Fishing boat behavior analysis and calculation platform supporting big data analysis

Abstract

The invention belongs to the field of intelligent information systems and big data analysis, and discloses a fishing boat behavior analysis and calculation platform supporting big data analysis, and the platform comprises a data standardization management module which carries out the standardization processing of fishing boat behavior data; the metadata management module manages metadata information of the data source; the rule and index management module defines fishing boat behavior analysis rules and indexes and can automatically identify abnormal behaviors; when a user or the inside of the analysis and calculation platform requests a certain service, the system routes the request to a corresponding service function through the service route management module, the service governance management module monitors the operation condition of each service, if a certain service is abnormal, the service governance management module automatically adjusts resource allocation, and the service management module performs service management. The continuous availability of the service is ensured; the basic support management module provides bottom support and a visual interface for the platform. The fishing boat behavior is comprehensively and intelligently analyzed, multi-source data can be effectively managed, and the expansibility and flexibility of the system are improved.

Description

Technical Field

[0001] The present invention belongs to, but is not limited to, the fields of intelligent information systems and big data analysis technologies, and in particular relates to a fishing vessel behavior analysis computing platform that supports big data analysis. Background Art

[0002] With the increasingly stringent management of marine resources, the management of fishing vessel activities has become particularly important. Currently, information technology can achieve real-time and extensive management of fishing vessels. In the existing technology, although there are some fishing vessel behavior analysis and monitoring systems, they often lack sufficient intelligent analysis capabilities, have difficulty in processing complex behavior patterns, and lack unified data standards and

[0003] Governance architecture makes it difficult to effectively manage and integrate multi-source data. In order to improve the accuracy and efficiency of fishing vessel behavior analysis, it is necessary to design a fishing vessel behavior analysis computing platform that supports multi-source data aggregation and big data analysis. By integrating comprehensive capabilities such as data standardization, metadata management, and service governance, in-depth analysis and prediction of fishing vessel behavior can be achieved.

[0004] This invention provides a fishing vessel behavior analysis and computing platform that supports big data analysis. By incorporating multiple management mechanisms, including data standardization, metadata management, and rule-based indicator management, combined with big data analysis technologies, it enables comprehensive and intelligent analysis of fishing vessel behavior. The platform effectively manages multi-source data and supports service access, routing, and governance, enhancing the system's scalability and flexibility.

[0005] In view of the above analysis, the technical problems that need to be solved urgently in the existing technology are:

[0006] Existing technologies have problems such as insufficient data source integration capabilities, inability to identify complex behavioral patterns of fishing vessels, limited analytical capabilities, inability to support multi-dimensional complex queries, insufficient service governance and scalability.

[0007] In the prior art, there are three invention patents that are closest to this solution:

[0008] The first is "A Ship Intelligent Trajectory Analysis System and Method Thereof", with publication number CN117787604A. This patent proposes a fishing vessel management system that is mainly used in the field of ship management. The system consists of three parts: a fishing vessel intelligent management system, a photovoltaic intelligent management system, and a big data computing power management system. Among them, the photovoltaic intelligent management system is responsible for collecting basic data of the ship and transmitting this data to the data storage module, and then passing it to the fishing vessel intelligent management system through the network module. Then, the fishing vessel intelligent management system will further transmit the basic data to the big data computing power management system for in-depth analysis, and finally feed back the analysis results to the fishing vessel intelligent management system, thereby achieving efficient management of the ship. The entire system monitors the trajectory behavior of mobile devices by reporting real-time geographic location information, providing convenience for regulatory decision-making, breaking through the traditional ground-to-ground telephone reporting method, and effectively solving the problems of information delay and low efficiency of maritime rescue.

[0009] The second is "A Big Data Smart Fishery Management System," with publication number CN117273336A. This system achieves intelligent management and monitoring of fishery resources and fishing vessel operations through data collection, processing and storage, as well as alarm functions. The system uses IoT devices to collect real-time data on the marine environment and fishing vessel operations, and combines big data analysis and predictive models to reveal underlying patterns and predict future changes. At the same time, an alarm mechanism is used to monitor abnormal situations, such as excessive catches or entry into no-fishing zones, and to promptly notify relevant personnel. In addition, the system also uses tools such as fish migration models and BP neural networks to improve prediction accuracy and management efficiency, thereby optimizing fishing vessel scheduling, reducing overfishing, protecting fishery resources, and ultimately achieving more efficient fishery management.

[0010] The patent "A Ship Intelligent Trajectory Analysis System and Method Thereof" uses photovoltaic cells to collect basic ship data and monitor trajectories, but its design concept still remains at the level of a single data source and simple rule analysis, and cannot meet the complex needs of modern fishery management. Its core flaw is its over-reliance on photovoltaic cells as a single sensor, which limits the data dimension and can only provide basic information such as location and voltage. It lacks the ability to integrate multi-source heterogeneous data (such as radar, AIS, Beidou, etc.). In addition, the system has not established an effective data governance architecture. There is neither a metadata management mechanism to ensure data quality nor a standardized process to process data from different sources. This greatly reduces the credibility and traceability of data analysis results. In terms of behavioral analysis, the patent can only judge anomalies through simple rules such as electronic fences. It can neither identify complex behavioral patterns such as collaborative violations between fishing vessels nor cope with analysis scenarios with large data volumes and high real-time requirements. Service governance and dynamic resource allocation are not considered in the system architecture, and performance bottlenecks are bound to occur when faced with high-concurrency requests or large-scale data processing.

[0011] The patent "A Big Data Smart Fishery Management System" realizes the collection and analysis of fishery data through IoT devices and predictive models. However, although the system integrates marine environmental monitoring and fishing vessel positioning data, it lacks unified standards and metadata management mechanisms at the data governance level, making it difficult to ensure the quality and consistency of multi-source data. Its data analysis mainly relies on BP neural networks and fish migration models. Although it can predict resource distribution, it fails to build an association network between fishing vessels and cannot identify complex behavioral patterns such as collaborative operations. In terms of system architecture, although the patent mentions a big data platform, it does not clearly distinguish between the storage and analysis requirements of different types of data. It lacks the collaborative design of relational databases, graph databases, and vector databases, resulting in a relatively single analysis dimension. In addition, the alarm function of the system is only triggered based on preset rules, and it does not have the dynamic resource allocation capabilities of the service governance module. There may be performance bottlenecks when dealing with high concurrency or complex analysis scenarios. Summary of the Invention

[0012] In response to the problems existing in the prior art, the present invention provides a fishing vessel behavior analysis computing platform that supports big data analysis.

[0013] The present invention is implemented as follows: a fishing vessel behavior analysis and computing platform supporting big data analysis, which mainly consists of the following modules:

[0014] Data standardization management module: responsible for standardizing fishing vessel behavior data to ensure consistent data formats across different data sources;

[0015] Metadata management module: used to manage metadata information of data sources to facilitate data traceability and management;

[0016] Rule and indicator management module: defines the rules and indicators for fishing vessel behavior analysis and can automatically identify abnormal behavior;

[0017] Service management module: includes four sub-modules: service access management, service catalog management, service routing management, and service governance management. When a user or the analysis and computing platform requests a service, the system routes the request to the corresponding service function through the service routing management module. The service governance management module monitors the operating status of each service to ensure the stable operation of each service. If a service encounters an abnormality, the service governance management module can automatically adjust resource allocation to ensure the continuous availability of the service.

[0018] Basic support management module: provides underlying support for the platform and a visual interface.

[0019] Furthermore, the analysis and computing platform connects external fishing vessel monitoring data sources (such as Beidou, GPS, radar, AIS, etc.) to the platform through the service access management module. The accessed data is format converted and cleaned through the data standardization management module, and data from different sources are stored and processed in a unified format.

[0020] Furthermore, the metadata management module stores the standardized data into the metadata management module for registration. The module stores metadata information related to each data set, such as data source, format, timestamp, etc., to facilitate subsequent retrieval and management. During the data analysis process, the system can trace the original data source through metadata.

[0021] Furthermore, the rule indicator management module defines rules for judging the behavior of fishing vessels, including the activity range, speed, and stay time of fishing vessels. The rules can be dynamically adjusted according to different business needs to ensure flexible response to behavioral analysis in different situations.

[0022] Furthermore, the service management module includes:

[0023] The service access management module provides access to external data sources and services, and introduces data from different sources into the platform through a unified interface;

[0024] The service catalog management module maintains the catalog of all connected services and data sources in the system. Users can query registered service information through this module;

[0025] The service routing management module dynamically selects the optimal path to route the request to the appropriate service based on the user's request;

[0026] The service governance management module monitors and manages various services within the platform.

[0027] Furthermore, the basic support management module provides underlying support for the platform, including basic functions such as allocation of computing resources, data storage and transmission; through the basic support management module, the analysis and computing platform can display the analysis results to users, and users can view the real-time status of fishing vessels, historical behavior trajectories and risk warning information of system analysis through a visual interface; the basic support module also includes authentication and authorization functions, user identity authentication, permission control and security auditing, to prevent unauthorized access or data leakage, and ensure the information security of the platform.

[0028] Furthermore, the analytical computing platform is specifically designed for fishing vessel behavior monitoring and analysis business scenarios. The platform integrates multiple types of databases, including relational databases, object storage databases, graph databases, and vector databases. The uses of various types of data are as follows:

[0029] Relational database: used to store structured data such as basic information of fishing vessels and historical behavior records;

[0030] Object storage database: Suitable for storing unstructured data from fishing vessels, such as surveillance videos, audio recordings, and other large file data;

[0031] Graph database: used to construct and store complex relationships between fishing vessels, such as the interaction history of different fishing vessels and the association of their stopover areas;

[0032] Vector database: used to process and store high-dimensional data after feature extraction, such as the behavior pattern vector of a fishing boat or the feature vector of a radar signal.

[0033] Furthermore, the analysis and computing platform designs data replication and migration strategies to meet the needs of different analysis tasks and scenarios, and uses special scheduling tasks to copy or migrate data from one database to another based on data type and access requirements.

[0034] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0035] First, the present invention can access data from multiple different sources (such as GPS, radar, AIS, etc.) through a data standardization management module and process them in a unified format, thereby achieving seamless integration of different data sources. This integration capability provides a technical foundation for the unified analysis of large-scale, multi-source data.

[0036] This invention not only supports fishing vessel trajectory and behavior analysis, but also comprehensively monitors and manages all services within the system through a service governance management module, ensuring service stability, scalability, and efficient operation. The platform also features automatic capacity expansion and load balancing capabilities, adapting to large-scale data processing needs.

[0037] This invention incorporates graph database and knowledge graph technologies, enabling not only single-pattern recognition of fishing vessel behavior but also multi-dimensional behavioral pattern mining and prediction by constructing a knowledge graph based on the complex relationships between fishing vessels. This significantly improves the accuracy and depth of analysis, particularly in the identification and prediction of complex behavioral patterns.

[0038] The present invention incorporates multiple database types (relational, object-oriented, graph, and vector) capable of processing structured, unstructured, and relational data, as well as high-dimensional feature data, from fishing vessels. Data migration and replication strategies enable data sharing and collaboration between these different databases, significantly enhancing the system's flexibility and data processing capabilities.

[0039] Second, this technical solution has been validated in actual fishery supervision projects, increasing the accuracy of identifying fishing vessel violations by over 40% and management efficiency by 60%. Its modular design allows for rapid adaptation to the management needs of fisheries of varying scales, and is expected to generate significant economic and social benefits.

[0040] This invention creatively integrates metadata management, service governance, and multi-type database technologies for application in the fisheries sector. The knowledge graph-based fishing vessel association analysis method and the vector database-based behavioral feature clustering technology are pioneering applications in fisheries management, significantly improving the accuracy and predictive power of behavioral analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is an architecture diagram of a fishing vessel behavior analysis computing platform supporting big data analysis provided by an embodiment of the present invention;

[0042] Figure 2 This is a flowchart of migrating a relational database to a graph database provided by an embodiment of the present invention;

[0043] Figure 3 This is a flow chart of synchronization between an object storage database and a relational database provided by an embodiment of the present invention;

[0044] Figure 4 It is the collaboration between the graph database and the vector database provided by the embodiment of the present invention;

[0045] Figure 5 This is a synchronization flow chart between a relational database and a vector database provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0047] like Figure 1 As shown, the embodiment of the present invention provides a fishing vessel behavior analysis computing platform that supports big data analysis, which is mainly composed of the following modules:

[0048] Data standardization management module: responsible for standardizing fishing vessel behavior data, making the data formats of different data sources consistent, facilitating subsequent analysis and processing;

[0049] Metadata management module: used to manage metadata information of data sources, including data source, format, storage location and update time, etc., to facilitate data traceability and management;

[0050] Rule and indicator management module: defines the rules and indicators for fishing vessel behavior analysis and can automatically identify abnormal behavior;

[0051] Service Management Module: Contains four sub-modules, namely service access management, service catalog management, service routing management, and service governance management. The service access management module provides access to external data sources and services, introducing data from different sources into the platform through a unified interface to ensure system compatibility; the service catalog management module maintains a directory of all connected services and data sources in the system, through which users can query registered service information; the service routing management module dynamically selects the optimal path to route requests to the appropriate service based on user requests, thereby improving the system's response efficiency; the service governance management module monitors and manages various services within the platform to ensure service stability and availability. This module provides functions such as load balancing, service quality monitoring, and automatic capacity expansion.

[0052] Basic support management module: provides underlying support for the platform and a visual interface.

[0053] The platform connects external fishing vessel monitoring data sources (such as Beidou, GPS, radar, AIS, etc.) to the platform through the service access management module. The accessed data is format converted and cleaned through the data standardization management module, and data from different sources are stored and processed in a unified format.

[0054] The metadata management module stores the metadata information related to each data set, such as data source, format, timestamp, etc., to facilitate subsequent retrieval and management. During the data analysis process, the system can trace the original data source through metadata to determine the integrity and reliability of the data.

[0055] The rule indicator management module defines rules for judging fishing vessel behavior, including the vessel's range, speed, and dwell time. For example, speed exceeding a certain threshold is considered illegal, or prolonged stays in sensitive areas are considered abnormal. Rules can be dynamically adjusted based on different business needs, ensuring flexible response to behavioral analysis in different scenarios.

[0056] In the overall process, when a user or the analytical computing platform requests a service, the service routing module routes the request to the appropriate service function. The service governance module monitors the operational status of each service to ensure stable operation. If a service experiences an anomaly, the service governance module automatically adjusts resource allocation to ensure continued service availability. Below is a detailed explanation of each submodule.

[0057] The basic support management module provides underlying support for the platform, including fundamental functions such as computing resource allocation, data storage, and transmission, ensuring high system availability. Through this module, the analytical computing platform can present analysis results to users. Users can view the real-time status of fishing vessels, historical behavior trajectories, and risk warning information analyzed by the system through a visual interface. The basic support module also includes authentication and authorization functions, including user identity verification, permission control, and security audits, to prevent unauthorized access or data leakage and ensure platform information security.

[0058] The embodiments of the present invention are specifically designed for fishing vessel behavior monitoring and analysis business scenarios.

[0059] When monitoring fishing vessel behavior, the system needs to frequently receive and process real-time positioning data from fishing vessels and update the location information in the database. Each fishing vessel regularly reports its location information to the platform, and the system needs to quickly record these changes to ensure real-time tracking of the vessel's route. This is a typical OLTP (online transaction processing) scenario, processing frequent small transactions. Furthermore, when a fishing vessel performs certain operations (such as entering a port or leaving a specific fishing area), the system immediately records these operations, including the time, location, and operation type. These transactions must be recorded with high throughput to ensure that each operation is quickly processed and stored. For example, a fishing vessel may send thousands of location updates per day. The system needs to quickly write these updates and query them when needed. Users may query the current status and location of a specific fishing vessel at any time, requiring a rapid system response.

[0060] In fishing vessel behavior analysis, in order to discover the behavioral patterns of a certain fishing vessel or a certain type of fishing vessel, the system may analyze the behavior of fishing vessels over the past few months or even years. For example, by analyzing the navigation path, operating area and residence time of fishing vessels, the system can identify potential violations or regular usage patterns of dangerous areas. For example, by analyzing the historical trajectories of multiple fishing vessels, the future action patterns of a certain type of fishing vessel can be predicted, thereby providing early warning of possible illegal operations. For example, by analyzing the behavioral data of all fishing vessels in the past year, it was found that certain fishing areas have a high-frequency trend of illegal fishing in certain seasons. This analysis process involves multi-dimensional query and processing of large amounts of data, which is a typical OLAP (online analytical processing) operation. The system should be designed and optimized in this regard.

[0061] Considering the specific scenarios described above for monitoring and analyzing fishing vessel behavior, the present invention has been specifically designed. The platform integrates multiple database types, including relational databases, object storage databases, graph databases, and vector databases, to meet the diverse needs of analytical computing platform users. Specifically, the various data types are used as follows:

[0062] Relational databases: Used to store structured data such as basic fishing vessel information and historical activity records. This type of data storage is suitable for frequent OLTP (online transaction processing) operations, such as storing basic information or activity records for a particular fishing vessel. Examples of such databases include MySQL, PosgreSQL, and DAMO.

[0063] Object-based databases are suitable for storing unstructured data from fishing vessels, such as large files like surveillance video and audio recordings. These databases offer high scalability and support large-scale data storage and access. Here, we use S3 storage to implement the object-based database.

[0064] Graph databases: These are used to build and store complex relationships between fishing vessels, such as interaction histories and associations between stopover areas. These graphs facilitate the construction of knowledge graphs and, in LAP (online analytical processing) scenarios, help the system identify potential relationships in fishing vessel behavior and conduct in-depth behavioral pattern analysis and prediction. Examples of such databases include Neo4J, JanusGraph, and HugeGraph.

[0065] Vector databases: These are primarily used to process and store high-dimensional data after feature extraction, such as fishing vessel behavior pattern vectors or radar signal feature vectors. They support efficient similarity retrieval and cluster analysis in OLAP (online analytical processing) scenarios. Examples of such databases include Milvus, Faiss, and Qdrant.

[0066] Based on data type and usage, the present invention designs data replication and migration strategies to meet the needs of different analysis tasks and scenarios. The platform uses specialized scheduling tasks to copy or migrate data from one database to another, depending on the data type and access requirements.

[0067] Different databases serve different data storage needs, so the data needs to be categorized and mapped:

[0068] Relational data: stores structured data such as basic information of fishing vessels, operation logs, and activity records.

[0069] Unstructured data: such as surveillance videos and audio files, stored in object storage databases.

[0070] Related data: such as complex interactions between fishing vessels, stored in graph databases to support the construction of knowledge graphs.

[0071] High-dimensional vector data: such as behavioral pattern feature vectors and radar signal features, stored in vector databases for deep learning or similarity search.

[0072] The replication and migration tasks between different data storage systems are executed by the scheduler. The specific strategies are as follows:

[0073] (1) Migration from relational database to graph database

[0074] Purpose: When basic information or behavior records of a fishing vessel (such as interaction history and stop locations) need to be associated with other fishing vessels, the data is migrated from a relational database to a graph database.

[0075] Process such as Figure 2 :

[0076] S1. Extract updated fishing vessel interaction data from the relational database on a regular basis every day.

[0077] S2. Through the extraction, transformation, and loading processes, the structured data in the relational database is converted into a relational model suitable for storage in the graph database (such as the structure of nodes and edges).

[0078] S3. Import the data into the graph database and update the association between fishing vessels.

[0079] (2) Synchronization between object storage database and relational database

[0080] Purpose: The metadata of some unstructured data (such as video or audio clips) needs to be stored in a relational database for fast retrieval and management, while the object store holds the actual files.

[0081] Process such as Figure 3 :

[0082] S1. When new unstructured data (such as a newly uploaded video) enters the object storage, the system automatically generates metadata (such as file path, generation time, file type, etc.) and stores this metadata in the relational database.

[0083] S2. After metadata storage is completed, the files in the object storage database can be accessed by querying the metadata of the relational database.

[0084] (3) Collaboration between graph databases and vector databases

[0085] Purpose: When in-depth analysis of fishing vessel behavior patterns is required, the relational structure in the graph database can be combined with the high-dimensional behavioral feature vectors in the vector database to perform complex similarity search or cluster analysis.

[0086] Process such as Figure 4 :

[0087] S1. The graph database regularly passes the relationship model of fishing vessels to the analysis module, and the analysis module generates corresponding behavioral feature vectors based on these relationships.

[0088] S2. Store these vector data into a vector database for further analysis of behavior patterns.

[0089] S3. When the system needs to perform complex behavioral pattern predictions or similarity queries between fishing vessels, the system extracts relevant data from the vector database and combines it with the relational structure in the graph database to complete multi-level analysis.

[0090] (4) Synchronization between relational database and vector database

[0091] Purpose: When in-depth analysis of a specific fishing vessel is required, its historical behavior data (stored in a relational database) is extracted and converted into vector features, which are then stored in the vector database for use in subsequent machine learning models or similarity analysis.

[0092] Process such as Figure 5 :

[0093] S1. Data is regularly extracted from the relational database to record the historical behavior of fishing vessels and passed to the feature extraction module.

[0094] S2, the feature extraction module converts these behavioral data into high-dimensional feature vectors.

[0095] S3. Vector data is stored in a vector database for use by deep learning models or behavior analysis algorithms.

[0096] In terms of task scheduling and monitoring:

[0097] Scheduling tasks: All data migration tasks can be set as periodic tasks through a scheduler (such as Apache Airflow) to ensure that data synchronization and migration between different databases proceed as planned.

[0098] Task monitoring: Use monitoring tools (such as Prometheus) to monitor task execution in real time to ensure reliability and performance during data migration. If a task fails or is delayed, the system will issue an alarm.

[0099] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art will appreciate that the above-mentioned devices and methods can be implemented using computer-executable instructions and / or contained in processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The devices and modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, or can be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0100] The above description is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with this technical field within the technical scope disclosed by the present invention and within the spirit and principles of the present invention should be covered by the scope of protection of the present invention.

Claims

1. A fishing vessel behavior analysis computing platform supporting big data analysis, characterized in that: The analysis and computing platform mainly consists of the following modules: Data standardization management module: responsible for standardizing fishing vessel behavior data to ensure consistent data formats across different data sources; Metadata management module: used to manage metadata information of data sources, and to trace and manage data; Rule and indicator management module: defines rules and indicators for fishing vessel behavior analysis and automatically identifies abnormal behavior; Service Management Module: This module includes four submodules: service access management, service catalog management, service routing management, and service governance management. When a user or the analytical computing platform requests a service, the system routes the request to the corresponding service function through the service routing management module. The service governance management module monitors the operating status of each service to ensure its stable operation. If a service encounters an anomaly, the service governance management module can automatically adjust resource allocation to ensure the continuous availability of the service. Basic support management module: provides underlying support for the platform and a visual interface.

2. The fishing vessel behavior analysis computing platform supporting big data analysis as claimed in claim 1, characterized in that: The analysis and computing platform connects external fishing vessel monitoring data sources to the platform through the service access management module. The accessed data is format converted and cleaned through the data standardization management module, and data from different sources are stored and processed in a unified format.

3. The fishing vessel behavior analysis computing platform supporting big data analysis as claimed in claim 1, characterized in that: The metadata management module stores the metadata information related to each data set, such as data source, format, and timestamp.

4. The fishing vessel behavior analysis computing platform supporting big data analysis according to claim 1, characterized in that: The rule index management module defines rules for judging the behavior of fishing vessels, including the activity range, speed, and stay time of fishing vessels.

5. The fishing vessel behavior analysis computing platform supporting big data analysis as claimed in claim 1, characterized in that: The service management module includes: The service access management module provides access to external data sources and services, and introduces data from different sources into the platform through a unified interface; The service catalog management module maintains the catalog of all connected services and data sources in the system. Users can query registered service information through this module; The service routing management module dynamically selects the optimal path to route the request to the appropriate service based on the user's request; The service governance management module monitors and manages various services within the platform.

6. The fishing vessel behavior analysis computing platform supporting big data analysis as claimed in claim 1, characterized in that: The basic support management module provides underlying support for the platform, including basic functions such as allocation of computing resources, data storage and transmission; through the basic support management module, the analysis and computing platform displays the analysis results to users, and users can view the real-time status of fishing vessels, historical behavior trajectories and risk warning information analyzed by the system through a visual interface; the basic support module also includes authentication and authorization functions, user identity authentication, permission control and security audit.

7. The fishing vessel behavior analysis computing platform supporting big data analysis according to claim 1, characterized in that: The analytical computing platform is specifically designed for fishing vessel behavior monitoring and analysis scenarios. It integrates multiple database types, including relational databases, object storage databases, graph databases, and vector databases. The uses of these various types of data are as follows: Relational database: used to store structured data such as basic information of fishing vessels and historical behavior records; Object storage database: Suitable for storing unstructured data from fishing vessels, surveillance videos, audio recordings, and other large file data; Graph database: used to build and store complex relationships between fishing vessels, including interaction histories and stopover area associations between different fishing vessels; Vector database: used to process and store high-dimensional data after feature extraction, such as fishing boat behavior pattern vectors or radar signal feature vectors.

8. The fishing vessel behavior analysis computing platform supporting big data analysis as claimed in claim 1, characterized in that: The analytical computing platform designs data replication and migration strategies to meet the needs of different analytical tasks and scenarios, and uses dedicated scheduling tasks to copy or migrate data from one database to another based on data type and access requirements.

Images