthed.

[0123] like Figure 4As shown, an embodiment of this application provides a vessel arrival status determination device 200, including: a first acquisition module 210, a first determination module 220, a second determination module 230, a third determination module 240, a second acquisition module 250, a fourth determination module 260, a third acquisition module 270, and a fifth determination module 280; the first acquisition module 210 is used to acquire the target vessel's navigation dynamic data and static attribute data, wherein the navigation dynamic data includes at least heading data, speed data, and position data; the first determination module 220 is used to determine the target port coordinate data of the target vessel based on the vessel's static attribute data; the second determination module 230 is used to determine the target port coordinate data of the target vessel based on the spherical distance calculation formula, the target port coordinate data, and the target port coordinate data. The first module uses port coordinate data and location data to determine the rate of change of distance between the target vessel and the target port; the second module uses heading data and target port coordinate data to determine the heading change trend of the target vessel relative to the target port; the third module uses speed data to obtain the rate of change of speed; the fourth module uses distance change rate, speed change rate and heading change trend to determine dynamic approach degree, wherein dynamic approach degree is used to characterize the degree to which the target vessel approaches the target port; the fifth module uses time series characteristics of dynamic approach degree according to a preset time window; and the sixth module uses time series characteristics to determine the arrival status of the target vessel.

[0124] The vessel arrival status determination device 200 provided in the embodiments of this application acquires navigation dynamic data and vessel static attribute data through the first acquisition module 210, locks the target port coordinate data through the first determination module 220, and then accurately calculates the distance change rate, heading change trend and speed change rate by the second determination module 230, the third determination module 240 and the second acquisition module 250 respectively. The fourth determination module 260 integrates the three types of indicators to construct a dynamic approach degree to quantify the degree of vessel approach. Finally, the third acquisition module 270 extracts the time series features and the fifth determination module 280 determines the arrival status. The whole device realizes dynamic perception and early determination of vessel arrival status, effectively solves the problems of traditional methods relying on static thresholds, high determination delay and lack of dynamic trend analysis, significantly shortens the determination delay, improves the accuracy and versatility of determination, and provides timely and reliable decision support for port scheduling and logistics docking.

[0125] like Figure 5 As shown, an embodiment of this application provides a ship arrival status determination device 300, including a processor 302 and a memory 304. The memory 304 stores a program or instructions. When the processor 302 executes the program or instructions in the memory 304, it implements the steps of the ship arrival status determination method as described in any of the above embodiments. Therefore, the ship arrival status determination device 300 possesses all the beneficial effects of the ship arrival status determination method as described in any of the above embodiments.

[0126] Embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the ship arrival status determination method as described in any of the above embodiments. Therefore, the readable storage medium possesses all the beneficial effects of the ship arrival status determination method as described in any of the above embodiments.

[0127] In the claims, description, and accompanying drawings of this application, the term "plural" refers to two or more objects. Unless otherwise explicitly defined, the terms "upper," "lower," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used solely for the convenience of describing this application and simplifying the descriptive process, and are not intended to indicate or imply that the device or element referred to must have the described specific orientation, or be constructed and operated in a specific orientation. Therefore, these descriptions should not be construed as limitations on this application. The terms "connection," "installation," "fixing," etc., should be interpreted broadly. For example, "connection" can be a fixed connection between multiple objects, a detachable connection between multiple objects, or an integral connection; it can be a direct connection between multiple objects or an indirect connection between multiple objects through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in this application can be understood based on the specific circumstances described above.

[0128] In the claims, description, and accompanying drawings of this application, the terms "one embodiment," "some embodiments," "specific embodiment," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of this application. In the claims, description, and accompanying drawings of this application, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0129] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining the arrival status of a ship, characterized in that, include: Acquire the target vessel's navigation dynamic data and static attribute data, wherein the navigation dynamic data includes at least heading data, speed data, and position data; Based on the ship's static attribute data, determine the target port coordinates of the target ship; Based on the spherical distance calculation formula, the target port coordinate data, and the location data, the rate of change of distance between the target vessel and the target port is determined. Based on the heading data and the target port coordinate data, determine the heading change trend of the target vessel relative to the target port; The rate of change of speed is obtained based on the speed data; Based on the distance change rate, the speed change rate, and the heading change trend, a dynamic approach degree is determined, wherein the dynamic approach degree is used to characterize the degree to which the target vessel approaches the target port; Based on a preset time window, obtain the temporal characteristics of the dynamic convergence. Based on the aforementioned time-series characteristics, the arrival status of the target vessel is determined; The determination of dynamic approach degree based on the distance change rate, the speed change rate, and the heading change trend includes: Based on the importance ratio of the distance change rate, the speed change rate, and the heading change trend, three weight coefficients are set to satisfy the condition that the sum of their weights is 1. The set weight coefficients correspond to the distance change rate, the speed change rate, and the heading change trend, respectively. According to the preset normalization rules, the indicators corresponding to the distance change rate, the speed change rate and the heading change trend are normalized respectively to obtain a normalized set of indicators. According to the weighted summation algorithm, the normalized indicators in the indicator set are fused and calculated according to their corresponding weight coefficients to determine the dynamic convergence degree; The importance percentage refers to the relative importance of the distance change rate, the speed change rate, and the heading change trend in characterizing the ship's approach degree. The importance percentage is obtained by historical data modeling or based on big data calculation. The heading change trend refers to the deviation pattern of the ship's current heading from the ideal heading toward the target port.

2. The method for determining the arrival status of a ship according to claim 1, characterized in that, After acquiring the target vessel's navigation dynamics data and static attribute data, the method further includes: The navigation dynamic data is preprocessed, wherein the preprocessing includes at least one of removing outlier data points, supplementing missing data, and smoothing filtering the navigation dynamic data and the ship static attribute data.

3. The method for determining the arrival status of a ship according to claim 1, characterized in that, The location data includes the ship's latitude and longitude; The determination of the rate of change of distance between the target vessel and the target port based on the spherical distance calculation formula, the target port coordinate data, and the location data includes: The spherical distance is calculated using the semi-sine formula, and the spherical distance between the target ship and the target port is calculated at consecutive time points using the ship's latitude and longitude and the target port's coordinate data. The rate of change of distance is determined by the ratio of the difference in spherical distance at adjacent time points to the time difference.

4. The method for determining the arrival status of a ship according to claim 1, characterized in that, The step of determining the course change trend of the target vessel relative to the target port based on the course data and the target port coordinate data includes: Determine the ideal course to the target port based on the target port coordinate data; Calculate the heading deviation between the current heading and the ideal heading in the navigation dynamic data; The trend of heading change is determined by the variation pattern of the heading deviation within a continuous time window; Specifically, when the heading deviation continuously decreases or remains within a preset range, the heading change trend toward the target port is determined.

5. The method for determining the arrival status of a ship according to claim 1, characterized in that, The step of obtaining the rate of change of velocity based on the velocity data includes: Based on the speed data, determine the speed data at consecutive time points in the navigation dynamic data; Based on the speed data, the ratio of the speed difference between adjacent time points to the time difference is calculated to determine the speed change rate; The rate of change of speed is used to characterize whether the target vessel decelerates before berthing.

6. The method for determining the arrival status of a ship according to claim 1, characterized in that, Before determining the arrival status of the target vessel based on the time-series characteristics, the method further includes: Based on the ship type, tonnage data, and size data in the ship static attribute data, determine the corresponding type class and size class of the ship; Based on the type level, a statistical mean threshold for the time series features is determined, wherein the type level includes a first ship type and a second ship type, and the statistical mean threshold corresponding to the first ship type is higher than the statistical mean threshold corresponding to the second ship type. Based on the size level, a fluctuation characteristic threshold for the time series feature is determined, wherein the size level includes a first size level and a second size level, and the fluctuation characteristic threshold corresponding to the first size level is lower than the fluctuation characteristic threshold corresponding to the second size level. The determination threshold for the target vessel is determined based on the statistical mean threshold and the fluctuation characteristic threshold. The determination threshold includes the statistical mean threshold and the fluctuation characteristic threshold corresponding to the expected arrival status and the already arrived status, respectively, as well as the duration threshold corresponding to the already arrived status.

7. A device for determining the arrival status of a ship, characterized in that, include: The first acquisition module is used to acquire the target vessel's navigation dynamic data and static attribute data, wherein the navigation dynamic data includes at least heading data, speed data and position data; The first determining module is used to determine the target port coordinates of the target vessel based on the vessel's static attribute data. The second determining module is used to determine the rate of change of distance between the target vessel and the target port based on the spherical distance calculation formula, the target port coordinate data, and the location data. The third determining module is used to determine the course change trend of the target vessel relative to the target port based on the course data and the target port coordinate data; The second acquisition module is used to acquire the rate of change of speed based on the speed data; The fourth determining module is used to determine the dynamic approach degree based on the distance change rate, the speed change rate, and the heading change trend, wherein the dynamic approach degree is used to characterize the degree to which the target vessel approaches the target port; The third acquisition module is used to acquire the temporal characteristics of the dynamic convergence according to a preset time window; The fifth determining module is used to determine the arrival status of the target vessel based on the time-series characteristics; The fourth determining module is specifically used to: set three weight coefficients that satisfy a weight sum of 1 based on the importance ratio of the distance change rate, the speed change rate, and the heading change trend, wherein the set weight coefficients correspond to the distance change rate, the speed change rate, and the heading change trend, respectively; normalize the indicators corresponding to the distance change rate, the speed change rate, and the heading change trend according to a preset normalization rule to obtain a normalized indicator set; and perform a weighted summation algorithm to fuse and calculate the normalized indicators in the indicator set according to their corresponding weight coefficients to determine the dynamic approach degree; the importance ratio refers to the relative importance of the distance change rate, the speed change rate, and the heading change trend in characterizing the ship's approach degree, and the importance ratio is obtained by historical data modeling or based on big data calculation; the heading change trend refers to the deviation change pattern of the ship's current heading relative to the ideal heading toward the target port.

8. A device for determining the arrival status of a ship, characterized in that, include: processor; A memory containing programs or instructions, wherein the processor, when executing the programs or instructions in the memory, implements the steps of the method for determining the arrival status of a ship as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method for determining the ship's arrival status as described in any one of claims 1 to 6.

Images