Information integration service virtualization management system

Abstract

The invention relates to the technical field of port information management, and particularly discloses an information integration service virtualization management system, which is characterized in that a two-dimensional plane graph of a berthing area is acquired through a GIS, the two-dimensional plane graph is divided through grid division to acquire first position data, and first state data and first position data of a ship are acquired; dividing the berthing area according to the first state data, determining second position data of the ship in the divided area, marking the ship reaching the berthing area in the berthing area as' arrived ', and updating the' arrived 'ship according to the data, so that a dispatching center can obtain the latest ship dynamic state; therefore, potential safety hazards and operation errors caused by information delay are reduced.

Description

Technical Field

[0001] This invention relates to the field of port information management technology, and more specifically, to an information integration service virtualization management system. Background Technology

[0002] In modern port operation and management, the vessel scheduling system undertakes the unified management of all berthed vessels throughout the entire process from arrival, berthing, loading and unloading to departure. This system relies on historical data, real-time dynamic information, and predictive models to optimize the allocation of vessel and berth resources. Existing literature (Guo Liming. Research on Optimization of Container Terminal Berth Allocation under Cooperative Background [D]. Dalian Maritime University, 2024. DOI:10.26989 / d.cnki.gdlhu.2024.000112.) has conducted research on container terminal berth allocation under cooperative background and provided the following... Figure 2 The container terminal operation system shown is an example. However, frontline loading and unloading systems often use batch updates, which involves uploading data centrally over a certain period of time, rather than transmitting it piecemeal in real time. While this reduces the system's frequent communication load and network bandwidth pressure, it inevitably introduces delays in data collection and transmission. When a vessel arrives ahead of schedule, the system has not yet completed the latest data update, causing the information received by the dispatch center to be delayed, displaying "not yet arrived" instead of reflecting the real-time operational status on site.

[0003] This asynchrony between data directly affects the rational allocation of berth resources, leading to longer waiting times for ships after berthing, and even having a chain reaction on subsequent operational plans and overall port operations. This exposes the shortcomings of the current port information system in data fusion and real-time synchronization mechanisms. It is urgent to improve the information interoperability between subsystems by optimizing the transmission architecture, unifying interface standards, and introducing advanced real-time monitoring and early warning mechanisms, so as to ensure that port scheduling decisions can be based on accurate and timely on-site dynamic data, thereby achieving efficient, coordinated, and safe management of operational processes. To solve the above problems, a technical solution is provided. Summary of the Invention

[0004] To overcome the aforementioned deficiencies of the prior art, this invention provides an information integration service virtualization management system. This system divides berthing areas based on first state data, determines the second location data of the vessel within the divided area, marks vessels arriving at their designated berthing areas as "arrived," and updates the list of "arrived" vessels based on this data. This addresses the problem of delayed information reception at the dispatch center when vessels arrive ahead of schedule, before the system has updated its latest data. This allows the dispatch center to obtain the latest vessel dynamics, thereby reducing safety hazards and operational errors caused by information delays, and solving the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A virtualized management system for information integration services includes a static berthing monitoring module, a front-line loading and unloading system terminal, a region attribution determination module, a dynamic scheduling decision module, and a real-time update module. The static berthing monitoring module acquires a two-dimensional plan view of the berthing area via GIS and divides the plan view into grids to obtain first location data. The front-line loading and unloading system terminal acquires first status data and first location data of the vessel and performs batch data storage. The region attribution determination module divides the berthing area based on the first status data and determines the second location data of the vessel within the divided area. The region attribution determination module includes a region segmentation unit, a berthing trend analysis unit, and a region dynamic determination unit. The region segmentation unit initially divides the berthing area into a warning area, a buffer area, and a stopping area. The berthing trend analysis unit analyzes vessel berthing trend indicators based on the first status data. The region dynamic determination unit dynamically divides the berthing area based on the berthing trend indicators and formulates adaptive region division rules based on the output of the berthing trend analysis unit. When the berthing area boundary does not need adjustment, the berthing area adopts a first adaptive region division rule; when the berthing area boundary needs adjustment, the berthing area adopts a second adaptive region division rule.

[0007] The area attribution determination module is used to segment the berthing area based on the first state data and determine the second location data of the segmented area where the vessel is located.

[0008] The dynamic scheduling decision module is used to mark ships that have arrived at the berthing area as "arrived".

[0009] As a further embodiment of the present invention, the frontline loading and unloading system terminal includes a real-time data acquisition module and a batch storage module; the real-time data acquisition module is connected to the batch storage module.

[0010] The real-time data acquisition module is used to acquire the ship's first state data and first position data;

[0011] The batch storage module is used to store the first state data and the first position data in batches.

[0012] As a further aspect of the present invention, the first adaptive region division rule is as follows: when the vessel berthing trend index R is less than the preset minimum threshold R1, the vessel is divided into the warning region, and the corresponding region is denoted as x1; when the vessel berthing trend index R is within the range of the preset minimum threshold R1 to the preset maximum threshold R2 (inclusive of R1 but excluding R2), the vessel is divided into the buffer region, and the corresponding region is denoted as x2; when the vessel berthing trend index R is greater than the preset maximum threshold R2, the vessel is divided into the mooring region, and the corresponding region is denoted as x3.

[0013] The specific formula is expressed as follows:

[0014]

[0015] In the formula: f(x) is the area where the ship is located, x1 is the warning area, x2 is the buffer area, x3 is the berthing area, R1 is the minimum value within the preset range of the ship berthing trend index, and R2 is the maximum value within the preset range of the ship berthing trend index.

[0016] As a further aspect of the present invention, the operation steps of the second adaptive region partitioning rule are as follows:

[0017] Using the initial position data of the ships as input data, the K-means algorithm is used to cluster the initial position data to automatically identify densely populated areas of ships, thereby determining the cluster centers C. i The number of clusters is determined based on the current number of ships and a preset target ship number threshold.

[0018] The region boundary is determined based on each clustering result: For each cluster i, the distance from all ships to the cluster center is calculated, and the maximum distance between clusters is used as the basic radius r. i At the basic radius r i Add a redundant safety distance d on top of the existing one safe That is, r i '=d safe +r i r i To determine the radius;

[0019] The division of each region is determined by the center point and the way it expands with its radius;

[0020] The region where the ship is located is output as the second location data based on the region division results.

[0021] As a further aspect of the present invention, the division of each region is determined according to the center point and its radius expansion method: setting the buffer width. and the width of the warning zone d warn =2r i ';That is, the berthing area: in r i'Defined by radius; Buffer zone: with Defined by radius; Warning area: defined by 2r i ′ is used to define the radius.

[0022] As a further aspect of the present invention, the berthing trend analysis unit is used to analyze ship berthing trend indicators based on first state data. The steps include: calculating the ship number density ρ in the berthing area based on the first state data, where N is the number of ships in the berthing area and S is the area of ​​the berthing area; when ρ exceeds a preset density threshold ρ th When the number of ships is high, it indicates that the berthing area boundary needs to be adjusted; otherwise, no adjustment is needed.

[0023] After normalization based on the vessel number density, first difference, and vessel speed analysis within the berthing area, the vessel berthing trend index is determined using the following formula:

[0024]

[0025] In the formula: R is the ship berthing trend index, α is the weighting parameter of ship number density, ρ is the ship number density, β is the weighting parameter of the first difference, |Δt| is the first difference, and γ is the weighting parameter of the ship speed deviation. v is the deviation value of the ship's running speed. th Let v be the safe threshold for the ship's operating speed.

[0026] As a further aspect of the present invention, the berthing trend analysis unit is used to analyze the berthing trend index of ships based on the first state data. The steps further include: calculating the arrival time difference of ships in the berthing area based on the first state data, determining the estimated berthing time based on the ship's operating speed, determining whether the ship berths earlier or later based on a first difference Δt between the estimated berthing time and the actual berthing time, and determining whether the ship berths earlier or later when the first difference Δt exceeds a preset difference threshold Δt. th When the time is right, it indicates that the berthing area boundary needs to be adjusted; otherwise, no adjustment of the berthing area boundary is required.

[0027] As a further aspect of the present invention, the berthing trend analysis unit is used to analyze the berthing trend index of a vessel based on the first state data. The steps further include: determining the berthing trend index of a vessel after normalization processing based on the vessel number density, the first difference, and the vessel speed analysis in the berthing area; and obtaining the berthing trend index of a vessel by normalizing each data item and adding them together according to the weight parameters of each data item.

[0028] The technical effects and advantages of this invention's information integration service virtualization management system are as follows: After dividing a two-dimensional planar map into grids, the generated first location data clearly delineates each sub-region within the berthing area, making subsequent vessel positioning and zoning processing more detailed and data-driven. Based on the collected first state data, the berthing area is divided to determine the second location data of the segmented area where the vessel is located. Through data analysis, the original map information is combined with the real-time vessel status, making the division results more consistent with actual operational situations. The area can be divided into warning areas, buffer areas, or berthing areas, allowing for flexible adjustment of the berthing area according to actual conditions and timely response to the risks of dense or abnormal vessel berthing. Through area attribution determination, it is possible to identify… The system identifies vessels entering the berthing area and marks them as "arrived," enabling scheduling and safety control of these vessels, effectively improving scheduling accuracy and response speed. It integrates information from static monitoring, real-time frontline data, and dynamic scheduling. Through information integration service virtualization technology, port management personnel can intuitively view the real-time situation within the berthing area on a single platform, achieving unified management of vessel status, area division, and scheduling instructions. The dynamic scheduling decision module marks and schedules vessels entering the berthing area based on attribution determination results, effectively coordinating frontline operations and backend scheduling, ensuring safe berthing, improving terminal resource utilization efficiency, and alleviating vessel congestion. Attached Figure Description

[0029] Figure 1 The present invention provides a graph showing the change of ship density over time.

[0030] Figure 2 The prior art container terminal operation system provided by the present invention;

[0031] Figure 3 The bar chart showing the distribution of the number of ships in each region over a week is provided for the purposes of this invention.

[0032] Figure 4 This is a schematic diagram of the structure of an information integration service virtualization management system provided by the present invention. Detailed Implementation

[0033] The technical solutions of this invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described technical solutions are only a part of this invention, and not all of it. All other technical solutions obtained by those skilled in the art based on the technical solutions of this invention without inventive effort are within the scope of protection of this invention.

[0034] Example 1

[0035] Figure 4The present invention provides a schematic diagram of the structure of an information integration service virtualization management system. As shown in the figure, the information integration service virtualization management system includes a static berthing monitoring module, a front-line loading and unloading system terminal, a region affiliation determination module, a dynamic scheduling decision module, and a real-time update module. The static berthing monitoring module is connected to the front-line loading and unloading system terminal, the front-line loading and unloading system terminal is connected to the region affiliation determination module, the region affiliation determination module is connected to the dynamic scheduling decision module, and the dynamic scheduling decision module is connected to the real-time update module.

[0036] The static berthing monitoring module is used to obtain a two-dimensional plan view of the berthing area through GIS (Geographic Information System), and to obtain the first location data by dividing the two-dimensional plan view into grids;

[0037] The frontline loading and unloading system terminal is used to acquire the first status data and first position data of the vessel, and to store the data in batches;

[0038] The area attribution determination module is used to segment the berthing area based on the first state data and determine the second location data of the segmented area where the vessel is located.

[0039] The dynamic scheduling decision module is used to mark ships that have arrived at the berthing area as "arrived";

[0040] The real-time update module is used to update the "arrived" ships based on data.

[0041] The initial status data of a vessel includes the number of vessels in the berthing area and the vessel's operating speed.

[0042] Specifically, the frontline loading and unloading system terminal includes a real-time data acquisition module and a batch storage module; the real-time data acquisition module is connected to the batch storage module.

[0043] The real-time data acquisition module is used to acquire the ship's first state data and first position data;

[0044] The batch storage module is used to store the first state data and the first position data in batches.

[0045] Specifically, the region attribution determination module includes a region segmentation unit, a berthing trend analysis unit, and a region dynamic determination unit; the region segmentation unit is connected to the berthing trend analysis unit, and the berthing trend analysis unit is connected to the region dynamic determination unit.

[0046] The area segmentation unit is used to initially divide the berthing area into a warning area, a buffer area, and a berthing area;

[0047] The berthing trend analysis unit is used to analyze vessel berthing trend indicators based on the first state data.

[0048] The area dynamic determination unit is used to dynamically segment the berthing area based on berthing trend indicators.

[0049] It should be noted that the early warning zone is primarily used to detect vessels approaching the port from a distance. When the number of vessels in this zone is small, regular batch data updates can be used. However, once the number of vessels increases or anomalies occur, the system will activate a preliminary early warning mechanism. The buffer zone serves as a transition area from early warning to berthing. Vessel density is higher in this zone, and vessels are gradually decelerating and adjusting their course. The system requires increased monitoring frequency, but still primarily relies on batch updates, although some critical events can be addressed in advance. The berthing zone indicates that vessels have entered the berthing boundary or are about to berth, requiring real-time data uploads and immediate feedback to trigger alarms and real-time dispatch.

[0050] Specifically, the berthing trend analysis unit is used to analyze vessel berthing trend indicators based on the first-state data, reflecting the safety status and vessel berthing trends throughout the area, specifically:

[0051] The number of ships in the berthing area is calculated based on the first-state data. Where N is the number of ships in the berthing area, and S is the area of ​​the berthing area; when ρ exceeds the preset density threshold ρ th When the number of ships is high, it indicates that the berthing area boundary needs to be adjusted; otherwise, no adjustment of the berthing area boundary is required.

[0052] The arrival time difference of ships within the berthing area is calculated based on the first state data. The estimated berthing time is determined based on the ship's operating speed. The first difference Δt between the estimated berthing time and the actual berthing time is used to determine whether the ship should berth earlier or later. When the first difference Δt exceeds the preset difference threshold Δt... th When the time is right, it indicates that the berthing area boundary needs to be adjusted; otherwise, no adjustment of the berthing area boundary is required.

[0053] After normalization based on the vessel number density, first difference, and vessel speed analysis within the berthing area, the vessel berthing trend index is determined using the following formula:

[0054]

[0055] In the formula: R is the ship berthing trend index, α is the weighting parameter of ship number density, ρ is the ship number density, β is the weighting parameter of the first difference, |Δt| is the first difference, and γ is the weighting parameter of the ship speed deviation. v is the deviation value of the ship's running speed. th Let v be the safe threshold for the ship's operating speed.

[0056] The first adaptive rule partitions vessels using preset thresholds, enabling timely detection of anomalies in vessel berthing trends. When a vessel's berthing index is low, the system places it in a warning zone to proactively identify approaching vessels from a distance or those potentially posing a risk. When the index is high, it places the vessel in a berthing zone, triggering real-time data uploads, alarms, and scheduling to ensure berthing safety. A simple threshold rule is used when vessel distribution is normal, ensuring efficient and stable system operation. However, when vessels are densely packed, data is abnormal, or berthing trends change drastically, the system can quickly switch to a second adaptive rule based on K-means clustering to reconstruct berthing zone boundaries and improve responsiveness to emergencies. The first adaptive zone partitioning rule is suitable for normal conditions, achieving simple and efficient zone partitioning through fixed thresholds. The second adaptive rule, however, addresses surges in vessel numbers or abnormal situations by using the K-means algorithm to automatically adjust the number of clusters and zone boundaries based on real-time location data, ensuring efficient system operation under various working conditions. By utilizing two levels of adaptive rules, the system can not only respond quickly to the division of regions under normal conditions, but also make fine adjustments through clustering algorithms when there are dense ships and a sudden increase in traffic, so as to achieve dynamic adjustment of region subdivision. This two-level mechanism ensures the high robustness of the system in the face of different situations.

[0057] Specifically, the area dynamic determination unit is used to dynamically segment the berthing area based on the berthing trend index. It formulates adaptive area division rules based on the output of the berthing trend analysis unit. When the berthing area boundary does not need to be adjusted, the berthing area adopts the first adaptive area division rule; when the berthing area boundary needs to be adjusted, the berthing area adopts the second adaptive area division rule.

[0058] Specifically, the first adaptive region division rule is as follows:

[0059] When the ship berthing trend index R is less than the preset minimum threshold R1, the ship is classified into the warning area, and the corresponding area is denoted as x1.

[0060] When the ship berthing trend index R is within the range of the preset minimum threshold R1 to the preset maximum threshold R2 (inclusive of R1 but excluding R2), the ship is assigned to the buffer zone, and the corresponding zone is denoted as x2.

[0061] When the ship berthing trend index R is greater than the preset maximum threshold R2, the ship is assigned to the berthing area, and the corresponding area is denoted as x3.

[0062]

[0063] In the formula: f(x) is the area where the ship is located, x1 is the warning area, x2 is the buffer area, x3 is the berthing area, R1 is the minimum value within the preset range of the ship berthing trend index, and R2 is the maximum value within the preset range of the ship berthing trend index.

[0064] Specifically, the operation steps of the second adaptive region partitioning rule are as follows:

[0065] Using the initial position data of the ships as input data, the K-means algorithm is used to cluster the initial position data to automatically identify densely populated areas of ships, thereby determining the cluster centers C. i The number of clusters is determined based on the current number of ships and a preset target ship number threshold.

[0066]

[0067] In the formula: k is the number of clusters, m is the expected number of ships in each cluster, and k max To limit the maximum number of clusters, k min This represents the minimum limit for the number of clusters.

[0068] It can automatically increase the number of clusters when the number of ships surges, achieving more refined regional division; while when there are fewer ships, it ensures that the system does not over-segment and maintains the continuity of the overall region.

[0069] The region boundary is determined based on each clustering result: For each cluster i, the distance from all ships to the cluster center is calculated, and the maximum distance between clusters is used as the basic radius r. i At the basic radius r i Add a redundant safety distance d on top of the existing one safe That is, r i '=d safe +r i r i To determine the radius;

[0070] The division of each region is determined by its center point and the expansion method of its radius: set the buffer width. and the width of the warning zone d warn =2r i ';That is, the berthing area: in r i 'Defined by radius; Buffer zone: with Defined by radius; Warning area: defined by 2r i Define the radius;

[0072] The region where the ship is located is output as the second location data based on the region division results.

[0073] Figure 1The graph shows the ship density over time. The horizontal axis represents different time points within a day (e.g., 00:00, 03:00, 06:00, 09:00, 12:00, 15:00, 18:00, 21:00), and the vertical axis represents the ship density (units can be ships / km² or ships / m², depending on the actual definition). The curve fluctuates over time, gradually rising from early morning to noon, slightly decreasing in the afternoon, and rising again in the late afternoon and evening. When the mouse hovers over 15:00, the ship density is displayed as 0.9.

[0074] Figure 3 This is a bar chart showing the distribution of vessel numbers in different areas over a week. The horizontal axis represents the different days of the week (Monday to Sunday), and the vertical axis represents the number of vessels. The bars are distinguished by different colors or legends to differentiate the number of vessels in warning areas, buffer areas, and docking areas. As shown in the figure, when the mouse hovers over "Tuesday," the following is displayed: Warning area: 15 vessels, Buffer area: 7 vessels, Docking area: 4 vessels.

[0075] By combining vessel density, berthing time difference, and speed deviation, a comprehensive indicator is formed, which can reflect the dynamic situation within the berthing area from multiple perspectives. The berthing trend indicator can reflect the latest status within the berthing area in real time. When the indicator changes and reaches a preset threshold (such as a density threshold or a time difference threshold), the system can immediately determine whether there is an abnormal berthing or congestion tendency, and issue an early warning. Once the R value is abnormal, it indicates that vessels are densely packed, or berthing times are earlier or later than expected. The system can trigger relevant emergency scheduling measures to prevent berthing problems or safety accidents caused by vessel congestion. Based on the calculation results of the berthing trend indicator R, the area classification module can dynamically adjust the berthing area boundary. When vessels are densely packed or abnormal, the system will switch to a more granular second adaptive area division rule, thereby achieving more accurate area division and providing more scientific data support for berthing management. When the R indicator reaches or exceeds the preset upper limit, it indicates that the vessel is in a dangerous or high-risk area. The system can quickly allocate resources accordingly to achieve real-time management and efficient control of vessel status. This is of great significance for port management and vessel scheduling, effectively reducing resource waste or safety hazards caused by uneven berthing areas.

[0076] Example 2

[0077] There are 10 ships approaching the port simultaneously in the berthing area of a certain port. First, the static berthing monitoring module of the system uses GIS to obtain the two-dimensional plan of the entire berthing area and generates the basic first position data by dividing it in a grid manner; then, the front-line loading and unloading system terminal real-time collects the status data and position data of each ship, such as the ship's running speed, predicted and actual docking times, etc., to form the original data table (Table 1); subsequently, the regional attribution determination module in the system calculates the berthing trend index of each ship using the first status data. Among them, the example parameters are adopted: the ship quantity density (the local density value in the area is 0.3, unit: ship / m 2 , which can be calculated from the number of ships in the area and the area of the region), weight parameters: α = 0.5, β = 0.3, γ = 0.2, and the ship running safety speed threshold is 10 knots.

[0078] Based on the calculated index R, the system uses the first adaptive regional division rule to divide each ship into regions:

[0079] When R < R1 (R1 = 1.5), the ship is in the warning area (denoted as x1);

[0080] When R1 ≤ R < R2 (R2 = 3.0), the ship is in the buffer area (denoted as x2);

[0081] When R ≥ R2, the ship is in the docking area (denoted as x3).

[0082] When the number of ships surges or the data is abnormal and further refined regional division is required, the system will use the K-means clustering algorithm based on the first position data (the second adaptive regional division rule) to automatically determine the ship-dense areas and calculate the regional boundaries of each cluster:

[0083] As shown in Table 1, it gives the original data collection table of the front-line loading and unloading system terminal, which records the first status data and first position data of each ship collected in real time by the front-line terminal:

[0084]

[0085]

[0086] Table 1 Original Data Collection Table of Front-line Loading and Unloading System Terminal

[0087] Table 2 gives the regional attribution result table based on the first adaptive regional division rule. Using the

[0088] first status data in Table 1, the system calculates the berthing trend index R of each ship. Table 2 is as follows:

[0089] Ship ID Calculate index R Area where the ship is located S001 0.49 <![CDATA[X1 (Early Warning Area)]]> S002 1.10 <![CDATA[x1 (Early Warning Area)]]> S003 0.15 <![CDATA[x1 (Early warning area)]]> S004 1.67 <![CDATA[x2 (Buffer Area)]]> S005 2.33 <![CDATA[x2 (Buffer Area)]]> S006 0.17 <![CDATA[x1 (Warning Area)]]> S007 3.24 <![CDATA[x3 (Docking area)]]> S008 1.38 <![CDATA[X1 (Early Warning Area)]]> S009 0.76 <![CDATA[x1 (Early Warning Area)]]> S0010 2.01 <![CDATA[x2 (Buffer Area)]]>

[0090] Table 2. Regional Attribution Results Based on the First Adaptive Regional Division Rule

[0091] When there are a large number of ships or abnormal situations occur, the system will activate the second adaptive region partitioning rule. Taking the current 10 ships as an example, assuming that the expected number of clusters is set to a threshold m = 4, the number of clusters calculated is limited to 2.

[0092] Cluster 1:

[0093] Vessels under its jurisdiction: S001, S002, S003, S006, S007, S010;

[0094] Cluster center: approximately (100.0, 201.33);

[0095] Number of ships: 6;

[0096] Basic radius: The maximum distance from a ship within a cluster to the cluster center, simulated at 15.12m;

[0097] Redundancy safety distance: Let d safe =5m, then determine the radius r i =20.12m;

[0098] Area boundaries:

[0099] Buffer zone radius: d buf ≈30.18m;

[0100] Warning area radius: d warn ≈40.24m.

[0101] Cluster 2:

[0102] Vessels under their jurisdiction: S004, S005, S008, S009;

[0103] Cluster center: approximately (122.5, 205.0);

[0104] Number of ships: 4;

[0105] Basic radius: The maximum distance from a ship within a cluster to the cluster center, simulated at 12.5m;

[0106] Redundancy safety distance: Let d safe =5m, then determine the radius r i =17.5m;

[0107] Area boundaries:

[0108] Buffer zone radius: d buf ≈26.25m;

[0109] Warning area radius: d warn≈35.0m.

[0110] Table 3 provides examples of region partitioning based on the second adaptive region partitioning rule (K-means clustering):

[0111]

[0112] Table 3. Region partitioning based on the second adaptive region partitioning rule (K-means clustering)

[0113] This invention utilizes a gridded two-dimensional planar map to generate first location data that clearly delineates each sub-region within the berthing area, making subsequent vessel positioning and zoning processing more detailed and data-driven. Based on the collected first state data, the berthing area is segmented, determining the second location data of the segmented area where the vessel is located. Data analysis combines the original map information with real-time vessel status, making the segmentation results more consistent with actual operational situations. The area can be divided into warning areas, buffer areas, or berthing areas, allowing for flexible adjustment of the berthing area according to actual conditions and timely response to the risks of dense or abnormal vessel berthing. Through area attribution determination, it is possible to identify vessels entering the berthing area (or berthing area). The system marks arriving vessels as "arrived" and schedules and controls their safety, effectively improving scheduling accuracy and response speed. It integrates information from static monitoring, real-time frontline data, and dynamic scheduling. Through information integration service virtualization technology, port managers can intuitively view the real-time situation within the berthing area on a single platform, achieving unified management of vessel status, area division, and scheduling instructions. The dynamic scheduling decision module marks and schedules vessels entering the berthing area based on their affiliation determination, effectively coordinating frontline operations and backend scheduling. This ensures safe berthing, improves terminal resource utilization efficiency, and alleviates vessel congestion.

[0114] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0115] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An information integration service virtualization management system, comprising a static berthing monitoring module, a front-line loading and unloading system terminal, a region affiliation determination module, a dynamic scheduling decision module, and a real-time update module; characterized in that, The static berthing monitoring module is used to obtain a two-dimensional plan view of the berthing area through GIS, and to divide the two-dimensional plan view into grids to obtain the first position data; the front-line loading and unloading system terminal is used to obtain the first status data and first position data of the vessel, and to store the data in batches. The area attribution determination module is used to segment the berthing area based on the first state data and determine the second location data of the segmented area where the vessel is located. The area attribution determination module includes an area segmentation unit, a berthing trend analysis unit, and an area dynamic determination unit. The area segmentation unit is used to initially segment the berthing area into a warning area, a buffer area, and a docking area. The berthing trend analysis unit is used to analyze vessel berthing trend indicators based on the first state data. The area dynamic determination unit is used to dynamically segment the berthing area based on the berthing trend index. It formulates adaptive area division rules based on the output of the berthing trend analysis unit. When the berthing area boundary does not need to be adjusted, the berthing area adopts the first adaptive area division rule; when the berthing area boundary needs to be adjusted, the berthing area adopts the second adaptive area division rule.

2. The data mining-based archival information classification and management system according to claim 1, characterized in that, The first adaptive zone division rule is: when the ship berthing trend index R is less than the preset minimum threshold R1, the ship is divided into the warning zone, and the corresponding zone is denoted as x1. When the vessel berthing trend index R is within the range of the preset minimum threshold R1 to the preset maximum threshold R2 (inclusive of R1 but excluding R2), the vessel is assigned to the buffer zone, and the corresponding zone is denoted as x2. When the vessel berthing trend index R is greater than the preset maximum threshold R2, the vessel is assigned to the mooring zone, and the corresponding zone is denoted as x3.

3. The data mining-based archival information classification and management system according to claim 1, characterized in that, The steps for implementing the second adaptive region partitioning rule are as follows: Using the initial position data of the ships as input data, the K-means algorithm is used to cluster the initial position data to automatically identify densely populated areas of ships, thereby determining the cluster centers C. i The number of clusters is determined based on the current number of ships and a preset target ship number threshold. The region boundary is determined based on each clustering result: For each cluster i, the distance from all ships to the cluster center is calculated, and the maximum distance between clusters is used as the basic radius r. i At the basic radius r i Add a redundant safety distance d on top of the existing one safe That is, r i '=d safe +R i r i To determine the radius; The division of each region is determined by the center point and the way it expands with its radius; The region where the ship is located is output as the second location data based on the region division results.

4. The data mining-based archival information classification and management system according to claim 3, characterized in that, The division of each region is determined by its center point and the expansion method of its radius: set the buffer width. and the width of the warning zone d warn =2R i '; that is, the parking area: denoted by R i Defined by radius; buffer zone: with Defined by radius; Warning area: defined by 2r i 'Delineate the radius.' 5. The data mining-based archival information classification and management system according to claim 1, characterized in that, The berthing trend analysis unit is used to analyze ship berthing trend indicators based on the first state data. The steps include: calculating the ship number density ρ in the berthing area based on the first state data, where N is the number of ships in the berthing area and S is the area of ​​the berthing area; when ρ exceeds the preset density threshold ρ th When the number of ships is high, it indicates that the berthing area boundary needs to be adjusted; otherwise, no adjustment is needed.

6. The data mining-based archival information classification and management system according to claim 1, characterized in that, The berthing trend analysis unit is used to analyze vessel berthing trend indicators based on the first-state data. The steps also include: calculating the arrival time difference of vessels within the berthing area based on the first-state data; determining the estimated berthing time based on the vessel's operating speed; judging whether a vessel berths earlier or later based on a first difference Δt between the estimated and actual berthing times; and determining whether the vessel berths earlier or later than the first difference Δt exceeds a preset difference threshold Δt. th When the time is right, it indicates that the berthing area boundary needs to be adjusted; otherwise, no adjustment of the berthing area boundary is required.

7. The data mining-based archival information classification and management system according to claim 1, characterized in that, The berthing trend analysis unit is used to analyze the berthing trend index of ships based on the first state data. The steps also include: determining the berthing trend index of ships after normalization based on the ship number density, first difference and ship speed analysis in the berthing area. The ship berthing trend index of ships is obtained by normalizing each data and adding them according to the weight parameters of each data.

8. The data mining-based archival information classification and management system according to claim 1, characterized in that, The area attribution determination module is used to segment the berthing area based on the first state data and determine the second location data of the segmented area where the vessel is located; the dynamic scheduling decision module is used to mark vessels that have arrived at the berthing area as "arrived".

Images