Automatic ship route recommending and matching method and system based on big data

Abstract

The invention relates to a ship route automatic recommendation and matching method and system based on big data, and the method comprises the steps: receiving a starting point position and an end point position selected by a user, and automatically matching a corresponding nearest port as an actual starting point port and an actual end point port; generating a plurality of candidate routes in combination with historical navigation data, real-time meteorological data and ship performance parameters in the route database; carrying out adaptive analysis on the candidate routes based on the ship type and the cargo capacity, and excluding candidate routes which do not conform to ship navigation conditions; performing multi-dimensional evaluation on the candidate airlines through a preset optimization algorithm, generating an airline recommendation list, and sending the airline recommendation list to a user interface; and continuously monitoring the real-time state data of the route selected by the user, and triggering an automatic re-planning process if detecting that the channel is abnormal or the weather is suddenly changed. According to the method, big data analysis, intelligent matching and dynamic optimization are integrated, and automatic, multi-dimensional and high-reliability route recommendation and collaborative management are realized.

Description

Technical Field

[0001] This application relates to the technical field of ship route matching, and in particular to a method and system for automatic recommendation and matching of ship routes based on big data. Background Technology

[0002] In the shipping industry, route planning is a core element in improving transportation efficiency and reducing operating costs. Traditional route planning methods mainly rely on human experience, requiring users to manually input origin and destination ports or query pre-set fixed route databases. However, existing technologies have the following significant drawbacks: 1. Limited data dimensions: Traditional systems are mostly based on static historical route data, failing to integrate multi-source dynamic information such as real-time weather, channel congestion, and vessel performance, making it difficult for recommended results to adapt to complex navigation environments; 2. Lack of dynamic response: When sudden weather changes, channel control, or vessel path conflicts occur, the system lacks real-time monitoring and adaptive adjustment capabilities, easily leading to navigation delays or safety hazards.

[0003] Therefore, there is an urgent need for a ship route planning method that integrates big data analysis, intelligent matching, and dynamic optimization to overcome the limitations of traditional technologies and achieve automated, multi-dimensional, and highly reliable route recommendation and collaborative management. Summary of the Invention

[0004] In order to overcome the limitations of traditional technologies and achieve automated, multi-dimensional, and highly reliable route recommendation and collaborative management, this application provides a method and system for automatic recommendation and matching of ship routes based on big data.

[0005] The above-mentioned objective of this application is achieved through the following technical solution:

[0006] A method for automatic recommendation and matching of ship routes based on big data, including the following steps:

[0007] The system receives the starting point and ending point selected by the user on the electronic map interface, and automatically matches the nearest port corresponding to the starting point and ending point based on geographic information system and big data analysis, which are respectively used as the actual starting point port and the actual ending point port.

[0008] Based on the actual origin and destination ports, and combined with historical navigation data, real-time meteorological data, and ship performance parameters in the route database, multiple candidate routes are generated.

[0009] Adaptability analysis is performed on candidate routes based on vessel type and cargo capacity to eliminate candidate routes that do not meet the navigation conditions, and channel congestion information and temporary control data are integrated in real time to update the candidate route set.

[0010] The candidate routes are evaluated from multiple dimensions using a preset optimization algorithm. The candidate routes are then arranged in descending order of matching degree to generate a route recommendation list, which is then sent to the user interface.

[0011] After the user confirms the selected route, the system continuously monitors the real-time status data of the selected route. If an abnormality in the airway or a sudden change in weather is detected, the system will trigger an automatic replanning process and send an updated list of recommended routes to the user interface.

[0012] By adopting the above technical solutions, the entire process from user input to dynamic recommendation is automated, reducing manual intervention. By integrating multi-source data (GIS, meteorology, ship performance), the comprehensiveness and reliability of route planning are improved. Real-time monitoring and replanning mechanisms are used to deal with sudden anomalies, ensuring navigation safety and efficiency.

[0013] In a preferred embodiment of this application, the step of receiving the start and end locations selected by the user on the electronic map interface, and automatically matching the nearest ports corresponding to the start and end locations based on geographic information systems and big data analysis, as the actual start and end ports respectively, specifically includes the following steps:

[0014] The global sea area is divided into multi-layered grid units, each grid is associated with a list of ports it covers, and each port is labeled with its geographical coordinates, size level, average berthing cost and historical berthing frequency, and stored in the index node;

[0015] Based on the starting and ending coordinates selected by the user on the electronic map interface, the system locates the first-level grid, filters all ports within the grid as a preliminary selection set, and generates a preliminary candidate port list.

[0016] The system uses a preset dynamic weighting rule that includes three dimensions: port size, berthing fees, and historical berthing frequency. It scores each dimension of the initial candidate ports and sums the scores according to the preset weights to output the comprehensive score of each initial candidate port.

[0017] The preliminary candidate port with the highest comprehensive score will be used as the actual starting port and the actual ending port.

[0018] By adopting the above technical solution, global search is transformed into local layer-by-layer filtering through gridded spatial indexing, which greatly reduces computational complexity. Priority weights can be adaptively adjusted according to user needs, real-time status, and historical feedback, avoiding the rigidity of matching caused by static rules. By annotating recommendation reasons and scoring details, users' trust in the matching results and decision-making efficiency are enhanced.

[0019] In a preferred embodiment of this application, the step of generating multiple candidate routes based on the actual origin port and the actual destination port, combined with historical navigation data, real-time meteorological data, and ship performance parameters in the route database, specifically includes the following steps:

[0020] Historical navigation records are extracted from the route database, and the real-time meteorological data interface is connected to obtain wind speed, wave height, ocean current direction and extreme weather warnings for the current and forecast periods, while synchronizing ship performance parameters.

[0021] By combining real-time meteorological data and ship performance parameters, successful routes that match the actual origin port and the actual destination port in the historical database are selected as the initial candidate set.

[0022] Key nodes are identified on the main routes, and multiple local alternative paths are generated for each node. The number of candidate routes is expanded by combining alternatives for different nodes.

[0023] Predict the overlap between candidate routes and other vessel routes at key time points. If potential congestion is detected, mark the route and generate detour suggestions.

[0024] By adopting the above technical solutions, historical and real-time data are integrated, historical high-frequency flight routes provide experience references, and real-time weather is combined to avoid dynamic risks. The alternative path combination of key nodes enables the candidate set to cover multiple scenarios, detect potential congestion in advance and generate detour suggestions, and reduce subsequent negotiation costs.

[0025] In a preferred embodiment of this application, the step of performing an adaptive analysis of candidate routes based on vessel type and cargo capacity, excluding candidate routes that do not meet vessel navigation conditions, and integrating channel congestion information and temporary control data in real time to update the candidate route set specifically includes the following steps:

[0026] Receive information on vessel type and cargo capacity, associate it with a pre-set vessel navigation rule library, calculate the actual draft of the current vessel based on the cargo capacity information, and mark waterway sections in the route that have insufficient water depth, bridge height restrictions, or excessively small curve radii.

[0027] Remove routes from the candidate route set that have a cargo capacity exceeding the route's capacity limit or that clearly violate ship navigation rules;

[0028] The system accesses the congestion index and temporary traffic control notices from the waterway monitoring system in real time, scans the remaining candidate routes one by one, and dynamically updates the candidate route set based on the scan results.

[0029] By adopting the above technical solutions, the dual-layer filtering mechanism first quickly eliminates high-risk routes through static rules, and then makes fine adjustments based on dynamic data to balance efficiency and accuracy; the cargo capacity-channel depth coupling transforms the cargo capacity into actual navigation restrictions, avoiding misjudgments caused by relying solely on ship type.

[0030] In a preferred embodiment of this application, the step of evaluating the candidate routes from multiple dimensions using a preset optimization algorithm, arranging the candidate routes in descending order of matching degree to generate a route recommendation list, and sending the route recommendation list to the user interface specifically includes the following steps:

[0031] Extract flight time, fuel consumption, safety factor, carbon emissions and economic cost data for each candidate route, and convert the raw data of each dimension into relative scores;

[0032] Based on user preset preferences or system default strategies, the weights of each dimension are dynamically allocated. If an extreme weather warning is detected, the safety factor weight is automatically increased. If fuel price fluctuations exceed the threshold, the economic cost calculation logic is dynamically adjusted.

[0033] For each route, multiply its relative score by the weight of each dimension, and then sum them to generate a comprehensive score. If multiple routes have the same score, routes with high historical usage frequency or those manually saved by users are retained first, followed by routes arranged in ascending order of carbon emissions.

[0034] The candidate routes are arranged in descending order of their overall scores, and a route recommendation list is generated. The route recommendation list is then sent to the user interface.

[0035] By adopting the above technical solutions, the dynamic weighting mechanism supports adaptive adjustment of user preferences and external conditions, breaking through the limitations of the traditional fixed weighting model. Through comprehensive scoring and single-dimensional highlight annotation, it helps users quickly understand the advantages and disadvantages of routes, realizes adaptive strategy and scenario-based evaluation, and introduces historical and user behavior data on the basis of quantitative scoring to enhance the rationality of ranking.

[0036] In a preferred embodiment of this application, the method further includes a collaborative optimization mechanism:

[0037] If path conflicts are detected among the recommended routes of multiple ships, the route planning of each ship is adjusted based on a game theory model or a distributed negotiation algorithm to achieve global resource allocation optimization.

[0038] By adopting the above technical solutions, port congestion and route overlap can be avoided through multi-ship path conflict detection and adjustment, reducing reliance on central control nodes, improving fault tolerance and scalability, and balancing individual goals with overall efficiency.

[0039] In a preferred example, this application includes the following steps: if path conflicts are detected among the recommended routes of multiple vessels, the route planning of each vessel is adjusted based on a game theory model or a distributed negotiation algorithm to achieve global resource allocation optimization.

[0040] The system monitors the current position, planned route, and speed of all vessels in real time. It calculates the spatiotemporal overlap area of ​​the future paths of each vessel through a predictive model. When a potential route conflict is identified, the relevant vessels exchange basic information through a distributed communication network.

[0041] For each vessel, an adjustable set of alternative routes is generated, and each alternative route is marked with its impact on itself and other vessels. Each vessel selects an adjustment plan from the alternative routes and broadcasts the proposal via the network.

[0042] After receiving proposals from other vessels, each vessel assesses its own changes in benefits, calculates the overall degree of conflict mitigation, and dynamically assigns negotiation weights based on vessel priority.

[0043] When a proposal receives less than a preset threshold of acceptance or opposition from all affected vessels, the proposal is considered a temporary consensus, triggering a local route adjustment.

[0044] The adjusted route enters the execution phase, and the actual navigation status is continuously monitored. If new conflicts are detected or the original plan deviates from the expected results, a new round of negotiation process is automatically triggered.

[0045] By adopting the above technical solutions, decentralized decision-making does not rely on a central control node. Ships can autonomously negotiate through local information exchange, improving the system's fault tolerance and scalability. The interest balancing mechanism takes into account individual goals and overall efficiency through multiple rounds of game theory and dynamic weights, avoiding unfairness caused by the simple rule of "majority rule". Small-scale conflicts are resolved through local negotiation first. This gradual adjustment reduces the computational and communication overhead caused by large-scale route resets.

[0046] The second objective of this invention is achieved through the following technical solution:

[0047] A big data-based automatic recommendation and matching system for ship routes includes:

[0048] The port matching module is used to receive the starting point and ending point selected by the user on the electronic map interface, and automatically match the nearest port corresponding to the starting point and ending point based on geographic information system and big data analysis, which are respectively used as the actual starting point port and the actual ending point port.

[0049] The candidate route generation module is used to generate multiple candidate routes based on the actual origin port and the actual destination port, combined with historical navigation data, real-time meteorological data and ship performance parameters in the route database.

[0050] The candidate route analysis module performs an adaptability analysis on candidate routes based on vessel type and cargo capacity, eliminates candidate routes that do not meet the vessel navigation conditions, and integrates waterway congestion information and temporary control data in real time to update the candidate route set.

[0051] The route recommendation module is used to evaluate the candidate routes in multiple dimensions using a preset optimization algorithm, arrange the candidate routes in descending order of matching degree and generate a route recommendation list, and send the route recommendation list to the user interface.

[0052] The feedback module continuously monitors the real-time status data of the selected route after the user confirms the route selection. If an abnormality in the airway or a sudden change in weather is detected, it triggers an automatic replanning process and sends an updated list of recommended routes to the user interface.

[0053] By adopting the above technical solution, the method and process are broken down into independent functional modules, which facilitates system expansion and maintenance. Each module achieves efficient data flow through standardized interfaces, supports minute-level response, and enhances the feasibility of technology implementation.

[0054] The above-mentioned objective three of this application is achieved through the following technical solution:

[0055] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for automatic recommendation and matching of ship routes based on big data.

[0056] The fourth objective of this application is achieved through the following technical solution:

[0057] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for automatic recommendation and matching of ship routes based on big data.

[0058] In summary, this application includes at least one of the following beneficial technical effects:

[0059] 1. The entire process from user input to dynamic recommendation is automated, reducing manual intervention. It integrates multi-source data (GIS, meteorology, ship performance) to improve the comprehensiveness and reliability of route planning. Through real-time monitoring and replanning mechanisms, it can respond to sudden anomalies and ensure navigation safety and efficiency.

[0060] 2. The dual-layer filtering mechanism first quickly eliminates high-risk routes through static rules, and then makes fine adjustments based on dynamic data to balance efficiency and accuracy. The cargo volume and waterway depth are coupled to convert the cargo volume into actual navigation restrictions, avoiding misjudgments caused by relying solely on ship type.

[0061] 3. The dynamic weighting mechanism supports adaptive adjustment of user preferences and external conditions, breaking through the limitations of the traditional fixed weighting model. Through comprehensive scoring and single-dimensional highlight annotation, it helps users quickly understand the advantages and disadvantages of routes, realizes adaptive strategy and scenario-based evaluation, and introduces historical and user behavior data on the basis of quantitative scoring to enhance the rationality of ranking.

[0062] 4. The collaborative optimization mechanism avoids port congestion and route overlap by detecting and adjusting multi-ship path conflicts. Decentralized decision-making does not rely on a central control node. Ships autonomously negotiate through local information exchange, improving the system's fault tolerance and scalability. The interest balancing mechanism takes into account individual goals and global efficiency through multi-round game and dynamic weights, avoiding unfairness caused by the simple rule of "majority rule". Small-scale conflicts are resolved through local negotiation first. This gradual adjustment reduces the computation and communication overhead caused by large-scale route resets. Attached Figure Description

[0063] Figure 1 This is a flowchart of an embodiment of a method for automatic recommendation and matching of ship routes based on big data according to this application;

[0064] Figure 2 This is a flowchart of step S20 in an embodiment of a big data-based automatic recommendation and matching method for ship routes in this application.

[0065] Figure 3 This is a flowchart of step S40 in an embodiment of a big data-based automatic recommendation and matching method for ship routes in this application;

[0066] Figure 4 This is a schematic diagram of an automatic ship route recommendation and matching system based on big data, as described in this application.

[0067] Figure 5 This is a schematic block diagram of a computer device according to this application. Detailed Implementation

[0068] The present application will be further described in detail below with reference to the accompanying drawings.

[0069] In one embodiment, such as Figure 1-3 As shown, this application discloses a method for automatic recommendation and matching of ship routes based on big data, which specifically includes the following steps:

[0070] S10: Receive the starting point and ending point selected by the user on the electronic map interface, and automatically match the nearest port corresponding to the starting point and ending point based on geographic information system and big data analysis, and use them as the actual starting point port and actual ending point port respectively.

[0071] S20: Based on the actual origin port and actual destination port, and combined with historical navigation data, real-time meteorological data and ship performance parameters in the route database, generate multiple candidate routes;

[0072] S30: Based on vessel type and cargo capacity, perform adaptability analysis on candidate routes, eliminate candidate routes that do not meet the navigation conditions, and integrate channel congestion information and temporary control data in real time to update the candidate route set.

[0073] S40: The candidate routes are evaluated from multiple dimensions using a preset optimization algorithm. The candidate routes are then arranged in descending order of matching degree to generate a route recommendation list. The route recommendation list is then sent to the user interface.

[0074] S50: After the user confirms the selected route, it continuously monitors the real-time status data of the selected route. If an abnormality in the airway or a sudden change in weather is detected, it triggers an automatic replanning process and sends an updated list of recommended routes to the user interface.

[0075] In this embodiment, historical navigation data includes travel time and fuel consumption for previous routes; real-time meteorological data includes wind speed, wave height, and visibility; and ship performance parameters include ship speed and load capacity. Route evaluation dimensions include travel time, cost, safety, and environmental friendliness.

[0076] Specifically, users first select their desired starting and ending points on an electronic map. The system then uses Geographic Information System (GIS) and big data analytics to automatically identify and match the nearest ports to these locations. These matched ports serve as the actual starting and ending points. Using these ports, combined with historical navigation data, real-time weather data, and ship performance parameters stored in the route database, multiple possible route options—candidate routes—are generated. Each candidate route is further analyzed, considering ship type (e.g., tankers, container ships) and cargo capacity—to determine its suitability for navigation, eliminating unsuitable routes. Simultaneously, real-time channel congestion information (e.g., a high number of ships on a particular channel) and temporary traffic control data (e.g., channel closures due to military exercises) are integrated to update and adjust the candidate route set. A pre-set optimization algorithm comprehensively evaluates the remaining candidate routes from multiple dimensions. Based on the evaluation results, these routes are sorted from highest to lowest match level, and a route recommendation list is sent to the user interface. Once a user selects a route, the system continuously monitors its real-time status, including channel conditions and weather changes. If an abnormality is detected in the waterway (such as a waterway blockage caused by a sudden accident) or a sudden change in weather (such as a sudden storm), the system will automatically initiate a replanning process, generate a new list of recommended routes, and notify the user to ensure navigation safety and economy.

[0077] In one embodiment, step S10 specifically includes the following steps:

[0078] S11: Divide the global sea area into multi-layer grid units. Each grid is associated with a list of ports it covers. Mark the geographical coordinates, size level, average berthing cost and historical berthing frequency of each port and store them in the index node.

[0079] S12: Based on the starting point and ending point coordinates selected by the user on the electronic map interface, locate the first-level grid, filter all ports within the grid as the initial selection set, and generate a preliminary candidate port list.

[0080] S13: Preset dynamic weight allocation rules including three dimensions: port size, berthing cost and historical berthing frequency. Score each dimension of the preliminary candidate ports, sum them according to the preset weights, and output the comprehensive score of each preliminary candidate port.

[0081] S14: The preliminary candidate port with the highest comprehensive score will be used as the actual starting port and the actual ending port.

[0082] In this embodiment, the dynamic weight allocation rule includes three dimensions: port size (large hub ports have higher base scores, reflecting their facility completeness and navigation capacity); berthing fees (lower fees result in higher score bonuses, but this can be ignored for high-priority vessels such as emergency supply ships); and historical berthing frequency (ports with frequent berthings receive increased trust scores, reducing the risk of trial and error with new ports). If a port is detected to be currently congested (e.g., berthing queue time exceeds a threshold), its score is lowered; if a port issues temporary preferential policies (e.g., berthing fee reductions), the weight of the fee dimension is increased.

[0083] Specifically, the global sea area is divided into multi-layered grid units. The higher-level grid covers a large area (100km × 100km), while the lower-level grid refines to a smaller area (1km × 1km). Each grid is associated with a list of ports it covers, and each port is labeled with its geographical coordinates, size level (e.g., large hub port, regional port), average berthing cost, and historical berthing frequency, stored in an index node. Based on the user's selected location coordinates, the system locates the higher-level grid and filters all ports within that grid as an initial selection set. This is then refined level by level towards the lower-level grid, supplementing neighboring ports within a smaller area to ensure no omissions. Ports whose straight-line distance from the user's location exceeds a preset maximum service radius (e.g., 500 nautical miles) are removed, generating a preliminary candidate port list. Each dimension of the preliminary candidate ports is scored, and the scores are summed according to preset weights to output a comprehensive score for each preliminary candidate port. For example, the comprehensive score = size score × 0.5 + cost score × 0.3 + frequency score × 0.2, with weights dynamically adjusted according to user type. The initial candidate ports with the highest overall scores are used as the actual starting and ending ports. Finally, a sorted list is generated based on the scores from high to low, with the reasons for the recommendation (such as "lowest overall cost" or "best historical service"). For ports with the same score, the option that is closer to the user's location is given priority.

[0084] In one embodiment, step S20 specifically includes the following steps:

[0085] S21: Extract historical navigation records from the route database, connect to the real-time meteorological data interface, obtain wind speed, wave height, ocean current direction and extreme weather warnings for the current and forecast periods, and synchronize ship performance parameters;

[0086] S22: Combining real-time meteorological data and ship performance parameters, select successful routes in the historical database that match the actual origin port and the actual destination port as the initial candidate set;

[0087] S23: Identify key nodes on the main route, generate multiple local alternative paths for each node, and expand the number of candidate routes by combining alternatives for different nodes;

[0088] S24: Predict the overlap between each candidate route and other vessel routes at key time points. If potential congestion is detected, mark the route and generate detour suggestions.

[0089] In this embodiment, historical navigation records include commonly used routes, navigation duration, locations of obstacles encountered, and avoidance strategies. Step S23 introduces scenario-based strategies: Economy First: Selecting the route combination with the lowest historical fuel consumption, prioritizing the use of slow navigation strategies to reduce energy consumption; Time Sensitive: Using direct routes and calculating the shortest travel time based on the ship's maximum speed; Safety Redundancy: Adding alternative routes passing through areas with dense rescue stations or stable weather conditions.

[0090] Specifically, historical navigation records are extracted from the route database, and a real-time meteorological data interface is connected to obtain wind speed, wave height, ocean current direction, and extreme weather warnings for the current and forecast periods. Ship performance parameters, such as maximum speed, draft, load capacity, and fuel efficiency rating, are synchronized. Outliers in historical data (such as excessively long voyage times due to malfunctions) are filtered out, and the spatiotemporal granularity of meteorological data is standardized (e.g., wave height forecasts are standardized to 30-minute intervals per hour). Ship parameters are categorized by type (e.g., bulk carriers, tankers, container ships) and matched with corresponding navigation restrictions. A basic waterway network from the origin port to the destination port is drawn using a Geographic Information System (GIS), marking main routes, alternative waterways, and prohibited areas (e.g., military control zones, ecological protection zones). Successful routes matching the current origin and destination in the historical database are screened, sorted by usage frequency, and high-frequency routes are prioritized as the initial candidate set. Each candidate route is compared with real-time weather data to exclude routes that pass through the current typhoon path, areas with strong waves (wave height exceeding the ship's wave resistance rating), or routes that significantly affect speed due to counter-currents. Routes passing through shallow waters (e.g., channel depth below the ship's safe draft threshold) are also excluded based on the ship's draft. For ships with low fuel efficiency, routes with shorter distances or a high proportion of downstream sections are prioritized. Key nodes (e.g., river estuaries, international channel junctions) are identified on the main routes, and multiple local alternative routes are generated for each node (e.g., bypassing congested areas, avoiding low-visibility sea areas at night). The number of candidate routes is expanded by combining alternative solutions for different nodes. The overlap between each candidate route and other ship routes at key time points (e.g., the estimated time to pass through narrow channels) is predicted. If potential congestion is detected (e.g., multiple ships arriving at the same port simultaneously), the route is marked and a detour suggestion is generated. To avoid multiple candidate routes recommending the same alternative channel, a flow allocation algorithm is introduced to dynamically adjust the recommendation strategy to balance channel load.

[0091] In one embodiment, step S30 specifically includes the following steps:

[0092] S31: Receive information on vessel type and cargo capacity, associate with the preset vessel navigation rule library, calculate the actual draft of the current vessel based on the cargo capacity information, and mark waterway sections in the route that have insufficient water depth, bridge height restrictions, or excessively small curve radii.

[0093] S32: Remove routes from the candidate route set that have a cargo capacity exceeding the route's capacity limit or that clearly violate ship navigation rules;

[0094] S33: Real-time access to the congestion index and temporary control notices of the waterway monitoring system, scan the remaining candidate routes one by one, and dynamically update the candidate route set based on the scan results.

[0095] In this embodiment, the ship types include bulk carriers, tankers, and container ships. The preset ship navigation rules include: tankers: prohibited from passing through ecological protection areas or densely populated areas; large bulk carriers: required to have a channel depth ≥ the safe draft threshold; dangerous goods transport ships: required to stay away from other densely populated shipping routes.

[0096] Specifically, the system receives information on vessel type and cargo capacity, associates it with a pre-defined vessel navigation rules database, calculates the actual draft of the vessel based on the cargo capacity, and marks channel sections with insufficient water depth, bridge height restrictions, or excessively small curve radii. It removes routes that clearly violate vessel navigation rules from the candidate route set (e.g., oil tankers passing through ecological protection zones, bulk carriers entering shallow waterways). If the cargo capacity exceeds the route's capacity limit (e.g., a channel only allows vessels with a deadweight of 100,000 tons or less to pass), the route is disabled and the reason is noted. It also accesses real-time congestion indices (e.g., port queuing times, vessel density in narrow channels) and temporary control notices (e.g., military exercise areas, temporary navigation bans) from the channel monitoring system. The remaining candidate routes are scanned one by one: if a route passes through a channel section where the current congestion index exceeds the limit, the route's priority is reduced and the estimated delay time is noted; if a route overlaps with a temporary control area, the route is directly removed and an alternative route suggestion is generated. For routes that are removed or downgraded, alternative routes are derived from nearby channel nodes (such as tributary estuaries and backup anchorages) to ensure that the number of candidate routes is not less than a preset lower limit. Combining vessel type characteristics (such as dangerous goods vessels needing to prioritize avoiding congested areas) and the degree of impact from real-time data, the overall route score is recalculated and ranked. For example, for safety-priority routes: routes that avoid controlled areas are ranked higher; for economy-priority routes: routes with mild congestion but the lowest cost are retained.

[0097] In one embodiment, step S40 specifically includes the following steps:

[0098] S41: Extract the flight time, fuel consumption, safety factor, carbon emissions and economic cost data for each candidate route, and convert the raw data of each dimension into relative scores;

[0099] S42: Based on user preset preferences or system default strategies, dynamically allocate weights for each dimension. If an extreme weather warning is detected, automatically increase the safety factor weight. If fuel price fluctuations exceed the threshold, dynamically adjust the economic cost calculation logic.

[0100] S43: For each route, multiply its relative score by the weight of each dimension, and then sum them to generate a comprehensive score. If multiple routes have the same score, prioritize routes with high historical usage frequency or those manually favorited by users, and then sort them in ascending order of carbon emissions.

[0101] S44: Arrange the candidate routes in descending order of their comprehensive scores and generate a route recommendation list, then send the route recommendation list to the user interface.

[0102] In this embodiment, the sailing time is represented based on historical average speed and real-time ocean current prediction; fuel consumption is represented by the correlation between ship energy efficiency level and route distance; safety factor is represented by the integration of meteorological risk index and waterway accident rate statistics; carbon emissions are represented by the calculation based on fuel type and engine emission coefficient; and economic cost is represented by the inclusion of fuel costs, port berthing fees, and potential delay penalties.

[0103] Specifically, the system extracts data on flight time, fuel consumption, safety factor, carbon emissions, and economic cost for each candidate route. The raw data for each dimension is converted into a 0-1 relative score (e.g., the shortest flight time is set to 1 point, and other routes are proportionally weighted), eliminating differences in unit of measurement. Based on user-preset preferences (e.g., "economy priority" or "safety priority") or the system's default strategy, the weight of each dimension is dynamically allocated. For example, in environmental mode, carbon emissions are weighted at 40%, and economic cost is weighted at 20%; in emergency mode, flight time is weighted at 50%, and the remaining weights are evenly distributed among the other dimensions. If an extreme weather warning is detected, the safety factor weight is automatically increased; if fuel price fluctuations exceed a threshold, the economic cost calculation logic is dynamically adjusted. For each route, the scores for each dimension are multiplied by their respective weights, and the results are summed to generate a comprehensive score (e.g., flight time × 0.3 + safety factor × 0.4 + …). If multiple routes have the same score, routes with high historical usage frequency or those manually saved by the user are prioritized, followed by routes sorted in ascending order of carbon emissions. Candidate routes are ranked from highest to lowest based on their overall score, generating a route recommendation list which is then sent to the user interface. Candidate routes are categorized into three levels: high matching score (overall score ≥ 0.8), medium matching score (0.6-0.8), and low matching score (< 0.6), with each level assigned a distinct identifier (e.g., green / yellow / red labels). The ranking list also individually highlights the advantages of each route (e.g., "optimal carbon emissions" or "highest safety"), allowing users to quickly filter by a single dimension. The system records the user's final route selections and rejected options, analyzes scenarios where preferences deviate from preset weights (e.g., users frequently select "highest safety" but the system does not prioritize these options), and automatically fine-tunes the weight allocation rules.

[0104] In one embodiment, the automatic recommendation and matching method for ship routes based on big data further includes a collaborative optimization mechanism:

[0105] S60: If path conflicts are detected among the recommended routes of multiple ships, the route planning of each ship is adjusted based on a game theory model or a distributed negotiation algorithm to achieve global resource allocation optimization.

[0106] Step S60 specifically includes the following steps:

[0107] S61: Real-time monitoring of the current position, planned route and speed of all ships; calculation of the spatiotemporal overlap area of ​​the future paths of each ship through a predictive model; when potential route conflicts are identified, the relevant ships exchange basic information through a distributed communication network.

[0108] S62: Generate an adjustable set of alternative routes for each vessel, marking the impact of each alternative route on itself and other vessels. Each vessel selects an adjustment plan from the alternative routes and broadcasts the proposal via the network.

[0109] S63: After receiving proposals from other vessels, each vessel assesses its own changes in benefits, calculates the overall degree of conflict mitigation, and dynamically assigns negotiation weights based on vessel priority.

[0110] S64: When a proposal receives less than a preset threshold of acceptance or opposition from all affected vessels, the proposal is considered a temporary consensus and a local route adjustment is triggered.

[0111] S65: The adjusted route enters the execution phase, continuously monitoring the actual navigation status. If a new conflict is detected or the original plan deviates from the expected effect, a new round of negotiation process will be automatically triggered.

[0112] In this embodiment, basic information includes the current route objective, such as estimated arrival time and priority; the type of cargo carried by the vessel and the adjustable range, such as the maximum detour distance. When a potential route conflict is identified, each vessel declares its core interests based on its own needs. For example, economy vessels prioritize reducing fuel consumption and time delays; emergency supply vessels require minimizing sailing time and are willing to accept higher costs; and environmentally friendly vessels prioritize reducing carbon emissions. If multiple rounds of negotiation fail to reach a consensus (e.g., the conflict of interests is irreconcilable), a tiered arbitration mechanism is initiated: primary arbitration: the system recommends a compromise solution based on historical data (e.g., evenly distributing the detour distance); advanced arbitration: the manual dispatch center intervenes and, in conjunction with real-time emergency rules (e.g., maritime control), mandates an adjustment plan.

[0113] Specifically, the system monitors the current position, planned route, and speed of all vessels in real time. A predictive model calculates the spatiotemporal overlap of future routes for each vessel, identifying potential route conflicts (such as channel intersections and port congestion). Upon detection of a conflict, the relevant vessels exchange basic information via a distributed communication network. An adjustable set of alternative routes is generated for each vessel, with each route labeled with its impact on itself and other vessels, such as detour distance, time increase / decrease, and conflict mitigation level. Each vessel selects an adjustment plan from the alternative routes and broadcasts its proposal via the network, such as "Vessel A proposes to delay its departure by 2 hours to avoid a channel intersection." Upon receiving proposals from other vessels, each vessel assesses its own benefit changes (such as time loss and fuel savings) and calculates the overall conflict mitigation level. If a proposal results in a loss exceeding a threshold, the proposal is rejected, and a counter-proposal is generated (such as "Vessel B agrees to detour but requests Vessel A to share some fuel costs"). Negotiation weights are dynamically assigned based on vessel priority (such as government-granted routes and dangerous goods transport), with proposals from higher-priority vessels having greater influence, but the interests of all parties must still be balanced within a reasonable range. When a proposal is accepted by all affected vessels (or the opposition rate is below a preset threshold), the system locks the proposal as a temporary consensus and triggers a partial route adjustment. The adjusted route enters the execution phase, and the system continuously monitors the actual navigation status (such as changes in wind speed and new congestion). If a new conflict is detected or the original plan deviates from the expected effect (such as a vessel slowing down due to a malfunction), a new round of negotiation is automatically triggered to ensure the continuous adaptability of the route planning.

[0114] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0115] In one embodiment, a big data-based automatic ship route recommendation and matching system is provided, which corresponds one-to-one with the big data-based automatic ship route recommendation and matching method described in the above embodiments. For example... Figure 4 As shown, the system includes:

[0116] The port matching module is used to receive the starting point and ending point selected by the user on the electronic map interface, and automatically match the nearest port corresponding to the starting point and ending point based on geographic information system and big data analysis, which are respectively used as the actual starting point port and the actual ending point port.

[0117] The candidate route generation module is used to generate multiple candidate routes based on the actual origin port and the actual destination port, combined with historical navigation data, real-time meteorological data and ship performance parameters in the route database.

[0118] The candidate route analysis module performs an adaptability analysis on candidate routes based on vessel type and cargo capacity, eliminates candidate routes that do not meet the vessel navigation conditions, and integrates waterway congestion information and temporary control data in real time to update the candidate route set.

[0119] The route recommendation module is used to evaluate the candidate routes in multiple dimensions using a preset optimization algorithm, arrange the candidate routes in descending order of matching degree and generate a route recommendation list, and send the route recommendation list to the user interface.

[0120] The feedback module continuously monitors the real-time status data of the selected route after the user confirms the route selection. If an abnormality in the airway or a sudden change in weather is detected, it triggers an automatic replanning process and sends an updated list of recommended routes to the user interface.

[0121] For specific limitations regarding the automatic recommendation and matching system for ship routes based on big data, please refer to the limitations of the automatic recommendation and matching method for ship routes based on big data mentioned above, which will not be repeated here. Each module in the aforementioned automatic recommendation and matching system for ship routes based on big data can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0122] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a big data-based automatic recommendation and matching method for ship routes.

[0123] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a method for automatically recommending and matching ship routes based on big data.

[0124] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a method for automatically recommending and matching ship routes based on big data.

[0125] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0126] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to several functional units or modules as needed, that is, the internal structure of the device can be divided into several functional units or modules to complete all or part of the functions described above.

[0127] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for automatic recommendation and matching of ship routes based on big data, characterized in that, Including the following steps: The system receives the starting point and ending point selected by the user on the electronic map interface, and automatically matches the nearest port corresponding to the starting point and ending point based on geographic information system and big data analysis, which are respectively used as the actual starting point port and the actual ending point port. Based on the actual origin and destination ports, and combined with historical navigation data, real-time meteorological data, and ship performance parameters in the route database, multiple candidate routes are generated. Adaptability analysis is performed on candidate routes based on vessel type and cargo capacity to eliminate candidate routes that do not meet the navigation conditions, and channel congestion information and temporary control data are integrated in real time to update the candidate route set. The candidate routes are evaluated from multiple dimensions using a preset optimization algorithm. The candidate routes are then arranged in descending order of matching degree to generate a route recommendation list, which is then sent to the user interface. After the user confirms the selected route, the system continuously monitors the real-time status data of the selected route. If an abnormality in the airway or a sudden change in weather is detected, the system will trigger an automatic replanning process and send an updated list of recommended routes to the user interface.

2. The method for automatic recommendation and matching of ship routes based on big data according to claim 1, characterized in that, The step of receiving the start and end points selected by the user on the electronic map interface, and automatically matching the nearest ports corresponding to the start and end points based on geographic information systems and big data analysis, and using them as the actual start and end ports respectively, specifically includes the following steps: The global sea area is divided into multi-layered grid units, each grid is associated with a list of ports it covers, and each port is labeled with its geographical coordinates, size level, average berthing cost and historical berthing frequency, and stored in the index node; Based on the starting and ending coordinates selected by the user on the electronic map interface, the system locates the first-level grid, filters all ports within the grid as a preliminary selection set, and generates a preliminary candidate port list. The system uses a preset dynamic weighting rule that includes three dimensions: port size, berthing fees, and historical berthing frequency. It scores each dimension of the initial candidate ports and sums the scores according to the preset weights to output the comprehensive score of each initial candidate port. The preliminary candidate port with the highest comprehensive score will be used as the actual starting port and the actual ending port.

3. The method for automatic recommendation and matching of ship routes based on big data according to claim 1, characterized in that, The step of generating multiple candidate routes based on the actual origin and destination ports, combined with historical navigation data, real-time meteorological data, and ship performance parameters in the route database, specifically includes the following steps: Historical navigation records are extracted from the route database, and the real-time meteorological data interface is connected to obtain wind speed, wave height, ocean current direction and extreme weather warnings for the current and forecast periods, while synchronizing ship performance parameters. By combining real-time meteorological data and ship performance parameters, successful routes that match the actual origin port and the actual destination port in the historical database are selected as the initial candidate set. Key nodes are identified on the main routes, and multiple local alternative paths are generated for each node. The number of candidate routes is expanded by combining alternatives for different nodes. Predict the overlap between candidate routes and other vessel routes at key time points. If potential congestion is detected, mark the route and generate detour suggestions.

4. The method for automatic recommendation and matching of ship routes based on big data according to claim 1, characterized in that, The steps of performing adaptive analysis on candidate routes based on vessel type and cargo capacity, excluding candidate routes that do not meet vessel navigation conditions, and integrating channel congestion information and temporary control data in real time to update the candidate route set specifically include the following steps: Receive information on vessel type and cargo capacity, associate it with a pre-set vessel navigation rule library, calculate the actual draft of the current vessel based on the cargo capacity information, and mark waterway sections in the route that have insufficient water depth, bridge height restrictions, or excessively small curve radii. Remove routes from the candidate route set that have a cargo capacity exceeding the route's capacity limit or that clearly violate ship navigation rules; The system accesses the congestion index and temporary traffic control notices from the waterway monitoring system in real time, scans the remaining candidate routes one by one, and dynamically updates the candidate route set based on the scan results.

5. The method for automatic recommendation and matching of ship routes based on big data according to claim 1, characterized in that, The step of evaluating the candidate routes from multiple dimensions using a preset optimization algorithm, arranging the candidate routes in descending order of matching degree to generate a route recommendation list, and sending the route recommendation list to the user interface specifically includes the following steps: Extract flight time, fuel consumption, safety factor, carbon emissions and economic cost data for each candidate route, and convert the raw data of each dimension into relative scores; Based on user preset preferences or system default strategies, the weights of each dimension are dynamically allocated. If an extreme weather warning is detected, the safety factor weight is automatically increased. If fuel price fluctuations exceed the threshold, the economic cost calculation logic is dynamically adjusted. For each route, multiply its relative score by the weight of each dimension, and then sum them to generate a comprehensive score. If multiple routes have the same score, routes with high historical usage frequency or those manually saved by users are retained first, followed by routes arranged in ascending order of carbon emissions. The candidate routes are arranged in descending order of their overall scores, and a route recommendation list is generated. The route recommendation list is then sent to the user interface.

6. The method for automatic recommendation and matching of ship routes based on big data according to claim 1, characterized in that, The method also includes a collaborative optimization mechanism: If path conflicts are detected among the recommended routes of multiple ships, the route planning of each ship is adjusted based on a game theory model or a distributed negotiation algorithm to achieve global resource allocation optimization.

7. The method for automatic recommendation and matching of ship routes based on big data according to claim 6, characterized in that, The step of adjusting the route planning of each ship based on a game theory model or a distributed negotiation algorithm to optimize global resource allocation if path conflicts are detected among the recommended routes of multiple ships, specifically includes the following steps: The system monitors the current position, planned route, and speed of all vessels in real time. It calculates the spatiotemporal overlap area of ​​the future paths of each vessel through a predictive model. When a potential route conflict is identified, the relevant vessels exchange basic information through a distributed communication network. For each vessel, an adjustable set of alternative routes is generated, and each alternative route is marked with its impact on itself and other vessels. Each vessel selects an adjustment plan from the alternative routes and broadcasts the proposal via the network. After receiving proposals from other vessels, each vessel assesses its own changes in benefits, calculates the overall degree of conflict mitigation, and dynamically assigns negotiation weights based on vessel priority. When a proposal receives less than a preset threshold of acceptance or opposition from all affected vessels, the proposal is considered a temporary consensus, triggering a local route adjustment. The adjusted route enters the execution phase, and the actual navigation status is continuously monitored. If new conflicts are detected or the original plan deviates from the expected results, a new round of negotiation process is automatically triggered.

8. A system for automatically recommending and matching ship routes based on big data, characterized in that, include: The port matching module is used to receive the starting point and ending point selected by the user on the electronic map interface, and automatically match the nearest port corresponding to the starting point and ending point based on geographic information system and big data analysis, which are respectively used as the actual starting point port and the actual ending point port. The candidate route generation module is used to generate multiple candidate routes based on the actual origin port and the actual destination port, combined with historical navigation data, real-time meteorological data and ship performance parameters in the route database. The candidate route analysis module performs an adaptability analysis on candidate routes based on vessel type and cargo capacity, eliminates candidate routes that do not meet the vessel navigation conditions, and integrates waterway congestion information and temporary control data in real time to update the candidate route set. The route recommendation module is used to evaluate the candidate routes in multiple dimensions using a preset optimization algorithm, arrange the candidate routes in descending order of matching degree and generate a route recommendation list, and send the route recommendation list to the user interface. The feedback module continuously monitors the real-time status data of the selected route after the user confirms the route selection. If an abnormality in the airway or a sudden change in weather is detected, it triggers an automatic replanning process and sends an updated list of recommended routes to the user interface.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the automatic recommendation and matching method for ship routes based on big data as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the automatic recommendation and matching method for ship routes based on big data as described in any one of claims 1 to 7.

Images