A method and system for managing and controlling fishing vessels based on spatiotemporal data, a terminal, and a storage medium

Abstract

This invention belongs to the field of ship management technology, specifically relating to a method, system, terminal, and storage medium for fishing vessel management based on spatiotemporal data. It includes constructing a berth matching score function comprising a spatial dimension fit function, a temporal coordination function, and safety environment impact factors. The weight coefficients of each factor are dynamically adjusted based on real-time port congestion. By comprehensively considering multi-dimensional constraints such as the target fishing vessel's approved length, beam, full-load draft, estimated arrival time, and the berth line length, design safe water depth, and estimated idle time of candidate berths, the invention achieves globally optimal allocation of berth resources. This fundamentally eliminates the safety hazards of high-grade deep-water berths being inefficiently occupied by small fishing vessels or large fishing vessels running aground due to insufficient water depth, significantly improving the turnover potential of core berth resources.

Description

Technical Field

[0001] This invention belongs to the field of ship management technology, specifically relating to a method, system, terminal, and storage medium for the management and control of fishing vessels based on spatiotemporal data. Background Technology

[0002] With the deepening of smart fishing port construction, information management of fishing ports has become a core support for the development of modern fisheries. However, traditional fishing port management relies heavily on VHF voice communication, manual lookout, and paper-based records, which are insufficient to cope with the increasing volume of fishing vessels and the complex navigation environment. While existing technologies have introduced Automatic Identification Systems (AIS) and BeiDou positioning terminals for monitoring, the phenomenon of "data silos" is prevalent: AIS systems, radar detection systems, port video surveillance systems, and hydrological and meteorological systems operate independently, with inconsistent data formats and sampling frequencies, and a lack of effective spatiotemporal alignment mechanisms. This results in the command center being unable to obtain high-precision, low-latency, full-element situational information.

[0003] Regarding berth scheduling, existing solutions mostly employ static allocation or manual experience-based scheduling, failing to fully consider the real-time dynamics of fishing vessels, the dynamic matching of berth physical dimensions, and the coordination of port entry and exit times. This not only leads to the inefficient occupation of high-grade deep-water berths by small fishing vessels, or grounding accidents of large fishing vessels due to insufficient water depth, but also often results in both idle berth resources and vessel congestion due to the lack of accurate estimated time of arrival (ETA) predictions. Furthermore, for violations such as fishing vessel deviation, illegal fishing, and overstaying of berth time, existing methods mainly rely on post-event inspections, lacking proactive early warning capabilities based on trajectory trends and automated compliance verification mechanisms. Summary of the Invention

[0004] To address the aforementioned shortcomings of existing technologies, this invention provides a fishing vessel management method, system, terminal, and storage medium based on spatiotemporal data.

[0005] In a first aspect, the present invention provides a method for managing fishing vessels based on spatiotemporal data, comprising: S1. Obtain multi-source heterogeneous equipment data within the fishing port jurisdiction, and perform spatiotemporal alignment processing on the multi-source heterogeneous equipment data to generate a full-element spatiotemporal feature vector under a unified spatiotemporal benchmark. S2. Based on the spatiotemporal feature vector of all elements, construct and update the dynamic spatiotemporal grid of the fishing port in real time to monitor the real-time status of fishing boats in the dynamic spatiotemporal grid. S3. When the target fishing vessel is detected to have issued an intention to enter the port or cross the preset electronic fence for entering the port based on real-time status monitoring, the berth dynamic allocation algorithm is executed: according to the vessel attributes of the target fishing vessel and the availability status of each berth in the dynamic spatiotemporal grid, the matching degree score between the target fishing vessel and each available berth is calculated, and the target berth is allocated to the target fishing vessel based on the matching degree score. S4. Based on the spatiotemporal feature vector of all elements, predict the spatiotemporal trajectory trend of the target fishing vessel. If the predicted trajectory of the target fishing vessel is found to have abnormal behavior risk, generate and issue intelligent guidance instructions. S5. When a target fishing vessel is detected to have entered the target berth, a joint compliance verification is performed. If the verification result is a violation, a corresponding violation handling strategy is generated and executed.

[0006] Secondly, the present invention provides a fishing vessel management and control system based on spatiotemporal data, comprising: The data acquisition and governance module is used to acquire multi-source heterogeneous equipment data within the fishing port jurisdiction, and to perform spatiotemporal alignment processing on the multi-source heterogeneous equipment data to generate a full-element spatiotemporal feature vector under a unified spatiotemporal benchmark. The spatiotemporal grid computing module is used to construct and update the dynamic spatiotemporal grid of the fishing port in real time based on the spatiotemporal feature vector of all elements, so as to monitor the real-time status of fishing boats in the dynamic spatiotemporal grid. The berth dynamic scheduling module is used to execute the berth dynamic allocation algorithm when the target fishing vessel sends an intention to enter the port or crosses the preset port entry electronic fence based on the real-time status monitoring: according to the vessel attributes of the target fishing vessel and the availability status of each berth in the dynamic spatiotemporal grid, the matching degree score between the target fishing vessel and each available berth is calculated, and the target berth is allocated to the target fishing vessel based on the matching degree score. The trajectory prediction and guidance module is used to predict the spatiotemporal trajectory trend of the target fishing vessel based on the spatiotemporal feature vector of all elements. If the predicted trajectory of the target fishing vessel is found to have abnormal behavior risk, an intelligent guidance command is generated and issued. The compliance verification and handling module is used to perform a joint compliance verification when a target fishing vessel is detected entering the target berth. If the verification result is a violation, the module generates and executes the corresponding violation handling strategy.

[0007] Thirdly, a terminal is provided, including: Processor, memory, among which, This memory is used to store computer programs. The processor is used to retrieve and run the computer program from memory, causing the terminal to perform the terminal method described above.

[0008] Fourthly, a computer storage medium is provided, wherein instructions are stored therein, which, when executed on a computer, cause the computer to perform the methods described in the above aspects.

[0009] The beneficial effects of this invention are as follows: By establishing a spatial projection transformation matrix, the original coordinates of AIS stream data, Beidou satellite positioning stream data, radar detection data, and port panoramic monitoring video stream data are uniformly converted into the WGS-84 geographic coordinate system. With the global reference time axis generated by the unified system timing as a reference, a cubic spline interpolation algorithm is used to fit the time points of devices with sampling frequencies below a preset threshold, generating full-element spatiotemporal feature vectors under the same time slice. This effectively solves the "data island" phenomenon caused by inconsistent data formats and sampling frequencies in existing technologies, and realizes high-precision, low-latency full-element situational awareness, providing a unified data foundation for subsequent dynamic spatiotemporal grid construction, berth allocation, and anomaly early warning.

[0010] By constructing a berth matching score function that includes spatial size fit function, time coordination function, and safety and environmental impact factors, and dynamically adjusting the weight coefficients of each factor based on the real-time congestion situation of the fishing port, and comprehensively considering multi-dimensional constraints such as the target fishing vessel's approved length, beam, full-load draft, and estimated arrival time, as well as the berth line length, design safe water depth, and estimated idle time of the candidate berths, the global optimal allocation of berth resources is achieved. This fundamentally eliminates the safety hazards of high-grade deep-water berths being inefficiently occupied by small fishing vessels or large fishing vessels running aground due to insufficient water depth, and significantly improves the turnover potential of core berth resources.

[0011] By constructing a trajectory estimation model based on ship kinematic constraints, the continuous spatial coordinate vector of the target fishing vessel within a preset future time window is extrapolated in real time. The predicted trajectory point sequence is then used to verify the topological relationship with the polygonal boundaries of the legal port entry and exit channels and the polygonal boundaries of the authorized berth area. This achieves a technological improvement from the traditional "post-event passive interception and alarm" to "pre-event trend prediction and flexible intelligent guidance". It can calculate the optimal correction path in advance and generate dynamic guidance command messages containing the target correction heading angle and the recommended safe speed, which are then sent to the shipboard terminal to mitigate the risk of crossing the boundary in advance.

[0012] By introducing a joint verification mechanism that combines physical scale mismatch calculation with dynamic time window overtime monitoring, after the target fishing vessel enters the target berth, the system automatically extracts the target fishing vessel's approved length, beam, full-load draft, and tonnage class and performs cross-collision verification with the static design capacity threshold of the target berth. At the same time, a dwell timer is activated to monitor the duration of continuous stay in real time. This enables automated identification and intelligent guidance for "mismatch between fishing vessel business requests and berth type" and "long-term illegal occupation of unauthorized berth areas," filling the gap in in-depth safety supervision under dynamic scheduling. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic flowchart illustrating a method according to an embodiment of the present invention.

[0015] Figure 2 This is a schematic block diagram of a system according to an embodiment of the present invention.

[0016] Figure 3 This is a schematic diagram of the overall system architecture.

[0017] Figure 4 This is a schematic diagram of the structure of a terminal provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the specific embodiments. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0020] Figure 1 This is a schematic flowchart illustrating a fishing vessel management method based on spatiotemporal data provided by the present invention. Figure 1 The implementing entity can be a fishing vessel management system based on spatiotemporal data. Depending on different needs, the order of the steps in this flowchart can be changed, and some can be omitted.

[0021] like Figure 1 As shown, the method includes: S1. Obtain multi-source heterogeneous equipment data within the fishing port jurisdiction, and perform spatiotemporal alignment processing on the multi-source heterogeneous equipment data to generate a full-element spatiotemporal feature vector under a unified spatiotemporal benchmark. S2. Based on the spatiotemporal feature vector of all elements, construct and update the dynamic spatiotemporal grid of the fishing port in real time to monitor the real-time status of fishing boats in the dynamic spatiotemporal grid. S3. When the target fishing vessel is detected to have issued an intention to enter the port or cross the preset electronic fence for entering the port based on real-time status monitoring, the berth dynamic allocation algorithm is executed: according to the vessel attributes of the target fishing vessel and the availability status of each berth in the dynamic spatiotemporal grid, the matching degree score between the target fishing vessel and each available berth is calculated, and the target berth is allocated to the target fishing vessel based on the matching degree score. S4. Based on the spatiotemporal feature vector of all elements, predict the spatiotemporal trajectory trend of the target fishing vessel. If the predicted trajectory of the target fishing vessel is found to have abnormal behavior risk, generate and issue intelligent guidance instructions. S5. When a target fishing vessel is detected to have entered the target berth, a joint compliance verification is performed. If the verification result is a violation, a corresponding violation handling strategy is generated and executed.

[0022] To facilitate understanding of the present invention, the following description further illustrates the fishing vessel management method based on spatiotemporal data provided by the present invention, using the principle of the fishing vessel management method based on spatiotemporal data and the process of managing fishing vessels based on spatiotemporal data in the embodiments.

[0023] First, step S1 includes: S11. Parallel access to the Automatic Identification System (AIS), BeiDou satellite positioning data, radar detection data, and port panoramic monitoring video data within the fishing port jurisdiction via high-concurrency data channels, extract the original spatial coordinates and original sampling timestamps carried in various types of data, and construct an initial heterogeneous dataset; S12. Establish a spatial projection transformation matrix to uniformly convert the original coordinates captured by each sensor in the initial heterogeneous dataset into the WGS-84 geographic coordinate system (World Geodetic System, 1984), thus obtaining an intermediate dataset after coordinate standardization. S13. Using the global reference time axis generated by the unified time synchronization of the system as a reference, the cubic spline interpolation algorithm is used to fit the time points of devices in the intermediate dataset whose sampling frequency is lower than a preset threshold, generating a full-element spatiotemporal feature vector under the same time slice. Its expression is: ; in, and These represent the longitude and latitude values ​​of the fishing vessel in the WGS-84 geographic coordinate system at time t, respectively. This represents the instantaneous velocity of the fishing boat calculated based on displacement difference under continuous time slices. This represents the real-time heading angle of the fishing vessel, calculated based on coordinate changes over continuous time slices. This represents the global reference timestamp generated by the system's unified time synchronization, used to eliminate clock offset errors between different data sources.

[0024] Secondly, step S2 includes: S21. Read the spatiotemporal feature vector of all elements. Unique identifier for fishing vessels in China, longitude value in WGS-84 geographic coordinate system with latitude value The fishing port and its surrounding sea area are divided into several regularly arranged dynamic grids with a fixed resolution. A dynamic grid index mapping table is established, and the spatiotemporal feature vectors of all elements are mapped. Mapping to the corresponding grid cells generates an initialized dynamic spatiotemporal grid for the fishing port; S22. Based on the dynamic grid index mapping table, extract the full-element spatiotemporal feature vector sequence under continuous time slices within the same grid cell. Use a time window-based trajectory compression algorithm to preprocess the fishing boat trajectory and set a trajectory point distance threshold. If the height of the chord formed by three consecutive trajectory points is less than the trajectory point distance threshold... Then, by removing the redundant trajectory points in the middle, we obtain the denoised fishing boat trajectory point sequence. S23. Based on the denoised fishing vessel trajectory point sequence, a Kalman filter state update model is constructed. The optimal estimate from the previous moment is used to recursively calculate the current fishing vessel position and velocity. The denoised fishing vessel trajectory point sequence is then smoothed to restore the actual navigation path of the fishing vessels. Based on the actual navigation path, the distribution status of fishing vessels and the online status of equipment in each grid cell of the fishing port dynamic spatiotemporal grid are updated in real time. The state update equation is expressed as: ; in, This represents the optimal estimation vector of the fishing vessel's state updated based on the dynamic grid index mapping table at time k, which includes the fishing vessel's position coordinates and instantaneous velocity in the WGS-84 geographic coordinate system. denoted as the prior state estimation vector obtained at time k based on the state at the previous time, whose data source is the denoised sequence of fishing boat trajectory points; This represents the Kalman gain matrix at time k, used to weigh the confidence levels of the predicted and observed values. This represents the observation vector extracted from the spatiotemporal feature vector of all elements at time k; This represents the observation matrix, a data structure used to map state vectors to the observation space to match the spatiotemporal feature vectors of all elements.

[0025] In addition, step S3 includes: S31. Based on the real-time status of the target fishing vessel monitored in the dynamic spatiotemporal grid, when it is determined that the target fishing vessel has issued an intention to enter the port or crosses the preset electronic fence for entering the port, the approved length, beam, full-load draft and tonnage class of the target fishing vessel are extracted from the spatiotemporal feature vector of all elements. At the same time, the berth line length, design safe water depth, berth class and expected idle time of each candidate berth are retrieved from the dynamic spatiotemporal grid to construct a vessel-berth feature matching dataset. S32. Invoke the pre-stored dynamic berth allocation algorithm, input the ship-berth feature matching dataset into the berth matching score function, calculate the spatial size fit, temporal coordination, and safety environment impact factors between the target fishing vessel and each candidate berth, and dynamically adjust the weight coefficients of each factor according to the real-time congestion situation of the fishing port to calculate the final matching score of each candidate berth. The calculation formula of the berth matching score function is as follows: ; in, This represents the matching score of the i-th target fishing vessel to the j-th candidate berth, with a score range of [0,1]. The weighting coefficients are dynamically adjusted by the system based on the real-time congestion situation at the fishing port, and they satisfy the constraints. ; This is a spatial dimension fit function used to quantify the approved length of the target fishing vessel. Berth line length relative to candidate berths The degree of compatibility; This is a time coordination function used to quantify the estimated arrival time (ETA) of the target fishing vessel and the estimated idle time of the candidate berth. The degree of synchronization; This is a safety and environmental impact factor used to comprehensively assess the operational safety margin of candidate berths under current environmental conditions. S33. Traverse the matching scores of all candidate berths, select the candidate berth with the highest matching score and determine it as the target berth. At the same time, write the spatial coordinates and berth attribute information of the target berth into the spatiotemporal feature vector of all elements to update the scheduling instruction set of the target fishing vessel.

[0026] Furthermore, the spatial size fit function The calculation formula is: ; Among them, when When this occurs, a hard constraint elimination mechanism is triggered, setting the matching score of the candidate berth to zero and excluding it from the possibility of being the target berth.

[0027] Specifically, the distribution status of fishing vessels in each grid cell of the dynamic spatiotemporal grid is scanned in real time. When a target fishing vessel is detected to enter the port entrance, a first warning distance threshold is set. Within a grid range of 500 meters (default value), extract the instantaneous velocity sequence of the target fishing vessel at the current time t and the preceding N consecutive time slices (N defaults to 10, corresponding to a 10-second historical window) from the spatiotemporal feature vector of all elements. Real-time heading angle sequence and position coordinate sequence .

[0028] Subsequently, the confidence level of the target fishing vessel's intention to enter the port was calculated. This confidence level is used to quantify the probability that a fishing vessel will actively sail to the port, and its calculation formula is as follows: ; in, The average instantaneous velocity over the first N time slices. This is the maximum speed of this type of fishing vessel, used to normalize the speed factor; The average azimuth of the preset main channel centerline. It indicates the degree of deviation between the current course and the course direction; This represents the reduction in distance between the target fishing vessel and the port entrance at the current moment relative to the initial monitoring time. Distance at the initial monitoring time; These are the weighting coefficients for changes in speed, heading, and distance, respectively, and they satisfy... (The default values ​​are 0.3, 0.4, and 0.3 respectively).

[0029] like M consecutive time slices (M defaults to 5) are all greater than the preset intent threshold. (The default value is 0.75), then it is determined that the target fishing vessel has made a clear intention to enter the port.

[0030] The system retrieves a polygonal boundary dataset of the electronic fence at the port, which is pre-stored in the geographic information database. This dataset defines the precise boundaries of the port control area.

[0031] Based on the continuous position coordinates provided by the dynamic spatiotemporal grid, an electronic fence crossing verification is performed. Let the position coordinates of the target fishing vessel at time t-1 be... The position coordinates at time t are By calculating line segments By analyzing the intersection relationships with each side of the electronic fence polygon, we can determine whether a topological crossing exists.

[0032] Define the crossing determination function : ; Here, the symbol ∩ represents the geometric intersection operation. This represents the empty set. When... When the target fishing vessel crosses from the outer area to the inner area of ​​the port between two adjacent time slices, it is determined to have crossed the preset electronic fence for entering the port.

[0033] When the "entry intention determination condition" is met ( (lasting for M cycles) or "electronic fence crossing criteria" ( At that time, the berth dynamic scheduling module 230 is triggered immediately.

[0034] The system then locks the unique identifier of the target fishing vessel, freezes its current state snapshot in the dynamic spatiotemporal grid, and jumps to execute the berth dynamic allocation algorithm (i.e., steps S31-S33): extracts the approved length, beam, full-load draft and tonnage class of the target fishing vessel, combines the real-time availability status of each candidate berth in the dynamic spatiotemporal grid, calculates the matching degree score and determines the target berth, thereby realizing millisecond-level real-time response scheduling for fishing vessels entering the port.

[0035] In addition, step S4 includes: S41. Extract the target fishing vessel's historical navigation trajectory sequence, current position coordinates in the WGS-84 geographic coordinate system, instantaneous speed, and real-time heading angle from the full-element spatiotemporal feature vector. Construct a trajectory estimation model based on ship kinematic constraints. Extrapolate the target fishing vessel's continuous spatial coordinate vectors within a preset future time window to generate a predicted trajectory point sequence. The formula for calculating the spatial coordinate vector at the future time Δt in the trajectory estimation model is: ; in, and These are the longitude and latitude values ​​of the target fishing vessel at time t in the WGS-84 geographic coordinate system, extracted from the spatiotemporal feature vector of all elements. θ(t) is the instantaneous velocity of the target fishing vessel at time t extracted from the spatiotemporal feature vector of all elements; θ(t) is the real-time heading angle of the target fishing vessel at time t extracted from the spatiotemporal feature vector of all elements; Δt is the preset future prediction time step, with a value range of 10 seconds to 300 seconds; S42. Retrieve the pre-stored datasets of legal port entry / exit channel polygon boundaries and authorized berth area polygon boundaries in the system. Perform topological relationship verification on each spatial coordinate vector in the predicted track point sequence against the pre-set polygon boundaries of legal port entry / exit channels and authorized berth areas to determine whether the predicted coordinates are located inside or on the edge of the polygon boundaries. If the verification result shows that any predicted coordinate is topologically separated from the polygon boundary, it is determined that the predicted track of the target fishing vessel has an abnormal behavior risk of crossing the boundary or deviating from the course. The determination condition for the topological separation state is as follows: ; in, Let be the predicted spatial coordinate vector at the future time Δt. This is the set of pre-defined legal port entry / exit channel polygon boundaries or authorized berth area polygon boundaries; the symbol ∩ represents geometric intersection operation; This indicates an empty set, meaning that when the predicted coordinate vector is not within the set of legal boundaries, it is considered a topological separation. S43. When it is determined that the predicted trajectory of the target fishing vessel poses a risk of abnormal behavior, based on the real-time navigation status in the dynamic spatiotemporal grid, the A* path search algorithm is invoked to calculate the optimal correction path from the current position coordinates to the nearest legal boundary. Based on the optimal correction path, the target correction heading angle and safe recommended speed are calculated, and a dynamic guidance command message containing the target correction heading angle, safe recommended speed, and target guidance coordinates is generated. This dynamic guidance command message is then sent to the shipborne terminal or crew mobile terminal associated with the target fishing vessel via a wireless communication link. The calculation formula is: ; in, and These are the longitude and latitude values ​​of the endpoint of the optimal correction path in the WGS-84 geographic coordinate system, respectively. and These are the longitude and latitude values ​​of the target fishing vessel in the WGS-84 geographic coordinate system at the current time.

[0036] In practical implementation, when the system detects a target fishing vessel's intention to enter the port or crosses a preset electronic fence for entering the port based on dynamic spatiotemporal grid monitoring, or when the trajectory calculation model determines that there is a risk of deviation, the trajectory prediction and guidance module generates a dynamic guidance instruction message containing the target's correction heading angle, recommended safe speed, and target guidance coordinates. This message is then sent to the crew's mobile terminal associated with the target fishing vessel via a wireless communication link. Upon receiving the message, the terminal displays a port return guidance interface. The top of this interface displays the current berthing status of the port area in real time (e.g., 78 fishing vessels are currently berthed, maximum berthing capacity is 200 vessels). The middle trajectory display area uses dashed lines to mark the planned driving path from the current location to the target berth, and marks the target guidance point at the end of the path. The interface also displays the estimated arrival time (e.g., 10 minutes) and the guidance information "Please follow the planned path." At the bottom, a "I have arrived at the port" button is provided for the crew to manually confirm their arrival status after arrival. This visually presents pre-emptive intelligent guidance and flexible correction to the crew's operating terminal.

[0037] Finally, step S5 includes: S51. Based on real-time monitoring of the target fishing vessel's position coordinates using a dynamic spatiotemporal grid, when the target fishing vessel is detected entering the electronic fence area of ​​the target berth, the approved length, beam, full-load draft, and tonnage class of the target fishing vessel are extracted from the full-element spatiotemporal feature vector. Simultaneously, the static design capacity threshold of the target berth is retrieved, including berth line length, design safe water depth, and berth class. A physical scale mismatch verification dataset is constructed, and physical scale mismatch calculation is performed. The criteria for determining physical scale mismatch are: ; in, The berth depth fit coefficient is used to characterize the actual water depth of the target berth. With the target fishing vessel at full load draft The degree of matching; The preset ship navigation safety factor has a default value of 1.2. This is the safe water depth threshold, with a default value of 0.9. The tonnage class of the target fishing vessel. The berth class of the target berth; The resource degradation tolerance coefficient is set to 0.5 by default. If any of the above judgment conditions are met, it is determined that a physical scale mismatch has occurred, that is, there is a risk of large fishing boats running aground in shallow water berths or small fishing boats occupying high-grade deep water berths, resulting in resource waste. S52. Upon determining that the target fishing vessel has successfully entered the target berth, the system uses a unified global reference timestamp. Start the dwell timer to accumulate the continuous dwell time of the target fishing vessel in the target berth in real time. And will remain there for a certain period of time. With the preset safety buffer threshold A comparison is performed; if the target fishing vessel meets the requirements while not unloading cargo... If the timeout is exceeded, it is considered an unauthorized occupation, and the formula for updating the dwell time is: ; in, A global reference timestamp generated for unified time synchronization of the system; To monitor the entry timestamp when the target fishing vessel enters the electronic fence of the target berth; This is the safety buffer threshold during non-unloading operations, with a default value of 1800 seconds. S53. If the physical scale mismatch calculation result is determined to be a violation, or the dwell timer is determined to be an overdue violation, then a corresponding violation handling strategy will be generated: For violations related to physical scale mismatch, the dynamic berth allocation algorithm is re-invoked to calculate suitable available berths, generating a secondary guidance instruction containing the coordinates of the new target berth and sending it to the crew's mobile terminal. For violations related to overdue occupation, the target fishing vessel's status is marked as "overdue occupation," and a troubleshooting prompt message containing the target fishing vessel's unique identifier, violation type, and suggested handling measures is generated. This troubleshooting prompt message is then sent to the port dispatch terminal's monitoring screen and the duty personnel's terminal, completing the closed loop for violation handling.

[0038] In practice, once the target fishing vessel enters the target berth, the compliance verification and handling module activates a joint accounting mechanism. If the physical scale mismatch calculation determines that the target fishing vessel's approved length exceeds the berth line length of the target berth, its full-load draft exceeds the design safe water depth, or its accumulated dwell timer exceeds the approved business cycle, the system triggers a violation berthing warning state and displays a warning interface on the port dispatch terminal or related terminals. The top of the interface displays the target fishing vessel's unique identifier and "Warning in Progress" status. The middle alarm details area lists the specific parameter comparisons of the spatial scale mismatch (ship length, berth length, draft, water depth) and the conclusion of "berth physical scale mismatch." It also lists the timekeeping details of the overstay violation (dwell time, approved cycle, overstay violation status). The bottom of the interface provides "Issue Secondary Guidance Coordinates" and "Send Troubleshooting Prompt" operation buttons. After the dispatcher clicks, they can trigger secondary berth allocation or send a departure instruction to the violating fishing vessel, completing the entire process supervision from violation identification to handling.

[0039] In some embodiments, the spatiotemporal data-based fishing vessel management system 200 may include multiple functional modules composed of computer program segments. The computer programs for each program segment in the spatiotemporal data-based fishing vessel management system 200 may be stored in the memory of a computer device and executed by at least one processor to perform (see details). Figure 1 (Description) Functions for managing fishing vessels based on spatiotemporal data.

[0040] In this embodiment, the fishing vessel management system 200 based on spatiotemporal data can be divided into multiple functional modules according to the functions it performs, such as... Figure 2 As shown. The functional modules may include: a data acquisition and management module 210, a spatiotemporal grid calculation module 220, a berth dynamic scheduling module 230, a trajectory prediction and guidance module 240, and a compliance verification and handling module 250. The module referred to in this invention is a series of computer program segments that can be executed by at least one processor and perform a fixed function, stored in memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0041] The data acquisition and management module 210 is used to acquire multi-source heterogeneous equipment data within the fishing port area and perform spatiotemporal alignment processing on the multi-source heterogeneous equipment data to generate a full-element spatiotemporal feature vector under a unified spatiotemporal benchmark. The spatiotemporal grid calculation module 220 is used to construct and update the dynamic spatiotemporal grid of the fishing port in real time based on the full-element spatiotemporal feature vector to monitor the real-time status of fishing vessels in the dynamic spatiotemporal grid. The berth dynamic scheduling module 230 is used to execute a berth dynamic allocation algorithm when the target fishing vessel is detected to have issued an intention to enter the port or cross the preset electronic fence for entering the port based on the real-time status monitoring: according to the vessel attribute of the target fishing vessel. The system assesses the availability of each berth in the dynamic spatiotemporal grid, calculates the matching score between the target fishing vessel and each available berth, and assigns a target berth to the target fishing vessel based on the matching score; the trajectory prediction and guidance module 240 is used to predict the spatiotemporal trajectory trend of the target fishing vessel based on the full-element spatiotemporal feature vector. If the predicted trajectory of the target fishing vessel is found to have abnormal behavior risks, an intelligent guidance command is generated and issued; the compliance verification and handling module 250 is used to perform a joint compliance verification when the target fishing vessel is detected to have entered the target berth. If the verification result is a violation, a corresponding violation handling strategy is generated and executed.

[0042] like Figure 3 As shown, the data acquisition and governance module 210 corresponds to the data acquisition layer and spatiotemporal fusion computing layer in the attached figure. It accesses multi-source heterogeneous equipment data such as AIS data source, Beidou positioning data, video surveillance data source, radar data source, and meteorological and tidal data source in parallel through a high-concurrency data channel. The spatial coordinate transformation submodule converts the original coordinates captured by each sensor into the WGS-84 geographic coordinate system. Then, the timestamp synchronization and interpolation submodule uses a sliding time window mechanism to fit the time points of data with inconsistent sampling frequencies, generating a full-element spatiotemporal feature vector under a unified spatiotemporal reference.

[0043] Based on the spatiotemporal feature vector of all elements, the spatiotemporal grid computing module 220 constructs a spatiotemporal data fusion matrix in the spatiotemporal fusion computing layer, divides the fishing port and surrounding sea area into several dynamic grids and establishes a grid index mapping table, and updates the distribution status of fishing boats and the online status of equipment in each grid unit in real time through the spatiotemporal data service interface to form a dynamic spatiotemporal grid.

[0044] The berth dynamic scheduling module 230 corresponds to the berth scheduling algorithm layer in the attached diagram. When the dynamic spatiotemporal grid detects that a target fishing vessel intends to enter the port or crosses the preset port entry electronic fence, it calls the berth resource pool management submodule to obtain the available status data of each berth. The berth dynamic allocation algorithm calculation submodule calculates the matching degree score by comprehensively considering the vessel attributes of the target fishing vessel and the berth line length, design safe water depth, and expected idle time of each berth. Then, the berth allocation decision output submodule selects the berth with the highest matching degree score as the target berth. Finally, the berth allocation is completed by the scheduling instruction generation and issuance submodule.

[0045] The trajectory prediction and guidance module 240 also relies on the full-element spatiotemporal feature vectors provided by the spatiotemporal fusion computing layer. Based on the ship's kinematic constraints, it constructs a trajectory estimation model to extrapolate the spatial coordinate vector of the target fishing vessel at future times. It performs topological relationship verification between the predicted trajectory and the legal entry and exit channel boundaries. If it is determined that there is a risk of overstepping the boundary or deviating from the course, it generates an intelligent guidance instruction that includes the target correction heading angle and the recommended safe speed. This instruction is then sent to the shipboard terminal via the application display layer's scheduling instruction.

[0046] After the target fishing vessel enters the target berth, the compliance verification and handling module 250 calls the static design capacity threshold of the berth stored in the berth scheduling algorithm layer to perform physical scale mismatch calculation with the physical feature vector of the target fishing vessel. At the same time, it starts the dwell timer to monitor the time window overdue. If the verification result is that the physical scale is mismatched or the vessel is illegally occupied due to overdue time, it generates secondary guidance coordinates or troubleshooting prompts. The intelligent early warning and alarm module and the visualization one-map display module of the application display layer complete the closed loop of violation handling.

[0047] Figure 4 This is a schematic diagram of the structure of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the fishing vessel management method based on spatiotemporal data provided in the embodiment of the present invention.

[0048] The terminal 300 may include a processor 310, a memory 320, and a communication module 330. These components communicate via one or more buses. Those skilled in the art will understand that the server structure shown in the figure does not constitute a limitation of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0049] The memory 320 can be used to store the execution instructions of the processor 310. The memory 320 can be implemented by any type of volatile or non-volatile memory terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 is able to perform some or all of the steps in the above method embodiments.

[0050] The processor 310 serves as the control center of the storage terminal, connecting various parts of the electronic terminal via various interfaces and lines. It executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 310 may consist only of a central processing unit (CPU). In this embodiment of the invention, the CPU may have a single processing core or include multiple processing cores.

[0051] The communication module 330 is used to establish a communication channel, enabling the storage terminal to communicate with other terminals. It receives user data sent by other terminals or sends user data to other terminals.

[0052] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps provided in the embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0053] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, mobile hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or other media capable of storing program code. It includes several instructions to cause a computer terminal (which may be a personal computer, server, or a second terminal, network terminal, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0054] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.

Claims

1. A method for managing fishing vessels based on spatiotemporal data, characterized in that, include: S1. Obtain multi-source heterogeneous equipment data within the jurisdiction of the fishing port, and perform spatiotemporal alignment processing on the multi-source heterogeneous equipment data to generate a full-element spatiotemporal feature vector under a unified spatiotemporal benchmark. S2. Based on the spatiotemporal feature vector of all elements, construct and update the dynamic spatiotemporal grid of the fishing port in real time to monitor the real-time status of fishing boats in the dynamic spatiotemporal grid. S3. When the target fishing vessel is detected to have issued an intention to enter the port or cross the preset electronic fence for entering the port based on real-time status monitoring, the berth dynamic allocation algorithm is executed: according to the vessel attributes of the target fishing vessel and the availability status of each berth in the dynamic spatiotemporal grid, the matching degree score between the target fishing vessel and each available berth is calculated, and the target berth is allocated to the target fishing vessel based on the matching degree score. S4. Based on the spatiotemporal feature vector of all elements, predict the spatiotemporal trajectory trend of the target fishing vessel. If the predicted trajectory of the target fishing vessel is found to have abnormal behavior risk, generate and issue intelligent guidance instructions. S5. When a target fishing vessel is detected to have entered the target berth, a joint compliance verification is performed. If the verification result is a violation, a corresponding violation handling strategy is generated and executed.

2. The fishing vessel management method based on spatiotemporal data according to claim 1, characterized in that, Step S1 includes: S11. Parallel access of AIS stream data, BeiDou satellite positioning stream data, radar detection data and port panoramic monitoring video stream data within the fishing port jurisdiction through high-concurrency data channels, extract the original spatial coordinates and original sampling timestamps carried in various types of data, and construct an initial heterogeneous dataset; S12. Establish a spatial projection transformation matrix to uniformly convert the original coordinates captured by each sensor in the initial heterogeneous dataset into the WGS-84 geographic coordinate system, and obtain the intermediate dataset after coordinate standardization. S13. Using the global reference time axis generated by the unified time synchronization of the system as a reference, the cubic spline interpolation algorithm is used to fit the time points of devices in the intermediate dataset whose sampling frequency is lower than a preset threshold, generating a full-element spatiotemporal feature vector under the same time slice. Its expression is: ； in, and These represent the longitude and latitude values ​​of the fishing vessel in the WGS-84 geographic coordinate system at time t, respectively. This represents the instantaneous velocity of the fishing boat calculated based on displacement difference under continuous time slices. This represents the real-time heading angle of the fishing vessel, calculated based on coordinate changes over continuous time slices. This represents the global reference timestamp generated by the system's unified time synchronization.

3. The fishing vessel management method based on spatiotemporal data according to claim 2, characterized in that, Step S2 includes: S21. Read the spatiotemporal feature vector of all elements. Unique identifier for fishing vessels in China, longitude value in WGS-84 geographic coordinate system with latitude value The fishing port and its surrounding sea area are divided into several regularly arranged dynamic grids with a fixed resolution. A dynamic grid index mapping table is established, and the spatiotemporal feature vectors of all elements are mapped. Mapping to the corresponding grid cells generates an initialized dynamic spatiotemporal grid for the fishing port; S22. Based on the dynamic grid index mapping table, extract the full-element spatiotemporal feature vector sequence under continuous time slices within the same grid cell. Use a time window-based trajectory compression algorithm to preprocess the fishing boat trajectory and set a trajectory point distance threshold. If the height of the chord formed by three consecutive trajectory points is less than the trajectory point distance threshold... Then, by removing the redundant trajectory points in the middle, we obtain the denoised fishing boat trajectory point sequence. S23. Based on the denoised fishing vessel trajectory point sequence, construct a Kalman filter state update model, recursively calculate the fishing vessel position and speed at the current moment using the optimal estimate of the previous moment, smooth the denoised fishing vessel trajectory point sequence, restore the actual navigation path of the fishing vessel, and update the distribution status of fishing vessels and the online status of equipment in each grid cell of the fishing port dynamic spatiotemporal grid in real time based on the actual navigation path.

4. The fishing vessel management method based on spatiotemporal data according to claim 1, characterized in that, Step S3 includes: S31. Based on the real-time status of the target fishing vessel monitored in the dynamic spatiotemporal grid, when it is determined that the target fishing vessel has issued an intention to enter the port or crosses the preset electronic fence for entering the port, the approved length, beam, full-load draft and tonnage class of the target fishing vessel are extracted from the spatiotemporal feature vector of all elements. At the same time, the berth line length, design safe water depth, berth class and expected idle time of each candidate berth are retrieved from the dynamic spatiotemporal grid to construct a vessel-berth feature matching dataset. S32. Invoke the pre-stored dynamic berth allocation algorithm, input the ship-berth feature matching dataset into the berth matching score function, calculate the spatial size fit, temporal coordination, and safety environment impact factors between the target fishing vessel and each candidate berth, and dynamically adjust the weight coefficients of each factor according to the real-time congestion situation of the fishing port to calculate the final matching score of each candidate berth. The calculation formula of the berth matching score function is as follows: ； in, This represents the matching score of the i-th target fishing vessel to the j-th candidate berth; The weighting coefficients are dynamically adjusted by the system based on the real-time congestion situation at the fishing port, and they satisfy the constraints. ; This is a function for spatial dimension fit. This is a time coordination function used to quantify the estimated arrival time (ETA) of the target fishing vessel and the estimated idle time of the candidate berth. The degree of synchronization; Environmental impact factors; S33. Traverse the matching scores of all candidate berths, select the candidate berth with the highest matching score and determine it as the target berth. At the same time, write the spatial coordinates and berth attribute information of the target berth into the spatiotemporal feature vector of all elements to update the scheduling instruction set of the target fishing vessel.

5. The fishing vessel management method based on spatiotemporal data according to claim 4, characterized in that, Spatial Dimension Fit Function The calculation formula is: ； Among them, when When this occurs, a hard constraint elimination mechanism is triggered, setting the matching score of the candidate berth to zero and excluding it from the possibility of being the target berth.

6. The fishing vessel management method based on spatiotemporal data according to claim 1, characterized in that, Step S4 includes: S41. Read the historical navigation trajectory sequence of the target fishing vessel, its current position coordinates in the WGS-84 geographic coordinate system, instantaneous speed and real-time heading angle from the spatiotemporal feature vector of all elements. Construct a trajectory estimation model based on ship kinematic constraints, and extrapolate the continuous spatial coordinate vector of the target fishing vessel in the future preset time window to generate a predicted trajectory point sequence. S42. Retrieve the pre-stored dataset of polygonal boundaries of legal entry and exit channels and authorized berth areas stored in the system. Perform topological relationship verification on each spatial coordinate vector in the predicted track point sequence with the preset polygonal boundaries of legal entry and exit channels and authorized berth areas to determine whether the predicted coordinates are located inside or on the edge of the polygonal boundary. If the verification result shows that any predicted coordinate is topologically separated from the polygonal boundary, it is determined that the predicted track of the target fishing vessel has the risk of abnormal behavior such as crossing the boundary or deviating from the course. S43. When it is determined that the predicted trajectory of the target fishing vessel has an abnormal behavior risk, based on the real-time navigation status in the dynamic spatiotemporal grid, the A* path search algorithm is called to solve the optimal correction path from the current position coordinates to the nearest legal boundary. Based on the optimal correction path, the target correction heading angle and safe recommended speed are calculated, and a dynamic guidance command message containing the target correction heading angle, safe recommended speed and target guidance coordinates is generated. The dynamic guidance command message is then sent to the shipborne terminal or crew mobile terminal associated with the target fishing vessel through the wireless communication link.

7. The fishing vessel management method based on spatiotemporal data according to claim 1, characterized in that, Step S5 includes: S51. Based on real-time monitoring of the target fishing vessel's position coordinates using a dynamic spatiotemporal grid, when the target fishing vessel is detected entering the electronic fence area of ​​the target berth, the approved length, beam, full-load draft, and tonnage class of the target fishing vessel are extracted from the full-element spatiotemporal feature vector. Simultaneously, the static design capacity threshold of the target berth is retrieved, including berth line length, design safe water depth, and berth class. A physical scale mismatch verification dataset is constructed, and physical scale mismatch calculation is performed. The criteria for determining physical scale mismatch are: ； in, The berth depth fit coefficient is used to characterize the actual water depth of the target berth. With the target fishing vessel at full load draft The degree of matching; This is the preset ship navigation safety factor; This refers to the safe water depth threshold. The tonnage class of the target fishing vessel. The berth class of the target berth; The tolerance coefficient for resource degradation; if any of the above judgment conditions are met, it is determined that a physical scale mismatch has occurred, that is, there is a risk of large fishing boats entering shallow water berths and causing them to run aground or small fishing boats occupying high-grade deep water berths and causing waste of resources. S52. Upon determining that the target fishing vessel has successfully entered the target berth, the system uses a unified global reference timestamp. Start the dwell timer to accumulate the continuous dwell time of the target fishing vessel in the target berth in real time. And will remain there for a certain period of time. With preset safety buffer threshold A comparison is performed; if the target fishing vessel meets the requirements while not unloading cargo... If so, it will be judged as an unauthorized occupation exceeding the time limit; S53. If the physical scale mismatch calculation result is determined to be a violation, or the dwell timer is determined to be an overdue violation, then a corresponding violation handling strategy will be generated: For violations related to physical scale mismatch, the dynamic berth allocation algorithm is re-invoked to calculate suitable available berths, generating a secondary guidance instruction containing the coordinates of the new target berth and sending it to the crew's mobile terminal. For violations related to overdue occupation, the target fishing vessel's status is marked as "overdue occupation," and a troubleshooting message containing the target fishing vessel's unique identifier, violation type, and suggested handling measures is generated. This troubleshooting message is then sent to the port dispatch terminal's monitoring screen and the duty personnel's terminal, completing the closed loop for violation handling.

8. A fishing vessel management and control system based on spatiotemporal data, characterized in that, include: The data acquisition and governance module is used to acquire multi-source heterogeneous equipment data within the fishing port jurisdiction, and to perform spatiotemporal alignment processing on the multi-source heterogeneous equipment data to generate a full-element spatiotemporal feature vector under a unified spatiotemporal benchmark. The spatiotemporal grid computing module is used to construct and update the dynamic spatiotemporal grid of the fishing port in real time based on the spatiotemporal feature vector of all elements, so as to monitor the real-time status of fishing boats in the dynamic spatiotemporal grid. The berth dynamic scheduling module is used to execute the berth dynamic allocation algorithm when the target fishing vessel sends an intention to enter the port or crosses the preset port entry electronic fence based on the real-time status monitoring: according to the vessel attributes of the target fishing vessel and the availability status of each berth in the dynamic spatiotemporal grid, the matching degree score between the target fishing vessel and each available berth is calculated, and the target berth is allocated to the target fishing vessel based on the matching degree score. The trajectory prediction and guidance module is used to predict the spatiotemporal trajectory trend of the target fishing vessel based on the spatiotemporal feature vector of all elements. If the predicted trajectory of the target fishing vessel is found to have abnormal behavior risk, an intelligent guidance command is generated and issued. The compliance verification and handling module is used to perform a joint compliance verification when a target fishing vessel is detected entering the target berth. If the verification result is a violation, the module generates and executes the corresponding violation handling strategy.

9. A terminal, characterized in that, include: processor; Memory used to store the processor's execution instructions; The processor is configured to perform the method of any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images