Ship cargo data management method and system based on two-dimensional model interaction

Abstract

The invention discloses a two-dimensional model interaction-based ship cargo data management method and system. The method comprises the steps of obtaining cargo data uploaded by an operator and a ship map corresponding to a target ship; determining a preliminary distribution two-dimensional model corresponding to the cargo data according to a data matching rule and the ship map; determining a plurality of corresponding reference distribution two-dimensional models according to the historical loading data of the target ship and the ship map; and based on a preset distribution optimization algorithm, correcting the preliminary distribution two-dimensional model according to the reference distribution two-dimensional model to obtain a corrected cargo distribution two-dimensional model. Therefore, the accuracy and rationality of the ship cargo distribution model can be improved, so that the cargo distribution is visually reflected, and an accurate data reference basis is provided for subsequent cargo processing.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a ship cargo data management method and system based on two-dimensional model interaction. Background Art

[0002] With the rapid development of modern shipping industry, the demand for automation and intelligence of cargo loading is increasing day by day. Using data modeling technology to generate cargo distribution model has become an important means to improve loading efficiency and optimize cargo management. The existing cargo distribution determination technology is generally based on the manual settings of operators or based on simple data matching rules to automatically generate cargo distribution models in the cabin. It usually only relies on basic rule matching or static calculation models. The accuracy and rationality of the generated cargo distribution model are insufficient, and it is difficult to accurately reflect the actual distribution of cargo in the cabin, which affects the subsequent cargo management and scheduling efficiency. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a ship cargo data management method and system based on two-dimensional model interaction, which can improve the accuracy and rationality of the ship cargo distribution model, so as to intuitively reflect the cargo distribution and provide an accurate data reference basis for subsequent cargo processing.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for managing ship cargo data based on two-dimensional model interaction, the method comprising: Obtain cargo data uploaded by the operator and the vessel map corresponding to the target vessel; Determine a preliminary distribution two-dimensional model corresponding to the cargo data according to the data matching rules and the vessel map; Determining a plurality of corresponding reference distribution two-dimensional models according to the historical loading data of the target vessel and the vessel map; Based on a preset distribution optimization algorithm, the preliminary distribution two-dimensional model is corrected according to the reference distribution two-dimensional model to obtain a corrected cargo distribution two-dimensional model.

[0005] As an optional embodiment, in the first aspect of the present invention, the cargo data includes multiple cargo label data, which are obtained by the operator identifying the labels of the cargo on the target ship through a portable device; the cargo label data includes obtaining at least one of location, name, category, quantity, weight, volume, packaging type, storage requirements, loading method and transportation information.

[0006] As an optional implementation, in the first aspect of the present invention, determining the preliminary distribution two-dimensional model corresponding to the cargo data according to the data matching rule and the ship map includes: Based on the data matching rule, determine the cargo location information of multiple cargos corresponding to the cargo data; Determine the corresponding map location on the ship map for each of the cargo location information; Based on the map location, using the cargo loading area of the ship map as the base map, generate a preliminary distribution two-dimensional model corresponding to the cargo data.

[0007] As an optional implementation manner, in the first aspect of the present invention, the step of determining the cargo location information of multiple cargos corresponding to the cargo data based on the data matching rule includes: For each cargo label data in the cargo data, based on the data matching rule, determine whether there is location data in the cargo label data; If the cargo label data has location data, determine the location data as the cargo location information of the cargo corresponding to the cargo label data; If the cargo label data does not have location data, input the cargo label data into the trained location prediction model to obtain the predicted location corresponding to the cargo label data; the location prediction model is trained by a training data set including multiple training cargo label data and corresponding location annotations; Judge whether the predicted location coincides with the existing cargo location information. If not, determine the predicted location as the cargo location information of the cargo corresponding to the cargo label data. If so, determine the prediction location result with the second highest prediction probability in the output prediction result of the location prediction model as the cargo location information of the cargo corresponding to the cargo label data.

[0008] As an optional implementation manner, in the first aspect of the present invention, the step of determining multiple corresponding reference distribution two-dimensional models according to the historical loading data of the target ship and the ship map includes: From a preset historical database, determine multiple historical loading cargo data corresponding to the target ship; the historical loading cargo data includes historical cargo label data and corresponding historical cargo distribution two-dimensional models; For each of the historical loading cargo data, input the historical cargo label data in the historical loading cargo data into the location prediction model to obtain the predicted cargo distribution location corresponding to the historical loading cargo data; Calculate the first similarity between the predicted cargo distribution location and the historical cargo distribution two-dimensional model in the historical loading cargo data to obtain the data priority corresponding to the historical loading cargo data; Filter out the historical loading cargo data with the data priority greater than the first priority threshold to obtain multiple preferred historical cargo data; Determine a plurality of reference two-dimensional distribution models from the plurality of preferred historical cargo data according to the matching degree between the vessel map and the two-dimensional historical cargo distribution model.

[0009] As an optional implementation manner, in the first aspect of the present invention, the determining a plurality of reference two-dimensional distribution models from the plurality of preferred historical cargo data according to the matching degree between the vessel map and the two-dimensional historical cargo distribution model includes: For the two-dimensional historical cargo distribution model in each of the preferred historical cargo data, calculate the second similarity between the background map of the two-dimensional historical cargo distribution model and the vessel map; Calculate the weighted sum average of the first similarity and the second similarity corresponding to the two-dimensional historical cargo distribution model to obtain the model priority corresponding to the two-dimensional historical cargo distribution model; wherein, the weight corresponding to the first similarity is less than the weight corresponding to the second similarity; the weight corresponding to the first similarity is proportional to the data volume of the historical cargo label data; the weight corresponding to the second similarity is proportional to the clarity of the background map; the clarity is obtained by inputting the background map into a clarity evaluation model; Screen out the two-dimensional historical cargo distribution models corresponding to the model priority greater than the second priority threshold from the two-dimensional historical cargo distribution models in all the preferred historical cargo data to obtain a plurality of reference two-dimensional distribution models.

[0010] As an optional implementation manner, in the first aspect of the present invention, the correcting the preliminary two-dimensional distribution model according to the reference two-dimensional distribution model based on a preset distribution optimization algorithm to obtain a corrected two-dimensional cargo distribution model includes: For each of the reference two-dimensional distribution models, input the reference two-dimensional distribution model and the corresponding cargo label data into a feature calculation model to obtain the cargo distribution feature information corresponding to the reference two-dimensional distribution model; the cargo distribution feature information includes at least one of the correspondence between cargo spacing, the correspondence between cargo type and cargo position, the correspondence between cargo size and cargo position, and the correspondence between cargo size and cargo spacing; Cluster all the reference two-dimensional distribution models based on the cargo distribution feature information to obtain a cluster model set; the cluster model set includes a plurality of reference two-dimensional distribution models with a similarity of the cargo distribution feature information between them greater than the first similarity threshold; Correct the preliminary two-dimensional distribution model based on the cluster model set by means of a dynamic programming algorithm to obtain a corrected two-dimensional cargo distribution model.

[0011] As an alternative embodiment, in the first aspect of the present invention, based on the clustering model set and the dynamic programming algorithm, the preliminary distribution two-dimensional model is corrected to obtain a corrected two-dimensional model of the cargo distribution, including: Set the objective function to maximize the similarity between the calculation result of the two-dimensional model and the preliminary distribution two-dimensional model; Set the constraints including: The position distance between the cargo positions in the calculation result of the two-dimensional model and the cargo positions of the corresponding cargoes in the preliminary distribution two-dimensional model is less than the distance threshold; The similarity between the calculation result of the two-dimensional model and any one of the reference distribution two-dimensional models in the clustering model set is greater than a preset second similarity threshold; The similarity between the cargo distribution characteristic information corresponding to the calculation result of the two-dimensional model and the cargo distribution characteristic information of any one of the reference distribution two-dimensional models in the clustering model set is greater than a preset third similarity threshold; Based on the dynamic programming algorithm, according to the objective function and the constraints, randomly adjust and optimize the cargo positions of the preliminary distribution two-dimensional model until the best calculation result of the two-dimensional model is obtained, which is determined as the corrected two-dimensional model of the cargo distribution.

[0012] A second aspect of the embodiments of the present invention discloses a vessel cargo data management system based on two-dimensional model interaction. The system includes: An acquisition module for acquiring the cargo data uploaded by the operator and the vessel map corresponding to the target vessel; A first determination module for determining the preliminary distribution two-dimensional model corresponding to the cargo data according to the data matching rule and the vessel map; A second determination module for determining a plurality of corresponding reference distribution two-dimensional models according to the historical loading data of the target vessel and the vessel map; A correction module for correcting the preliminary distribution two-dimensional model according to the reference distribution two-dimensional model based on a preset distribution optimization algorithm to obtain a corrected two-dimensional model of the cargo distribution.

[0013] As an alternative embodiment, in the second aspect of the present invention, the cargo data includes a plurality of cargo label data, which are obtained by the operator identifying the labels of the cargoes on the target vessel through a portable device; the cargo label data includes at least one of acquisition location, name, category, quantity, weight, volume, packaging type, storage requirements, loading method, and transportation information.

[0014] As an alternative embodiment, in the second aspect of the present invention, the specific manner in which the first determination module determines the preliminary distribution two-dimensional model corresponding to the cargo data according to the data matching rule and the vessel map includes: Based on the data matching rule, determine the cargo position information of multiple cargos corresponding to the cargo data; Determine the corresponding map position of each cargo position information on the vessel map; According to the map position, generate the preliminary distribution two-dimensional model corresponding to the cargo data with the cargo loading area of the vessel map as the base map.

[0015] As an alternative embodiment, in the second aspect of the present invention, the specific manner in which the first determination module determines the cargo position information of multiple cargos corresponding to the cargo data based on the data matching rule includes: For each cargo label data in the cargo data, based on the data matching rule, determine whether there is position data in the cargo label data; If the cargo label data has position data, determine the position data as the cargo position information of the cargo corresponding to the cargo label data; If the cargo label data does not have position data, input the cargo label data into the trained position prediction model to obtain the predicted position corresponding to the cargo label data; the position prediction model is trained through a training data set including multiple training cargo label data and corresponding position annotations; Judge whether the predicted position coincides with the existing cargo position information. If not, determine the predicted position as the cargo position information of the cargo corresponding to the cargo label data. If so, determine the prediction position result with the second highest prediction probability in the output prediction result of the position prediction model as the cargo position information of the cargo corresponding to the cargo label data.

[0016] As an alternative embodiment, in the second aspect of the present invention, the specific manner in which the second determination module determines multiple corresponding reference distribution two-dimensional models according to the historical loading data of the target vessel and the vessel map includes: Determine multiple historical loading cargo data corresponding to the target vessel from a preset historical database; the historical loading cargo data includes historical cargo label data and corresponding historical cargo distribution two-dimensional models; For each historical loading cargo data, input the historical cargo label data in the historical loading cargo data into the position prediction model to obtain the predicted cargo distribution position corresponding to the historical loading cargo data; Calculate a first similarity between the predicted cargo distribution position and the historical cargo distribution two-dimensional model in the historical loaded cargo data to obtain a data priority corresponding to the historical loaded cargo data; Filter out the historical loaded cargo data with the data priority greater than a first priority threshold to obtain a plurality of preferred historical cargo data; Determine a plurality of reference distribution two-dimensional models from the plurality of preferred historical cargo data according to the matching degree between the ship map and the historical cargo distribution two-dimensional model.

[0017] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the second determination module determines a plurality of reference distribution two-dimensional models from the plurality of preferred historical cargo data according to the matching degree between the ship map and the historical cargo distribution two-dimensional model includes: For the historical cargo distribution two-dimensional model in each of the preferred historical cargo data, calculate a second similarity between the background map of the historical cargo distribution two-dimensional model and the ship map; Calculate a weighted sum average of the first similarity and the second similarity corresponding to the historical cargo distribution two-dimensional model to obtain a model priority corresponding to the historical cargo distribution two-dimensional model; wherein, the weight corresponding to the first similarity is less than the weight corresponding to the second similarity; the weight corresponding to the first similarity is proportional to the data volume of the historical cargo label data; the weight corresponding to the second similarity is proportional to the clarity of the background map; the clarity is obtained by inputting the background map into a clarity evaluation model; Filter out the historical cargo distribution two-dimensional models with the corresponding model priority greater than a second priority threshold from the historical cargo distribution two-dimensional models in all the preferred historical cargo data to obtain a plurality of reference distribution two-dimensional models.

[0018] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the correction module corrects the preliminary distribution two-dimensional model according to the reference distribution two-dimensional model based on a preset distribution optimization algorithm to obtain a corrected cargo distribution two-dimensional model includes: For each of the reference distribution two-dimensional models, input the reference distribution two-dimensional model and the corresponding cargo label data into a feature calculation model to obtain cargo distribution feature information corresponding to the reference distribution two-dimensional model; the cargo distribution feature information includes at least one of the corresponding relationship between cargo spacing, cargo type and cargo position, the corresponding relationship between cargo size and cargo position, and the corresponding relationship between cargo size and cargo spacing; Based on the cargo distribution feature information, clustering is performed on all the reference distribution two-dimensional models to obtain a clustering model set; the clustering model set includes multiple reference distribution two-dimensional models whose similarity of the cargo distribution feature information to each other is greater than a first similarity threshold; Based on the clustering model set and using the dynamic programming algorithm, the preliminary distribution two-dimensional model is corrected to obtain a corrected cargo distribution two-dimensional model.

[0019] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the correction module corrects the preliminary distribution two-dimensional model based on the clustering model set and using the dynamic programming algorithm to obtain a corrected cargo distribution two-dimensional model includes: Setting the objective function to maximize the similarity between the two-dimensional model calculation result and the preliminary distribution two-dimensional model; Setting the constraint conditions to include: The position distance between the cargo positions in the two-dimensional model calculation result and the corresponding cargo positions in the preliminary distribution two-dimensional model is less than a distance threshold; The similarity between the two-dimensional model calculation result and any one of the reference distribution two-dimensional models in the clustering model set is greater than a preset second similarity threshold; The similarity between the cargo distribution feature information corresponding to the two-dimensional model calculation result and the cargo distribution feature information of any one of the reference distribution two-dimensional models in the clustering model set is greater than a preset third similarity threshold; Based on the dynamic programming algorithm, according to the objective function and the constraint conditions, randomly adjust and optimize the cargo positions of the preliminary distribution two-dimensional model until the best two-dimensional model calculation result is obtained, which is determined as the corrected cargo distribution two-dimensional model.

[0020] The third aspect of the present invention discloses another vessel cargo data management system based on two-dimensional model interaction, and the system includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory and executes some or all of the steps in the vessel cargo data management method based on two-dimensional model interaction disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, and the computer storage medium stores computer instructions, which are used to execute some or all of the steps in the vessel cargo data management method based on two-dimensional model interaction disclosed in the first aspect of the present invention when called.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: Based on the cargo data uploaded by the operator and the vessel map of the target vessel, the present invention can determine the preliminary distribution of the cargo on the vessel, generate a reference distribution model in combination with the historical loading data of the target vessel, and correct the preliminary distribution through a distribution optimization algorithm to obtain a corrected two-dimensional model of the cargo distribution, thereby improving the accuracy and rationality of the vessel cargo distribution model, intuitively reflecting the cargo distribution, and providing an accurate data reference basis for subsequent cargo handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0024] Figure 1 It is a flowchart of a method for managing vessel cargo data based on two-dimensional model interaction disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural diagram of a system for managing vessel cargo data based on two-dimensional model interaction disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural diagram of another system for managing vessel cargo data based on two-dimensional model interaction disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0029] As used herein, the mention of "embodiment" means that the specific features, structures, or characteristics described in connection with the embodiment may be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a method and system for managing vessel cargo data based on two-dimensional model interaction. It can determine the preliminary distribution of cargo on the vessel based on the cargo data uploaded by the operator and the vessel map of the target vessel, generate a reference distribution model in combination with the historical loading data of the target vessel, and correct the preliminary distribution through a distribution optimization algorithm to obtain a corrected two-dimensional model of the cargo distribution, thereby improving the accuracy and rationality of the vessel cargo distribution model, intuitively reflecting the cargo distribution, and providing an accurate data reference basis for subsequent cargo handling. The following will be described in detail respectively.

[0031] Embodiment 1 Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for managing vessel cargo data based on two-dimensional model interaction disclosed in an embodiment of the present invention. Among them, Figure 1 the described method for managing vessel cargo data based on two-dimensional model interaction can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 1 shown, the method for managing vessel cargo data based on two-dimensional model interaction may include the following operations: 101. Obtain the cargo data uploaded by the operator and the vessel map corresponding to the target vessel.

[0032] 102. Determine the preliminary distribution two-dimensional model corresponding to the cargo data according to the data matching rule and the vessel map.

[0033] 103. Determine a plurality of corresponding reference distribution two-dimensional models according to the historical loading data of the target vessel and the vessel map.

[0034] 104. Based on a preset distribution optimization algorithm, correct the preliminary distribution two-dimensional model according to the reference distribution two-dimensional model to obtain a corrected two-dimensional model of the cargo distribution.

[0035] It can be seen that the above-mentioned invention embodiments can determine the preliminary distribution of goods on the ship based on the goods data uploaded by the operator and the ship map of the target ship, generate a reference distribution model in combination with the historical loading data of the target ship, and correct the preliminary distribution through a distribution optimization algorithm to obtain a corrected two-dimensional model of the goods distribution, thereby improving the accuracy and rationality of the ship's goods distribution model, intuitively reflecting the goods distribution, and providing an accurate data reference basis for subsequent goods handling.

[0036] As an optional embodiment, in the above steps, the goods data includes a plurality of goods label data, which are obtained by the operator identifying the labels of the goods on the target ship through a portable device; the goods label data includes at least one of acquisition location, name, category, quantity, weight, volume, packaging type, storage requirements, loading method, and transportation information.

[0037] It can be seen that through the above optional embodiment, the acquisition method and content of the goods data are defined to comprehensively reflect the relevant characteristics of the goods, improve the integrity and accuracy of the goods data, provide accurate data support for the optimization and management of the ship's goods distribution, assist in improving the accuracy and rationality of the ship's goods distribution model, intuitively reflect the goods distribution, and provide an accurate data reference basis for subsequent goods handling.

[0038] As an optional embodiment, in the above steps, determining the corresponding preliminary two-dimensional model of the goods distribution according to the data matching rule and the ship map includes: Based on the data matching rule, determining the goods position information of multiple goods corresponding to the goods data; Determining the corresponding map position of each goods position information on the ship map; According to the map position, using the goods loading area of the ship map as the base map, generating the corresponding preliminary two-dimensional model of the goods distribution.

[0039] It can be seen that through the above optional embodiment, the goods position information corresponding to the goods data is determined based on the data matching rule, the corresponding map position is matched on the ship map, and the preliminary two-dimensional model is generated using the goods loading area of the ship map as the base map, thereby intuitively reflecting the preliminary distribution of the goods in the cabin, improving the visualization degree and spatial layout rationality of the goods distribution, providing basic data support for subsequent correction and optimization, assisting in improving the accuracy and rationality of the ship's goods distribution model, intuitively reflecting the goods distribution, and providing an accurate data reference basis for subsequent goods handling.

[0040] As an optional embodiment, in the above steps, based on the data matching rule, determining the goods position information of multiple goods corresponding to the goods data includes: For each piece of cargo label data in the cargo data, based on the data matching rule, determine whether there is location data in the cargo label data; If the cargo label data has location data, determine the location data as the cargo location information of the cargo corresponding to the cargo label data; If the cargo label data does not have location data, input the cargo label data into the trained location prediction model to obtain the predicted location corresponding to the cargo label data; Optionally, the location prediction model is trained through a training data set including a plurality of training cargo label data and corresponding location annotations; Determine whether the predicted location coincides with the existing cargo location information. If not, determine the predicted location as the cargo location information of the cargo corresponding to the cargo label data. If so, determine the prediction location result with the second highest prediction probability in the output prediction result of the location prediction model as the cargo location information of the cargo corresponding to the cargo label data.

[0041] It can be seen that through the above optional embodiments, the location data in the cargo label data is determined based on the data matching rule, and when it is missing, the trained location prediction model is used for prediction. By judging the coincidence between the predicted location and the existing cargo location information, an appropriate predicted location is selected as the final cargo location information, thereby ensuring the accuracy of the existing location data while improving the filling accuracy of the missing location data, enhancing the integrity of the cargo location information and the reliability of the cargo distribution model, providing more accurate data support for the subsequent correction of the cargo distribution model, assisting in improving the accuracy and rationality of the vessel cargo distribution model, intuitively reflecting the cargo distribution, and providing an accurate data reference basis for subsequent cargo handling.

[0042] As an optional embodiment, in the above steps, according to the historical loading data of the target vessel and the vessel map, determine the corresponding multiple reference distribution two-dimensional models, including: Determine multiple historical loaded cargo data corresponding to the target vessel from the preset historical database; Optionally, the historical loaded cargo data includes historical cargo label data and the corresponding historical cargo distribution two-dimensional model; For each piece of historical loaded cargo data, input the historical cargo label data in the historical loaded cargo data into the location prediction model to obtain the predicted cargo distribution location corresponding to the historical loaded cargo data; Calculate the first similarity between the predicted cargo distribution location and the historical cargo distribution two-dimensional model in the historical loaded cargo data to obtain the data priority corresponding to the historical loaded cargo data; Screen out the historical loaded cargo data with a data priority greater than the first priority threshold to obtain multiple preferred historical cargo data; Determine multiple reference distribution two-dimensional models from multiple preferred historical cargo data according to the matching degree between the ship map and the historical cargo distribution two-dimensional model.

[0043] It can be seen that through the above optional embodiments, based on the historical loaded cargo data of the target ship, calculate the predicted positions of the historical cargo distribution through the position prediction model, determine the data priority according to the similarity with the historical cargo distribution two-dimensional model, screen out the preferred historical cargo data, and combine the matching degree of the ship map to finally determine multiple reference distribution two-dimensional models, thereby improving the rationality and adaptability of the reference distribution two-dimensional model, providing more accurate data support for the subsequent correction of the cargo distribution model, assisting in improving the accuracy and rationality of the ship cargo distribution model, intuitively reflecting the cargo distribution, and providing an accurate data reference basis for the subsequent cargo handling.

[0044] As an optional embodiment, in the above steps, determining multiple reference distribution two-dimensional models from multiple preferred historical cargo data according to the matching degree between the ship map and the historical cargo distribution two-dimensional model includes: For the historical cargo distribution two-dimensional model in each preferred historical cargo data, calculate the second similarity between the background map of the historical cargo distribution two-dimensional model and the ship map; Calculate the weighted sum average of the corresponding first similarity and the second similarity of the historical cargo distribution two-dimensional model to obtain the model priority corresponding to the historical cargo distribution two-dimensional model; optionally, among them, the weight corresponding to the first similarity is less than the weight corresponding to the second similarity; the weight corresponding to the first similarity is proportional to the data volume of the historical cargo label data; the weight corresponding to the second similarity is proportional to the clarity of the background map; the clarity is obtained by inputting the background map into the clarity evaluation model; Screen out the historical cargo distribution two-dimensional models corresponding to the model priority greater than the second priority threshold from the historical cargo distribution two-dimensional models in all preferred historical cargo data to obtain multiple reference distribution two-dimensional models.

[0045] It can be seen that through the above optional embodiments, for the historical cargo distribution two-dimensional model in each preferred historical cargo data, calculate the second similarity by combining its background map and the ship map, and obtain the model priority by weighted summing the first similarity and the second similarity, and screen out the historical cargo distribution two-dimensional models with a priority higher than the second priority threshold, thereby improving the rationality and adaptability of the reference distribution two-dimensional model, providing more accurate data support for the subsequent correction of the cargo distribution model, assisting in improving the accuracy and rationality of the ship cargo distribution model, intuitively reflecting the cargo distribution, and providing an accurate data reference basis for the subsequent cargo handling.

[0046] As an alternative embodiment, in the above steps, based on a preset distribution optimization algorithm, the preliminary two-dimensional distribution model is corrected according to the reference two-dimensional distribution model to obtain a corrected two-dimensional cargo distribution model, including: For each reference two-dimensional distribution model, the reference two-dimensional distribution model and the corresponding cargo label data are input into the feature calculation model to obtain the cargo distribution feature information corresponding to the reference two-dimensional distribution model; optionally, the cargo distribution feature information includes at least one of the correspondence between cargo spacing, cargo type and cargo position, the correspondence between cargo size and cargo position, and the correspondence between cargo size and cargo spacing; Based on the cargo distribution feature information, all the reference two-dimensional distribution models are clustered to obtain a set of clustering models; optionally, the set of clustering models includes multiple reference two-dimensional distribution models with a similarity of cargo distribution feature information greater than the first similarity threshold among them; According to the set of clustering models, the preliminary two-dimensional distribution model is corrected based on the dynamic programming algorithm to obtain a corrected two-dimensional cargo distribution model.

[0047] It can be seen that through the above alternative embodiment, by inputting each reference two-dimensional distribution model and the corresponding cargo label data into the feature calculation model, after obtaining the cargo distribution feature information, all the reference two-dimensional distribution models are clustered and analyzed, and the models with higher similarity are selected to correct the preliminary two-dimensional distribution model, so as to improve the accuracy and rationality of the vessel's cargo distribution model, intuitively reflect the cargo distribution, and provide an accurate data reference basis for subsequent cargo handling.

[0048] As an alternative embodiment, in the above steps, according to the set of clustering models, the preliminary two-dimensional distribution model is corrected based on the dynamic programming algorithm to obtain a corrected two-dimensional cargo distribution model, including: Set the objective function to maximize the similarity between the two-dimensional model calculation result and the preliminary two-dimensional distribution model; Set the constraints to include: The position distance between the cargo positions in the two-dimensional model calculation result and the cargo positions of the corresponding cargoes in the preliminary two-dimensional distribution model is less than the distance threshold; The similarity between the two-dimensional model calculation result and any reference two-dimensional distribution model in the set of clustering models is greater than the preset second similarity threshold; The similarity between the cargo distribution feature information corresponding to the two-dimensional model calculation result and the cargo distribution feature information of any reference two-dimensional distribution model in the set of clustering models is greater than the preset third similarity threshold; Based on the dynamic programming algorithm, according to the objective function and the constraint conditions, randomly adjust and optimize the positions of the goods in the preliminary distribution two-dimensional model until the best two-dimensional model calculation result is obtained, and determine it as the corrected two-dimensional model of the goods distribution.

[0049] It can be seen that through the above optional embodiments, by setting the objective function to maximize the similarity between the two-dimensional model calculation result and the preliminary distribution two-dimensional model, and setting multiple constraint conditions to optimize the positions of the goods, the similarity, and the feature information, using the dynamic programming algorithm to optimize and adjust the preliminary distribution, and finally obtaining the corrected two-dimensional model of the goods distribution, so as to improve the accuracy and rationality of the ship's goods distribution model, visually reflect the goods distribution, and provide an accurate data reference basis for subsequent goods processing.

[0050] Embodiment 2 Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a ship's goods data management system based on two-dimensional model interaction disclosed in an embodiment of the present invention. Among them, Figure 2 the described ship's goods data management system based on two-dimensional model interaction can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 2 shown, the ship's goods data management system based on two-dimensional model interaction may include: An acquisition module 201, configured to acquire the goods data uploaded by the operator and the ship map corresponding to the target ship.

[0051] A first determination module 202, configured to determine a preliminary distribution two-dimensional model corresponding to the goods data according to the data matching rule and the ship map.

[0052] A second determination module 203, configured to determine a plurality of corresponding reference distribution two-dimensional models according to the historical loading data of the target ship and the ship map.

[0053] A correction module 204, configured to correct the preliminary distribution two-dimensional model based on the preset distribution optimization algorithm according to the reference distribution two-dimensional model to obtain the corrected two-dimensional model of the goods distribution.

[0054] It can be seen that the above embodiments of the present invention can determine the preliminary distribution of the goods on the ship based on the goods data uploaded by the operator and the ship map of the target ship, generate a reference distribution model in combination with the historical loading data of the target ship, and correct the preliminary distribution through the distribution optimization algorithm to obtain the corrected two-dimensional model of the goods distribution, so as to improve the accuracy and rationality of the ship's goods distribution model, visually reflect the goods distribution, and provide an accurate data reference basis for subsequent goods processing.

[0055] As an alternative embodiment, the cargo data includes a plurality of cargo label data, which are obtained by an operator identifying the labels of the cargo on the target ship through a portable device; the cargo label data includes at least one of acquisition location, name, category, quantity, weight, volume, packaging type, storage requirements, loading method, and transportation information.

[0056] It can be seen that through the above alternative embodiment, the acquisition method and content of the cargo data are defined to comprehensively reflect the relevant characteristics of the cargo, improve the integrity and accuracy of the cargo data, provide accurate data support for the optimization and management of the ship's cargo distribution, assist in improving the accuracy and rationality of the ship's cargo distribution model, intuitively reflect the cargo distribution, and provide an accurate data reference basis for subsequent cargo handling.

[0057] As an alternative embodiment, the specific manner in which the first determination module determines the preliminary distribution two-dimensional model corresponding to the cargo data according to the data matching rule and the ship map includes: Based on the data matching rule, determine the cargo location information of the multiple cargos corresponding to the cargo data; Determine the corresponding map location on the ship map for each cargo location information; According to the map location, generate a preliminary distribution two-dimensional model corresponding to the cargo data with the cargo loading area of the ship map as the base map.

[0058] It can be seen that through the above alternative embodiment, the cargo location information corresponding to the cargo data is determined based on the data matching rule, the corresponding map location is matched on the ship map, and a preliminary distribution two-dimensional model is generated with the cargo loading area of the ship map as the base map, so as to intuitively reflect the preliminary distribution of the cargo in the cabin, improve the visualization degree and spatial layout rationality of the cargo distribution, provide basic data support for subsequent calibration and optimization, assist in improving the accuracy and rationality of the ship's cargo distribution model, intuitively reflect the cargo distribution, and provide an accurate data reference basis for subsequent cargo handling.

[0059] As an alternative embodiment, the specific manner in which the first determination module determines the cargo location information of the multiple cargos corresponding to the cargo data based on the data matching rule includes: For each cargo label data in the cargo data, based on the data matching rule, determine whether there is location data in the cargo label data; If the cargo label data has location data, determine the location data as the cargo location information of the cargo corresponding to the cargo label data; If the location data does not exist in the goods label data, input the goods label data into the trained location prediction model to obtain the predicted location corresponding to the goods label data; optionally, the location prediction model is trained through a training data set including a plurality of training goods label data and corresponding location annotations; Determine whether the predicted location coincides with the existing goods location information. If not, determine the predicted location as the goods location information of the goods corresponding to the goods label data. If so, determine the predicted location result with the second highest predicted probability in the output prediction result of the location prediction model as the goods location information of the goods corresponding to the goods label data.

[0060] It can be seen that through the above optional embodiments, the location data in the goods label data is determined based on the data matching rule, and when it is missing, the trained location prediction model is used for prediction. By judging the coincidence between the predicted location and the existing goods location information, an appropriate predicted location is selected as the final goods location information, so as to ensure the accuracy of the existing location data while improving the filling accuracy of the missing location data, enhancing the integrity of the goods location information and the reliability of the goods distribution model, providing more accurate data support for the subsequent correction of the goods distribution model, assisting in improving the accuracy and rationality of the ship goods distribution model, intuitively reflecting the goods distribution, and providing an accurate data reference basis for the subsequent goods handling.

[0061] As an optional embodiment, the specific manner in which the second determination module determines a plurality of corresponding reference distribution two-dimensional models according to the historical loading data of the target ship and the ship map includes: Determine a plurality of historical loading goods data corresponding to the target ship from a preset historical database; optionally, the historical loading goods data includes historical goods label data and corresponding historical goods distribution two-dimensional models; For each historical loading goods data, input the historical goods label data in the historical loading goods data into the location prediction model to obtain the predicted goods distribution location corresponding to the historical loading goods data; Calculate the first similarity between the predicted goods distribution location and the historical goods distribution two-dimensional model in the historical loading goods data to obtain the data priority corresponding to the historical loading goods data; Filter out the historical loading goods data with a data priority greater than the first priority threshold to obtain a plurality of preferred historical goods data; Determine a plurality of reference distribution two-dimensional models from the plurality of preferred historical goods data according to the matching degree between the ship map and the historical goods distribution two-dimensional model.

[0062] It can be seen that through the above optional embodiments, based on the historical loaded cargo data of the target vessel, the predicted positions of the historical cargo distribution are calculated through the position prediction model, and the data priority is determined according to the similarity with the two-dimensional model of the historical cargo distribution, and the preferred historical cargo data is screened out. Combining the vessel map matching degree, multiple reference distribution two-dimensional models are finally determined, thereby improving the rationality and adaptability of the reference distribution two-dimensional model, providing more accurate data support for the subsequent calibration of the cargo distribution model, assisting in improving the accuracy and rationality of the vessel cargo distribution model, intuitively reflecting the cargo distribution, and providing an accurate data reference basis for subsequent cargo handling.

[0063] As an optional embodiment, the specific manner in which the second determination module determines multiple reference distribution two-dimensional models from multiple preferred historical cargo data according to the matching degree between the vessel map and the two-dimensional model of the historical cargo distribution includes: For the two-dimensional model of the historical cargo distribution in each preferred historical cargo data, calculate the second similarity between the background map of the two-dimensional model of the historical cargo distribution and the vessel map; Calculate the weighted sum average of the first similarity and the second similarity corresponding to the two-dimensional model of the historical cargo distribution to obtain the model priority corresponding to the two-dimensional model of the historical cargo distribution; optionally, among them, the weight corresponding to the first similarity is less than the weight corresponding to the second similarity; the weight corresponding to the first similarity is proportional to the data volume of the historical cargo label data; the weight corresponding to the second similarity is proportional to the clarity of the background map; the clarity is obtained by inputting the background map into the clarity evaluation model; Screen out the two-dimensional models of the historical cargo distribution whose corresponding model priorities are greater than the second priority threshold from the two-dimensional models of the historical cargo distribution in all preferred historical cargo data to obtain multiple reference distribution two-dimensional models.

[0064] It can be seen that through the above optional embodiments, for the two-dimensional model of the historical cargo distribution in each preferred historical cargo data, the second similarity is calculated by combining its background map and the vessel map, and the first similarity and the second similarity are weighted and summed to obtain the model priority, and the two-dimensional models of the historical cargo distribution with a priority higher than the second priority threshold are screened out, thereby improving the rationality and adaptability of the reference distribution two-dimensional model, providing more accurate data support for the subsequent calibration of the cargo distribution model, assisting in improving the accuracy and rationality of the vessel cargo distribution model, intuitively reflecting the cargo distribution, and providing an accurate data reference basis for subsequent cargo handling.

[0065] As an optional embodiment, the specific manner in which the calibration module calibrates the preliminary distribution two-dimensional model according to the reference distribution two-dimensional model based on a preset distribution optimization algorithm to obtain the calibrated two-dimensional model of the cargo distribution includes: For each two-dimensional reference distribution model, input the two-dimensional reference distribution model and the corresponding cargo label data into the feature calculation model to obtain the cargo distribution feature information corresponding to the two-dimensional reference distribution model; optionally, the cargo distribution feature information includes at least one of the correspondence between cargo spacing, cargo type and cargo position, the correspondence between cargo size and cargo position, and the correspondence between cargo size and cargo spacing; Based on the cargo distribution feature information, cluster all the two-dimensional reference distribution models to obtain a set of clustering models; optionally, the set of clustering models includes multiple two-dimensional reference distribution models whose similarity of cargo distribution feature information to each other is greater than the first similarity threshold; According to the set of clustering models, based on the dynamic programming algorithm, correct the preliminary two-dimensional distribution model to obtain the corrected two-dimensional cargo distribution model.

[0066] It can be seen that through the above optional embodiments, by inputting each two-dimensional reference distribution model and the corresponding cargo label data into the feature calculation model, after obtaining the cargo distribution feature information, clustering analysis is performed on all the two-dimensional reference distribution models, and models with higher similarity are selected to correct the preliminary two-dimensional distribution model, so as to improve the accuracy and rationality of the vessel cargo distribution model, intuitively reflect the cargo distribution, and provide an accurate data reference basis for subsequent cargo handling.

[0067] As an optional embodiment, the specific manner in which the correction module corrects the preliminary two-dimensional distribution model based on the set of clustering models and the dynamic programming algorithm to obtain the corrected two-dimensional cargo distribution model includes: Set the objective function to maximize the similarity between the calculation result of the two-dimensional model and the preliminary two-dimensional distribution model; Set the constraint conditions to include: The position distance between the cargo positions in the calculation result of the two-dimensional model and the corresponding cargo positions in the preliminary two-dimensional distribution model is less than the distance threshold; The similarity between the calculation result of the two-dimensional model and any two-dimensional reference distribution model in the set of clustering models is greater than the preset second similarity threshold; The similarity between the cargo distribution feature information corresponding to the calculation result of the two-dimensional model and the cargo distribution feature information of any two-dimensional reference distribution model in the set of clustering models is greater than the preset third similarity threshold; Based on the dynamic programming algorithm, according to the objective function and the constraint conditions, randomly adjust and optimize the cargo positions of the preliminary two-dimensional distribution model until the best calculation result of the two-dimensional model is obtained, and determine it as the corrected two-dimensional cargo distribution model.

[0068] It can be seen that through the above optional embodiments, by setting an objective function to maximize the similarity between the two-dimensional model calculation result and the preliminary distribution two-dimensional model, and setting multiple constraint conditions to optimize the cargo position, similarity, and feature information, the dynamic programming algorithm is used to optimize and adjust the preliminary distribution. Finally, a corrected two-dimensional model of the cargo distribution is obtained to improve the accuracy and rationality of the vessel cargo distribution model, visually reflect the cargo distribution, and provide an accurate data reference basis for subsequent cargo handling.

[0069] Embodiment III Please refer to Figure 3 , Figure 3 which is another vessel cargo data management system based on two-dimensional model interaction disclosed in the embodiments of the present invention. Figure 3 The described vessel cargo data management system based on two-dimensional model interaction is applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 3 shown, the vessel cargo data management system based on two-dimensional model interaction may include: A memory 301 storing executable program code; A processor 302 coupled to the memory 301; Wherein, the processor 302 invokes the executable program code stored in the memory 301 to execute the steps of the vessel cargo data management method described in Embodiment I.

[0070] Embodiment IV The embodiments of the present invention disclose a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the vessel cargo data management method described in Embodiment I.

[0071] Embodiment V The embodiments of the present invention disclose a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the vessel cargo data management method described in Embodiment I.

[0072] The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily have to be performed in the specific order or continuous order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] The systems, apparatuses, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0074] For convenience of description, when describing the above apparatuses, they are divided into various units according to functions and described separately. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0075] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] This specification is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0077] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or boxes Figure 1 steps of the functions specified in one box or multiple boxes.

[0079] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0080] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0081] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0082] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, commodity or device including the said element.

[0083] This specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0084] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments.

[0085] Finally, it should be noted that: The method and system for managing vessel cargo data based on two-dimensional model interaction disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention. They are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for managing ship cargo data based on two-dimensional model interaction, characterized in that: The method comprises: Obtain cargo data uploaded by the operator and the vessel map corresponding to the target vessel; Determine a preliminary distribution two-dimensional model corresponding to the cargo data according to the data matching rules and the vessel map; Determining a plurality of corresponding reference distribution two-dimensional models according to the historical loading data of the target vessel and the vessel map; Based on a preset distribution optimization algorithm, the preliminary distribution two-dimensional model is corrected according to the reference distribution two-dimensional model to obtain a corrected cargo distribution two-dimensional model.

2. The method for managing ship cargo data based on two-dimensional model interaction according to claim 1, characterized in that: The cargo data includes multiple cargo label data, which are obtained by the operator identifying the labels of the cargo on the target ship through a portable device; the cargo label data includes at least one of the acquisition location, name, category, quantity, weight, volume, packaging type, storage requirements, loading method and transportation information.

3. The method for managing ship cargo data based on two-dimensional model interaction according to claim 1, characterized in that: Determining the preliminary distribution two-dimensional model corresponding to the cargo data according to the data matching rule and the ship map includes: Determining cargo location information of a plurality of cargoes corresponding to the cargo data based on a data matching rule; Determine a corresponding map position of each cargo location information on the ship map; According to the map position, a preliminary distribution two-dimensional model corresponding to the cargo data is generated with the cargo loading area of ​​the ship map as a base map.

4. The method for managing ship cargo data based on two-dimensional model interaction according to claim 3 is characterized in that: The determining, based on the data matching rule, cargo location information of the plurality of cargoes corresponding to the cargo data comprises: For each cargo label data in the cargo data, determining whether there is location data in the cargo label data based on a data matching rule; If the cargo label data contains location data, determining that the location data is cargo location information of the cargo corresponding to the cargo label data; If the cargo label data does not have location data, the cargo label data is input into a trained location prediction model to obtain a predicted location corresponding to the cargo label data; the location prediction model is trained by a training data set including a plurality of training cargo label data and corresponding location annotations; Determine whether the predicted position coincides with the existing cargo position information; if not, determine that the predicted position is the cargo position information of the cargo corresponding to the cargo label data; if so, determine the predicted position result with the second highest prediction probability in the output prediction result of the position prediction model as the cargo position information of the cargo corresponding to the cargo label data.

5. The method for managing ship cargo data based on two-dimensional model interaction according to claim 4 is characterized in that: The step of determining a plurality of corresponding reference distribution two-dimensional models according to the historical loading data of the target vessel and the vessel map comprises: Determining a plurality of historical cargo loading data corresponding to the target vessel from a preset historical database; the historical cargo loading data includes historical cargo label data and a corresponding historical cargo distribution two-dimensional model; For each of the historical cargo loading data, input the historical cargo label data in the historical cargo loading data into the position prediction model to obtain the predicted cargo distribution position corresponding to the historical cargo loading data; Calculating a first similarity between the predicted cargo distribution position and the historical cargo distribution two-dimensional model in the historical cargo loading data to obtain a data priority corresponding to the historical cargo loading data; Filter out the historical cargo loading data whose data priority is greater than a first priority threshold, and obtain a plurality of preferred historical cargo data; According to the matching degree between the ship map and the historical cargo distribution two-dimensional model, a plurality of reference distribution two-dimensional models are determined from the plurality of preferred historical cargo data.

6. The method for managing ship cargo data based on two-dimensional model interaction according to claim 5, characterized in that: The step of determining a plurality of reference distribution two-dimensional models from the plurality of preferred historical cargo data according to the matching degree between the vessel map and the historical cargo distribution two-dimensional model comprises: For each of the two-dimensional historical cargo distribution models in the preferred historical cargo data, calculating a second similarity between the background image of the two-dimensional historical cargo distribution model and the ship map; Calculate the weighted average of the first similarity and the second similarity corresponding to the historical cargo distribution two-dimensional model to obtain the model priority corresponding to the historical cargo distribution two-dimensional model; wherein the weight corresponding to the first similarity is less than the weight corresponding to the second similarity; the weight corresponding to the first similarity is proportional to the data volume of the historical cargo label data; the weight corresponding to the second similarity is proportional to the clarity of the background image; the clarity is obtained by inputting the background image into a clarity evaluation model; The historical cargo distribution two-dimensional models whose corresponding model priorities are greater than a second priority threshold are screened out from the historical cargo distribution two-dimensional models in all the preferred historical cargo data to obtain a plurality of reference distribution two-dimensional models.

7. The method for managing ship cargo data based on two-dimensional model interaction according to claim 1, characterized in that: The preset distribution optimization algorithm is based on which the preliminary distribution two-dimensional model is corrected according to the reference distribution two-dimensional model to obtain a corrected cargo distribution two-dimensional model, including: For each of the reference distribution two-dimensional models, the reference distribution two-dimensional model and the corresponding cargo label data are input into a feature calculation model to obtain cargo distribution feature information corresponding to the reference distribution two-dimensional model; the cargo distribution feature information includes at least one of cargo spacing, a correspondence between cargo type and cargo position, a correspondence between cargo size and cargo position, and a correspondence between cargo size and cargo spacing; Based on the cargo distribution characteristic information, clustering all the reference distribution two-dimensional models to obtain a cluster model set; the cluster model set includes a plurality of reference distribution two-dimensional models whose similarity of the cargo distribution characteristic information is greater than a first similarity threshold; According to the clustering model set, based on a dynamic programming algorithm, the preliminary distribution two-dimensional model is corrected to obtain a corrected cargo distribution two-dimensional model.

8. The method for managing ship cargo data based on two-dimensional model interaction according to claim 7, characterized in that: The step of correcting the preliminary distribution two-dimensional model based on the clustering model set and a dynamic programming algorithm to obtain a corrected cargo distribution two-dimensional model includes: The objective function is set to maximize the similarity between the two-dimensional model calculation result and the preliminary distribution two-dimensional model; Setting restrictions includes: The location distance between the cargo position in the two-dimensional model calculation result and the cargo position of the corresponding cargo in the preliminary distribution two-dimensional model is less than a distance threshold; The similarity between the two-dimensional model calculation result and any of the reference distribution two-dimensional models in the cluster model set is greater than a preset second similarity threshold; The similarity between the cargo distribution characteristic information corresponding to the two-dimensional model calculation result and the cargo distribution characteristic information of any of the reference distribution two-dimensional models in the clustering model set is greater than a preset third similarity threshold; Based on the dynamic programming algorithm, according to the objective function and the constraint conditions, the preliminary distribution two-dimensional model is randomly adjusted and optimized for cargo positions until the best two-dimensional model calculation result is obtained, which is determined as the corrected cargo distribution two-dimensional model.

9. A ship cargo data management system based on two-dimensional model interaction, characterized in that: The system comprises: An acquisition module, used to acquire cargo data uploaded by the operator and a ship map corresponding to the target ship; A first determination module is used to determine a preliminary distribution two-dimensional model corresponding to the cargo data according to a data matching rule and the ship map; A second determination module is used to determine a plurality of corresponding reference distribution two-dimensional models according to the historical loading data of the target vessel and the vessel map; The correction module is used to correct the preliminary distribution two-dimensional model according to the reference distribution two-dimensional model based on a preset distribution optimization algorithm to obtain a corrected cargo distribution two-dimensional model.

10. A ship cargo data management system based on two-dimensional model interaction, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the ship cargo data management method based on two-dimensional model interaction as described in any one of claims 1-8.

Images