Ship trade chain association state data processing method and related device

Abstract

The application provides a ship trade chain association state data processing method and related device. The ship trade chain association state data processing method comprises the following steps: in response to a current ship trade order, acquiring multi-source heterogeneous data corresponding to the current ship trade order through at least one data interface by a processor; based on the multi-source heterogeneous data, constructing an entity relationship graph data structure for representing the current ship trade order in the storage, the entity relationship graph data structure comprising node data for representing each association subject and edge data for representing the association relationship between each association subject; based on the entity relationship graph data structure, performing graph calculation processing on the multi-source heterogeneous data to generate state representation parameters for representing the association state of the ship trade chain; and based on the state representation parameters, generating state identification data corresponding to the current ship trade order. This method can improve the efficiency and accuracy of ship trade chain related data processing.

Description

Technical Field

[0001] This application relates to the field of ship trade technology, and more specifically, to a method and related apparatus for processing ship trade chain-related status data. Background Technology

[0002] With the rapid development of digital management and compliance supervision of the shipping trade chain, actual trade supervision work frequently requires processing shipping trade-related data to assist in compliance verification and risk prevention in the shipping trade sector. Accurate and efficient processing of shipping trade-related data is crucial for ensuring the orderly conduct of such supervision. Currently, the industry mainstream adopts a single data source collection and independent data processing model, that is, collecting and processing scattered shipping trade-related data separately to obtain various information related to shipping trade. However, relying solely on the separate collection and processing of scattered data, due to the large number of stakeholders involved in the shipping trade chain, the large volume of data, and the diverse sources, seriously affects the processing efficiency and accuracy of shipping trade-related data, hindering timely compliance verification and risk prevention supervision of the shipping trade chain. Summary of the Invention

[0003] This application provides a method and related apparatus for processing ship trade chain related status data, aiming to improve the efficiency and accuracy of ship trade chain related data processing.

[0004] In view of this, the first aspect of this application proposes a method for processing ship trade chain-related status data, including:

[0005] The processor performs the following steps:

[0006] In response to the current ship trade order, multi-source heterogeneous data corresponding to the current ship trade order is obtained through at least one data interface. The multi-source heterogeneous data includes at least: background data of each related entity, dynamic trajectory data of the transport vessel, and external constraint reference data.

[0007] Based on multi-source heterogeneous data, an entity relationship graph data structure is constructed in memory to represent the current ship trade order. The entity relationship graph data structure includes: node data to represent each associated entity, and edge data to represent the relationship between each associated entity.

[0008] Based on the entity relationship graph data structure, graph computation processing is performed on multi-source heterogeneous data to generate state representation parameters for characterizing the association status of the ship trade chain.

[0009] Based on the state representation parameters, generate the state identifier data corresponding to the current ship trade order.

[0010] In the above technical solution, the current ship trade order is the business source that triggers the entire data processing flow, clearly defining the processing object and business scenario; the data interface is the communication channel connecting various data sources and the processing system, used to stably acquire multi-source data; multi-source heterogeneous data is the core data foundation supporting the correlation status analysis, referring to a comprehensive data set from different data sources of varying types, including at least background data of each related entity, dynamic trajectory data of transport vessels, and external constraint reference data; related entities are the participating entities in the ship trade chain, including transport vessels, trade participants, and port entities; background data is the basic static information of related entities, including static data reflecting the basic attributes of the entity such as business registration information, qualification and licensing documents, equity structure data, corporate credit rating, trade scope, and partner association information; the dynamic trajectory data of transport vessels is obtained through AIS (Automatic Identification System) and GPS (Global Positioning System). The system collects real-time or historical ship location and navigation-related data from systems such as the Global Positioning System (GPS), including real-time coordinates, course, speed, port berthing status, port call records, route trajectory, AIS signal status, mileage, and time, as well as other dynamic data generated during ship navigation. External constraint reference data consists of reference identifiers used for trade compliance verification, including international sanctions list identifiers, restricted port / sea area identifiers, non-compliant trade entity registration identifiers, customs supervision focus identifiers, and maritime compliance warning identifiers, among other reference identifiers and related attribute data used for trade compliance determination. The entity relationship graph data structure is a structured network representing the current ship trade order association logic, composed of node data representing associated entities and edge data representing interaction relationships. Graph computation processing is a specialized calculation method based on the entity relationship graph to mine deep data associations. State representation parameters are core indicators for quantifying the association status of the ship trade chain, calculated by fusing multi-dimensional features. State identifier data is the result data that intuitively presents the association status level, providing direct reference for regulatory decisions.

[0011] In the above technical solution, the processor responds to ship trade orders to trigger the acquisition of multi-source heterogeneous data, ensuring that the data collection is accurately matched with the actual business scenario and guaranteeing the timeliness and relevance of the data. Based on the multi-source heterogeneous data, an entity relationship graph data structure is constructed in the memory, which integrates the originally isolated and scattered data into a semantically related network, solving the problem of data lacking effective association. The processor performs graph computation processing based on the entity relationship graph data structure, integrating multi-dimensional features such as static reference, dynamic behavior, and association strength to generate state representation parameters. Compared with single data processing, this can better guarantee the accuracy of the results, avoiding the limitations of single data processing and improving the accuracy of association state determination. Finally, state identification data is generated based on the state representation parameters, realizing an intuitive presentation of the ship trade chain association state. The entire process does not require manual intervention, greatly improving data processing efficiency and ensuring timely, comprehensive, and accurate acquisition of key information on the ship trade chain association state, providing efficient and reliable technical support for trade compliance supervision.

[0012] Optionally, in response to a current ship trade order, multi-source heterogeneous data corresponding to the current ship trade order is obtained through at least one data interface, including:

[0013] Based on current ship trade orders, identify multiple related entities in the ship trade chain, including transport vessels, trade participants, and port entities.

[0014] Based on the vessel identification of the transport vessel, dynamic trajectory data of the transport vessel is obtained from the vessel dynamic data source;

[0015] Obtain background data corresponding to multiple related entities from the background data source;

[0016] Obtain reference identifier data corresponding to multiple associated entities from external constraint reference data sources;

[0017] The acquired data is preprocessed to generate multi-source heterogeneous data.

[0018] In the above technical solution, vessel identification is the core identification basis for accurately associating dynamic trajectory data of transport vessels. Vessel identification includes standardized and unique identifiers such as IMO (International Maritime Organization Number) and MMSI (Maritime Mobile Service Identity) to ensure that data is not confused or mismatched with the target vessel. Vessel dynamic data source, background data source, and external constraint reference data source are the specific source carriers of multi-source heterogeneous data, respectively providing vessel navigation status data, basic information of associated entities, and compliance verification reference data. Each data source is configured with a dedicated interface to ensure the stability of data acquisition. Reference identification data is the core information in the external constraint reference data source corresponding to the associated entities, providing a direct basis for subsequent compliance dimension analysis. Data preprocessing is a key step in improving data quality, specifically including data cleaning, standardization, and association alignment operations, used to remove redundant and abnormal data, unify data formats, and achieve accurate binding of data with associated entities.

[0019] In the above technical solution, the relevant entities are first identified based on ship trade orders to accurately pinpoint the data collection scope and avoid invalid data collection. Then, corresponding data is obtained from different data sources according to data type to ensure the relevance and completeness of various types of data. Finally, data quality is optimized through data preprocessing to solve the problems of inconsistent formats and varying quality of multi-source data. Compared with the general method of data collection, this approach can better guarantee the accuracy and consistency of data. It not only provides a high-quality data foundation for subsequent entity relationship diagram construction and graph computation processing, but also further refines the acquisition logic of multi-source heterogeneous data, improves the reliability and efficiency of data collection, and provides strong support for the smooth operation of the entire ship trade chain related status processing process.

[0020] Optionally, in some technical solutions of this application, an entity relationship graph data structure for representing the current ship trade order is constructed in memory, including:

[0021] Generate node data for each associated entity;

[0022] Based on dynamic trajectory data, background data, and the interaction behavior between various related entities, edge data between nodes is generated.

[0023] Integrate node data and edge data into a graph data structure to form an entity relationship graph data structure.

[0024] In the above technical solution, interactive behavior refers to the specific business transactions between related entities in the trade process, including actual business actions such as transportation, delivery, receipt, and affiliation, which is the core basis for generating edge data; node data is the unique structured identification information assigned to each related entity, ensuring that each related entity can be accurately distinguished in the entity relationship graph; edge data is the core carrier connecting each node, generated based on specific business scenarios, and used to concretely present the interactive relationships between related entities; the graph data structure is a standardized form that integrates node data and edge data, through which the structured integration of scattered data is realized to form a network with semantic association.

[0025] In the above technical solution, a basic framework for the entity relationship graph is established by generating unique node data for each related entity; edge data is generated based on dynamic trajectory data, background data, and actual interaction behavior, so that the relationship has clear business support rather than abstract association; the node and edge data are integrated into a graph data structure, realizing the association and integration of originally isolated and scattered data, solving the problem of data lacking effective association. Compared with the unstructured integration method, it can more clearly present the business flow logic of each entity in the trade chain, providing clear structural support for subsequent graph traversal calculation and association strength analysis, and improving the accuracy and efficiency of association status analysis.

[0026] Optionally, in some technical solutions of this application, the edge data includes at least one attribute data, which includes:

[0027] Behavioral attribute data is used to characterize the types of interactions between related entities;

[0028] Time attribute data is used to characterize the time information corresponding to the interactive behavior;

[0029] Location attribute data is used to represent the spatial location information corresponding to interactive behaviors.

[0030] In the above technical solution, behavioral attribute data is the core information that characterizes the interaction type of the associated subjects, clearly recording the specific type of interaction action, which is the key to distinguishing the nature of different association relationships; time attribute data is information that records the specific time when the interaction occurs, including actual sailing time, cargo loading and unloading time, port berthing time, etc., used to reconstruct the time node of the interaction; location attribute data is information that records the spatial location where the interaction occurs, including port name, latitude and longitude coordinates, route segment identification, etc., used to locate the specific scenario of the interaction.

[0031] In the above technical solution, behavioral attribute data clarifies the association type, time attribute data locks the interaction node, and location attribute data locates the spatial scene. The three types of attribute data complement and corroborate each other, transforming the interaction relationship between the associated entities from an abstract association into a concrete association with specific business scenarios, time nodes, and spatial locations. Compared with the method of only recording a single association relationship, it can more comprehensively restore the business flow logic in the trade chain, providing detailed semantic support for accurate feature extraction and association strength analysis in the subsequent graph calculation process, and further improving the comprehensiveness and accuracy of association status determination.

[0032] Optionally, in some technical solutions of this application, based on an entity relationship graph data structure, graph computation processing is performed on multi-source heterogeneous data to generate state representation parameters for characterizing the association state of the ship trade chain, including:

[0033] Based on background data and external constraint reference data, static reference feature parameters are generated.

[0034] Based on dynamic trajectory data, dynamic behavioral feature parameters are generated.

[0035] Based on the entity relationship graph data structure, association strength feature parameters are generated by graph traversal calculation.

[0036] Static reference feature parameters, dynamic behavior feature parameters, and correlation strength feature parameters are fused and calculated to generate state characterization parameters.

[0037] In the above technical solution, static reference feature parameters are quantitative indicators generated based on the background data of the associated entities and external constraint reference data, reflecting the inherent compliance attributes and basic status of the associated entities, and possessing stability; dynamic behavior feature parameters are quantitative indicators generated based on the dynamic trajectory data of transport vessels, including quantitative indicators reflecting the real-time compliance status of vessel navigation behavior such as vessel navigation area compliance parameters, AIS signal transmission continuity parameters, vessel navigation speed / heading anomaly parameters, and port berthing compliance parameters, reflecting the real-time navigation status and behavioral trends of vessels, and possessing timeliness; association strength feature parameters are quantitative indicators generated based on entity relationship graphs through graph traversal calculations, reflecting the degree of association between associated entities; fusion calculation is the process of comprehensively calculating the three types of feature parameters according to preset logic, used to integrate multi-dimensional information to generate unified state representation parameters.

[0038] In the above technical solution, feature parameters are extracted from three dimensions: static inherent attributes, dynamic real-time behavior, and subject association strength. This comprehensively covers the core influencing factors of trade chain association status and avoids the limitations of single-dimensional analysis. By integrating multi-dimensional features into unified status representation parameters through fusion calculation, a comprehensive quantification of association status is achieved. Compared with single feature analysis, this ensures more comprehensiveness and accuracy of the results. The judgment results reflect the stability of inherent attributes, the dynamism of real-time behavior, and the tightness of association relationships, significantly improving the accuracy of association status judgment and providing a reliable quantitative basis for the subsequent generation of status identification data.

[0039] Optionally, in some technical solutions of this application, association strength feature parameters are generated by graph traversal based on the entity relationship graph data structure, including:

[0040] In the entity relationship graph data structure, locate the nodes corresponding to each associated entity and the reference nodes identified in the external constraint reference data;

[0041] Based on the graph traversal algorithm, obtain the associated paths and path lengths between nodes;

[0042] The association strength parameter is generated based on the path length, where the smaller the path length, the larger the corresponding association strength parameter.

[0043] Based on the correlation strength parameter, correlation strength feature parameters are generated.

[0044] In the above technical solution, the reference node is a specific node in the entity relationship graph that corresponds to the external constraint reference data, i.e., the structured identifier corresponding to the associated subject pointed to by the external constraint reference data; the graph traversal algorithm is a calculation method used to traverse the nodes and edges in the entity relationship graph, including depth-first search, breadth-first search, etc., to obtain the association path between nodes; the association path is the link formed by the edge data connection between the associated subject node and the reference node, reflecting the association level between the two; the path length is the number of edge data contained in the association path, which is the core indicator for measuring the association level; the association strength parameter is a quantitative value generated based on the path length, used to visualize the degree of association between the associated subject and the reference node.

[0045] In the above technical solution, the graph traversal algorithm is used to accurately locate the association paths between each associated subject node and the reference node, clearly presenting the association hierarchy between them. The association strength parameter is generated based on the path length as the core basis, establishing a quantitative relationship between the association hierarchy and the degree of closeness, making the originally abstract association relationship quantifiable and comparable. Compared with association analysis without clear quantitative standards, it can more accurately represent the degree of closeness between the associated subject and the compliant reference node, providing key association dimension support for the fusion calculation of state representation parameters, and improving the pertinence and accuracy of association state determination.

[0046] Optionally, in some technical solutions of this application, the status identification data is generated by comparing the status characterization parameters with a preset threshold range, and the status identification data is used to characterize the associated status level of the current ship trade order.

[0047] In the above technical solution, the preset threshold range is a numerical range set in advance according to regulatory requirements and business scenarios, used to divide different association status levels, and has flexible configuration; the association status level is a classification identifier determined based on the matching result of the status representation parameter and the preset threshold range, including low level, medium level, high level, etc., used to intuitively present the association status; the status identifier data is the result data that carries the association status level and is the final presentation form of the association status.

[0048] In the above technical solution, the quantified state representation parameters are transformed into intuitive associated state levels by preset threshold ranges. This allows for the rapid understanding of the associated state of ship trade orders without the need for complex data analysis by professionals. Compared to directly outputting quantified parameters, this method improves the readability and practicality of the results. The threshold ranges can be flexibly adjusted according to actual regulatory needs to adapt to different judgment standards in different scenarios. This ensures that the output results are both standardized and flexible, providing a concise and clear reference for regulatory decisions and improving the efficiency and convenience of regulatory work.

[0049] The second aspect of this application provides a data processing apparatus for ship trade chain association status, comprising: an acquisition module, configured to acquire multi-source heterogeneous data corresponding to the current ship trade order through at least one data interface in response to the current ship trade order, wherein the multi-source heterogeneous data includes at least background data of each associated entity, dynamic trajectory data of the transport vessel, and external constraint reference data; a construction module, configured to construct an entity relationship graph data structure representing the current ship trade order in a memory based on the multi-source heterogeneous data, wherein the entity relationship graph data structure includes node data representing each associated entity and edge data representing the relationship between the associated entities; a calculation module, configured to perform graph calculation processing on the multi-source heterogeneous data based on the entity relationship graph data structure to generate state representation parameters representing the ship trade chain association status; and a generation module, configured to generate state identifier data corresponding to the current ship trade order based on the state representation parameters.

[0050] In the above technical solution, the processor responds to ship trade orders to trigger the acquisition of multi-source heterogeneous data, ensuring that the data collection is accurately matched with the actual business scenario and guaranteeing the timeliness and relevance of the data. Based on the multi-source heterogeneous data, an entity relationship graph data structure is constructed in the memory, which integrates the originally isolated and scattered data into a semantically related network, solving the problem of data lacking effective association. The processor performs graph computation processing based on the entity relationship graph data structure, integrating multi-dimensional features such as static reference, dynamic behavior, and association strength to generate state representation parameters. Compared with single data processing, this can better guarantee the accuracy of the results, avoiding the limitations of single data processing and improving the accuracy of association state determination. Finally, state identification data is generated based on the state representation parameters, realizing an intuitive presentation of the ship trade chain association state. The entire process does not require manual intervention, greatly improving data processing efficiency and ensuring timely, comprehensive, and accurate acquisition of key information on the ship trade chain association state, providing efficient and reliable technical support for trade compliance supervision.

[0051] The third aspect of this application provides a ship trade chain-related status data processing device, comprising: a memory for storing programs or instructions; and a processor for executing programs or instructions to implement the steps of the ship trade chain-related status data processing method provided in any of the above technical solutions, thus achieving all the same technical effects. To avoid repetition, further details are omitted here.

[0052] The fourth aspect of this application provides a computer-readable storage medium having a program or instructions stored thereon. When the program or instructions are executed by a processor, they implement the steps of the ship trade chain-related status data processing method provided in any of the above technical solutions. Therefore, all the same technical effects can be achieved. To avoid repetition, further details are omitted here.

[0053] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0054] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0055] Figure 1 A flowchart illustrating the method for processing ship trade chain-related status data provided in this application embodiment;

[0056] Figure 2 A schematic diagram of the data processing flow for ship trade chain association status provided in the embodiments of this application;

[0057] Figure 3 A structural block diagram of a ship trade chain-related status data processing device provided in this application embodiment;

[0058] Figure 4 This is a structural block diagram of a ship trade chain-related status data processing device provided in an embodiment of this application. Detailed Implementation

[0059] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0060] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Therefore, the scope of protection of this application is not limited to the specific embodiments disclosed below.

[0061] The following reference Figures 1 to 4 This application describes a method and related apparatus for processing ship trade chain associated status data according to some embodiments.

[0062] like Figure 1 As shown, the first aspect of this application proposes a method for processing ship trade chain-related status data, including:

[0063] The processor performs the following steps:

[0064] S100: In response to the current ship trade order, obtain multi-source heterogeneous data corresponding to the current ship trade order through at least one data interface. The multi-source heterogeneous data includes at least: background data of each associated entity, dynamic trajectory data of the transport vessel, and external constraint reference data.

[0065] S120: Based on multi-source heterogeneous data, construct an entity relationship graph data structure in memory to represent the current ship trade order. The entity relationship graph data structure includes: node data to represent each associated entity, and edge data to represent the relationship between each associated entity.

[0066] S140: Based on the entity relationship graph data structure, graph computation processing is performed on multi-source heterogeneous data to generate state representation parameters for characterizing the association status of the ship trade chain.

[0067] S160: Generate status identifier data corresponding to the current ship trade order based on status representation parameters.

[0068] In the above embodiments, the current ship trade order is the business source that triggers the entire data processing flow, clearly defining the processing object and business scenario; the data interface is the communication channel connecting various data sources and the processing system, used to stably acquire multi-source data; multi-source heterogeneous data is the core data foundation supporting the correlation status analysis, referring to a comprehensive data set from different data sources of varying types, including at least background data of each related entity, dynamic trajectory data of transport vessels, and external constraint reference data; related entities are the participating entities in the ship trade chain, including transport vessels, trade participants, and port entities; background data is the basic static information of related entities, including static data reflecting the basic attributes of the entity such as business registration information, qualification and licensing documents, equity structure data, corporate credit rating, trade scope, and partner association information; the dynamic trajectory data of transport vessels is obtained through AIS (Automatic Identification System) and GPS (Global Positioning System). The data collected by systems such as the Global Positioning System (GPS) includes real-time or historical ship location and navigation-related data, such as real-time coordinates, course, speed, port berthing status, port call records, route trajectory, AIS signal status, mileage, and time. External constraint reference data is used for trade compliance verification, including various reference markers and associated attribute data for trade compliance determination, such as international sanctions list markers, restricted port / sea area markers, non-compliant trade entity registration markers, customs supervision key markers, and maritime compliance warning markers. The entity relationship graph data structure is a structured network representing the current ship trade order association logic, composed of node data representing associated entities and edge data representing interaction relationships. Graph computation processing is a specialized calculation method based on the entity relationship graph to mine deep data associations. State representation parameters are core indicators for quantifying the ship trade chain association status, calculated by fusing multi-dimensional features. State identifier data is the result data that intuitively presents the association status level, providing direct reference for regulatory decisions.

[0069] In the above embodiments, the processor responds to ship trade orders to trigger the acquisition of multi-source heterogeneous data, ensuring that the data collection is accurately matched with the actual business scenario and guaranteeing the timeliness and relevance of the data. Based on the multi-source heterogeneous data, an entity relationship graph data structure is constructed in the memory, which integrates the originally isolated and scattered data into a semantically related network, solving the problem of data lacking effective association. The processor performs graph computation processing based on the entity relationship graph data structure, integrating multi-dimensional features such as static reference, dynamic behavior, and association strength to generate state representation parameters. Compared with single data processing, this can better guarantee the accuracy of the results, avoiding the limitations of single data processing and improving the accuracy of association state determination. Finally, state identification data is generated based on the state representation parameters, realizing an intuitive presentation of the ship trade chain association state. The entire process does not require manual intervention, greatly improving data processing efficiency and ensuring timely, comprehensive, and accurate acquisition of key information on the ship trade chain association state, providing efficient and reliable technical support for trade compliance supervision.

[0070] For example, such as Figure 2 The process for processing ship trade chain association status data is as follows: S1: Trade order / bill of lading trigger; The data processing flow for ship trade chain association status is initiated by using a trade order or bill of lading as a trigger condition. S2: Real-time acquisition of multi-source data; Acquiring multi-source heterogeneous data corresponding to the current trade order / bill of lading, including background data of associated entities, dynamic trajectory data of transport vessels, and external constraint reference data. S3: Construction of entity relationship graph data structure; Based on the collected multi-source data, generating node data representing each associated entity and edge data representing the relationship between associated entities, and integrating the node data and edge data into an entity relationship graph data structure. S4: Multi-dimensional feature fusion calculation; Based on the entity relationship graph data structure, processing the multi-source data to generate static reference feature parameters, dynamic behavior feature parameters, and association strength feature parameters, and obtaining status representation parameters through fusion calculation. S5: Association status level determination; Comparing the status representation parameters with a preset threshold range to determine the corresponding association status level. S6: Generation of status identifier data; Outputting status identifier data containing the association status level, completing the data processing for ship trade chain association status.

[0071] In some embodiments of this application, optionally, in response to a current ship trade order, multi-source heterogeneous data corresponding to the current ship trade order is obtained through at least one data interface, including:

[0072] Based on current ship trade orders, identify multiple related entities in the ship trade chain, including transport vessels, trade participants, and port entities.

[0073] Based on the vessel identification of the transport vessel, the dynamic trajectory data of the transport vessel is obtained from the vessel dynamic data source;

[0074] Obtain background data corresponding to multiple related entities from the background data source;

[0075] Obtain reference identifier data corresponding to multiple associated entities from external constraint reference data sources;

[0076] The acquired data is preprocessed to generate multi-source heterogeneous data.

[0077] In the above embodiments, vessel identification is the core identification basis for accurately associating dynamic trajectory data of transport vessels. Vessel identification includes standardized and unique identifiers such as IMO number (International Maritime Organization Number) and MMSI number (Maritime Mobile Service Identity), as well as vessel-specific standardized identifiers such as vessel call sign, vessel registration number, and vessel name, ensuring accurate matching of the target vessel's dynamic trajectory data from multiple dimensions. Vessel dynamic data source, background data source, and external constraint reference data source are the specific source carriers of multi-source heterogeneous data, respectively providing vessel navigation status data, basic information of associated entities, and compliance verification reference data. Each data source is configured with a dedicated interface to ensure the stability of data acquisition. Reference identifier data is the core information in the external constraint reference data source corresponding to the associated entities, providing direct basis for subsequent compliance dimension analysis. Data preprocessing is a key step in improving data quality, specifically including data cleaning, standardization, and association alignment operations, used to remove redundant and abnormal data, unify data formats, and achieve accurate binding of data with associated entities.

[0078] In the above embodiments, by first identifying the related entities based on ship trade orders, the scope of data collection is accurately locked, avoiding invalid data collection; then, corresponding data is obtained from different data sources according to data type, ensuring the relevance and completeness of various types of data; finally, data quality is optimized through data preprocessing, solving the problems of inconsistent formats and varying quality of multi-source data. Compared with the general method of data collection, this approach better ensures the accuracy and consistency of data, providing a high-quality data foundation for subsequent entity relationship graph construction and graph computation processing, and further refining the acquisition logic of multi-source heterogeneous data, improving the reliability and efficiency of data collection, and providing strong support for the smooth operation of the entire ship trade chain related status processing process.

[0079] Optionally, in some embodiments of this application, an entity relationship graph data structure for representing the current ship trade order is constructed in memory, including:

[0080] Generate node data for each associated entity;

[0081] Based on dynamic trajectory data, background data, and the interaction behavior between various related entities, edge data between nodes is generated.

[0082] Integrate node data and edge data into a graph data structure to form an entity relationship graph data structure.

[0083] In the above embodiments, interactive behavior refers to the specific business transactions between related entities in the trade process, including actual business actions such as transportation, delivery, receipt, and affiliation, which is the core basis for generating edge data; node data is the unique structured identification information assigned to each related entity, ensuring that each related entity can be accurately distinguished in the entity relationship graph; edge data is the core carrier connecting each node, generated based on specific business scenarios, and used to concretely present the interactive relationships between related entities; the graph data structure is a standardized form that integrates node data and edge data, through which the structured integration of scattered data is realized to form a network with semantic association.

[0084] In the above embodiments, by generating unique node data for each associated entity, the basic framework of the entity relationship graph is established; edge data is generated based on dynamic trajectory data, background data, and actual interaction behavior, so that the relationship has clear business support rather than abstract association; the node and edge data are integrated into a graph data structure, realizing the association integration of originally isolated and scattered data, solving the problem of data lacking effective association. Compared with the unstructured integration method, it can more clearly present the business flow logic of each entity in the trade chain, providing clear structural support for subsequent graph traversal calculation and association strength analysis, and improving the accuracy and efficiency of association state analysis.

[0085] In some embodiments of this application, optionally, the edge data includes at least one attribute data, the attribute data including:

[0086] Behavioral attribute data is used to characterize the types of interactions between related entities;

[0087] Time attribute data is used to characterize the time information corresponding to the interactive behavior;

[0088] Location attribute data is used to represent the spatial location information corresponding to interactive behaviors.

[0089] In the above embodiments, behavioral attribute data is the core information that characterizes the interaction type of the associated subjects, clearly recording the specific type of interaction action, which is the key to distinguishing the nature of different association relationships; time attribute data is information that records the specific time when the interaction occurs, including actual sailing time, cargo loading and unloading time, port berthing time, etc., used to reconstruct the time node of the interaction; location attribute data is information that records the spatial location where the interaction occurs, including port name, latitude and longitude coordinates, route segment identification, etc., used to locate the specific scenario of the interaction.

[0090] In the above embodiments, behavioral attribute data clarifies the association type, time attribute data locks the interaction node, and location attribute data locates the spatial scene. The three types of attribute data complement and corroborate each other, transforming the interaction relationship between the associated entities from an abstract association into a concrete association with specific business scenarios, time nodes, and spatial locations. Compared with the method of recording only a single association relationship, it can more comprehensively restore the business flow logic in the trade chain, providing detailed semantic support for accurate feature extraction and association strength analysis in the subsequent graph calculation process, and further improving the comprehensiveness and accuracy of association status determination.

[0091] Optionally, in some embodiments of this application, graph computation processing is performed on multi-source heterogeneous data based on an entity relationship graph data structure to generate state representation parameters for characterizing the association state of the ship trade chain, including:

[0092] Based on background data and external constraint reference data, static reference feature parameters are generated.

[0093] Based on dynamic trajectory data, dynamic behavioral feature parameters are generated.

[0094] Based on the entity relationship graph data structure, association strength feature parameters are generated by graph traversal calculation.

[0095] Static reference feature parameters, dynamic behavior feature parameters, and correlation strength feature parameters are fused and calculated to generate state characterization parameters.

[0096] In the above embodiments, static reference feature parameters are quantitative indicators generated based on the background data of the associated entities and external constraint reference data, reflecting the inherent compliance attributes and basic status of the associated entities and possessing stability; dynamic behavior feature parameters are quantitative indicators generated based on the dynamic trajectory data of transport vessels, including quantitative indicators reflecting the real-time compliance status of vessel navigation behavior such as vessel navigation area compliance parameters, AIS signal transmission continuity parameters, vessel navigation speed / heading anomaly parameters, and port berthing compliance parameters, reflecting the real-time navigation status and behavioral trends of vessels and possessing timeliness; association strength feature parameters are quantitative indicators generated based on the entity relationship graph through graph traversal calculation, reflecting the degree of association between associated entities; fusion calculation is the process of comprehensively calculating the three types of feature parameters according to preset logic, used to integrate multi-dimensional information to generate unified state representation parameters.

[0097] In the above embodiments, feature parameters are extracted from three dimensions: static inherent attributes, dynamic real-time behavior, and subject association strength. This comprehensively covers the core influencing factors of trade chain association status, avoiding the limitations of single-dimensional analysis. By integrating multi-dimensional features into unified status representation parameters through fusion calculation, a comprehensive quantification of association status is achieved. Compared with single feature analysis, this ensures more comprehensiveness and accuracy of the results. The judgment results reflect both the stability of inherent attributes and the dynamism of real-time behavior, while also taking into account the tightness of the association relationship. This significantly improves the accuracy of association status judgment and provides a reliable quantitative basis for the subsequent generation of status identification data.

[0098] For example, the three types of feature parameters can be fused and calculated through specific factor quantification and weight configuration. For instance: the static reference feature parameter is whether the entity matches the reference identifier in the external constraint reference data, and the corresponding reference identifier's level (e.g., core reference identifier = 1.0, ordinary reference identifier = 0.6); the dynamic behavior feature parameter is determined based on real-time data such as AIS (e.g., entering a preset sensitive area = 0.7, turning off AIS signal within a sensitive area = 0.8); the association strength feature parameter is calculated using the entity relationship graph data structure. The calculation of the state representation parameters is shown in the following formula:

[0099] F = a × R1 + b × R2 + c × R3; (Formula 1)

[0100] Where F represents the state representation parameter, R1 represents the static reference feature parameter, R2 represents the dynamic behavior feature parameter, R3 represents the association strength feature parameter, a is the first weight corresponding to the static reference feature parameter, b is the second weight corresponding to the dynamic behavior feature parameter, and c is the third weight corresponding to the association strength feature parameter. Subsequently, the association state level (e.g., high, medium, and low association state levels) can be divided according to the magnitude of the state representation parameter, and corresponding state identification data can be formed.

[0101] In some embodiments of this application, optionally, association strength feature parameters are generated by graph traversal based on the entity relationship graph data structure, including:

[0102] In the entity relationship graph data structure, locate the nodes corresponding to each associated entity and the reference nodes identified in the external constraint reference data;

[0103] Based on the graph traversal algorithm, obtain the associated paths and path lengths between nodes;

[0104] The association strength parameter is generated based on the path length, where the smaller the path length, the larger the corresponding association strength parameter.

[0105] Based on the correlation strength parameter, correlation strength feature parameters are generated.

[0106] In the above embodiments, a reference node is a specific node in the entity relationship graph that corresponds to the external constraint reference data, i.e., a structured identifier corresponding to the associated entity pointed to by the external constraint reference data; a graph traversal algorithm is a calculation method used to traverse nodes and edges in the entity relationship graph, including depth-first search, breadth-first search, etc., to obtain the association path between nodes; an association path is a link formed by edge data connecting the associated entity node and the reference node, reflecting the association level between the two; path length is the number of edge data contained in the association path, which is the core indicator for measuring the association level; the association strength parameter is a quantitative value generated based on the path length, used to visualize the degree of association between the associated entity and the reference node.

[0107] In the above embodiments, the graph traversal algorithm is used to accurately locate the association paths between each associated subject node and the reference node, clearly presenting the association hierarchy between them. The association strength parameter is generated based on the path length as the core basis, establishing a quantitative relationship between the association hierarchy and the degree of closeness, making the originally abstract association relationship quantifiable and comparable. Compared with association analysis without clear quantitative standards, it can more accurately characterize the degree of closeness between the associated subject and the compliant reference node, providing key association dimension support for the fusion calculation of state characterization parameters, and improving the pertinence and accuracy of association state determination.

[0108] For example, the formula for calculating the correlation strength characteristic parameter is as follows:

[0109] ; (Formula 2)

[0110] Where R3 represents the association strength feature parameter, max represents the maximum value, and L represents the path length.

[0111] In some embodiments of this application, optionally, the status identification data is generated by comparing the status characterization parameters with a preset threshold range, and the status identification data is used to characterize the associated status level of the current ship trade order.

[0112] In the above embodiments, the preset threshold range is a numerical range set in advance according to regulatory requirements and business scenarios, used to divide different association status levels, and has flexible configuration; the association status level is a classification identifier determined based on the matching result of the status representation parameter and the preset threshold range, including low level, medium level, high level, etc., used to intuitively present the association status; the status identifier data is the result data that carries the association status level and is the final presentation form of the association status.

[0113] In the above embodiments, the quantified state representation parameters are transformed into intuitive associated state levels by preset threshold ranges. This allows for the rapid understanding of the associated state of ship trade orders without the need for complex data analysis by professionals. Compared to directly outputting quantified parameters, this method improves the readability and practicality of the results. The threshold range can be flexibly adjusted according to actual regulatory needs to adapt to different judgment standards in different scenarios. This ensures that the output results are both standardized and flexible, providing a concise and clear reference for regulatory decisions and improving the efficiency and convenience of regulatory work.

[0114] In some embodiments of this application, optionally, association strength feature parameters are generated by graph traversal based on the entity relationship graph data structure, including:

[0115] In the entity relationship graph data structure, locate the nodes corresponding to each associated entity and the reference nodes identified in the external constraint reference data;

[0116] Based on the graph traversal algorithm, obtain the associated paths and path lengths between nodes;

[0117] The credibility of each associated path is quantitatively scored, and the credibility score is positively correlated with the attribute completeness of the edge data in the associated path;

[0118] The association strength parameter is generated based on the path length and the corresponding credibility score.

[0119] Based on the correlation strength parameter, correlation strength feature parameters are generated.

[0120] In the above embodiments, the path credibility score is a quantitative value (ranging from 0.1 to 1.0) generated based on the attribute completeness (whether it contains complete behavioral, time, and location information) of the edge data in the associated path. The more complete the attributes, the higher the score, which is used to characterize the effectiveness of the associated path. The weighted association strength parameter is a quantitative value of association strength calculated by combining the path length and the credibility score. Specifically, it is implemented by multiplying the inverse of the square of the path length by the path credibility score, which reflects both the closeness of the association between the associated subject and the reference node and the authenticity of the associated path. The meanings of the other terms (reference node, graph traversal algorithm, associated path, path length, association strength parameter) are consistent with those in the aforementioned embodiments.

[0121] In the above embodiments, by adding a credibility quantification score to the associated paths and adopting the calculation logic of "multiplying the reciprocal of the path length squared by the path credibility score", the technical limitation of "only focusing on path length and ignoring path validity" in the existing graph traversal calculation is overcome. This can effectively filter out low-quality associated paths with missing attributes (such as invalid relationships without clear time information) and avoid misjudgment of association strength due to invalid paths. At the same time, by strengthening the quantitative difference of the closeness by using the reciprocal of the path length squared, the calculation of the association strength feature parameter not only reflects the closeness of the association, but also fits the real association logic of the business scenario, further improving the calculation accuracy of the state representation parameter and providing more reliable core data support for the determination of association state level.

[0122] like Figure 3 As shown, the second aspect of this application provides a ship trade chain associated state data processing device 300, comprising: an acquisition module 302, configured to acquire multi-source heterogeneous data corresponding to the current ship trade order through at least one data interface in response to the current ship trade order, wherein the multi-source heterogeneous data includes at least background data of each associated entity, dynamic trajectory data of the transport vessel, and external constraint reference data; a construction module 304, configured to construct an entity relationship graph data structure representing the current ship trade order in a memory based on the multi-source heterogeneous data, wherein the entity relationship graph data structure includes node data representing each associated entity and edge data representing the relationship between each associated entity; a calculation module 306, configured to perform graph calculation processing on the multi-source heterogeneous data based on the entity relationship graph data structure to generate state representation parameters representing the associated state of the ship trade chain; and a generation module 308, configured to generate state identifier data corresponding to the current ship trade order based on the state representation parameters.

[0123] In the above embodiments, the processor responds to ship trade orders to trigger the acquisition of multi-source heterogeneous data, ensuring that the data collection is accurately matched with the actual business scenario and guaranteeing the timeliness and relevance of the data. Based on the multi-source heterogeneous data, an entity relationship graph data structure is constructed in the memory, which integrates the originally isolated and scattered data into a semantically related network, solving the problem of data lacking effective association. The processor performs graph computation processing based on the entity relationship graph data structure, integrating multi-dimensional features such as static reference, dynamic behavior, and association strength to generate state representation parameters. Compared with single data processing, this can better guarantee the accuracy of the results, avoiding the limitations of single data processing and improving the accuracy of association state determination. Finally, state identification data is generated based on the state representation parameters, realizing an intuitive presentation of the ship trade chain association state. The entire process does not require manual intervention, greatly improving data processing efficiency and ensuring timely, comprehensive, and accurate acquisition of key information on the ship trade chain association state, providing efficient and reliable technical support for trade compliance supervision.

[0124] like Figure 4 As shown, the third aspect of this application provides a ship trade chain-related status data processing device 400, including: a memory 402 for storing programs or instructions; and a processor 404 for executing programs or instructions to implement the steps of the ship trade chain-related status data processing method provided in any of the above embodiments, thus achieving all the same technical effects. To avoid repetition, it will not be described again here.

[0125] The fourth aspect of this application provides a computer-readable storage medium having a program or instructions stored thereon. When the program or instructions are executed by a processor, they implement the steps of the ship trade chain associated status data processing method provided in any of the above embodiments, thus achieving all the same technical effects. To avoid repetition, further details are omitted here.

[0126] The methods can be implemented in various ways depending on specific features and / or example applications. For example, these methods can be implemented through a combination of hardware, firmware, and / or software. For instance, in a hardware implementation, the processor can be implemented in 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, electronic devices, other device units for performing the functions described above, and / or combinations thereof.

[0127] A computer-readable storage medium can be a tangible device that holds and stores instructions for use by an instruction execution device. A computer-readable storage medium can be an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing, but is not limited thereto. A non-exhaustive list of more specific examples of computer-readable storage media includes: portable computer floppy disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, static random-access memory (SRAM), portable optical disc read-only memory (CD-ROM), digital video disc (DVD), memory cards, floppy disks, encoding mechanical devices (e.g., punched cards or grooves with raised structures for recording instructions), and any suitable combination of the foregoing. The computer-readable storage medium used herein should not be construed as the transmission signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media, or electrical signals transmitted through wires.

[0128] In the claims, description, and accompanying drawings of this application, the term "plural" refers to two or more objects. Unless otherwise explicitly defined, the terms "upper," "lower," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used solely for the convenience of describing this application and simplifying the descriptive process, and are not intended to indicate or imply that the device or element referred to must have the described specific orientation, or be constructed and operated in a specific orientation. Therefore, these descriptions should not be construed as limitations on this application. The terms "connection," "installation," "fixing," etc., should be interpreted broadly. For example, "connection" can be a fixed connection between multiple objects, a detachable connection between multiple objects, or an integral connection; it can be a direct connection between multiple objects or an indirect connection between multiple objects through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in this application can be understood based on the specific circumstances described above.

[0129] In the claims, description, and accompanying drawings of this application, the terms "one embodiment," "some embodiments," "specific embodiment," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of this application. In the claims, description, and accompanying drawings of this application, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0130] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for processing ship trade chain-related status data, characterized in that, include: The processor performs the following steps: In response to a current ship trade order, multi-source heterogeneous data corresponding to the current ship trade order is obtained through at least one data interface. The multi-source heterogeneous data includes at least: background data of each associated entity, dynamic trajectory data of the transport vessel, and external constraint reference data. Based on the multi-source heterogeneous data, an entity relationship graph data structure for representing the current ship trade order is constructed in the memory. The entity relationship graph data structure includes: node data for representing each associated entity, and edge data for representing the relationship between each associated entity. Based on the entity relationship graph data structure, graph computation processing is performed on the multi-source heterogeneous data to generate state characterization parameters for characterizing the association state of the ship trade chain. Based on the state characterization parameters, the state identifier data corresponding to the current ship trade order is generated.

2. The method for processing ship trade chain related status data according to claim 1, characterized in that, The step of responding to a current ship trade order by acquiring multi-source heterogeneous data corresponding to the current ship trade order through at least one data interface includes: Based on the current ship trade orders, identify multiple related entities in the ship trade chain, including transport vessels, trade participants, and port entities; Based on the vessel's identification, the dynamic trajectory data of the vessel is obtained from the vessel dynamic data source. Obtain background data corresponding to multiple associated entities from the background data source; Obtain reference identifier data corresponding to the multiple associated entities from the external constraint reference data source; The acquired data is preprocessed to generate the multi-source heterogeneous data.

3. The method for processing ship trade chain-related status data according to claim 1, characterized in that, The step of constructing an entity relationship graph data structure in memory to represent the current ship trade order includes: Generate node data for each of the associated entities; Based on the dynamic trajectory data, the background data, and the interaction behavior between the associated entities, edge data between nodes is generated. The node data and the edge data are integrated into a graph data structure to form the entity relationship graph data structure.

4. The method for processing ship trade chain-related status data according to claim 3, characterized in that, The edge data includes at least one attribute data, the attribute data including: Behavioral attribute data is used to characterize the interaction types between the associated entities; Time attribute data is used to characterize the time information corresponding to the interactive behavior; Location attribute data is used to represent the spatial location information corresponding to interactive behaviors.

5. The method for processing ship trade chain related status data according to claim 1, characterized in that, The process of performing graph computation on the multi-source heterogeneous data based on the entity relationship graph data structure to generate state representation parameters for characterizing the association status of the ship trade chain includes: Based on the background data and the external constraint reference data, static reference feature parameters are generated; Based on the dynamic trajectory data, dynamic behavior feature parameters are generated; Based on the entity relationship graph data structure, association strength feature parameters are generated by graph traversal calculation. The static reference feature parameters, the dynamic behavior feature parameters, and the correlation strength feature parameters are fused and calculated to generate the state characterization parameters.

6. The method for processing ship trade chain related status data according to claim 5, characterized in that, The generation of association strength feature parameters based on the entity relationship graph data structure through graph traversal includes: In the entity relationship graph data structure, locate the nodes corresponding to each associated entity and the reference nodes identified in the external constraint reference data; Based on the graph traversal algorithm, the associated paths and path lengths between the nodes are obtained; A correlation strength parameter is generated based on the path length, wherein the smaller the path length, the larger the corresponding correlation strength parameter; Based on the correlation strength parameters, the correlation strength feature parameters are generated.

7. The method for processing ship trade chain related status data according to claim 1, characterized in that, The status identification data is generated by comparing the status representation parameters with a preset threshold range, and the status identification data is used to represent the associated status level of the current ship trade order.

8. A device for processing ship trade chain related status data, characterized in that, include: The acquisition module is used to acquire multi-source heterogeneous data corresponding to the current ship trade order through at least one data interface in response to the current ship trade order. The multi-source heterogeneous data includes at least the background data of each associated entity, the dynamic trajectory data of the transport vessel, and the external constraint reference data. A construction module is used to construct an entity relationship graph data structure in memory based on the multi-source heterogeneous data to represent the current ship trade order. The entity relationship graph data structure includes node data to represent each associated entity and edge data to represent the relationship between each associated entity. The calculation module is used to perform graph calculation processing on the multi-source heterogeneous data based on the entity relationship graph data structure, and generate state characterization parameters to characterize the association state of the ship trade chain. The generation module is used to generate status identifier data corresponding to the current ship trade order based on the status characterization parameters.

9. A data processing device for ship trade chain-related status, characterized in that, include: Memory, used to store programs or instructions; A processor, configured to implement the steps of the ship trade chain associated status data processing method as described in any one of claims 1 to 7 when executing the program or instructions.

10. A computer-readable storage medium, characterized in that, It stores a program or instruction that, when executed by a processor, implements the steps of the ship trade chain associated status data processing method as described in any one of claims 1 to 7.

Images