A method and system for monitoring and managing fishing vessels in a fishing port

Abstract

The application discloses a fishing boat abnormality monitoring method and management system in a fishing port, and relates to the technical field of harbor management.The application comprises the following steps: continuously acquiring the ship position data of the fishing boats in the fishing port after the fishing boats enter the port, wherein the ship position data comprises the MMSI code and the position of the fishing boats; marking the fishing boats confirmed to be abnormal to obtain the ship position data of the fishing boats in the fishing port in an abnormal state, and extracting the abnormal characteristics of the fishing boats; comparing the normal state characteristics of the fishing boats with the abnormal state characteristics to obtain a fishing boat abnormal behavior characteristic vector set; determining whether the fishing boats in the fishing port are in an abnormal state according to the abnormal characteristic vector set, and if yes, sending a warning instruction to the fishing boats in the abnormal state and / or the adjacent fishing boats, and if not, not responding.The application can effectively reduce the risk factors in the fishing port.

Description

Technical Field

[0001] This invention belongs to the field of port management technology, and in particular relates to a method and management system for monitoring abnormalities of fishing vessels in a fishing port. Background Technology

[0002] Traditional fishing vessel monitoring systems typically rely on equipment such as Automatic Identification System (AIS), GPS, and radar to monitor the position and movement trajectory of fishing vessels. Although existing positioning technologies can provide real-time location data for fishing vessels, GPS signals may be interfered with in fishing ports due to factors such as port topography and building obstructions, leading to decreased positioning accuracy. This makes it difficult to accurately determine abnormal behavior of fishing vessels and can easily result in collisions and other abnormal situations. Summary of the Invention

[0003] The purpose of this invention is to provide a method and management system for monitoring and managing abnormal fishing vessels in a fishing port. By analyzing the position data of fishing vessels, it can predict whether the fishing vessels are in a risky state, thereby providing timely warnings and effectively reducing risk factors in the fishing port.

[0004] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0005] This invention provides a method for monitoring abnormalities in fishing vessels within a fishing port, comprising:

[0006] After the fishing boats enter the port, the position data of the fishing boats in the port will be continuously acquired, including the MMSI code and position of the fishing boats.

[0007] Mark the fishing vessels that are confirmed to be abnormal, and obtain the vessel position data of the fishing vessels in the abnormal state in the fishing port during the abnormal period.

[0008] Extract the data features of fishing vessel positions within the fishing port as the vessel position features.

[0009] The range of abnormal vessel position characteristics is obtained based on the position characteristics of fishing vessels in abnormal states within the fishing port during abnormal periods and the position characteristics of fishing vessels in abnormal states.

[0010] Determine whether the fishing vessels in the fishing port are in an abnormal state at the current moment based on the range of abnormal vessel position characteristics.

[0011] If so, send a warning instruction to the fishing vessel in the abnormal state and / or adjacent fishing vessels.

[0012] If not, no response will be given.

[0013] This invention also discloses a method for monitoring abnormalities in fishing vessels within a fishing port, including:

[0014] Receive alert instructions;

[0015] Enter collision alert status.

[0016] This invention also discloses a monitoring and management system for abnormal fishing vessel conditions within a fishing port, comprising:

[0017] The port management terminal is used to continuously acquire the position data of fishing vessels in the port after they enter the port. The position data includes the MMSI code and location of the fishing vessel.

[0018] By marking the fishing vessels confirmed to be abnormal, the position data of the fishing vessels in the abnormal state in the fishing port during the abnormal period can be obtained.

[0019] Extract the data features of fishing vessel positions within the fishing port as the vessel position features.

[0020] The range of abnormal vessel position characteristics is obtained based on the position characteristics of fishing vessels in abnormal states within the fishing port during abnormal periods and the position characteristics of fishing vessels in abnormal states.

[0021] Determine whether the fishing vessels in the fishing port are in an abnormal state at the current moment based on the range of abnormal vessel position characteristics.

[0022] If so, send a warning instruction to the fishing vessel in the abnormal state and / or adjacent fishing vessels.

[0023] If not, no response will be given;

[0024] The end of the fishing boat is used to receive warning instructions;

[0025] Enter collision alert status.

[0026] This invention collects vessel position data reported by fishing vessels in the fishing port through the port management terminal, analyzes the abnormal vessel position characteristic range after marking the status of the fishing vessels, and determines whether the fishing vessels in the fishing port are in an abnormal state at the current time, thereby issuing warnings to the fishing vessels in an abnormal state and effectively reducing risk factors in the fishing port.

[0027] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a schematic diagram of the functional units and information flow of an embodiment of the fishing vessel anomaly monitoring and management system in a fishing port according to the present invention.

[0030] Figure 2 This is a schematic diagram of the steps of a port management terminal according to an embodiment of the present invention;

[0031] Figure 3 This is a schematic diagram of the steps of one embodiment of the fishing boat end described in the present invention;

[0032] Figure 4 This is a flowchart illustrating step S1 of the present invention in one embodiment;

[0033] Figure 5 This is a flowchart illustrating step S13 of the present invention in one embodiment.

[0034] Figure 6 This is a flowchart illustrating step S3 of the present invention in one embodiment;

[0035] Figure 7 This is a flowchart illustrating step S4 of the present invention in one embodiment;

[0036] Figure 8 This is a flowchart illustrating step S41 of the present invention in one embodiment.

[0037] Figure 9 This is a flowchart illustrating step S414 of the present invention in one embodiment.

[0038] Figure 10 This is a flowchart illustrating step S5 of the present invention in one embodiment.

[0039] The attached diagram lists the components represented by each number as follows:

[0040] 1-Port management terminal, 2-Fishing vessel terminal. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0042] It should be noted that the terms "first," "second," etc., used in this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0043] Please see Figures 1 to 3As shown, this invention provides a monitoring and management system for abnormal fishing vessel conditions within a fishing port. Functionally, it comprises a port management terminal 1 and a fishing vessel terminal 2. The port management terminal 1 can be a virtual functional unit, or in practice, a dedicated piece of equipment. The fishing vessel terminal 2 can be a communication device installed within the fishing vessel.

[0044] After fishing vessels enter the port, the port management terminal 1 in this solution continues to operate, continuously acquiring vessel position data within the port through step S1 via the VTS (Vessel Traffic Management System) and AIS (Automatic Identification System). This position data includes the vessel's MMSI code, location, speed, tonnage, and other information. The MMSI code is a nine-digit code transmitted by the vessel's radio communication system on its radio channel, uniquely identifying various stations and groups of calling stations; it is commonly known as a "nine-digit code." Next, step S2 can be executed to mark confirmed abnormal fishing vessels, obtaining the position data of vessels in abnormal states within the port during the abnormal period. This marking is done manually by fisheries administration, traffic control, or port staff.

[0045] Please see Figure 6 As shown, due to the complexity of fishing vessel position data, it is not convenient to compare and analyze different fishing vessels. Therefore, step S3 can be performed to extract the data features of the fishing vessel position data within the fishing port as the vessel position features. Considering that this scheme mainly considers the collision risk between fishing vessels within the fishing port, the factors closely related to collisions between fishing vessels are mainly the mass of the fishing vessels and navigation-related parameters. Therefore, in the process of extracting the vessel position features, step S31 can be performed first to extract the tonnage, speed, course, and position of the fishing vessels from the position data. To facilitate comparison and calculation, step S32 can be performed to vectorize the tonnage, speed, course, and position of each fishing vessel in the same order as the vessel position features of each fishing vessel.

[0046] Since fishing vessels in abnormal states usually share common characteristics, such as high speed, large tonnage, and abnormal navigation, in order to calculate the range of abnormal vessel position characteristics, step S4 can be executed first to obtain the range of abnormal vessel position characteristics based on the position characteristics of fishing vessels in abnormal states within the fishing port during the abnormal period and the position characteristics of fishing vessels in normal states.

[0047] In the real-time anomaly detection process of fishing vessels within the port in this scheme, the port management terminal 1 first executes step S5 to determine whether the fishing vessels in the port are in an abnormal state at the current moment based on the abnormal vessel position characteristic range. If so, it indicates that the fishing vessel is in collision danger, so step S6 can be executed to send a warning command to the fishing vessel in the abnormal state. Of course, a warning command can also be sent to the fishing vessel adjacent to the one in the abnormal state to serve as a warning. Otherwise, it means that no anomaly has been detected, so step S7 can be executed without responding.

[0048] After receiving the warning instruction in step S021, the fishing vessel terminal 2 installed inside the fishing vessel can then proceed to step S022 to enter the collision warning state, reminding the captain, captain, and other staff inside the fishing vessel to pay attention to navigation safety in the fishing port.

[0049] Please see Figures 4 to 5 As shown, the most important abnormal state of fishing vessels is whether they are in a collision-hazardous state, which is usually closely related to the distance between fishing vessels. The positions of fishing vessels obtained through VTS and AIS systems are not very accurate. This is especially true when fishing vessels are close together, requiring more precise positions. Therefore, the port management terminal 1 in this solution needs to appropriately improve the position accuracy of some fishing vessels during operation, taking into account the positional conditions between them. Specifically, firstly, a rough distance between fishing vessels can be obtained, that is, step S11 is executed to retrieve abnormal state records of fishing vessels in the fishing port based on the MMSI codes in the vessel position data, and fishing vessels with abnormal records are marked as high-risk vessels. Next, step S12 is executed to obtain the initial distance between multiple high-risk fishing vessels and their nearest neighboring fishing vessel under abnormal conditions, based on the vessel position data of fishing vessels in abnormal states during the abnormal period, as the critical distance.

[0050] Next, step S13 can be executed to obtain the safe distance within the fishing port based on the critical distances of multiple high-risk fishing vessels. Specifically, first, step S131 can be executed to take the maximum value among the critical distances of multiple high-risk fishing vessels as the baseline safe distance. Next, step S132 can be executed to take the difference between the maximum and minimum values ​​among the critical distances of multiple high-risk fishing vessels as the window width of the safe distance. Next, step S133 can be executed to take the ratio of the window width of the safe distance to the number of high-risk fishing vessels as the floating difference distance. Finally, step S134 can be executed to take the sum of the baseline safe distance and the floating difference distance as the safe distance within the fishing port.

[0051] To determine whether the distance between a fishing vessel and its neighboring vessels is too close, step S14 can be executed to determine whether the distance between fishing vessels in the harbor is less than the safe distance based on the vessel's position data. If not, the distance is safe enough, so step S15 can be executed without responding. If so, the distance is too close, so step S16 can be executed to mark fishing vessels whose distance is less than the safe distance as key fishing vessels. Finally, step S17 can be executed to obtain a more accurate position of the key fishing vessels through several other methods and correct the position in the vessel position data of the key fishing vessels.

[0052] Other methods for obtaining fishing vessel locations in this solution include panoramic high-definition camera image positioning, which uses video linkage tracking to monitor the accurate location of fishing vessels within the port. The video linkage tracking module provides on-site, full-process monitoring when key vessels enter key waters under maritime safety control, enabling automatic, continuous tracking by surveillance cameras to ensure the navigational safety of these vessels. The video linkage tracking module is linked with the vessel dynamic monitoring system, allowing the video feed to quickly locate the target vessel and automatically control the front-end equipment to keep the target vessel centered in the frame based on the vessel's direction and speed of movement.

[0053] To supplement the explanation of the implementation process of steps S11 to S17 above, source code for some functional modules is provided, with comparative explanations in the comments. To avoid data leakage involving trade secrets, data that does not affect the implementation of the solution has been anonymized, and the same applies below.

[0054] #include <iostream>

[0055] #include <vector>

[0056] #include <string>

[0057] #include <cmath>

[0058] #include<unordered_set>

[0059] #include <limits>

[0060] / / Define the vessel position data structure

[0061] struct ShipPosition {

[0062] std::string MMSI; / / MMSI encoding of the fishing vessel

[0063] double latitude; / / Latitude of the fishing boat's location

[0064] double longitude; / / Longitude of the fishing boat's location

[0065] bool isHighRisk; / / Whether it is a high-risk fishing vessel

[0066] bool isKeyShip; / / Whether it is a key fishing vessel

[0067] };

[0068] / / Simulate the acquisition of fishing boat position data

[0069] std::vector <shipposition>getShipPositions() {

[0070] return {

[0071] {"123456789", 34.5, 120.3, false, false},

[0072] {"987654321", 34.51, 120.32, false, false}

[0073] / / Add more data

[0074] };

[0075] }

[0076] / / Simulate obtaining the MMSI list of high-risk fishing vessels

[0077] std::unordered_set <std::string>getHighRiskMMSI() {

[0078] return {"987654321"}; / / Example of a high-risk fishing vessel MMSI

[0079] }

[0080] / / Calculate the distance between the two fishing boats

[0081] double calculateDistance(const ShipPosition&ship1, constShipPosition&ship2) {

[0082] return std::sqrt(std::pow(ship1.latitude - ship2.latitude, 2) +

[0083] std::pow(ship1.longitude - ship2.longitude, 2));

[0084] }

[0085] / / Critical distance for obtaining high-risk fishing vessels

[0086] std::vector <double>getCriticalDistances(const std::vector <shipposition>&ships) {

[0087] std::vector <double>criticalDistances;

[0088] for (const auto&ship : ships) {

[0089] if (ship.isHighRisk) {

[0090] double minDistance = std::numeric_limits <double>::max();

[0091] for (const auto& otherShip : ships) {

[0092] if (ship.MMSI != otherShip.MMSI) {

[0093] double distance = calculateDistance(ship, otherShip);

[0094] if (distance < minDistance) {

[0095] minDistance = distance;

[0096] }

[0097] }

[0098] }

[0099] criticalDistances.push_back(minDistance);

[0100] }

[0101] }

[0102] return criticalDistances;

[0103] }

[0104] / / Calculate the safety distance

[0105] double calculateSafetyDistance(const std::vector <double>&criticalDistances, size_t highRiskCount) {

[0106] if (criticalDistances.empty() || highRiskCount == 0) return 0.0;

[0107] double maxCriticalDistance = *std::max_element(criticalDistances.begin(), criticalDistances.end());

[0108] double minCriticalDistance = *std::min_element(criticalDistances.begin(), criticalDistances.end());

[0109] double windowWidth = maxCriticalDistance - minCriticalDistance;

[0110] double floatingDifference = windowWidth / highRiskCount;

[0111] return maxCriticalDistance + floatingDifference;

[0112] }

[0113] / / Correct the location of key fishing vessels

[0114] void correctPosition(ShipPosition&ship) {

[0115] / / Simulated position correction; in practical applications, data should be obtained from more precise sensors.

[0116] ship.latitude += 0.0001;

[0117] ship.longitude += 0.0001;

[0118] }

[0119] int main() {

[0120] / / Get fishing boat position data

[0121] std::vector <shipposition>shipPositions = getShipPositions();

[0122] / / Retrieve the MMSI codes of high-risk fishing vessels

[0123] auto highRiskMMSI = getHighRiskMMSI();

[0124] / / Mark high-risk fishing vessels

[0125] for (auto&ship : shipPositions) {

[0126] if (highRiskMMSI.find(ship.MMSI) != highRiskMMSI.end()) {

[0127] ship.isHighRisk = true;

[0128] }

[0129] }

[0130] / / Critical distance for obtaining high-risk fishing vessels

[0131] std::vector <double>criticalDistances = getCriticalDistances(shipPositions);

[0132] / / Calculate the safe distance

[0133] double safetyDistance = calculateSafetyDistance(criticalDistances,highRiskMMSI.size());

[0134] / / Determine if the distance between fishing boats is less than the safe distance.

[0135] for (auto&ship : shipPositions) {

[0136] for (auto&otherShip : shipPositions) {

[0137] if (ship.MMSI != otherShip.MMSI) {

[0138] double distance = calculateDistance(ship, otherShip);

[0139] if (distance <safetyDistance) {

[0140] ship.isKeyShip = true;

[0141] otherShip.isKeyShip = true;

[0142] }

[0143] }

[0144] }

[0145] }

[0146] / / Correct the location of key fishing vessels

[0147] for (auto&ship : shipPositions) {

[0148] if (ship.isKeyShip) {

[0149] correctPosition(ship);

[0150] }

[0151] }

[0152] / / Output results

[0153] for (const auto&ship : shipPositions) {

[0154] std::cout<<"MMSI: "< <ship.MMSI

[0155] <<", Latitude: "< <ship.latitude

[0156] <<", Longitude: "< <ship.longitude

[0157] <<", HighRisk: "< <ship.isHighRisk

[0158] <<", KeyShip: "< <ship.isKeyShip<<std::endl;

[0159] }

[0160] return 0;

[0161] }

[0162] This code implements continuous monitoring of fishing vessels within the fishing port. It identifies high-risk vessels using MMSI coding, calculates critical and safe distances, determines whether the distance between vessels is less than the safe distance, and marks them as priority vessels, further refining their position data. This process helps to effectively manage and monitor collision safety of fishing vessels within the fishing port.

[0163] Please see Figure 7 As shown, in step S4 above, the abnormal vessel position feature range can be calculated by referring to the vessel position features of fishing vessels in normal state against the abnormal vessel position features. Specifically, firstly, step S41 can be executed to divide the vessel position features of fishing vessels in abnormal and normal states into multiple internally correlated vessel position feature sets based on the degree of difference between the vessel position features. Next, step S42 can be executed to take the vessel position feature set composed entirely of the vessel position features of fishing vessels in abnormal state as the pure abnormal vessel position feature set, and obtain the vector range corresponding to each pure abnormal vessel position feature set as the pure abnormal vessel position feature range. Next, step S43 can be executed to take the vessel position feature set composed entirely of the vessel position features of fishing vessels in normal state as the pure normal vessel position feature set, and obtain the vector range corresponding to each pure normal vessel position feature set as the pure normal vessel position feature range. Next, step S44 can be executed to take the vessel position feature set composed of the mixed vessel position features of fishing vessels in normal and abnormal states as the mixed vessel position feature set, and obtain the vector range corresponding to each mixed vessel position feature set as the mixed vessel position feature range.

[0164] Since collisions between fishing vessels can result in incalculable losses, to minimize the risk of collisions within the fishing port, the range of abnormal vessel position characteristics can be appropriately widened. Specifically, step S45 can be executed to subtract the overlapping portion between the mixed vessel position characteristic range and the pure normal vessel position characteristic range, and the remaining portion can be used as the supplementary abnormal vessel position characteristic range. Finally, step S46 can be executed to include both the pure abnormal vessel position characteristic range and the supplementary abnormal vessel position characteristic range as the abnormal vessel position characteristic range.

[0165] Please see Figures 8 to 9 As shown, in the process of analyzing ship position features with internal correlation, the first step, S411, involves selecting multiple marker ship position features from all ship position features. This selection can be random or pre-selected by staff. Next, step S412 uses the vector difference norm between ship position features as the degree of difference between them, calculating the vector difference norm between each marker ship position feature and each of the other ship position features. Finally, step S413 groups each other ship position feature with the marker ship position feature having the smallest vector difference norm into the same ship position feature set.

[0166] In the process of classifying ship position features, step S414 can be executed to determine whether the ship position feature sets have sufficient correlation based on the vector difference norm between the ship position features within each set. Specifically, step S4141 can be executed first to calculate the mean vector of all ship position features contained in each ship position feature set. Next, step S4142 can be executed to select the ship position feature with the smallest vector difference norm between its vector difference and the mean vector as the updated labeled ship position feature. Next, step S4143 can be executed to determine whether the updated labeled ship position features have changed. If all the updated labeled ship position features remain unchanged, then step S4144 can be executed to determine that the ship position features within each set have sufficient correlation. If any of the updated labeled ship position features have changed, then step S4145 can be executed to determine that the ship position features within each set do not have sufficient correlation.

[0167] If it is determined that there is insufficient correlation between the ship position features within the ship position feature set, then steps S412 to S414 can be executed iteratively to generate updated labeled ship position features and ship position feature set, and the question of whether there is sufficient correlation can be continuously determined. If there is insufficient correlation between the ship position features within the ship position feature set, then step S415 can be executed to output the ship position feature set that is correlated internally.

[0168] To supplement the explanation of the implementation process of steps S411 to S415 above, source code for some functional modules is provided, with comparative explanations in the comments. To avoid data leakage involving trade secrets, data that does not affect the implementation of the solution has been anonymized, and the same applies below.

[0169] #include <iostream>

[0170] #include <vector>

[0171] #include <cmath>

[0172] #include <limits>

[0173] / / Define ship position feature structure

[0174] struct FeatureVector {

[0175] std::string MMSI;

[0176] std::vector <double>features

[0177] };

[0178] / / Calculate the vector difference norm

[0179] double calculateNorm(const std::vector <double>&v1, const std::vector <double>&v2) {

[0180] double sum = 0.0;

[0181] for (size_t i = 0; i <v1.size(); ++i) {

[0182] sum += std::pow(v1[i] - v2[i], 2);

[0183] }

[0184] return std::sqrt(sum);

[0185] }

[0186] / / Calculate the mean vector

[0187] std::vector <double>calculateMeanVector(const std::vector <featurevector>&featureSet) {

[0188] std::vector <double>mean(featureSet[0].features.size(), 0.0);

[0189] for (const auto&fv : featureSet) {

[0190] for (size_t i = 0; i <fv.features.size(); ++i) {

[0191] mean[i] += fv.features[i];

[0192] }

[0193] }

[0194] for (double&val : mean) {

[0195] val / = featureSet.size();

[0196] }

[0197] return mean;

[0198] }

[0199] / / Main function

[0200] int main() {

[0201] / / Example of extracted ship position features

[0202] std::vector <featurevector>allFeatures = {

[0203] {"123456789", {500.0, 15.5, 180.0, 34.5, 120.3}},

[0204] {"987654321", {600.0, 14.0, 90.0, 34.51, 120.32}},

[0205] {"111222333", {550.0, 16.0, 175.0, 34.6, 120.4}},

[0206] / / Add more data

[0207] };

[0208] / / Initialize the marker ship position features (the first two in the example are markers)

[0209] std::vector <featurevector>markedFeatures = {allFeatures[0],allFeatures[1]};

[0210] std::vector <featurevector>updatedMarkedFeatures = markedFeatures;

[0211] bool hasChanged;

[0212] do {

[0213] hasChanged = false;

[0214] / / Create feature set

[0215] std::vector <std::vector <featurevector>>featureSets(markedFeatures.size());

[0216] / / Classification of ship position characteristics

[0217] for (const auto&feature : allFeatures) {

[0218] double minNorm = std::numeric_limits <double>::max();

[0219] size_t bestIndex = 0;

[0220] for (size_t i = 0; i < markedFeatures.size(); ++i) {

[0221] double norm = calculateNorm(feature.features, markedFeatures[i].features);

[0222] if (norm < minNorm) {

[0223] minNorm = norm;

[0224] bestIndex = i;

[0225] }

[0226] }

[0227] featureSets[bestIndex].push_back(feature);

[0228] }

[0229] / / Update the marked ship position features

[0230] for (size_t i = 0; i < featureSets.size(); ++i) {

[0231] if (!featureSets[i].empty()) {

[0232] std::vector <double>meanVector = calculateMeanVector(featureSets[i]);

[0233] double minNorm = std::numeric_limits <double>::max();

[0234] FeatureVector bestFeature;

[0235] for (const auto&feature : featureSets[i]) {

[0236] double norm = calculateNorm(feature.features, meanVector);

[0237] if (norm <minNorm) {

[0238] minNorm = norm;

[0239] bestFeature = feature;

[0240] }

[0241] }

[0242] if (bestFeature.MMSI != updatedMarkedFeatures[i].MMSI) {

[0243] updatedMarkedFeatures[i] = bestFeature;

[0244] hasChanged = true;

[0245] }

[0246] }

[0247] }

[0248] / / Update marker ship position features

[0249] markedFeatures = updatedMarkedFeatures;

[0250] } while (hasChanged);

[0251] / / Output a set of ship position features with sufficient correlation

[0252] for (size_t i = 0; i <featureSets.size(); ++i) {

[0253] std::cout << "Feature Set " << i + 1 << ":\n";

[0254] for (const auto& feature : featureSets[i]) {

[0255] std::cout << "MMSI: " << feature.MMSI << ", Features: ";

[0256] for (const auto& f : feature.features) {

[0257] std::cout << f << " ";

[0258] }

[0259] std::cout << std::endl;

[0260] }

[0261] }

[0262] return 0;

[0263] }

[0264] This code implements the clustering process of ship position features. By calculating the difference between each ship position feature and the labeled feature, it performs classification and updates the labeled feature until there is no change. This method ensures that each feature set has sufficient relevance, forming internally related feature sets.

[0265] Please refer to Figure 10 As the above step S4 uses ship position features to judge abnormal states, in the process of judging whether the fishing boats in the fishing port are in an abnormal state at the current time, step S51 can be performed first to extract the ship position features of the fishing boats in the fishing port at the current time according to the ship position data of the fishing boats in the fishing port at the current time. Next, step S52 can be performed to judge whether the ship position features of the fishing boats in the fishing port at the current time are within the abnormal ship position feature range. If yes, step S53 is triggered to determine that the fishing boats are in an abnormal state, and if no, step S54 is triggered to determine that the fishing boats are not in an abnormal state.

[0266] The computer program product of the second aspect can include a computer readable storage medium. The computer readable storage medium can include instructions. The instructions can include one or both of: instructions for causing a computer to implement a method as described above; and instructions for causing a computer to operate based on a product of design as described above.

[0267] It is also noted that each of the blocks of the flowchart and / or the block diagrams, and combinations of the blocks in the flowchart and / or the block diagrams, can be implemented by hardware, software, firmware or a combination thereof, as appropriate. Also, the blocks in the flowchart and / or the block diagrams can be implemented in hardware, software, firmware or a combination thereof, as appropriate.

[0268] Although the present application has been described in connection with various embodiments, it will be understood that the application is capable of further modifications. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude a plurality. A single processor or other unit can fulfil the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. The references in the specification to "one embodiment" or "the embodiment" mean that a particular feature, structure, or characteristic described is included in at least one embodiment. Thus, the appearance of the phrases "in one embodiment" or "in the embodiment" in various places in the specification are not necessarily all referring to the same embodiment.

[0269] As various changes could be made in the above constructions, methods and order of operations without departing from the scope of the application, it is intended that all matter contained in the above description shall be interpreted as illustrative and not in a limiting sense. The language used in the specification is expressly intended to be illustrative only and not limiting, unless specifically stated otherwise.< / double> < / double> < / double> < / featurevector> < / featurevector> < / featurevector> < / featurevector> < / double> < / featurevector> < / double> < / double> < / double> < / double> < / limits> < / cmath> < / vector> < / iostream> < / double> < / shipposition> < / double> < / double> < / double> < / shipposition> < / double> < / std::string> < / shipposition> < / limits> < / cmath> < / string> < / vector> < / iostream>

Claims

1. A method for monitoring abnormalities in fishing vessels within a fishing port, characterized in that, include, After the fishing boats enter the port, the position data of the fishing boats in the port will be continuously acquired, including the MMSI code and position of the fishing boats. The fishing vessels confirmed to be abnormal are marked, and the position data of the fishing vessels in abnormal state in the fishing port during the abnormal period are obtained. Extract the data features of fishing vessel positions within the fishing port as the vessel position features. Based on the degree of difference between vessel position characteristics, the vessel position characteristics of fishing vessels in abnormal and normal states are divided into multiple sets of internally correlated vessel position characteristics. The set of vessel position features consisting entirely of the vessel position features of fishing vessels in abnormal states is taken as the pure abnormal vessel position feature set, and the vector range corresponding to each pure abnormal vessel position feature set is taken as the pure abnormal vessel position feature range. The set of vessel position features consisting entirely of vessel position features of fishing vessels in normal condition is taken as the pure normal vessel position feature set, and the vector range corresponding to each pure normal vessel position feature set is taken as the pure normal vessel position feature range. The set of vessel position features composed of the mixed vessel position features of fishing vessels in normal and abnormal states is called the mixed vessel position feature set, and the vector range corresponding to each mixed vessel position feature set is obtained as the mixed vessel position feature range. The remaining portion after subtracting the overlap with the pure normal ship position characteristic range from the mixed ship position characteristic range is used as the supplementary abnormal ship position characteristic range. Both the pure abnormal ship position feature range and the supplementary abnormal ship position feature range are considered as the abnormal ship position feature range. Determine whether the fishing vessels in the fishing port are in an abnormal state at the current moment based on the range of abnormal vessel position characteristics. If so, send a warning instruction to the fishing vessel in the abnormal state and / or adjacent fishing vessels. If not, no response will be given.

2. The method according to claim 1, characterized in that, The step of continuously acquiring the position data of fishing vessels within the fishing port includes, Based on the MMSI code in the fishing vessel's position data, retrieve records of abnormal conditions of the fishing vessel in the fishing port, and mark the fishing vessel with abnormal records as a high-risk fishing vessel. Based on the position data of fishing vessels in abnormal conditions within the fishing port during the abnormal period, the initial distance between multiple high-risk fishing vessels and the nearest adjacent fishing vessel under abnormal conditions is obtained as the critical distance. The safe distance within the fishing port is determined based on the critical distance between multiple high-risk fishing vessels. Determine whether the distance between fishing boats in the fishing port is less than the safe distance based on the position data of the fishing boats. If not, no response will be given; If so, fishing vessels that are less than the safe distance from each other will be marked as key fishing vessels; We will obtain more precise positions of key fishing vessels through several other methods and correct the positions in the vessel position data of key fishing vessels.

3. The method according to claim 2, characterized in that, The step of determining the safe distance within the fishing port based on the critical distance between multiple high-risk fishing vessels... include, The maximum value among the critical distances of multiple high-risk fishing vessels is used as the benchmark safe distance; The difference between the maximum and minimum critical distances of multiple high-risk fishing vessels is used as the window width for safe distance; The ratio of the window width of the safe distance to the number of high-risk fishing vessels is used as the floating difference distance; The sum of the baseline safety distance and the floating difference distance is taken as the safety distance within the fishing port.

4. The method according to claim 1, characterized in that, The step of extracting data features of fishing vessel positions within the fishing port as the vessel position features includes, Extract the tonnage, speed, course, and position of the fishing vessel from the vessel position data; The tonnage, speed, course, and position of each fishing vessel are arranged in the same order and vectorized as the position characteristics of each fishing vessel.

5. The method according to claim 1, characterized in that, The step of dividing the position characteristics of fishing vessels in abnormal and normal states into multiple sets of internally correlated position characteristics based on the degree of difference between their position characteristics includes, Select multiple marker ship position features from all ship position features; The vector difference norm between ship position features is used as the difference between ship position features. The vector difference norm between each labeled ship position feature and each other ship position feature is calculated. For each other position feature, classify it and the labeled position feature with the smallest vector difference norm into the same position feature set; Determine whether the ship position feature set has sufficient correlation based on the vector difference norm between ship position features within each ship position feature set; If so, the updated marked ship position features and ship position feature set are generated iteratively, and the correlation is continuously judged. If not, then a set of ship position features with internal correlation is obtained.

6. The method according to claim 1, characterized in that, The step of determining whether a ship position feature set has sufficient correlation based on the vector difference norm between ship position features within each ship position feature set includes: For each of the aforementioned ship position feature sets Calculate the mean vector of all ship position features contained in the aforementioned ship position feature set. The ship position feature with the smallest vector difference norm between itself and the mean vector within the set of ship position features is used as the updated labeled ship position feature. Determine whether the updated marker ship position characteristics have changed; If all the updated marked ship position features remain unchanged, then there is sufficient correlation between the ship position features within each set of ship position features. If none of the existing updated marked vessel position features change, then there is no sufficient correlation between the vessel position features within each set of vessel position features.

7. The method according to claim 1, characterized in that, The step of determining whether fishing vessels in the port are in an abnormal state at the current moment based on the range of abnormal vessel position characteristics includes, The position characteristics of fishing vessels in the fishing port at the current moment are extracted based on the position data of fishing vessels in the fishing port at the current moment. Determine whether the current position characteristics of fishing vessels in the fishing port are within the range of abnormal position characteristics. If so, then it is in an abnormal state; If not, then it is not in an abnormal state.

8. A method for monitoring abnormalities in fishing vessels within a fishing port, characterized in that, include, Receive the warning command in the method for monitoring abnormal fishing vessels in a fishing port as described in any one of claims 1 to 7; Enter collision alert status.

9. A monitoring and management system for abnormal fishing vessel conditions in a fishing port, characterized in that, include, The port management terminal is used to continuously acquire the position data of fishing vessels in the port after they enter the port. The position data includes the MMSI code and location of the fishing vessel. Mark the fishing vessels that are confirmed to be abnormal, and obtain the vessel position data of the fishing vessels in the abnormal state in the fishing port during the abnormal period. Extract the data features of the fishing vessel positions in the fishing port as the vessel position features. Based on the degree of difference between vessel position characteristics, the vessel position characteristics of fishing vessels in abnormal and normal states are divided into multiple sets of internally correlated vessel position characteristics. The set of vessel position features consisting entirely of the vessel position features of fishing vessels in abnormal states is taken as the pure abnormal vessel position feature set, and the vector range corresponding to each pure abnormal vessel position feature set is taken as the pure abnormal vessel position feature range. The set of vessel position features consisting entirely of vessel position features of fishing vessels in normal condition is taken as the pure normal vessel position feature set, and the vector range corresponding to each pure normal vessel position feature set is taken as the pure normal vessel position feature range. The set of vessel position features composed of the mixed vessel position features of fishing vessels in normal and abnormal states is called the mixed vessel position feature set, and the vector range corresponding to each mixed vessel position feature set is obtained as the mixed vessel position feature range. The remaining portion after subtracting the overlap with the pure normal ship position characteristic range from the mixed ship position characteristic range is used as the supplementary abnormal ship position characteristic range. Both the pure abnormal ship position feature range and the supplementary abnormal ship position feature range are considered as the abnormal ship position feature range. Determine whether the fishing vessels in the fishing port are in an abnormal state at the current moment based on the range of abnormal vessel position characteristics. If so, send a warning instruction to the fishing vessel in the abnormal state and / or adjacent fishing vessels. If not, no response will be given; The end of the fishing boat is used to receive warning instructions; Enter collision alert status.

Images