A ship port intelligent correction method and system

Abstract

This invention provides a method and system for intelligent port correction of ships. The method includes: acquiring the location information of all deformation points of the target port; dividing all deformation points into multiple correction groups based on the location information of all deformation points and the number and capacity information of currently available correction resource groups, with each correction group containing the same number of deformation points; and allocating a correction resource group to each correction group based on the currently available correction resource groups to perform correction operations on the target port. This invention combines artificial intelligence algorithms with shipbuilding process knowledge, transforming a rough operation relying on personal experience into a controllable modern industrial process, thereby improving the efficiency of port correction operations.

Description

Technical Field

[0001] This invention relates to the field of marine technology, and more specifically, to a method and system for intelligent correction of ship ports. Background Technology

[0002] In modern shipbuilding, sectional construction has become the mainstream technology. The geometric accuracy of the joint ports (i.e., welding surfaces) of large hull sections (such as side sections and deck sections) directly determines the quality of the ship's assembly, the smoothness of its lines, and the final structural strength. However, during the manufacturing, welding, hoisting, and storage of sections, due to factors such as the release of residual welding stress, gravity, temperature changes, and improper support, local deformation inevitably occurs on the port surface, forming multiple protrusions or depressions that exceed the design tolerances (such as ±3mm).

[0003] Traditional port calibration procedures rely heavily on human experience, which has the following significant drawbacks:

[0004] Task allocation is crude and inefficient: The team leader usually assigns tasks in a "regional contracting" style based on experience, which easily leads to a serious imbalance in the workload of each team. Some teams are overloaded while others are idle, resulting in low overall resource utilization.

[0005] Decision-making lacks data support: the order of correction and resource allocation mainly rely on the "feel" of experienced workers. There is a lack of quantitative and unified evaluation standards for the priority of handling deformation points (such as which points have the greatest impact on structural safety and which need to be dealt with urgently), making it difficult to guarantee quality stability.

[0006] Inflexible and rigid scheduling: When on-site resources (such as the number of work teams) change temporarily, the original division of labor needs to be manually re-coordinated, which is slow and affects the continuity of production.

[0007] In summary, existing technologies rely on human experience for resource scheduling and task planning, which suffers from problems such as low efficiency, uneven load distribution, and poor adaptability, and cannot meet the ever-increasing efficiency requirements of the modern shipbuilding industry. Summary of the Invention

[0008] The purpose of this invention is to provide a method and system for intelligent correction of ship ports to improve the above-mentioned problems.

[0009] To achieve the above objectives, the embodiments of this application provide the following technical solutions:

[0010] On one hand, embodiments of this application provide a method for intelligent correction of ship ports, the method comprising:

[0011] Obtain the location information of all deformation points at the target port;

[0012] Based on the location information of all deformation points and the number and capacity information of currently available correction resource groups, all deformation points are divided into multiple correction groups, with the same number of deformation points in each correction group.

[0013] Based on the currently available correction resource groups, allocate a correction resource group to each group to be corrected in order to perform correction operations on the target port.

[0014] Secondly, embodiments of this application provide a ship port intelligent correction system, the system comprising:

[0015] The acquisition module is used to acquire the location information of all deformation points at the target port;

[0016] The partitioning module is used to divide all deformation points into multiple correction groups based on the location information of all deformation points and the number and capacity information of currently available correction resource groups. Each correction group contains the same number of deformation points.

[0017] The allocation module is used to allocate a correction resource group to each group to be corrected based on the currently available correction resource groups, so as to perform correction operations on the target port.

[0018] Thirdly, embodiments of this application provide a smart ship port correction device, the device including a memory and a processor. The memory is used to store a computer program; the processor is used to execute the computer program to implement the steps of the aforementioned smart ship port correction method.

[0019] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described intelligent correction method for ship ports.

[0020] The beneficial effects of this invention are as follows:

[0021] 1. This invention employs a two-stage strategy: first, clustering to ensure spatial concentration, and then adjusting to ensure equal quantity. The final result is that each group to be corrected contains a strictly identical number of deformation points. This fundamentally solves the problem of uneven workload and achieves absolute fairness in management.

[0022] 2. This invention constructs a transparent and interpretable priority quantification formula by integrating three core dimensions: deformation amount, process impact weight, and waiting days. This formula ensures that defects with the greatest impact on ship structural safety and assembly quality receive the highest priority, aligning algorithmic decisions with the judgment logic of experienced process engineers. This provides a clear and reliable basis for subsequent optimization allocation, directing resources towards the most critical tasks.

[0023] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of the intelligent correction method for ship ports described in this embodiment of the invention;

[0026] Figure 2 This is a schematic diagram of the intelligent correction system for ship ports described in this embodiment of the invention;

[0027] Figure 3 This is a schematic diagram of the intelligent correction device for ship ports described in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals or letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0030] Example 1

[0031] like Figure 1As shown, this embodiment provides a ship port intelligent correction method, which includes steps S1, S2 and S3.

[0032] Step S1: Obtain the location information of all deformation points at the target port;

[0033] In this step, the target port is the port that needs correction; in this embodiment, the port is the entire edge surface of the hull section that is to be welded to another section. The deformation point is the specific location on this port surface where local deformation occurs due to various reasons, exceeding the design tolerance. The position information of all deformation points, i.e., their three-dimensional coordinates (x, y, z), are measured based on the same hull coordinate system.

[0034] Step S2: Based on the location information of all deformation points and the number and capacity information of currently available correction resource groups, divide all deformation points into multiple correction groups, with the same number of deformation points in each correction group.

[0035] The specific implementation steps in this step include step S21;

[0036] Step S21: Obtain the number of currently available orthodontic resource groups and the historical average daily correction capacity of each orthodontic resource group. The number of currently available orthodontic resource groups is greater than or equal to 2. Calculate the average of the historical average daily correction capacity of all orthodontic resource groups to obtain a first value. Add the first value to the preset correction capacity fluctuation amount to obtain a second value. Count the number of deformed points to obtain a third value. Divide the third value by the second value to obtain a fourth value. Round the fourth value up to obtain a fifth value. Divide all deformed points into multiple groups to be corrected based on the fifth value and the number of currently available orthodontic resource groups.

[0037] In this step, the correction resource group is the team formed by the workers performing corrections. For example, there are two correction resource groups: the first group contains 4 correction workers, and the second group contains 3 correction workers. The historical average daily correction capacity of the correction resource group is the number of deformation points that can be corrected each day. For example, the historical average daily correction capacity of correction resource group 1 is 22, meaning that 22 deformation points can be corrected each day. The correction capacity fluctuation is set to 5, which is 5 deformation points. The historical average daily correction capacity can be obtained by counting the total number of deformation points corrected by correction resource group 1 over a past period (e.g., the past 30 days), and dividing the total number by the total number of days.

[0038] In this step, the specific implementation steps of dividing all deformation points into multiple correction groups according to the fifth value and the number of currently available correction resource groups include steps S211 and S212.

[0039] Step S211: Analyze the relationship between the fifth value and the number of currently available orthodontic resource groups. If the fifth value is equal to the number of currently available orthodontic resource groups, the fifth value is used as the K value of the K-Means algorithm. Clustering is performed based on the location information of the deformation points to obtain multiple clusters. If the fifth value is greater than the number of currently available orthodontic resource groups, the fifth value is used as the K value of the K-Means algorithm. Clustering is performed based on the location information of the deformation points to obtain multiple clusters. The centroid distance between each pair of clusters is calculated, and the pair of clusters with the closest centroid distance is found and merged. The merging operation is repeated until the number of clusters is equal to the number of currently available orthodontic resource groups. If the fifth value is less than the number of currently available orthodontic resource groups, the fifth value is used as the K value of the K-Means algorithm. Clustering is performed based on the location information of the deformation points to obtain multiple clusters. The cluster with the most deformation points is split into two clusters using the clustering algorithm. The splitting operation is repeated until the number of clusters is equal to the number of currently available orthodontic resource groups.

[0040] In this step, K-Means clustering is performed solely based on spatial location to ensure that the work points within each task group are geographically concentrated, thereby reducing the ineffective travel time of the work group from the root.

[0041] In this step, by calculating the theoretical number of groups (the fifth value) and comparing it with the actual number of resources, the system can automatically identify and adapt to three resource states (matched, strained, and abundant). Furthermore, when on-site resources change temporarily (such as when a work team is reassigned or reinforced), the system can automatically generate new plans through intelligent merging or splitting without manual replanning, ensuring the continuity and flexibility of production scheduling.

[0042] In this step, the centroid distance between all pairs of clusters is calculated, the pair of clusters with the closest centroid distance is found, and they are merged. This merging operation is repeated until the number of clusters equals the number of currently available orthodontic resource groups. This can be understood as follows: After clustering to obtain multiple clusters, the centroid distance between all pairs of clusters is calculated, the pair of clusters with the closest centroid distance is found, and they are merged. If the number of clusters after merging is still greater than the number of currently available orthodontic resource groups, then the centroid distance between all pairs of clusters is calculated again, the pair of clusters with the closest centroid distance is found, and they are merged again until the number of clusters equals the number of currently available orthodontic resource groups.

[0043] The process of splitting the cluster with the most deformed points into two clusters using a clustering algorithm can be understood as follows: After obtaining multiple clusters, the cluster with the most deformed points is split into two clusters using a clustering algorithm. If the number of clusters after splitting is still less than the number of available orthodontic resource groups, the same splitting operation is performed again on the cluster with the most deformed points, and this process continues until the number of clusters equals the number of available orthodontic resource groups.

[0044] Step S212: After clustering is completed, the clusters are adjusted to obtain multiple groups to be corrected.

[0045] The specific implementation steps of this step include step S2121;

[0046] Step S2121: Set up a task pool, which is initially empty; calculate the first centroid of all clusters, and simultaneously calculate the second centroid of each cluster. Calculate the Euclidean distance from the first centroid to the second centroid of each cluster. Sort the clusters in descending order based on the Euclidean distance. After sorting, adjust each cluster sequentially. During adjustment, each cluster being adjusted is designated as the target cluster. Count the number of deformable points in the target cluster. If the number equals the preset target number, the adjustment is complete; if the number is greater than the preset target number, calculate the distance from each deformable point in the target cluster to the first centroid, and adjust the deformable points according to their distance from the first centroid. Sort the data in ascending order, remove the first deformed points and add them to the task pool, until the number of deformed points in the target cluster equals the preset target number, then the adjustment is complete. If the number is less than the preset target number, calculate the distance from each deformed point in the task pool and all clusters except the target cluster and the completed cluster to the second centroid of the target cluster, and sort the deformed points in ascending order according to their distance to the second centroid. Add the first deformed points to the target cluster, until the number of deformed points in the target cluster equals the preset target number, then the adjustment is complete. The cluster that has been adjusted is called the completed cluster. The product of the target number and the number of clusters is the third value.

[0047] This step ensures a strict equality of the number of tasks in each group while maintaining the spatial structure as much as possible. This achieves management fairness (equalization of workload) and avoids the problem of uneven workload caused by regional contracting in traditional methods.

[0048] Step S3: Based on the currently available correction resource groups, allocate a correction resource group to each group to be corrected in order to perform correction operations on the target port.

[0049] The specific implementation steps of this step include step S31 and step S32;

[0050] Step S31: Obtain the deformation amount, process influence weight, and waiting days for each deformation point. Calculate the priority score for each deformation point based on the deformation amount, process influence weight, and waiting days. The process influence weight is determined based on the location information of the deformation point, and the waiting days are the number of days since the point was identified as a deformation point.

[0051] In this step:

[0052] Deformation A: This is the deviation value of the Z coordinate, in mm, directly quantifying the degree of deformation of the port at that point. A positive value indicates a bulge, and a negative value indicates a depression. For example, a point with a deformation of +12mm means that there is a bulge of up to 12mm at that location.

[0053] Process Influence Weight B: This directly reflects the importance of the deformation point location. For example, points at the port centerline or those intersecting with internal reinforcing structures (ribs) have a higher weight because deformation here has a greater impact on the overall structural strength. This weight is assigned by the operator and is typically between 1.0 and 2.0.

[0054] Waiting days C: The number of days since the deformation at this point was discovered. Port correction is usually the last critical step before closure; the longer the waiting time, the more likely it is to affect subsequent large-scale closure nodes.

[0055] The above deformation amount, process influence weight, and waiting days are all assigned values ​​by the staff and uploaded to the system;

[0056] Priority score b is the amplification factor for the influence of the process (the value can be 5-10, for example, 5), which is used to increase the weight of location criticality in decision-making; c is the adjustment factor for the number of waiting days (the value can be 0.1-0.5, for example, 0.1), which is used to balance the influence of time factors.

[0057] The total score in this formula is simply the sum of three independent items. An increase in any item directly raises the priority, aligning with the instinct of on-site personnel that a problem is serious, critical, and has been waiting a long time—it should be addressed first. Furthermore, each item corresponds to a clear business dimension (severity, criticality, urgency), and the calculation results can be directly explained to management, avoiding the difficulties of implementing a black-box model in industrial settings.

[0058] Step S32: Sum the priority scores of all deformation points in each group to be corrected to obtain a sum score. Sort the groups to be corrected in descending order of the sum score. At the same time, sort the correction resource groups in descending order of historical daily average correction capacity. After sorting, match the groups to be corrected and the correction resource groups in order to match the corresponding correction resource groups for the groups to be corrected.

[0059] This step can be understood as follows: For example, there are 2 groups to be corrected, which are sorted into group 1 and group 2. There are 2 correction resource groups, which are sorted into group 2 and group 1. Then, correction resource group 2 is matched for group 1, and correction resource group 1 is matched for group 2.

[0060] In this step, the groups to be rectified, ranked by total priority score, are matched with the rectification resource groups, ranked by historical capabilities. This simple yet effective rule achieves the optimal allocation principle: the most important tasks are handled by the strongest teams. It not only maximizes the advantages of high-capacity teams in handling complex tasks, improving overall work quality and efficiency, but its clear rules are also easy for on-site personnel to understand and accept.

[0061] Example 2

[0062] like Figure 2 As shown, this embodiment provides a ship port intelligent correction system, which includes an acquisition module 1, a division module 2, and an allocation module 3.

[0063] Module 1 is used to acquire the location information of all deformation points at the target port;

[0064] The division module 2 is used to divide all deformation points into multiple correction groups based on the location information of all deformation points and the number and capacity information of currently available correction resource groups. Each correction group has the same number of deformation points.

[0065] Allocation module 3 is used to allocate a correction resource group to each group to be corrected based on the currently available correction resource groups, so as to perform correction operations on the target port.

[0066] In one specific embodiment of this disclosure, the division module 2 further includes a first acquisition unit 21.

[0067] The first acquisition unit 21 is used to acquire the number of currently available orthodontic resource groups and the historical average daily correction capacity of each orthodontic resource group. The number of currently available orthodontic resource groups is greater than or equal to 2. The average of the historical average daily correction capacity of all orthodontic resource groups is calculated to obtain a first value. The first value is added to a preset correction capacity fluctuation amount to obtain a second value. The number of deformation points is counted to obtain a third value. The third value is divided by the second value to obtain a fourth value. The fourth value is rounded up to obtain a fifth value. Based on the fifth value and the number of currently available orthodontic resource groups, all deformation points are divided into multiple groups to be corrected.

[0068] In one specific embodiment of this disclosure, the first acquisition unit 21 further includes an analysis unit 211 and an adjustment unit 212.

[0069] Analysis unit 211 is used to analyze the relationship between the fifth value and the number of currently available orthodontic resource groups. If the fifth value is equal to the number of currently available orthodontic resource groups, the fifth value is used as the K value of the K-Means algorithm, and clustering is performed based on the location information of the deformation points to obtain multiple clusters. If the fifth value is greater than the number of currently available orthodontic resource groups, the fifth value is used as the K value of the K-Means algorithm, and clustering is performed based on the location information of the deformation points to obtain multiple clusters. The centroid distance between each pair of clusters is calculated, and the pair of clusters with the closest centroid distance is found and merged. The merging operation is repeated until the number of clusters is equal to the number of currently available orthodontic resource groups. If the fifth value is less than the number of currently available orthodontic resource groups, the fifth value is used as the K value of the K-Means algorithm, and clustering is performed based on the location information of the deformation points to obtain multiple clusters. A splitting operation is performed on the cluster with the most deformation points. In this cluster, the clustering algorithm is used to split it into two clusters. The splitting operation is repeated until the number of clusters is equal to the number of currently available orthodontic resource groups.

[0070] The adjustment unit 212 is used to adjust the clusters after the clustering is completed, and after adjustment, multiple groups to be corrected are obtained.

[0071] In one specific embodiment of this disclosure, the adjustment unit 212 further includes a setting unit 2121.

[0072] Setting unit 2121 is used to set the task pool, which is initially empty. The first centroid of all clusters is calculated, and the second centroid of each cluster is also calculated. The Euclidean distance from the first centroid to the second centroid of each cluster is calculated. The clusters are sorted in descending order based on the Euclidean distance. After sorting, each cluster is adjusted sequentially. During adjustment, each cluster being adjusted is designated as the target cluster. The number of deformable points in the target cluster is counted. If the number equals the preset target number, the adjustment is complete. If the number is greater than the preset number, the distance from each deformable point in the target cluster to the first centroid is calculated, and the deformable points are adjusted according to their distance from the first centroid. Sort the data in ascending order, remove the first deformed points and add them to the task pool, until the number of deformed points in the target cluster equals the preset target number, then the adjustment is complete. If the number is less than the preset target number, calculate the distance from each deformed point in the task pool and all clusters except the target cluster and the completed cluster to the second centroid of the target cluster, and sort the deformed points in ascending order according to their distance to the second centroid. Add the first deformed points to the target cluster, until the number of deformed points in the target cluster equals the preset target number, then the adjustment is complete. The cluster that has been adjusted is called the completed cluster. The product of the target number and the number of clusters is the third value.

[0073] In one specific embodiment of this disclosure, the allocation module 3 further includes a second acquisition unit 31 and a matching unit 32.

[0074] The second acquisition unit 31 is used to acquire the deformation amount, process influence weight, and waiting days of each deformation point, and to calculate the priority score of each deformation point based on the deformation amount, process influence weight, and waiting days of each deformation point. The process influence weight is determined based on the location information of the deformation point, and the waiting days are the number of days since the deformation point was identified.

[0075] Matching unit 32 is used to sum the priority scores of all deformation points in each group to be corrected, obtain a sum score, sort the groups to be corrected in descending order of the sum score, and sort the correction resource groups in descending order of historical daily average correction capacity. After sorting, the groups to be corrected and the correction resource groups are matched one by one in order to match the corresponding correction resource groups for the groups to be corrected.

[0076] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0077] Example 3

[0078] Corresponding to the above method embodiments, this disclosure also provides a ship port intelligent correction device. The ship port intelligent correction device described below and the ship port intelligent correction method described above can be referred to in correspondence.

[0079] Figure 3 This is a block diagram illustrating a ship port intelligent correction device 300 according to an exemplary embodiment. Figure 3 As shown, the ship port intelligent correction device 300 may include: a processor 301 and a memory 302. The ship port intelligent correction device 300 may also include one or more of the following: a multimedia component 303, an I / O interface 304, and a communication component 305.

[0080] The processor 301 controls the overall operation of the ship port intelligent correction device 300 to complete all or part of the steps in the aforementioned ship port intelligent correction method. The memory 302 stores various types of data to support the operation of the ship port intelligent correction device 300. This data may include, for example, instructions for any application or method operating on the ship port intelligent correction device 300, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 302 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 302 or transmitted via the communication component 305. The audio component also includes at least one speaker for outputting audio signals. I / O interface 304 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 305 is used for wired or wireless communication between the ship port intelligent correction device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 305 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0081] In an exemplary embodiment, the ship port intelligent correction device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the aforementioned ship port intelligent correction method.

[0082] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described intelligent ship port correction method. For example, the computer-readable storage medium may be the memory 302 including program instructions, which may be executed by the processor 301 of the intelligent ship port correction device 300 to complete the above-described intelligent ship port correction method.

[0083] Example 4

[0084] Corresponding to the above method embodiments, this disclosure also provides a readable storage medium, which can be referred to in conjunction with the ship port intelligent correction method described above.

[0085] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the intelligent correction method for ship ports described in the above method embodiments.

[0086] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0087] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent correction of ship ports, characterized in that, include: Obtain the location information of all deformation points at the target port; Based on the location information of all deformation points and the number and capacity information of currently available correction resource groups, all deformation points are divided into multiple correction groups, with the same number of deformation points in each correction group. Based on the currently available correction resource groups, allocate a correction resource group to each group to be corrected in order to perform correction operations on the target port; Based on the location information of all deformation points and the number and capacity information of currently available correction resource groups, all deformation points are divided into multiple correction groups, including: Obtain the number of currently available orthodontic resource groups and the historical average daily correction capacity of each orthodontic resource group. The number of currently available orthodontic resource groups is greater than or equal to 2. Calculate the average historical daily correction capacity of all orthodontic resource groups to obtain a first value. Add the first value to a preset correction capacity fluctuation amount to obtain a second value. Count the number of deformed points to obtain a third value. Divide the third value by the second value to obtain a fourth value. Round the fourth value up to obtain a fifth value. Divide all deformed points into multiple groups to be corrected based on the fifth value and the number of currently available orthodontic resource groups. Based on the fifth value and the number of currently available correction resource groups, all deformities are divided into multiple correction groups, including: The relationship between the fifth value and the number of currently available orthodontic resource groups is analyzed. If the fifth value equals the number of currently available orthodontic resource groups, the fifth value is used as the K value of the K-Means algorithm. Clustering is performed based on the location information of the deformation points to obtain multiple clusters. If the fifth value is greater than the number of currently available orthodontic resource groups, the fifth value is used as the K value of the K-Means algorithm. Clustering is performed based on the location information of the deformation points to obtain multiple clusters. The centroid distance between each pair of clusters is calculated, and the pair of clusters with the closest centroid distance is found and merged. This merging operation is repeated until the number of clusters equals the number of currently available orthodontic resource groups. If the fifth value is less than the number of currently available orthodontic resource groups, the fifth value is used as the K value of the K-Means algorithm. Clustering is performed based on the location information of the deformation points to obtain multiple clusters. The cluster with the most deformation points is split into two clusters using the clustering algorithm. This splitting operation is repeated until the number of clusters equals the number of currently available orthodontic resource groups. After clustering is completed, the clusters are adjusted, resulting in multiple groups to be corrected. Based on the currently available orthodontic resource groups, one orthodontic resource group is assigned to each group to be orthodontized, including: Obtain the deformation amount, process influence weight, and waiting days for each deformation point. Calculate the priority score for each deformation point based on these parameters. The process influence weight is determined based on the location information of the deformation point, and the waiting days are the number of days since the point was identified as a deformation point. The priority scores of all deformation points in each group to be corrected are summed to obtain a sum score. The groups to be corrected are sorted in descending order of the sum score. At the same time, the correction resource groups are sorted in descending order of historical average daily correction capacity. After sorting, the groups to be corrected and the correction resource groups are matched one by one in order to match the corresponding correction resource group for the group to be corrected.

2. The intelligent correction method for ship ports according to claim 1, characterized in that, The clusters were adjusted, resulting in several groups to be corrected, including: Set up a task pool, initially empty. Calculate the first centroid of all clusters, and simultaneously calculate the second centroid of each cluster. Calculate the Euclidean distance from the first centroid to the second centroid of each cluster. Sort the clusters in descending order based on the Euclidean distance. After sorting, adjust each cluster sequentially. During adjustment, designate each cluster being adjusted as the target cluster. Count the number of deformable points in the target cluster. If the number equals the preset target number, the adjustment is complete; otherwise, calculate the distance from each deformable point in the target cluster to the first centroid, and sort the deformable points in ascending order based on their distance to the first centroid. Remove the first deformed points sequentially and add them to the task pool until the number of deformed points in the target cluster equals the preset target number, thus completing the adjustment. If the number is less than the preset target number, calculate the distance from each deformed point in the task pool and all clusters except the target cluster and the completed cluster to the second centroid of the target cluster. Sort the deformed points in ascending order of their distance to the second centroid, and add the first deformed points sequentially to the target cluster until the number of deformed points in the target cluster equals the preset target number, thus completing the adjustment. The cluster that has been adjusted is recorded as the completed cluster. The product of the target number and the number of clusters is the third value.

3. A ship port intelligent correction system, characterized in that, include: The acquisition module is used to acquire the location information of all deformation points at the target port; The partitioning module is used to divide all deformation points into multiple correction groups based on the location information of all deformation points and the number and capacity information of currently available correction resource groups. Each correction group contains the same number of deformation points. The allocation module is used to allocate a correction resource group to each group to be corrected based on the currently available correction resource groups, so as to perform correction operations on the target port; The modules are divided into: The first acquisition unit is used to acquire the number of currently available orthodontic resource groups and the historical average daily correction capacity of each orthodontic resource group. The number of currently available orthodontic resource groups is greater than or equal to 2. The average historical daily correction capacity of all orthodontic resource groups is calculated to obtain a first value. The first value is added to a preset correction capacity fluctuation amount to obtain a second value. The number of deformed points is counted to obtain a third value. The third value is divided by the second value to obtain a fourth value. The fourth value is rounded up to obtain a fifth value. Based on the fifth value and the number of currently available orthodontic resource groups, all deformed points are divided into multiple groups to be corrected. The first acquisition unit includes: The analysis unit analyzes the relationship between the fifth value and the number of currently available orthodontic resource groups. If the fifth value equals the number of currently available orthodontic resource groups, it is used as the K value for the K-Means algorithm. Clustering is performed based on the location information of the deformation points to obtain multiple clusters. If the fifth value is greater than the number of currently available orthodontic resource groups, it is used as the K value for the K-Means algorithm. Clustering is performed based on the location information of the deformation points to obtain multiple clusters. The centroid distance between each pair of clusters is calculated, and the pair with the closest centroid distance is found and merged. This merging operation is repeated until the number of clusters equals the number of currently available orthodontic resource groups. If the fifth value is less than the number of currently available orthodontic resource groups, it is used as the K value for the K-Means algorithm. Clustering is performed based on the location information of the deformation points to obtain multiple clusters. The cluster with the most deformation points is split into two clusters using the clustering algorithm. This splitting operation is repeated until the number of clusters equals the number of currently available orthodontic resource groups. The adjustment unit is used to adjust the clusters after clustering is completed, resulting in multiple groups to be corrected. The allocation module includes: The second acquisition unit is used to acquire the deformation amount, process influence weight, and waiting days of each deformation point, and to calculate the priority score of each deformation point based on the deformation amount, process influence weight, and waiting days of each deformation point. The process influence weight is determined based on the location information of the deformation point, and the waiting days are the number of days since the deformation point was identified. The matching unit is used to sum the priority scores of all deformation points in each group to be corrected, obtain the sum score, sort the groups to be corrected in descending order of the sum score, and sort the correction resource groups in descending order of historical daily average correction capacity. After sorting, the groups to be corrected and the correction resource groups are matched one by one in order to match the corresponding correction resource groups for the groups to be corrected.

4. The intelligent ship port correction system according to claim 3, characterized in that, Adjustment unit, including: The setup unit is used to set up the task pool, which is initially empty. The first centroid of all clusters is calculated, along with the second centroid of each cluster. The Euclidean distance from the first to the second centroid of each cluster is calculated, and the clusters are sorted in descending order based on the Euclidean distance. Each cluster is then adjusted sequentially. During adjustment, each cluster being adjusted is designated as the target cluster. The number of deformable points within the target cluster is counted. If the number equals the preset target number, the adjustment is complete. If the number is greater than the preset number, the distance from each deformable point in the target cluster to the first centroid is calculated, and the deformable points are sorted in ascending order based on their distance to the first centroid. The process involves sorting the data, removing the top-ranked deformable points and adding them to the task pool, until the number of deformable points in the target cluster equals the preset target number, thus completing the adjustment. If the number is less than the preset target number, the distance between each deformable point in the task pool and all clusters except the target and completed clusters is calculated and placed in ascending order of distance to the second centroid of the target cluster. The top-ranked deformable points are then added to the target cluster, and the process continues until the number of deformable points in the target cluster equals the preset target number, thus completing the adjustment. The clusters that have completed the adjustment are designated as the completed clusters. The product of the target number and the number of clusters is the third value.

Images