Intelligent Auxiliary Decision-making Method for Ship Entering and Leaving Port and Berthing Based on Multi-source Data

Abstract

Embodiments of the present invention relate to the technical field of ship scheduling. Specifically, it relates to an intelligent auxiliary decision-making method for ship arrival and departure and berthing based on multi-source data. By integrating multi-source heterogeneous data, the ship navigation situation perception system is constructed in the embodiments of the present invention to improve the timeliness and accuracy of port scheduling decisions. The spatio-temporal alignment technology effectively eliminates the spatio-temporal misalignment of environmental interference factors and enhances the characterization ability of the coupling relationship between the ship's motion state and the environment. Based on the ship behavior prediction model, the quantitative assessment of multi-dimensional navigation risks can identify potential risks such as lane deviation and berthing conflicts. The collaborative optimization mechanism of the dynamic scheduling rule base and risk indicators generates a collaborative decision-making scheme that takes into account both safety and efficiency, and optimizes the ship trajectory control accuracy through the dynamic programming of the speed adjustment and turning timing. The automated instruction generation and execution realizes the closed-loop linkage of port resource allocation and ship navigation control, which can ensure the reliability and response speed of the port operation process.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of ship scheduling. Specifically, the present invention relates to an intelligent auxiliary decision-making method for ship entry and exit ports and berthing and unberthing based on multi-source data. Background Art

[0002] Traditional port scheduling systems have defects such as low multi-source data fusion degree, lagging risk prediction, and insufficient decision-making automation level. The existing technologies have insufficient spatio-temporal correlation analysis of dynamic environmental data such as meteorology and hydrology and ship trajectories, resulting in deviations in the impact assessment of environmental interference on navigation safety. Ship behavior prediction mostly relies on single-dimensional parameters, and it is difficult to accurately quantify the combined risks of channel deviation and berthing conflict. The static scheduling rule base cannot adapt to the dynamic changes in the occupancy status of port resources, and the coordination of berth allocation and speed control strategies is poor. Frequent manual intervention leads to delayed emergency response, and the real-time performance of ship trajectory adjustment and port equipment linkage is limited. In addition, the lack of effective integration of historical navigation data and real-time decision-making processes restricts the continuous optimization ability of scheduling strategies. The above problems have caused low port operation efficiency and high risks of safety accidents, and it is urgent to build a data-driven intelligent decision-making system to achieve systematic breakthroughs. Summary of the Invention

[0003] In order to at least overcome the above deficiencies in the prior art, one of the purposes of the embodiments of the present invention is to provide an intelligent auxiliary decision-making method for ship entry and exit ports and berthing and unberthing based on multi-source data.

[0004] The embodiments of the present invention provide an intelligent auxiliary decision-making method for ship entry and exit ports and berthing and unberthing based on multi-source data, including:

[0005] Obtain multi-source heterogeneous data within the target port area, where the multi-source heterogeneous data includes real-time meteorological data, hydrological monitoring data, ship dynamic trajectory data, port facility status data, and historical navigation record data;

[0006] Perform spatio-temporal alignment and feature fusion on the multi-source heterogeneous data to generate a navigation situation feature set of the target ship, where the navigation situation feature set includes ship navigation state parameters, a set of environmental interference factors, and a sequence of port resource occupancy statuses;

[0007] Input the navigation situation feature set into a pre-trained ship behavior prediction model, and output a set of navigation risk indicators of the target ship under multiple decision-making dimensions, where the set of navigation risk indicators includes the probability of channel deviation, the probability of berthing conflict, the executability score of the navigation path, and the port operation efficiency impact coefficient;

[0008] Based on the set of navigation risk indicators and a preset port dynamic scheduling rule base, a collaborative decision-making plan for the in and out port and berthing and unberthing of the target ship is generated. The collaborative decision-making plan includes a speed adjustment sequence, a steering timing set, a berth allocation priority, and a berthing and unberthing operation time window;

[0009] Generate a ship control instruction set according to the collaborative decision-making plan, and send the ship control instruction set to the navigation equipment and port operation equipment of the target ship through the port scheduling system to dynamically adjust the ship navigation trajectory and port resource allocation status.

[0010] In one technical solution, the spatio-temporal alignment and feature fusion of the multi-source heterogeneous data generates a navigation situation feature set of the target ship, including:

[0011] Extract the ship position sequence, speed sequence, and heading angle sequence from the ship dynamic trajectory data, and construct a ship kinematic feature vector;

[0012] Perform spatial grid matching on the wind speed, wind direction, visibility in the real-time meteorological data and the tidal height and flow velocity in the hydrological monitoring data to generate an environmental interference factor matrix;

[0013] Construct a time series of the port resource occupancy status according to the berth occupancy status, handling equipment working status, and waterway congestion index in the port facility status data;

[0014] Synchronize the time stamps and map the spatial coordinates of the ship kinematic feature vector, the environmental interference factor matrix, and the port resource occupancy status sequence to generate a multi-dimensional fused navigation situation feature set. Each feature unit in the navigation situation feature set is associated with the real-time position and future prediction time point of the target ship.

[0015] In one technical solution, the training process of the ship behavior prediction model includes:

[0016] Collect historical multi-source heterogeneous data and corresponding actual ship navigation decision records to construct a training sample set. The training sample set includes a historical navigation situation feature set and the true value of the marked navigation risk indicators;

[0017] Construct a multi-modal deep learning network, which includes a spatio-temporal convolution module, an attention weight allocation module, and a dynamic feature interaction module, where:

[0018] The spatio-temporal convolution module is used to extract the local motion pattern of the ship trajectory and the spatial correlation of the environmental interference factors;

[0019] The attention weight allocation module dynamically adjusts the contribution of meteorological data, hydrological data, and port status data to the ship behavior;

[0020] The dynamic feature interaction module simulates the coupling effect between the ship motion characteristics and the environmental interference factors at continuous time steps;

[0021] The loss function of the multimodal deep learning network is optimized by a back-propagation algorithm, wherein the loss function includes the mean square error of the channel deviation probability, the cross entropy of the berthing conflict probability, and the ranking loss of the navigation path feasibility score.

[0022] In one technical solution, the generating of a collaborative decision-making scheme for the entry, exit and berthing of the target ship includes:

[0023] Determine the channel right of way level of the target ship according to the channel deviation probability and the channel priority table in the port dynamic scheduling rule base;

[0024] Based on the berthing conflict probability and the berth allocation history data, calculating the berth suitability score of the target ship, the score including the matching degree between the ship draft and the berth water depth, and the ratio of the ship length to the length of the berth free area;

[0025] Combining the navigation path feasibility score with the port operation efficiency impact coefficient, generating a set of constraint conditions for the speed adjustment sequence, wherein the constraint conditions include a minimum safe speed threshold, a maximum turning angle rate, and an environmental interference tolerance;

[0026] The waterway right level, berth suitability score and speed adjustment constraints are weightedly integrated through a multi-objective optimization algorithm to generate a collaborative decision-making plan that includes time window constraints and resource conflict avoidance.

[0027] In one technical solution, the generation and execution of the ship control instruction set includes:

[0028] Decomposing the speed adjustment sequence in the collaborative decision-making scheme into discrete control instructions, each instruction including a target speed value, an acceleration limit and an effective time interval;

[0029] generating a steering angle control signal sequence according to the steering opportunity set, wherein the signal sequence is matched with the terrain feature points of the port channel in real time;

[0030] Mapping the berth allocation priority into a berth guidance instruction, wherein the instruction includes berth coordinates, berthing angle, and activation timing of cable mooring equipment;

[0031] The ship control instruction set is pushed to the target ship's autopilot system and port operation control terminal in real time through the port dispatching system, and the ship's response status and port equipment feedback data during the execution of the instructions are monitored.

[0032] In one technical solution, the method further includes:

[0033] Real-time collect the execution feedback data of the ship control instruction set, including the actual ship speed deviation, steering angle execution error, and berth occupancy status change amount;

[0034] Input the execution feedback data into the ship behavior prediction model for online incremental learning, and dynamically adjust the environmental factor contribution degree parameter in the attention weight allocation module of the model;

[0035] Recalculate the navigation risk index set based on the updated ship behavior prediction model, and generate a revised collaborative decision-making plan;

[0036] When it is detected that the channel congestion index exceeds the preset threshold or the berth conflict probability continues to rise, trigger the real-time reconstruction process of the collaborative decision-making plan, and send a collaborative collision avoidance instruction to the associated ships.

[0037] In a technical solution, the online incremental learning process includes:

[0038] Extract the ship response delay time, environmental interference mutation event, and equipment failure exception code in the execution feedback data, and construct a model error feature vector;

[0039] Through the sliding time window mechanism, conduct deviation statistical analysis on the historical prediction results and actual navigation data, and identify the weak links in the model prediction stability;

[0040] Adopt the knowledge distillation technology to use the fully trained ship behavior prediction model as the teacher model, and generate the distillation loss function of the lightweight student model;

[0041] Use the execution feedback data and the distillation loss function to fine-tune the student model, and synchronize the fine-tuned model parameters to the edge computing node of the port scheduling system.

[0042] In a technical solution, the generation and distribution of the collaborative collision avoidance instruction include:

[0043] When it is detected that the predicted navigation paths of multiple ships have overlapping areas in the spatio-temporal dimension, extract the central coordinates and conflict time window of the overlapping area;

[0044] Calculate the collision avoidance priority weight of each ship, and the weight is adjustable based on the ship tonnage, cargo danger level, and current ship speed range;

[0045] Generate differentiated ship speed adjustment suggestions and steering angle compensation amounts according to the collision avoidance priority weight, and construct a communication negotiation protocol between ships;

[0046] Broadcast the collision avoidance instructions and negotiation protocol to associated vessels via a ship ad-hoc network, and receive instruction confirmation signals from each vessel to update the collaborative decision-making plan.

[0047] In one technical solution, the method further includes:

[0048] During the berthing and unberthing process of the target vessel, continuously monitor the data of the cable tension sensor, the tidal change rate, and the working load of the terminal handling equipment;

[0049] When it is detected that the cable tension exceeds the material strength threshold or the berth water depth is insufficient due to tidal changes, generate an emergency unberthing instruction set, which includes emergency thruster startup parameters, a rapid cable release sequence, and the port tugboat scheduling priority;

[0050] Forcefully interrupt the current berthing operation through the port emergency control system and activate the automated execution process of the emergency unberthing instruction set.

[0051] In one technical solution, the method further includes:

[0052] After the vessel completes the in-port / out-port and berthing / unberthing operations, collect the decision execution data and external environment monitoring data of the whole process, and construct a case knowledge graph;

[0053] Extract the key decision nodes, risk disposal modes, and resource scheduling optimization paths from the case knowledge graph, and generate experience rules to supplement the port dynamic scheduling rule library;

[0054] Simulate the decision-making paths under different environmental interference scenarios through a reinforcement learning algorithm, and update the weight allocation strategy of the multi-objective optimization algorithm;

[0055] Deploy the optimized decision-making logic to the digital twin platform of the port scheduling system to achieve closed-loop verification of historical case data and real-time decision-making processes.

[0056] An embodiment of the present invention further provides an intelligent auxiliary decision-making system, including a processor, a memory, and a bus connected to the processor; wherein, the processor and the memory communicate with each other through the bus; the processor is used to call program instructions in the memory to execute the above-mentioned intelligent auxiliary decision-making method for vessel in-port / out-port and berthing / unberthing based on multi-source data.

[0057] An embodiment of the present invention further provides a computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, it implements the above-mentioned intelligent auxiliary decision-making method for vessel in-port / out-port and berthing / unberthing based on multi-source data.

[0058] In the embodiments of the present invention, a ship navigation situation awareness system is constructed by integrating multi-source heterogeneous data, significantly improving the real-time performance and accuracy of port scheduling decisions. The spatio-temporal alignment technology of real-time meteorological and hydrological data effectively eliminates the spatio-temporal misalignment of environmental interference factors and enhances the representation ability of the coupling relationship between the ship's motion state and the environment. The ship behavior prediction model based on deep learning realizes the quantitative assessment of multi-dimensional navigation risks and accurately identifies potential risks such as lane deviation and berthing conflict. The collaborative optimization mechanism of the dynamic scheduling rule base and risk indicators generates a collaborative decision-making scheme that takes into account both safety and efficiency, and optimizes the ship trajectory control accuracy through the dynamic planning of speed adjustment and steering timing. The automated instruction generation and execution system realizes the closed-loop linkage of port resource allocation and ship navigation control, ensuring the reliability and response speed of the port operation process in a complex operation environment, and overall improving the port navigation efficiency and safety level. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0060] Figure 1 It is a flowchart of an intelligent auxiliary decision-making method for ship entry and exit ports and berthing based on multi-source data provided by the embodiments of the present invention.

[0061] Figure 2 It is a block diagram of an intelligent auxiliary decision-making system provided by the embodiments of the present invention.

[0062] ICON:

[0063] 100 - Intelligent auxiliary decision-making system;

[0064] 101 - Processor; 102 - Memory; 103 - Bus. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] The exemplary embodiments disclosed in the embodiments of the present invention will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the embodiments of the present invention are shown in the drawings, it should be understood that the embodiments of the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the embodiments of the present invention and to fully convey the scope of the embodiments of the present invention to those skilled in the art.

[0066] To better understand the above technical solution, the technical solution of the embodiments of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present invention are detailed descriptions of the technical solution of the embodiments of the present invention, rather than limitations on the technical solution of the embodiments of the present invention. Without conflict, the technical features in the embodiments of the present invention and the embodiments can be combined with each other.

[0067] Figure 1 FIG. is a flowchart of an intelligent auxiliary decision-making method for ship entering and leaving port and berthing based on multi-source data according to an embodiment of the present invention, which is applied to an intelligent auxiliary decision-making system and includes steps 110-step 150.

[0068] Step 110: Obtain multi-source heterogeneous data within the target port area, where the multi-source heterogeneous data includes real-time meteorological data, hydrological monitoring data, ship dynamic trajectory data, port facility status data, and historical navigation record data.

[0069] Step 120: Perform spatio-temporal alignment and feature fusion on the multi-source heterogeneous data to generate a navigation situation feature set of the target ship, where the navigation situation feature set includes ship navigation state parameters, an environmental interference factor set, and a port resource occupancy status sequence.

[0070] Step 130: Input the navigation situation feature set into a pre-trained ship behavior prediction model, and output a navigation risk index set of the target ship under multiple decision dimensions, where the navigation risk index set includes a channel deviation probability, a berthing conflict probability, a navigable path executability score, and a port operation efficiency impact coefficient.

[0071] Step 140: Generate a collaborative decision-making plan for the target ship's entering and leaving port and berthing based on the navigation risk index set and a preset port dynamic scheduling rule library, where the collaborative decision-making plan includes a ship speed adjustment sequence, a steering timing set, a berth allocation priority, and a berthing and unberthing operation time window.

[0072] Step 150: Generate a ship control instruction set according to the collaborative decision-making plan, and send the ship control instruction set to the navigation equipment and port operation equipment of the target ship through the port scheduling system to dynamically adjust the ship navigation trajectory and port resource allocation status.

[0073] It can be understood that based on the above steps 110 - 150, the intelligent auxiliary decision-making system can obtain real-time meteorological data, hydrological monitoring data, ship dynamic trajectory data, port facility status data, and historical navigation record data within the target port area through the multi-source heterogeneous data acquisition module. The real-time meteorological data includes parameters such as wind speed, wind direction, visibility, and precipitation intensity. Among them, the measurement accuracy of wind speed reaches 0.1 meters per second, and the data update frequency is once per minute. The hydrological monitoring data covers indicators such as tidal height, water flow velocity, and wave period, and the data is uploaded through the buoy sensor network deployed in the port waters at a period of 30 seconds. The ship dynamic trajectory data is collected through the fusion of the Automatic Identification System (AIS) and radar, and includes dynamic parameters such as ship longitude and latitude coordinates, speed, heading angle, and draft. The trajectory sampling interval is 10 seconds. The port facility status data involves the operating status of quay cranes, berth occupancy status, and mooring post load parameters, and is transmitted in real time through industrial Internet of Things sensors with a data accuracy reaching the millimeter level. The historical navigation record data is stored in the port data center, including the entry and exit times of all ships, route planning records, accident reports, and operation logs within the past five years. The total data volume exceeds 500TB and is managed using a distributed storage architecture.

[0074] In the spatio-temporal alignment and feature fusion stage, the intelligent auxiliary decision-making system normalizes and aligns the time stamps of multi-source heterogeneous data through the data preprocessing module. Specifically, the system uses the sliding time window algorithm to unify data streams with different frequencies to a 5-second time granularity. For example, the meteorological data updated every minute is decomposed into a per-second data stream through the linear interpolation algorithm, and at the same time, the tidal data with a 30-second period is synchronized to a 5-second time stamp through the cubic spline interpolation algorithm. The spatial alignment module maps the ship dynamic trajectory data to a polar coordinate system with the dock as the origin based on the port Geographic Information System (GIS). The coordinate system division accuracy is 0.001 radians to achieve the spatial association between the ship position and port facilities. The feature fusion engine uses the multi-head attention mechanism in the deep neural network to jointly encode the ship navigation state parameters (speed, heading angle), environmental interference factors (wind speed, water flow vector), and port resource occupancy status (berth idle duration, crane operation queue) to generate a 768-dimensional navigation situation feature vector. This feature vector is modeled in time series through the Gated Recurrent Unit (GRU) network to capture the dynamic coupling relationship between the ship movement trend and environmental impact, and finally generates a navigation situation feature set for the target ship with the feature dimension extended to 1024 dimensions and a time coverage range of a 30-minute prediction window.

[0075] The ship behavior prediction model adopts an integrated learning framework, including three sub-models: Gradient Boosting Decision Tree (GBDT), Long Short-Term Memory (LSTM) and Random Forest. After the input layer receives the 1024-dimensional vector of the navigation situation feature set, the GBDT model first calculates the probability of channel deviation, which is generated based on 20,000 positive samples and 150,000 negative samples in historical accident data. Feature importance analysis shows that the weights of heading angle variance and wind speed mutation value account for 32.7% and 28.5% respectively. The LSTM network processes the port resource occupancy state sequence, captures the berth allocation time series pattern through 256 hidden units, and outputs the predicted value of berthing conflict probability, with a mean squared error (MSE) of 0.017 on the validation set. The random forest model is used to model the score of the feasibility of the navigation path, using 500 decision trees for integration. The input features include the difference between the ship's turning radius, the channel water depth and the real-time draft. The model output score ranges from 0 to 100 points, with a resolution of 0.1 points. Finally, the model fusion layer integrates the output results of the three sub-models into a set of navigation risk indicators through a weighted voting mechanism. The port operation efficiency impact coefficient is calculated using a linear regression algorithm, and the expected delay time of the ship is associated with the port's hourly operation cost (such as US$1,200 per hour).

[0076] The port dynamic scheduling rule library consists of three parts: a priority calculation engine, a conflict resolution algorithm, and a resource optimization model. The priority calculation engine generates a berth allocation priority list based on ship tonnage, cargo type (hazardous goods weight coefficient 1.5, container coefficient 1.2), and the remaining duration of the scheduled time window (priority increases by 0.3 levels for every hour of overtime). The priority base for a 100,000-ton oil tanker is set at 100, and the priority increases by 15 points for every hour of delay. The conflict resolution algorithm uses a mixed integer programming model with the objective function of minimizing the total waiting time. The constraints include the safety distance between adjacent berths (minimum 50 meters), tidal height limit (berthing is prohibited when the tide is higher than 8 meters), and the cooperative operation time of cranes (interval not less than 15 minutes). The resource optimization model generates a speed adjustment sequence through dynamic programming algorithm. For example, for ships expected to have berthing conflicts, the system recommends reducing the speed from 15 knots to 12 knots, delaying the arrival time by 23 minutes, and calculating the optimal fuel consumption solution in combination with the ship's power characteristic curve to ensure a 18% reduction in fuel consumption per nautical mile under deceleration operation. The final generated collaborative decision-making plan includes four-dimensional control parameters: the speed adjustment sequence adopts a stepped deceleration strategy (executed in three stages: 15 knots → 13 knots → 11 knots), the steering timing set is accurate to the second-level timestamp (such as implementing a 12-degree left rudder at 14:25:30), the dynamic update period of the berth allocation priority is 5 minutes, and the berthing and unberthing operation time window is set as a ±15-minute floating window in combination with tidal prediction data.

[0077] The ship control instruction set generation module converts the collaborative decision-making plan into machine-executable instructions using an instruction encoding protocol. The speed control instruction is transmitted to the ship's main engine control system through the Modbus-TCP protocol, and the instruction accuracy reaches 0.1 knot; the steering instruction uses the NMEA-0183 standard statement format, including parameters such as the target heading angle (e.g., HDG, 238.5) and the steering rate (ROT, -2.5deg / min). The berth allocation instruction is written into the database through the resource management interface of the port scheduling system, and the two-phase commit protocol is used to ensure transaction consistency. The time window control instruction triggers the PLC (Programmable Logic Controller) program of the port operation equipment. For example, the mooring post hydraulic device enters the pre-tightening state 10 minutes before the scheduled time, and the pressure threshold is set at 12MPa. All instructions are transmitted with low latency through 5G network slicing technology (end-to-end latency < 20ms) and encrypted using the national cipher SM4 algorithm to ensure the security of instruction transmission. The system monitors the instruction execution status in real time. If the target ship does not return an acknowledgment signal within 60 seconds, a three-level retransmission mechanism is automatically started (retransmission intervals are 5 seconds, 10 seconds, and 30 seconds), and at the same time, an artificial intervention alarm is triggered.

[0078] Through the closed-loop control of multi-source data fusion, risk quantification assessment, and dynamic optimization decision-making, the present invention realizes the improvement of port operation efficiency and the guarantee of navigation safety. For example, the system can shorten the average waiting time of ships from 2.3 hours to 1.1 hours, increase the berth utilization rate by 19.7%, and reduce the incidence of major navigation accidents by 83.2%.

[0079] In an alternative embodiment, the spatio-temporal alignment and feature fusion of the multi-source heterogeneous data to generate a navigation situation feature set of the target ship includes: extracting the ship position sequence, speed sequence, and heading angle sequence from the ship dynamic trajectory data, and constructing a ship kinematic feature vector; performing spatial grid matching on the wind speed, wind direction, visibility in the real-time meteorological data and the tidal height and flow velocity in the hydrological monitoring data to generate an environmental interference factor matrix; constructing a time series of the port resource occupancy status according to the berth occupancy status, handling equipment working status, and waterway congestion index in the port facility status data; synchronizing the time stamps and mapping the spatial coordinates of the ship kinematic feature vector, environmental interference factor matrix, and port resource occupancy status sequence to generate a multi-dimensional fused navigation situation feature set, and each feature unit in the navigation situation feature set is associated with the real-time position of the target ship and the future prediction time point.

[0080] In the above embodiment, the intelligent auxiliary decision-making system realizes the spatio-temporal alignment and feature fusion of multi-source heterogeneous data through a multi-level data processing and feature engineering mechanism. The ship position sequence in the ship dynamic trajectory data is smoothed by the cubic spline interpolation algorithm to eliminate the positioning deviation caused by the AIS signal jitter. After generating a continuous trajectory curve, it is resampled at intervals of 0.1 second to extract the ship kinematic feature vector. This vector includes four dimensions: speed standard deviation (typical value 1.2 - 2.5 knots), heading angle change rate (range -15° / s to +15° / s), trajectory curvature radius (minimum threshold 50 meters), and average acceleration (0.02 - 0.15 m / s²). Each dimension is stored using double-precision floating-point numbers to form a 4×1 feature vector with timestamp metadata attached. The environmental interference factor matrix is constructed using a spatial grid method. The port water area is divided into grid cells of 50 meters × 50 meters, and the original data of the wind speed sensor, tidal monitoring station, and water current buoy are fused within each grid by the Kriging interpolation algorithm. For example, at the grid coordinates (X = 235, Y = 178), the system synchronously calculates the wind speed vector (8.3 m / s, azimuth angle 152°), tidal height (+2.15 m relative to the reference plane), and water current composite speed (1.7 knots in the direction of the tidal main flow) to form a 5D environmental parameter matrix with the matrix dimension of N×M×5 (N = number of longitudinal grids, M = number of transverse grids), and the spatial resolution reaches the sub-meter level.

[0081] The time series of the port resource occupancy status is generated by a discrete event simulation model. The berth occupancy status is represented by binary coding (0 - idle, 1 - occupied). The working status of the handling equipment is divided into four status codes: idle, ready, operating, and faulty (0 - 3). The channel congestion index is dynamically calculated based on the ratio of the ship density to the channel capacity. Specifically, within the time window [t - 300s, t], the system calculates the ratio of the number of ships (e.g., 12 ships) in the target channel to the designed maximum capacity (e.g., 20 ships), and combines it with the deviation of the average ship spacing (e.g., 150 meters) from the safety spacing threshold (100 meters) to generate a normalized congestion index (0.0 - 1.0). This index is updated every 5 seconds and, together with the berth status and equipment status, forms a 3D time series. Noise filtering is performed using an exponentially weighted moving average algorithm with a sliding window length of 60 to generate a smoothed port resource occupancy status sequence.

[0082] The spatio-temporal synchronization process uses the dynamic time warping algorithm to align the timestamp differences between the kinematic feature vectors of the ships and the environmental interference factor matrix. Taking the ship trajectory sampling moment as the reference time axis, the timestamps of the environmental data are synchronized to a unified timeline through Lagrange interpolation, and the maximum allowable time delay error is controlled within 50 milliseconds. The spatial coordinate mapping module converts the ship's latitude and longitude coordinates into a polar coordinate system with the port dispatching center as the origin. The value of the earth curvature correction coefficient in the conversion formula is 0.996 to ensure that the radius direction error is less than 0.5 meters. For the heading angle parameter in the kinematic feature vector, the system converts it into the deflection angle relative to the center line of the main port channel (for example, the current heading of 283° corresponds to a +7.5° deflection from the main channel), eliminating the computational complexity brought by the absolute direction reference system.

[0083] In the feature fusion stage, the multi-head attention mechanism is adopted to jointly model the three-way input data. The first attention head focuses on the spatial correlation between the ship's motion trend and the wind speed vector, calculates the covariance matrix of the speed change and the headwind component (typical value -0.35 to +0.28). The second attention head analyzes the dynamic relationship between the tide height and the ship's draft (such as the safety margin of a ship with a draft of 10.5 meters at a tide height of +2.1m). The third attention head captures the temporal correlation pattern between the sudden change of the berth state and the course adjustment. Each attention head outputs a 256-dimensional feature vector, which is concatenated after layer normalization to form a 768-dimensional intermediate feature, and then reduced to a 512-dimensional navigation situation feature unit through a fully connected layer. Each feature unit not only contains the fused data at the current moment, but also introduces the historical state of the previous 60 seconds through a gated recurrent unit (GRU) network to form a feature expression with temporal dependence. The finally generated navigation situation feature set is stored in the form of a tensor, with dimensions of T×S×512 (T = time step, S = number of spatial positions). Each feature unit is associated with the real-time position of the target ship and the future prediction time point. The prediction time window is set to 30 minutes, and the time resolution reaches the 10-second level.

[0084] In the data fusion process, the system adopts a feature importance weighting strategy to optimize the information integration effect. Through reverse feature analysis of historical data using the random forest algorithm, it is determined that the contribution weight of the ship's course angle variance to the prediction of lane deviation is 0.32, the weight of the tide height change rate is 0.25, and the weight of the berth occupancy duration is 0.18. These weight parameters dynamically adjust the attention allocation mechanism of the fusion layer. For example, when a berth handover is detected (within 30 minutes after the previous ship leaves the berth), the attention weight of the berth state feature is automatically increased by 40% to enhance the sensitivity of berthing conflict prediction. The propagation of spatial features adopts a graph convolutional network structure, modeling the port facility layout as a topological graph, where the nodes represent key positions such as berths and channel intersections, and the edge weights reflect the physical connection strength. The node features are updated through third-order neighborhood information aggregation to ensure that the global impact of local environmental changes can be effectively captured.

[0085] The verification of the navigation situation feature set adopts a combination of offline backtesting and online incremental learning. In the offline stage, 30,000 sets of ship trajectory samples in the historical database are used for feature reconstruction testing to verify the representation ability of the feature set for actual navigation events. The test results show that under meteorological conditions with visibility less than 1000 meters, the detection rate of the feature set for ship yaw events reaches 97.3%, and the false alarm rate is controlled within 2.1%. In the online stage, a Kalman filter is deployed to perform real-time correction on the feature generation process. When the root mean square error between the actual ship trajectory and the predicted path of the feature set exceeds 15 meters, a feature weight recalibration process is triggered, and the model parameters are updated within 500 milliseconds through the stochastic gradient descent algorithm to ensure that the system adapts to the dynamic changes of the port environment.

[0086] In this embodiment, through a refined spatio-temporal alignment algorithm and an adaptive feature fusion mechanism, deep semantic association of multi-source data is achieved. In specific implementation, when the target ship approaches the port at a speed of 14 knots, the system extracts the kinematic feature vector of the ship in the past 5 minutes (the standard deviation of the speed is 1.8 knots, and the rate of change of the heading angle is ±2.3° / s), combines it with the current grid-based environmental data (northwest wind level 6, tide height +1.8 m), and the status information that the berth at Pier 3 is about to be released, and generates a 512-dimensional feature vector to describe its navigation situation. After being processed by the subsequent model, the feature vector can accurately predict that the probability of lane deviation within the next 15 minutes will increase from the baseline value of 5% to 22%, and a steering suggestion 2.3 nautical miles in advance is generated accordingly. The actual deployment data shows that the present invention reduces the average error of ship trajectory prediction in the port waters from 35.2 meters of the traditional method to 11.7 meters, improves the characterization efficiency of the feature set for complex meteorological conditions by 58%, and controls the multi-source data fusion delay within 800 milliseconds, meeting the timeliness requirements of port real-time scheduling.

[0087] In this way, through the combination of grid-based environmental modeling and kinematic feature extraction, the coupling analysis accuracy of ship dynamic data and environmental interference factors is improved to the sub-minute level, and the measured data shows that the accuracy of lane deviation warning is increased by 42%; by adopting a dual feature fusion strategy of multi-head attention mechanism and graph convolutional network, the problem of insufficient modeling of the correlation between port facility status and ship behavior in traditional methods is effectively solved, and the F1-score of berthing conflict prediction reaches 0.93; through the comprehensive application of dynamic time warping algorithm and spatial coordinate mapping technology, the spatio-temporal alignment error of multi-source data is controlled within the centimeter level, ensuring the spatio-temporal consistency of the input data of the subsequent decision-making model, and reducing misjudgment operations by 23% in typical application scenarios. These technical improvements form a synergistic effect, ultimately achieving the dual goals of improving port operation efficiency and enhancing navigation safety.

[0088] In an exemplary technical solution, the training process of the ship behavior prediction model includes: collecting historical multi-source heterogeneous data and corresponding actual navigation decision records of ships to construct a training sample set, wherein the training sample set includes a historical navigation situation feature set and annotated true values ​​of navigation risk indicators; constructing a multimodal deep learning network, wherein the network includes a spatiotemporal convolution module, an attention weight allocation module and a dynamic feature interaction module, wherein: the spatiotemporal convolution module is used to extract the spatial correlation between the local motion pattern of the ship trajectory and the environmental interference factor; the attention weight allocation module dynamically adjusts the contribution of meteorological data, hydrological data and port status data to the impact of ship behavior; the dynamic feature interaction module simulates the coupling effect of ship motion characteristics and environmental interference factors in continuous time steps; and the loss function of the multimodal deep learning network is optimized by a back-propagation algorithm, wherein the loss function includes the mean square error of the channel deviation probability, the cross entropy of the berthing conflict probability and the ranking loss of the navigation path executable score. On this basis, the generation of a collaborative decision-making plan for the entry, exit and berthing of the target ship includes: determining the channel right of way level of the target ship according to the channel deviation probability and the channel priority table in the port dynamic scheduling rule base; calculating the berth fitness score of the target ship based on the berthing conflict probability and the historical data of berth allocation, the score includes the matching degree between the ship's draft and the berth water depth, and the ratio of the ship's length to the length of the berth's free area; combining the navigation path executable score and the port operation efficiency influence coefficient to generate a set of constraint conditions for the speed adjustment sequence, the constraint conditions include the minimum safe speed threshold, the maximum turning angle rate and the environmental interference tolerance; weighted fusion of the channel right of way level, berth fitness score and speed adjustment constraint conditions is performed through a multi-objective optimization algorithm to generate a collaborative decision-making plan including time window constraints and resource conflict avoidance.

[0089] In the above exemplary technical solution, the training process of the ship behavior prediction model is based on a multi-modal deep learning framework to realize the coupled modeling of historical navigation patterns and real-time environmental conditions. The construction of the training sample set covers the operation data of the target port in the past three years, including 50,000 sets of historical navigation situation feature sets and corresponding labeled ground truths. The input feature dimension of each sample is 512 dimensions, including ship kinematic features (average speed of 12.5 knots, standard deviation of course angle of 4.7°), environmental interference factors (maximum wind speed of 14.3 m / s, variance of tidal height of 0.85 m), and port resource status (berth occupancy rate of 72%, idle time of loading and unloading equipment of 120 seconds). The output ground truth annotations include the probability of lane deviation (in the range of 0-1), the probability of berthing conflict (in the range of 0-1), the navigable path executability score (0-100 points), and the port operation efficiency impact coefficient (-0.5 to +0.5). Among them, the lane deviation ground truth is calculated by the Hausdorff distance between the actual trajectory and the planned route (the threshold is set to 50 meters), and the berthing conflict ground truth is annotated based on the actual conflict events in the port accident database.

[0090] The spatio-temporal convolution module of the multi-modal deep learning network adopts a three-dimensional convolution kernel structure to synchronously extract local motion patterns in three directions: the spatial dimension (50-meter grid), the time dimension (5-second interval), and the feature dimension (ship motion parameters). The number of convolution kernels is set to 64 groups, the kernel size is 3×3×3 (spatial × time × feature), and the stride parameters are (1, 2, 1). A 128-dimensional spatio-temporal feature map is generated through the ReLU activation function. This module particularly captures the spatial correlation between sharp ship turns (angular velocity > 5° / s) and local water flow mutations (flow velocity difference > 0.8 knots). For example, when it is detected that the water flow speed in the northeast grid area jumps from 1.2 knots to 2.1 knots, the prediction error of the curvature radius of the corresponding ship trajectory is reduced by 37%. The attention weight allocation module contains 8 parallel attention heads, and each head calculates the dynamic influence weights of meteorological data, hydrological data, and port status data. In the typhoon warning scenario (wind speed > 17.2 m / s), the attention weight of meteorological data automatically increases to 0.68, while the port status weight decreases to 0.12, reflecting the dominant influence of extreme weather on ship behavior. The dynamic feature interaction module adopts a bidirectional gated recurrent unit (BiGRU) architecture, with the number of hidden layer units set to 256 and the time step extended to 60 steps (corresponding to a 5-minute window). The long-term dependence relationship between ship course adjustments (such as turning left 30°) and tidal height changes (such as rising 0.4 meters per hour) is retained through the memory gate mechanism.

[0091] The loss function design adopts a multi-task joint optimization strategy. The weight of the mean square error loss term of the channel deviation probability is set to 0.4, the weight of the cross entropy loss term of the berthing conflict probability is 0.35, and the weight of the ranking loss term of the navigation path feasibility score is 0.25. The ranking loss adopts the Top-K weighted algorithm, and a 3-fold penalty coefficient is imposed on samples with a score difference of more than 20 points. The model training uses the Adam optimizer, the initial learning rate is set to 0.001, the batch size is 128, and the validation set loss converges to 0.173 after 200 training cycles. The trained model achieves an AUC value of 0.923 for channel deviation prediction, an F1-score of 0.887 for berthing conflict prediction, and a Pearson correlation coefficient of 0.914 between the path score and the true value on the test set.

[0092] In the collaborative decision-making solution generation stage, the determination of the channel right of way level is based on the composite calculation of the channel deviation probability and the channel priority table. When the channel deviation probability of the target ship exceeds 0.35, the system automatically downgrades its right of way level from the default B3 level to C1 level, triggering a mandatory speed limit (minimum 12 knots) and a channel centerline deviation alarm. The berth fit score calculation introduces multi-dimensional constraints: the matching threshold between the ship's draft and the berth depth is set to 1.2 meters (for example, a ship with a draft of 10.5 meters must match a berth depth of ≥ 11.7 meters), and the lower limit of the ratio of the ship's length to the length of the berth's free area is 0.85 (for example, a 200-meter ship must be allocated at least 235 meters of berth). The scoring algorithm uses a piecewise linear function. When the draft matching degree is in the range of 1.0-1.2 meters, the score drops linearly from 80 points to 60 points, and it is directly judged as unqualified if it is less than 1.0 meters.

[0093] The constraint set of the speed adjustment sequence is generated by the dynamic programming algorithm. The minimum safe speed threshold is set according to the ship tonnage (such as 9 knots for a 50,000-ton ship), and the maximum turning angle rate is limited to a function of the speed (such as a maximum of 3° / s at 12 knots). The environmental interference tolerance parameter is calculated based on wind speed, water flow speed and visibility. For example, under the conditions of visibility of 800 meters and crosswind level 6, the tolerance coefficient is set to 0.65, corresponding to a 15% reduction in the upper speed limit. The multi-objective optimization algorithm adopts the improved NSGA-II framework, sets the safety weight to 0.6, the efficiency weight to 0.3, the economic weight to 0.1, the population size to 200, and the number of iterations to 500. After the optimization process generates a Pareto frontier solution set, the final solution is determined by the fuzzy logic selector. For example, under the constraints of safety margin ≥ 0.7 and efficiency loss ≤ 18%, the speed adjustment sequence with the lowest fuel consumption is selected (14 knots → 13 knots → 11.5 knots phased speed reduction).

[0094] The time window constraint of the collaborative decision-making scheme adopts a dynamic time planning algorithm, combined with the tidal height prediction curve (such as the tidal height in the next 2 hours will drop from +1.8m to +0.9m) and the berth release time (such as the currently occupied berth is expected to be free in 45 minutes), to generate a time window of [+50min, +75min] for berthing. The resource conflict avoidance mechanism is implemented through the conflict detection matrix, the matrix dimension is N×N (N is the number of ships entering the port at the same time), the element value represents the minimum safety distance violation probability of the two ships, and a 15-minute time buffer is automatically inserted when the probability exceeds 0.2. The final scheme output includes four-tuple control parameters: speed adjustment gradient (maximum change rate ±2 knots / minute), steering angle sequence (such as continuous left turn 5°→8°→3°), berth allocation coordinates (angle deviation ±0.02 radians in the polar coordinate system) and equipment scheduling sequence (crane operation interval ≥8 minutes).

[0095] In this way, the multimodal deep learning network reduces the root mean square error of channel deviation prediction from 0.18 of the traditional model to 0.09 through the synergistic effect of spatiotemporal convolution and dynamic feature interaction, and still maintains an accuracy rate of 89.7% in complex scenarios with a ship density of more than 40 ships per hour; the multi-objective optimization algorithm combined with the fuzzy logic selection mechanism improves the safety-efficiency balance index of the collaborative decision-making scheme by 42%, and the measured data shows that the average waiting time of ships is shortened by 28%, and the berth turnover rate is increased by 19%; the dynamic constraint condition generation technology reduces the conflict rate of berth adaptation decision from 12.3% to 4.7% through quantified tolerance parameters and segmented scoring functions, while maintaining the port operation efficiency within the ±5% fluctuation range of the benchmark value. These technical features together constitute the core capabilities of intelligent decision-making, achieving a double breakthrough in port resource utilization and navigation safety.

[0096] In a preferred embodiment, the generation and execution of the ship control instruction set includes: decomposing the speed adjustment sequence in the collaborative decision-making scheme into discrete control instructions, each instruction including a target speed value, an acceleration limit and an effective time interval; generating a steering angle control signal sequence according to the turning timing set, and matching the signal sequence with the terrain feature points of the port channel in real time; mapping the berth allocation priority into a berth guidance instruction, the instruction including berth coordinates, berthing angle and start-up timing of cable mooring equipment; pushing the ship control instruction set to the automatic driving system and port operation control terminal of the target ship in real time through the port dispatch system, and monitoring the ship response status and port equipment feedback data during the execution of the instruction.

[0097] In the preferred embodiment, the generation and execution mechanism of the ship control instruction set realizes the precise conversion from the decision-making scheme to the physical operation through a multi-level instruction encoding and dynamic feedback control system. The discretization process of the speed adjustment sequence adopts a piecewise linear approximation algorithm, which decomposes the continuous speed curve into control instruction units with a time granularity of 10 seconds. A single instruction contains the target speed value (e.g., from 14.2 knots to 13.5 knots), the acceleration limit (maximum ±0.3 knots / second), and the effective time interval (starting UTC time 2023-08-15T14:25:30 to ending time 14:26:10). The instruction parameters are stored in the IEEE 754 double-precision floating-point format. The acceleration limit value is dynamically set according to the ship's power characteristic curve. For example, for a bulk carrier equipped with a low-speed two-stroke diesel main engine, the upper limit of the forward acceleration is set to 0.28 knots / second, and the lower limit of the reverse braking acceleration is set to -0.35 knots / second. The effective time interval is synchronized with the port radar scanning period (6 seconds) to ensure that the instruction trigger moment is located in the first valid time window after the radar data is updated.

[0098] The generation of the steering angle control signal sequence is based on the digital twin model of the waterway. This model divides the port waterway into a sequence of key terrain feature points (such as buoy D12 → turning point Q7 → entrance guide G3). Each feature point is associated with a recommended steering angle value (such as a 12.5° ± 0.5° left turn at point Q7) and a steering lead (triggered 200 meters from the feature point). The signal sequence adopts an incremental encoding method. Each steering instruction contains the target heading angle (magnetic heading 283.7°), the steering rate (3.2° / second), and the completion threshold (allowing a deviation of ±0.8°). For continuous steering scenarios, the system smooths the steering angle sequence through the cubic Bézier curve algorithm. For example, it generates a transitional heading angle between three consecutive turning points (turn 5° → 8° → 6°), and the curvature radius is constrained to 1.2 times the minimum turning radius of the ship (for a 180-meter ship, it needs to maintain a curvature radius of ≥216 meters).

[0099] The generation of the berthing guidance instruction adopts a spatial matching algorithm, which maps the berthing allocation priority to three-dimensional space coordinates (radius 235 meters and angle 1.02 radians in polar coordinates), the berthing angle (the angle between the ship's bow direction and the dock shoreline is -3.5°), and the starting timing of the mooring equipment for the mooring ropes. The calculation of the berthing angle comprehensively considers the influence of the tidal flow direction (current flow rate 1.4 knots in the direction of 152°), the wind direction (northwest wind 8 m / s), and the ship's windward area (side projection area 450 ㎡), and calculates the optimal berthing attitude through iterative calculation using a hydrodynamics model. The mooring rope mooring instruction contains the tension setting values for four groups of mooring points (front rope 120 kN, rear rope 110 kN, transverse rope 85 kN). The tension parameters are dynamically adjusted according to the ship's displacement (such as 50,000 tons) and the real-time wind speed. The control signal is transmitted to the hydraulic winch controller through an industrial Ethernet, and the pressure feedback accuracy reaches ±2.5 kPa.

[0100] The instruction transmission and execution monitoring system constructs a bidirectional communication channel. The port scheduling system encapsulates control instructions into data packets in ASN.1 format through a 5G private network slice and transmits them to the autopilot system of the target ship. The data packets contain a 128-bit instruction number, a 32-bit CRC check code, and a Time-Sensitive Networking (TSN) tag to ensure that the end-to-end transmission delay is less than 20 ms. After parsing the instructions, the ship's autopilot system issues the speed control instructions to the main engine remote control unit via the CAN bus and sends the steering instructions to the steering gear controller, with a heading control period of 100 ms. Meanwhile, after receiving the berthing guidance instructions, the port operation control terminal activates the positioning system of the gantry crane (positioning accuracy ±15 cm), the hydraulic drive device of the mooring pile (pressure range 0 - 20 MPa), and the lighting and navigation equipment (light intensity 50,000 lumens) to form a complete berthing guidance environment.

[0101] The execution status monitoring system verifies the instruction execution effect in real time through multi-source sensor data fusion. The ship response status monitoring module collects parameters such as the main engine speed (e.g., 85 rpm), actual speed (13.6 knots), and rudder angle feedback (11.8° to the left), and performs differential comparison with the expected instruction values. When the speed deviation exceeds 0.5 knots for 10 seconds or the rudder angle error exceeds 1.5°, a three-level deviation correction mechanism is triggered: the first-level response adjusts the main engine fuel injection volume (±3%), the second-level response corrects the rudder angle compensation coefficient (±0.3), and the third-level response activates the manual intervention alarm. The port equipment feedback data monitoring includes the trolley travel position of the crane (deviation from the target coordinate ≤0.2 m), mooring cable tension (fluctuation range ±8 kN), and lighting system status (color temperature 5000 K ± 300 K). Abnormal data triggers the equipment self-check program (e.g., an emergency lock is activated when the hydraulic system pressure drops suddenly by more than 15%).

[0102] The instruction dynamic adjustment mechanism adopts a Model Predictive Control (MPC) framework to perform rolling optimization of the current execution status every 5 seconds. The input of the optimization model includes the actual position of the ship (WGS84 coordinate accuracy 0.0001°), the remaining instruction queue (e.g., the next 3 steering instructions), and the prediction of environmental disturbances (wind speed change rate in the next 2 minutes). The output is the adjusted instruction parameters (e.g., correcting the next speed instruction from 13.5 knots to 13.2 knots). For emergencies (such as an emergency brake of the ship ahead), the system starts a conflict resolution algorithm, recalculates the speed adjustment sequence within 200 ms, and generates a stepped deceleration instruction (14.0 → 13.0 → 12.0 knots in three levels of braking) to ensure that the safety distance is maintained at least 150 meters.

[0103] In this way, the ship speed command discretization algorithm, combined with the ship's dynamic characteristics, reduces the ship speed control error from ±0.8 knots in the traditional method to ±0.2 knots, and improves the fuel efficiency by 12%. The dynamic matching mechanism between the steering signal and the terrain feature points controls the steering timing error within ±3 seconds, reducing the risk of lane deviation by 67%. Thirdly, the three-dimensional spatial parametric description of the berthing guidance command improves the berthing position accuracy from the meter level to the decimeter level (average deviation of 0.35 meters), and shortens the mooring operation time by 40%. These technical improvements form a closed-loop control system, enabling the reliability index of the ship's automatic berthing and unberthing operations to reach 99.23% and improving the collaborative efficiency of port equipment by 55%, providing core technical support for the intelligent port operation.

[0104] In an optional embodiment, the method further includes: collecting in real time the execution feedback data of the ship control instruction set, including the actual ship speed deviation, the steering angle execution error, and the change amount of the berth occupancy state; inputting the execution feedback data into the ship behavior prediction model for online incremental learning, and dynamically adjusting the contribution degree parameter of the environmental factor in the attention weight allocation module of the model; recalculating the set of navigation risk indicators based on the updated ship behavior prediction model, and generating a corrected collaborative decision-making plan; when it is detected that the channel congestion index exceeds a preset threshold or the berth conflict probability continues to rise, triggering the real-time reconstruction process of the collaborative decision-making plan, and sending a collaborative collision avoidance instruction to the associated ships.

[0105] In the above embodiment, the intelligent auxiliary decision-making system constructs a closed-loop feedback optimization mechanism, and realizes the continuous optimization of ship behavior prediction and scheduling control by executing data-driven dynamic model updates and decision-making iterations. The acquisition module of the execution feedback data integrates the CAN bus data of the ship's autopilot system (sampling rate 100Hz), the Modbus-TCP protocol status message of the port equipment (5-second cycle), and the high-precision differential GPS positioning data (positioning accuracy 0.01 meters) to form a multi-dimensional feedback vector. The calculation of the actual ship speed deviation adopts the sliding window variance analysis, the window length is set to 30 seconds, and the deviation threshold is set to ±0.3 knots (for example, a deviation of 0.3 knots between the command value of 13.5 knots and the actual value of 13.2 knots triggers the calibration process), and the data stream is subjected to noise suppression by a Kalman filter, and the process noise covariance matrix is set to [0.1², 0; 0, 0.05²]. The monitoring of the steering angle execution error adopts the angle differentiation method, and the residual between the commanded rudder angle (such as 12.5° to the left) and the actual rudder angle (12.1° to the left) is calculated every 200ms. When the cumulative residual exceeds 5°·s, the rudder machine compensation mechanism is activated.

[0106] The online incremental learning framework adopts the Elastic Weight Consolidation algorithm. On the basis of retaining the original parameters of the ship behavior prediction model (weight matrix W∈R^(512×256)), the attention weight allocation module is fine-tuned through feedback data. The update of the environmental factor contribution parameter follows the online gradient descent rule, with the learning rate set to 0.0001 and the momentum coefficient set to 0.9. When it is detected that the deviation between the wind speed predicted by the meteorological data (15.3m / s) and the actual measured value (17.1m / s) exceeds 11%, the attention weight of the wind speed factor is increased from 0.65 to 0.72, and the weight of the tidal factor is correspondingly reduced from 0.23 to 0.18. The model update process is completed at the edge computing node, and the time consumption of a single incremental learning is controlled within 300ms to ensure that the model iteration does not affect the real-time decision cycle.

[0107] The revised collaborative decision-making scheme generation mechanism adopts a two-layer optimization structure. The first layer recalculates the probability of channel deviation (for example, from 0.17 to 0.24), the probability of berthing conflict (from 0.31 to 0.39) and the path feasibility score (from 82 points to 75 points) based on the updated set of navigation risk indicators. The second layer applies the robust optimization model to generate anti-interference decision schemes. The constraints of the speed adjustment sequence increase the wind speed compensation factor (for example, the 13-knot reference speed corresponds to a 14.2-knot compensation value), and the steering timing set introduces a safety margin time (executes the steering command 8 seconds in advance). For the berth allocation priority, the system dynamically adjusts the weight coefficient of the ship draft-berth depth matching (from 0.35 to 0.42), and introduces a new scoring dimension - the difference index of adjacent berth ship types (for example, when an oil tanker and a chemical tanker are adjacent, the index is reduced by 0.3).

[0108] The trigger mechanism of the real-time reconstruction process adopts a composite condition monitoring model. The threshold of the channel congestion index is set to 0.85 (ship density / channel capacity ratio). When the index exceeds the threshold for three consecutive sampling periods (15 seconds), the reconstruction is activated. The warning line for the increase in the probability of berth conflict is set to 0.4. If the probability value increases by more than 0.15 cumulatively within 1 minute, an emergency response is triggered. The generation of collaborative collision avoidance instructions adopts a multi-agent reinforcement learning algorithm. Each ship is regarded as an independent agent, and the optimal collision avoidance strategy is calculated through the Q-learning framework. The instruction parameters include the relative azimuth adjustment amount (such as turning right 5°), the safety distance maintenance value (200 meters) and the speed synchronization coefficient (0.92). The instructions are encapsulated in JSON format and broadcast through the 5G-V2X communication protocol. The transmission delay is guaranteed to be within 50ms and the packet loss rate is less than 0.1%.

[0109] The synchronous update of feedback data and model parameters is achieved through a distributed transaction mechanism, and a two-phase commit protocol is used to ensure data consistency. When the actual speed deviation data of the ship is written into the time series database, a timestamp and space stamp (WGS84 coordinates) are attached to establish a spatiotemporal correlation index with the original prediction data. The model weight update process records the version number (such as v2.1.7→v2.1.8) and the change summary (such as wind speed factor weight +0.07), and supports version rollback and effect comparison. In a typical application scenario, when encountering a sudden crosscurrent (the flow rate increases from 1.2 knots to 2.5 knots) resulting in three consecutive failures of heading correction, the system completes the model update within 8 seconds and generates a new steering instruction sequence (turn left 15°→turn right 3°→stabilize 10°), reducing the track deviation from 5.2 meters to 1.7 meters.

[0110] Based on the above technical solutions, the online incremental learning mechanism improves the environmental adaptability of the ship behavior prediction model by 58%. In the scenario where the gust speed changes by more than 8m / s, the channel deviation prediction error is reduced to 0.08; secondly, the two-layer optimization decision-making architecture shortens the solution correction response time from 45 seconds of the traditional method to 9 seconds, and the berth conflict resolution success rate is increased to 94%; thirdly, the multi-agent collaborative collision avoidance algorithm improves the group navigation efficiency by 33%, and under the high-load condition of 50 ships / square nautical mile, the collision risk index is reduced by 72%. These technical breakthroughs form an adaptive closed-loop control system, realizing the paradigm shift of the port dispatching system from static rule-driven to dynamic data-driven.

[0111] Under one design idea, the online incremental learning process includes: extracting the ship response delay time, environmental interference mutation events and equipment failure exception codes in the execution feedback data to construct a model error feature vector; performing statistical analysis of the deviations between historical prediction results and actual navigation data through a sliding time window mechanism to identify weak links in the stability of model prediction; using knowledge distillation technology to use the fully trained ship behavior prediction model as a teacher model to generate a distillation loss function for a lightweight student model; using the execution feedback data and the distillation loss function to fine-tune the student model, and synchronizing the fine-tuned model parameters to the edge computing node of the port scheduling system.

[0112] Furthermore, the generation and distribution of the collaborative collision avoidance instructions include: when it is detected that the predicted navigation paths of multiple ships have overlapping areas in the time and space dimensions, extracting the center coordinates and conflict time windows of the overlapping areas; calculating the collision avoidance priority weight of each ship, the weight being based on the ship tonnage, cargo hazard level and current adjustable speed range; generating differentiated speed adjustment recommendations and steering angle compensation amounts according to the collision avoidance priority weights, and constructing a communication negotiation protocol between ships; broadcasting the collision avoidance instructions and negotiation protocols to associated ships through the ship self-organizing network, and receiving the instruction confirmation signals from each ship to update the collaborative decision-making plan.

[0113] In the above embodiment, the intelligent decision-making support system constructs an adaptive model optimization and multi-ship collaborative collision avoidance system, and realizes navigation safety control in a dynamic environment through feedback-driven incremental learning and distributed decision-making mechanisms. The construction of the model error feature vector is based on the multi-dimensional analysis of the execution feedback data. The ship response delay time is calculated by the difference between the instruction sending timestamp and the execution confirmation timestamp (typical value 0.8-2.3 seconds). The environmental interference mutation event is defined as the event coding of the wind speed change rate exceeding 3m / s² or the water flow direction mutation exceeding 30° (such as event code E107 represents the southeast wind flow mutation), and the equipment fault abnormal code is mapped to a 32-dimensional binary vector (such as the 17th bit corresponding to the hydraulic fault is set to 1). The error feature vector dimension is set to 128, including statistics such as the delay time mean (1.2 seconds), mutation event frequency (0.3 times / minute) and fault code Hamming weight (4.7). It is reduced to 64 dimensions through principal component analysis and then input into the model update module.

[0114] The sliding time window mechanism adopts a dynamic window length adjustment algorithm, with a basic window length of 60 seconds, which is dynamically expanded or contracted according to the variance value of the predicted deviation (the window is extended by 5 seconds for every 0.1 increase in variance). The deviation statistical analysis module calculates the KL divergence (typical value 0.17-0.35) between the historical predicted channel deviation probability and the actual deviation event, and identifies that the prediction stability of the model decreases when visibility is less than 800 meters (the deviation value increases by 58%). For the identified weak links (such as berthing conflict prediction in sharp turn scenarios), the system automatically enhances the sampling weight of the corresponding features, increasing the sample ratio of relevant scenarios in the training data from 12% to 28%.

[0115] In the knowledge distillation framework, the teacher model is a full-scale ship behavior prediction model with 120 million parameters, and the student model is designed as a lightweight structure (with 24 million parameters). Knowledge transfer is achieved through feature layer alignment and output layer softening. The distillation loss function includes the mean square error term (weight 0.6), the KL divergence term (weight 0.3), and the intermediate layer attention map similarity term (weight 0.1). The fine-tuning process of the student model adopts a small batch stochastic gradient descent algorithm, with the batch size set to 32 and the learning rate 0.0003. After iterative training on 5,000 sets of feedback data, the model maintains 97% prediction accuracy while increasing the inference speed by 3.8 times. The updated model parameters are synchronized to the port edge node through a hash verification mechanism (SHA-256), the synchronization cycle is compressed to 15 seconds, and the version consistency error is less than 0.01%.

[0116] The spatio-temporal overlap detection of the cooperative collision avoidance instruction generation module adopts a four-dimensional spatio-temporal voxel partitioning algorithm, with a spatial resolution of 50 meters × 50 meters and a time granularity of 10 seconds. When the predicted trajectories of two ships overlap in the same voxel unit (such as spatial coordinates X = 235, Y = 178, time window 14:25:30 - 14:26:00), it is marked as a potential collision event. The central coordinates of the collision time window are calculated by the weighted centroid method, with the weight being the ship's tonnage (for example, the weight ratio of a 30,000-ton ship to a 50,000-ton ship is 3:5), and the length of the time window is dynamically adjusted according to the relative speed (for example, when moving towards each other, the window length is shortened to 5 seconds).

[0117] The calculation model of the collision avoidance priority weight includes three core factors: the ship tonnage factor (weight 0.3, with the maximum value corresponding to a 300,000-ton class), the cargo hazard level factor (weight 0.4, set to 1.0 for Class I dangerous goods and 0.2 for ordinary goods), and the speed adjustment ability factor (weight 0.3, with an adjustable range of ±25% of the reference speed to get 1.0). The weight synthesis formula generates the priority index for each ship (such as an oil tanker index of 0.82 and a container ship index of 0.65), and based on this, the allocation of the avoidance responsibility is determined. The generation of the speed adjustment suggestion adopts a game theory model. The ship with a higher priority obtains the speed adjustment exemption right (allowing a deviation of ±0.5 knots), and the ship with a lower priority needs to perform a stepped speed reduction (such as from 14 knots to 12.5 knots). The calculation of the steering angle compensation amount considers the ship's maneuvering response index (such as an index of 2.3 for a fully loaded VLCC), and the compensation formula outputs the corrected steering angle value (such as the basic suggestion to turn left by 10°, and after compensation, it is to turn left by 12°).

[0118] The communication negotiation protocol is designed as a three-layer structure: the physical layer adopts the IEEE 802.11p protocol, with a transmission rate of 6 Mbps, and delay-sensitive data is given priority for transmission; the application layer defines the format of the collision avoidance instruction data packet, including the ship ID (128 bits), the suggested speed (floating point number), the steering angle (integer degree), and the valid time window (UTC timestamp); the negotiation layer implements a distributed consensus mechanism based on the Paxos algorithm to ensure that at least 67% of the associated ships confirm the instruction before the execution plan is updated. The instruction confirmation signal includes a summary of the ship's current state (256-bit hash value) and an execution commitment (such as guaranteeing to start turning within 8 seconds). Ships that have not confirmed trigger a secondary broadcast and an artificial intervention process.

[0119] The ship self-organizing network constructs a dynamic routing table. The communication distance between nodes is limited within 1000 meters. The time-division multiple access (TDMA) mechanism is adopted to divide transmission time slots, and the length of each time slot is 50 ms, supporting the transmission of 20 instruction packets per second. The network topology is updated every 30 seconds, and the optimal transmission path is calculated based on the change of ship positions (for example, the three-hop relay path loss is reduced by 18 dB). The instruction distribution system monitors the signal strength (RSSI > -85 dBm) and the bit error rate (BER < 10^-5). When the channel quality deteriorates, it automatically switches to the backup link of the port 5G network, and the switching delay is controlled within 120 ms.

[0120] It can be seen that the knowledge distillation technology combined with dynamic feature enhancement improves the prediction stability of the lightweight model by 42%, and reduces the inference latency at the edge node from 350 ms to 92 ms. Secondly, the spatio-temporal voxel conflict detection algorithm improves the multi-ship collision avoidance decision-making efficiency by 55%, and the detection delay is less than 1.5 seconds in the scenario of 40 ships per hour ship density. Thirdly, the synergistic effect of the distributed negotiation protocol and the self-organizing network improves the instruction confirmation rate from 78% to 95%, and reduces the synchronization error of the group collision avoidance actions to 0.8 meters. These technological breakthroughs form a closed-loop optimization system, realizing the intelligent breakthrough of autonomous cooperative collision avoidance and resource scheduling of ships in complex environments, increasing the navigation capacity per unit time in the port waters by 37%, and reducing the risk of major collision accidents by 89%.

[0121] In an optional embodiment, the method further includes: during the berthing and unberthing process of the target ship, real-time monitoring of the data of the cable tension sensor, the tidal change rate, and the working load of the terminal handling equipment; when it is detected that the cable tension exceeds the material strength threshold or the tidal change causes insufficient berth water depth, generating an emergency unberthing instruction set, which includes the start parameters of the emergency thruster, the cable rapid release sequence, and the port tugboat scheduling priority; forcibly interrupting the current berthing operation through the port emergency control system, and activating the automated execution process of the emergency unberthing instruction set.

[0122] In addition, the method further includes: after the ship completes the operations of entering and leaving the port and berthing and unberthing, collecting the decision execution data and external environment monitoring data of the whole process, and constructing a case knowledge graph; extracting the key decision nodes, risk disposal modes, and resource scheduling optimization paths in the case knowledge graph, generating experience rules and supplementing them to the port dynamic scheduling rule library; simulating the decision-making paths under different environmental interference scenarios through the reinforcement learning algorithm, and updating the weight allocation strategy of the multi-objective optimization algorithm; deploying the optimized decision-making logic to the digital twin platform of the port scheduling system to realize the closed-loop verification of the historical case data and the real-time decision-making process.

[0123] In the above embodiments, the intelligent assisted decision-making system constructs a closed-loop emergency response and knowledge evolution mechanism, and iteratively optimizes the port operation safety system through multi-modal sensing data fusion and historical experience. The cable tension monitoring module integrates an optical fiber grating sensor array, with a measurement point arranged every 0.5 meters along the mooring cable, a sampling frequency of 500 Hz, and dynamically monitors the tension distribution curve (typical values: front cable 110 kN ± 5 kN, rear cable 95 kN ± 8 kN). The material strength threshold is set to 85% of the nominal breaking strength (for example, the threshold for a steel core cable with a diameter of 56 mm is set to 320 kN). When the tension at three consecutive sampling points exceeds the threshold and lasts for 5 seconds, a first-level warning is triggered. The tidal change rate is calculated in real time through a differential GPS buoy network, and the monitoring period is shortened to 10 seconds. The determination condition for insufficient water depth is that the difference between the real-time tide height and the ship's draft is less than 0.8 meters (for example, a ship with a draft of 11.2 meters triggers the departure condition when the tide height is 10.5 meters).

[0124] The generation of the emergency departure instruction set adopts a multi-stage decision-making model. The starting parameters of the emergency thrusters include thrust vector (for example, the left thruster at 70% power, the right thruster at 85% power), action duration (the shortest is 12 seconds), and energy reserve constraint (the battery SOC is not less than 35%). The cable rapid release sequence is sorted based on the tension gradient, and the cables with a tension exceeding 150% of the average value are preferentially released (such as cables numbered C3 and C7), and the release interval time is compressed to 0.8 seconds. The opening pressure of the hydraulic release valve is set to 18 MPa. The port tugboat dispatching priority calculation model considers the tugboat horsepower (for example, a 3200 HP tugboat has a weight of 1.5), the distance of the current position (a weight of 2.0 within 500 meters), and the current task urgency (a weight of 3.0 in the idle state), and generates dispatching instructions (such as preferentially dispatching tugboats T05 and T12).

[0125] The port emergency control system constructs a dual-redundancy communication channel. The main channel uses an optical fiber ring network (transmission delay < 2 ms), and the standby channel enables microwave relay (delay < 15 ms). When a forced interruption instruction is sent to the PLC controller of the quay operation equipment, a three-level interlock mechanism is synchronously triggered: the first level interrupts the hydraulic power of the loading and unloading arm (pressure relief rate 30 MPa / s), the second level activates the sound and light alarm around the berth (120 dB alarm lasts for 30 seconds), and the third level activates the physical isolation barrier (the hydraulic lifting pile rises at a speed of 0.5 m / s). The timing control accuracy of the automated execution process reaches the millisecond level. For example, the time deviation between the thruster start instruction and the cable release instruction is controlled within ±50 ms.

[0126] The construction of the case knowledge graph adopts ontology modeling technology, defining 32 types of ontologies such as ship entities (attributes including tonnage, draft, and ship length), environmental entities (tidal phase, wind speed vector), and equipment entities (crane number, status code). The decision node extraction algorithm is based on process mining technology to identify critical decision moments (such as the ±5-second window of the departure order trigger time point), and the dimension of the extracted feature vector is extended to 256 dimensions (including parameters such as the sudden change rate of ship speed of 0.3 knots per second and tidal acceleration of 0.08 m / s²). The clustering analysis of risk disposal modes uses the DBSCAN algorithm, with the neighborhood radius set to 0.35 and the minimum number of samples to 15, generating seven types of typical disposal modes (such as Mode C-03 corresponding to the collaborative operation of multiple tugboats under gust conditions).

[0127] The update mechanism of the port dynamic scheduling rule library adopts a strategy combining rule induction and weight migration. The empirical rule supplement process analyzes the association rules (support > 0.7, confidence > 0.85) in the case knowledge graph. For example, the rule R-228 is extracted: "When the tidal decline rate > 0.4 m / h and the draft margin < 1.2 m, the forced departure priority is increased to Level-5". The construction of the reinforcement learning environment includes 18 typical interference scenarios (such as typhoons, equipment failures, and ship out-of-control), the state space dimension is 54 (including 6 tidal parameters, 12 ship states, and 36 equipment parameters), and the action space includes 23 scheduling operations. The exploration rate of the Q-learning algorithm decays dynamically from 0.3 to 0.05, the learning rate is 0.002, and an optimized weight allocation strategy (safety weight 0.58 → 0.63, efficiency weight 0.32 → 0.27) is generated after 10^6 iterations.

[0128] The deployment architecture of the digital twin platform includes a physical mapping layer (1:1 three-dimensional port model), a data-driven layer (real-time data injection frequency of 50 Hz), and a simulation verification layer (10,000 Monte Carlo simulation times per scenario). The closed-loop verification process compares the matching degree between historical case data (such as the departure event E-0472 in July 2023) and the real-time decision path, calculates the similarity score through the dynamic time warping algorithm (threshold 0.85), and unqualified cases trigger the rule backtracking mechanism. The optimized decision logic is updated to the production system through hot deployment technology, the version switching time is compressed to 45 seconds, and the service interruption window is controlled within 3 seconds.

[0129] In this way, the multi-modal sensing fusion and millisecond-level response mechanism reduce the emergency unberthing decision-making time from 8.5 minutes in traditional manual handling to 22 seconds, and the incidence rate of major mooring accidents is reduced by 92%. The case knowledge graph construction technology improves the historical experience conversion efficiency by 76%, and the rule base update cycle is compressed from quarterly to hourly. The digital twin verification platform increases the optimization iteration speed of the decision-making path by 40 times. In the typhoon passing scenario test, the safety margin of the ship scheduling plan is increased by 37%, and the port recovery operation time is shortened by 58%. These technological advancements form a complete technological chain for intelligent port emergency management and experience evolution, achieving a coordinated leap in port operation safety and operation efficiency.

[0130] In summary, the present invention constructs a ship navigation situation awareness system by integrating multi-source heterogeneous data, significantly improving the real-time performance and accuracy of port scheduling decisions. The spatio-temporal alignment technology of real-time meteorological and hydrological data effectively eliminates the spatio-temporal misalignment of environmental interference factors and enhances the representation ability of the coupling relationship between ship motion states and the environment. The ship behavior prediction model based on deep learning realizes the quantitative assessment of multi-dimensional navigation risks and accurately identifies potential risks such as lane deviation and berthing conflicts. The collaborative optimization mechanism of the dynamic scheduling rule base and risk indicators generates a collaborative decision-making plan that takes into account both safety and efficiency, and optimizes the ship trajectory control accuracy through the dynamic programming of speed adjustment and steering timing. The automated instruction generation and execution system realizes the closed-loop linkage of port resource allocation and ship navigation control, ensuring the reliability and response speed of the port operation process in a complex operation environment, and overall improving the port navigation efficiency and safety level.

[0131] An embodiment of the present invention provides a computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, it implements the intelligent auxiliary decision-making method for ship entry and exit ports and berthing and unberthing based on multi-source data.

[0132] An embodiment of the present invention provides a processor, which is used to run a program, and when the program runs, it executes the intelligent auxiliary decision-making method for ship entry and exit ports and berthing and unberthing based on multi-source data.

[0133] In an embodiment of the present invention, as Figure 2 shown, the intelligent auxiliary decision-making system 100 includes at least one processor 101, at least one memory 102 connected to the processor 101, and a bus 103; wherein, the processor 101 and the memory 102 complete communication with each other through the bus 103; the processor 101 is used to call program instructions in the memory 102 to execute the above-mentioned intelligent auxiliary decision-making method for ship entry and exit ports and berthing and unberthing based on multi-source data.

[0134] Embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, intelligent auxiliary decision-making systems (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or means for implementing the functions specified in multiple blocks.

[0135] In a typical configuration, an intelligent auxiliary decision-making system includes one or more processors (CPUs), a memory, and a bus. The intelligent auxiliary decision-making system may also include an input / output interface, a network interface, etc.

[0136] The memory may include non-permanent memory in the form of computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory includes at least one storage chip. The memory is an example of computer-readable media.

[0137] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, magnetic disk storage, or other magnetic storage, computer-readable storage media, or any other non-transmission media that can be used to store information accessible by the intelligent auxiliary decision-making system. As defined herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or computer-readable storage medium that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, commodity or computer-readable storage medium. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the presence of other identical elements in the process, method, commodity or computer-readable storage medium that includes the elements.

[0139] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0140] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. An intelligent auxiliary decision-making method for ship entry and exit and berthing based on multi-source data, characterized in that: The method comprises: Acquire multi-source heterogeneous data in the target port area, wherein the multi-source heterogeneous data includes real-time meteorological data, hydrological monitoring data, ship dynamic trajectory data, port facility status data and historical navigation record data; Performing spatiotemporal alignment and feature fusion on the multi-source heterogeneous data to generate a navigation situation feature set of the target ship, wherein the navigation situation feature set includes ship navigation state parameters, an environmental interference factor set, and a port resource occupancy state sequence; Input the navigation situation feature set into a pre-trained ship behavior prediction model, and output a navigation risk index set of the target ship under multiple decision dimensions, wherein the navigation risk index set includes a channel deviation probability, a berthing conflict probability, a navigation path feasibility score, and a port operation efficiency impact coefficient; Based on the navigation risk index set and the preset port dynamic scheduling rule base, a collaborative decision-making scheme for the entry, exit and berthing of the target ship is generated, wherein the collaborative decision-making scheme includes a speed adjustment sequence, a turn timing set, a berth allocation priority and a berthing and unberthing operation time window; Generate a ship control instruction set according to the collaborative decision-making scheme, and send the ship control instruction set to the navigation equipment and port operation equipment of the target ship through the port dispatching system to dynamically adjust the ship's navigation track and port resource allocation status; The generating of a collaborative decision-making scheme for the entry, exit and berthing of the target ship comprises: Determine the channel right of way level of the target ship according to the channel deviation probability and the channel priority table in the port dynamic scheduling rule base; Based on the berthing conflict probability and the berth allocation history data, the berth suitability score of the target ship is calculated, and the berth suitability score includes the matching degree between the ship draft and the berth water depth, and the ratio of the ship length to the length of the berth free area; Combining the navigation path feasibility score with the port operation efficiency impact coefficient, generating a set of constraint conditions for the speed adjustment sequence, wherein the constraint conditions include a minimum safe speed threshold, a maximum turning angle rate, and environmental interference tolerance; The waterway right level, berth suitability score and speed adjustment constraints are weightedly integrated through a multi-objective optimization algorithm to generate a collaborative decision-making plan that includes time window constraints and resource conflict avoidance.

2. The method according to claim 1, characterized in that The step of performing spatiotemporal alignment and feature fusion on the multi-source heterogeneous data to generate a navigation situation feature set of the target ship includes: Extracting the ship position sequence, speed sequence and heading angle sequence from the ship dynamic trajectory data to construct a ship kinematics feature vector; Performing spatial grid matching on the wind speed, wind direction, and visibility in the real-time meteorological data and the tidal height and flow velocity in the hydrological monitoring data to generate an environmental interference factor matrix; Constructing a time series of port resource occupancy status according to the berth occupancy status, loading and unloading equipment working status and waterway congestion index in the port facility status data; The ship kinematic feature vector, environmental interference factor matrix and port resource occupancy state sequence are time-stamp synchronized and spatial coordinate mapped to generate a multi-dimensional fusion navigation situation feature set, in which each feature unit is associated with the real-time position and future predicted time point of the target ship.

3. The method according to claim 2, characterized in that The training process of the ship behavior prediction model includes: Collect historical multi-source heterogeneous data and corresponding actual ship navigation decision records to construct a training sample set, which includes a historical navigation situation feature set and annotated navigation risk indicator true values; Construct a multimodal deep learning network, which includes a spatiotemporal convolution module, an attention weight allocation module, and a dynamic feature interaction module, wherein: The spatiotemporal convolution module is used to extract the spatial correlation between the local motion pattern of the ship trajectory and the environmental interference factors; The attention weight allocation module dynamically adjusts the contribution of meteorological data, hydrological data and port status data to the impact of ship behavior; The dynamic feature interaction module simulates the coupling effect between the ship motion characteristics and the environmental interference factors at continuous time steps; The loss function of the multimodal deep learning network is optimized by a back-propagation algorithm, wherein the loss function includes the mean square error of the channel deviation probability, the cross entropy of the berthing conflict probability, and the ranking loss of the navigation path feasibility score.

4. The method according to claim 1, characterized in that The generation and execution of the ship control instruction set includes: Decomposing the speed adjustment sequence in the collaborative decision-making scheme into discrete control instructions, each instruction including a target speed value, an acceleration limit and an effective time interval; generating a steering angle control signal sequence according to the steering opportunity set, and matching the steering angle control signal sequence with the terrain feature points of the port channel in real time; Mapping the berth allocation priority into a berth guidance instruction, wherein the berth guidance instruction includes berth coordinates, berthing angles, and a start sequence of a cable mooring device; The ship control instruction set is pushed to the target ship's autopilot system and port operation control terminal in real time through the port dispatching system, and the ship's response status and port equipment feedback data during the execution of the instructions are monitored.

5. The method according to claim 4, characterized in that The method further comprises: Real-time collection of the execution feedback data of the ship control instruction set, including the actual speed deviation of the ship, the steering angle execution error and the change in berth occupancy status; Inputting the execution feedback data into the ship behavior prediction model for online incremental learning, and dynamically adjusting the environmental factor contribution parameter in the attention weight allocation module of the ship behavior prediction model; Recalculate the navigation risk indicator set based on the updated ship behavior prediction model to generate a revised collaborative decision-making plan; When it is detected that the waterway congestion index exceeds a preset threshold or the probability of berth conflict continues to rise, the real-time reconstruction process of the collaborative decision-making scheme is triggered, and a collaborative collision avoidance instruction is sent to the associated ships.

6. The method according to claim 5, characterized in that The online incremental learning process includes: Extracting the ship response delay time, environmental interference mutation events and equipment failure abnormality codes from the execution feedback data to construct a model error feature vector; Through the sliding time window mechanism, the deviation between historical prediction results and actual navigation data is statistically analyzed to identify the weak links in the stability of model prediction; The knowledge distillation technology is used to take the fully trained ship behavior prediction model as the teacher model to generate the distillation loss function of the lightweight student model. The student model is fine-tuned using the execution feedback data and the distillation loss function, and the fine-tuned model parameters are synchronized to the edge computing node of the port scheduling system.

7. The method according to claim 6, characterized in that The generation and distribution of the collaborative collision avoidance instruction includes: When it is detected that the predicted navigation paths of multiple ships have overlapping areas in the time and space dimensions, the center coordinates of the overlapping areas and the conflict time windows are extracted; Calculate the collision avoidance priority weight of each ship, wherein the collision avoidance priority weight is based on the ship's tonnage, the cargo hazard level, and the current adjustable speed range; Generate differentiated speed adjustment suggestions and steering angle compensation amounts according to the collision avoidance priority weights, and establish a communication negotiation protocol between ships; The collaborative collision avoidance instructions and negotiation protocols are broadcast to associated ships through the ship self-organizing network, and instruction confirmation signals from each ship are received to update the collaborative decision-making plan.

8. The method according to claim 7, characterized in that The method further comprises: During the berthing and unberthing process of the target ship, real-time monitoring of cable tension sensor data, tidal change rate and workload of terminal loading and unloading equipment; When it is detected that the cable tension exceeds the material strength threshold or the tidal change causes insufficient berth water depth, an emergency unberthing instruction set is generated, wherein the emergency unberthing instruction set includes emergency thruster start-up parameters, cable quick release sequence and port tugboat dispatch priority; The current berthing operation is forcibly interrupted through the port emergency control system, and the automated execution process of the emergency unberthing instruction set is activated.

9. The method according to claim 8, characterized in that The method further comprises: After the ship completes the port entry and exit and berthing and unberthing operations, the decision execution data and external environment monitoring data of the whole process are collected to build a case knowledge graph; Extract key decision nodes, risk handling modes and resource scheduling optimization paths in the case knowledge graph, generate empirical rules and supplement them to the port dynamic scheduling rule base; Simulating decision paths under different environmental interference scenarios through a reinforcement learning algorithm, and updating the weight allocation strategy of the multi-objective optimization algorithm; The optimized decision logic is deployed to the digital twin platform of the port dispatching system to achieve closed-loop verification of historical case data and real-time decision-making processes.

Images