CN112862321B - Ocean transportation statistical system based on AIS big data and statistical method thereof - Google Patents

Ocean transportation statistical system based on AIS big data and statistical method thereof Download PDF

Info

Publication number
CN112862321B
CN112862321B CN202110182609.5A CN202110182609A CN112862321B CN 112862321 B CN112862321 B CN 112862321B CN 202110182609 A CN202110182609 A CN 202110182609A CN 112862321 B CN112862321 B CN 112862321B
Authority
CN
China
Prior art keywords
data
ais
time
analysis
statistical
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110182609.5A
Other languages
Chinese (zh)
Other versions
CN112862321A (en
Inventor
赵龙飞
姜晓轶
吕憧憬
曹磊
孙苗
郭雪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NATIONAL MARINE DATA AND INFORMATION SERVICE
Original Assignee
NATIONAL MARINE DATA AND INFORMATION SERVICE
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NATIONAL MARINE DATA AND INFORMATION SERVICE filed Critical NATIONAL MARINE DATA AND INFORMATION SERVICE
Priority to CN202110182609.5A priority Critical patent/CN112862321B/en
Publication of CN112862321A publication Critical patent/CN112862321A/en
Application granted granted Critical
Publication of CN112862321B publication Critical patent/CN112862321B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/248—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/284—Relational databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
    • G06F2216/05—Energy-efficient information retrieval

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Computational Linguistics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Fuzzy Systems (AREA)
  • Remote Sensing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A maritime transportation statistical system based on AIS big data and a statistical method thereof aim at forming a specific basic database and a data analysis model by combining a mining knowledge base of ship archives, port data, research data and the like based on real-time and historical AIS data and assisting online processing through continuous data mining and experience accumulation, and finally outputting statistical indexes of ports, maritime channels, goods transportation volumes and the like and dynamic information related to various commodities and ships automatically and regularly, and supporting open type editing operation, visual interactive display and report exporting. The statistical system and the statistical method provide an AIS big data platform for marine statistics, a marine statistics AIS big data mining analysis model is constructed, a whole set of technical solutions of AIS data access, cleaning, storage management, mining analysis, index product generation and the like are formed, and high-quality, timely and accurate marine transportation industry statistical index products can be provided for marine economic management.

Description

Ocean transportation statistical system based on AIS big data and statistical method thereof
Technical Field
The invention relates to the technical field of marine big data management, in particular to a marine statistical system based on AIS big data and a statistical method thereof.
Background
The ocean transportation industry is the basic industry and the pillar industry of ocean economy, and international trade is mostly realized through the marine transportation, and marine statistics is the important tool that provides the marine transportation industry operational aspect, and to the scientific industry policy of making, the continuous healthy development of promotion industry has the important effect. Currently, as a department statistic in government statistics, maritime statistics adopts a comprehensive investigation mode, follows the flow development of statistical scheme formulation, system design, investigation acquisition, data arrangement and reporting, data auditing, data analysis and data publishing, and forms statistical indexes in the aspects of ships and navigation, port operation, goods transportation, external trade and the like. Wherein, the customs administration is responsible for making and designing the implementation scheme of overseas trade statistics of the maritime goods and the customs statistics investigation system, each maritime logistics company reports the customs declaration form of the maritime import and export goods to the customs statistics department, the customs statistical departments at all levels check the reported data in an electronic and manual mode, and finally, the reported data is submitted to a customs administration for data summarization and statistical analysis, and the formed foreign trade statistical products are issued by the customs administration monthly and yearly in the form of quickness, monthly newspapers, yearbooks and the like; the transportation department is responsible for making and designing a statistical implementation scheme and a comprehensive port statistical statement system in aspects of marine vessel navigation, port operation, freight volume, passenger volume and the like, each coastal port sends related data in a statistical statement form according to the month, season and year, each port administrative management department and each regional transportation department collect, examine and submit the data to the transportation department, and finally the transportation department collects and statistically analyzes the data to form monthly, quarterly, semiannual and annual port marine statistical analysis products and releases the products to the outside.
The existing maritime transport statistical method and system do not effectively apply and play the role of big data technology, and have great difference with the modern statistical work requirement on the analysis and mining of maritime transport related data information and the development and use of statistical products, and on the whole, the problems of slow data collection and processing speed, low data quality, lag in data release, low timeliness and the like still exist.
(1) Low efficiency
The marine transportation statistics needs a lot of indexes, large data volume, large data collection engineering quantity and large consumption of manpower and material resources. In each data reporting period, basic level statistics personnel of all parts contact port enterprises and maritime logistics companies to carry out report form filling in a reporting system, data auditing is carried out step by step after filling, data publishing can be carried out only after the national level collects and audits data of all parts of the whole country, and efficiency is low.
(2) Data quality is difficult to guarantee
The existing marine statistical data needs to be distributed from production and collection to processing, needs the cooperation of respondents, needs statistical personnel to collect data and process analysis data, has many intermediate links, and is easy to generate human errors. The quality of statistical data is affected by human errors, wrong data sources are provided and the like, and the statistical products and issued statistical information generated by marine statistical personnel through processing and analyzing the error data can deviate from the actual condition greatly, so that the social public can question the marine statistical data information, and the authority of the marine official statistical data in China can be impacted.
(3) The data release is lagged and the timeliness is not strong
Limited by the existing maritime statistical method, system and statistical flow, the overseas foreign trade statistical monthly newspaper data is usually published about 25 days per month, and the statistical yearbook can be published only at the end of 7 months; the monthly report data of port statistics of the transportation department are published about 20 days per month. However, the raw materials, product prices, material consumption and the like in the current maritime trade are in rapid dynamic change, and the timeliness of the current maritime statistical data cannot meet the application requirements of various complex international and domestic trade processes and governments, industries, enterprises, scholars and the like.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a maritime transportation statistical system based on AIS big data and a statistical method thereof.
The purpose of the invention is realized by the following technical scheme:
a marine transportation statistical system based on AIS big data comprises a data source module, a data access processing module, a data storage management module, a data calculation and analysis module and a data display application module, wherein the data source module provides real-time AIS data and historical AIS data for the data access processing module, and the data source module provides basic support data for the data storage management module; the data access processing module cleans and screens real-time AIS data and historical AIS data and stores the data into the data storage management module; the data calculation and analysis module calls real-time AIS data of the data management module and feeds the information after calculation back to the data storage and management module for storage; the data presentation application module provides analysis services by the data analysis module and data support by the underlying support data of the data storage management module.
A statistical method adopted by a marine statistical system based on AIS big data comprises the following steps: step 1, constructing a big data platform; step 2, AIS data access; step 3, AIS data cleaning; step 4, constructing a data warehouse; step 5, constructing a big data mining analysis model; step 6, analyzing a navigation event; step 7, navigation frequency excavation; and 8, generating a statistical index.
Moreover, the big data platform in the step 1 comprises four parts, namely an infrastructure layer, a data resource layer, a data analysis layer and a service encapsulation layer, wherein the infrastructure layer manages basic support data of the data source module; the data resource layer manages real-time AIS data and historical AIS data of the data source module and the data storage management module; the data analysis layer manages a data calculation analysis module; the service encapsulation layer manages a data display application module;
the step 1 comprises the following substeps:
step 1.1, constructing a data source module, wherein the data source module comprises real-time AIS data, historical AIS data and basic support data of ship files, ports, berths, offshore channels and electronic sea charts;
step 1.2, constructing a data access processing module, wherein the data access processing module comprises a flash stream data processing engine and a flash log collector; for real-time AIS data, firstly, a streaming data processing frame is built, an external real-time AIS data source is accessed through a TCP protocol, and the external real-time AIS data source is uniformly delivered to a Kafka message middleware for storage and is distributed to a flight streaming data processing engine for multi-machine multi-thread processing; the flight stream data processing engine firstly needs to complete the cleaning work of the AIS data, remove the integrated position, eat water, and completely compensate the navigation related data by comparing the invalid data and the repeated data of the destination with the previous AIS data, and simultaneously stores the processed AIS data into an AIS log file, and regularly acquires the AIS log file by a flight log collector and merges the AIS log file into an AIS month log file; for historical AIS data, an ETL tool button is adopted to execute batch tasks to extract message files, and batch operations of cleaning, duplicate removal and invalidation are carried out to form files to be processed in a uniform format, and processing results are stored in an AIS log file;
step 1.3, constructing a data storage management module, wherein the data storage management module comprises a Redis and H2GIS memory database, a Hive, HBase and MySQL, and for real-time AIS data processed by a Flink stream data processing engine, on one hand, MMSI + date is used as a Key to be stored in the Redis memory database for real-time analysis work of navigation event generation and judgment of an access sea channel of a Spark offline task; on the other hand, the latest position of the ship is recorded in the H2GIS memory database, the requirement of displaying the current position of the ship in real time in the later period is met, an AIS log file is formed after cleaning, the AIS log file is automatically guided into a Hive data warehouse through Flume, the problem backtracking in the later period is facilitated, and support is provided for data calculation and analysis; storing a navigation track, a navigation event, navigation information and a data mart formed by data calculation and analysis based on HBase; basic support data of ship archives, ports and berths need to be frequently called when data mining analysis is carried out, and are stored by a relational database MySQL (MySQL system);
step 1.4, a data calculation module is constructed, wherein the data calculation module comprises a Spark event analysis method, a Geomesa space-time big data processing engine and Kylin, AIS track data is extracted from a Redis memory database and Hive in batches by utilizing a Spark event analysis task, and is analyzed to form navigation event data and stored in HBase by combining with basic support data of MySQL (mySQL), ports and berths, and then the navigation event to be analyzed is obtained from the HBase by the Spark event analysis task and is analyzed to form navigation event data and stored in the HBase of the data storage management module; the data market is a statistical index table and a dimension table which are finally presented, and comprises port statistics, channel statistics and goods statistics, the multidimensional data statistics and query are realized through an interface provided by an analytic data warehouse Kylin, hive and HBase serve the Kylin, data are provided for the Kylin, and HBase is used for storing Cube generated by the Kylin; by utilizing a Geomesa space-time big data processing engine, a space-time index is established by reading AIS data stored in HBase and Hive, calculation analysis is carried out based on Spark, and further single-ship track playback, multi-ship track thermodynamic diagram and track line fitting space big data analysis are realized, and the method has OGC standard service interface data access capability and meets the requirement of later-stage data display application;
step 1.5, constructing a data display application module, wherein the data display application module comprises a statistical chart, a statistical report and map visual display, and reads the voyage data and statistical index data stored in HBase based on a UReport2 report engine and an ECharts visual library to realize report service and chart visual service; the method is based on real-time AIS point location data in an H2GIS and flight path line data in HBase, combines the space analysis service of a Geomesa space-time big data processing engine, utilizes a Geoserver map server to publish and form a standard map service, and achieves map visual analysis service of mass ship AIS flight path points and flight path lines based on an OpenLayers map library.
In step 2, on the basis of the constructed big data platform, acquiring real-time AIS data and historical AIS data, wherein the real-time AIS data refers to streaming AIS big data which are generated in real time and are dynamically increased at short time intervals, and the real-time AIS data are accessed through a TCP (transmission control protocol) protocol based on a streaming data processing engine of the big data platform; the historical AIS data refers to AIS data sent by all ships in a certain past time period, the AIS data is stored in a file form, the data format is a standard AIS original message, and the historical AIS data is accessed in a mode of extracting batch tasks executed by an ETL tool key.
Furthermore, step 3, cleaning the acquired real-time and historical AIS data, including removing invalid data and repeated data of the integration position, the draft and the destination, and comparing the invalid data and the repeated data with the previous AIS data sequenced according to time to complement navigation related data; and storing the cleaned AIS data into an AIS log file, and regularly acquiring the AIS log file by a flash log collector and merging the AIS log file into an AIS month log file.
And 4, storing and managing the cleaned AIS data based on a big data platform, meanwhile, aiming at global port and berth data, establishing an electronic fence by manually on-site investigation or drawing based on a remote sensing image and a method of drawing a circle according to a specified radius based on a central coordinate, laying a foundation for later-stage navigation event analysis and voyage mining, and finally, bringing the port, the berth and the electronic fence thereof as well as ship archive data into the big data platform for storage and management to complete data warehouse establishment.
Step 5, constructing an AIS big data mining analysis model comprising a model algorithm of electronic fence analysis, berth completion, berth commodity identification, navigation event analysis, navigation frequency mining and navigation frequency cargo capacity calculation;
and step 6, based on the AIS track point data, the ship file, the port, the berth and the electronic fence data stored in the data warehouse of the big data platform, the ships are divided according to the MMSI in the AIS data as the identity of the ships, the AIS track point data of each ship is arranged according to the ascending order of time, then, by utilizing the big data mining analysis model constructed in the steps, each AIS track point of the ship is correspondingly arranged into 8 navigation states of preassembling navigation, preparing loading, loading completion, unloading navigation, unloading preparation, unloading and unloading, and finally, a navigation state identifier is added to each AIS track point.
And step 7, on the basis of analysis of the sailing events, firstly arranging the AIS data of each ship according to the ascending order of time, then analyzing the sailing state identifier of each AIS data, dividing the sailing of the ship into sailing periods from the pre-loading sailing period to the unloading completion period, and finally analyzing and recording the arrival time and departure time of each sailing period and the information of a loading port, an unloading port, an approach marine route, a cargo type and a cargo capacity to form the sailing data which is used as a basis for generating statistical indexes.
And 8, on the basis of the voyage number data formed by the voyage number mining, firstly dividing the voyage number into different ports according to the loading and unloading ports of the voyage number, then screening the voyage number of the voyage entering and leaving time in a preset statistical period, and finally forming a multi-dimensional port statistical index according to the information of the loading ports, the unloading ports, the sea route, the cargo type and the cargo capacity of the voyage number data and the ship file data.
The invention has the advantages and technical effects that:
the ocean shipping statistical system based on AIS big data and the statistical method thereof have operability and practicability obviously superior to those of the prior art, and have the following specific effects:
(1) Improve the working efficiency
AIS data are generated in real time in the ship operation process and are automatically received through a satellite or a shore-based base station, the data acquisition, processing, storage, mining analysis and statistical product manufacturing are all automatically realized through a unified large data platform, the intermediate processes of data manual report form filling, step-by-step audit reporting, summary statistics and the like are reduced, the consumption of manpower and material resources is greatly reduced, the time period of marine statistical indexes and product production is shortened, and the working efficiency is improved.
(2) The accuracy and the reliability of statistical data are improved
The maritime department stipulates that the maritime ship must be provided with the shipborne AIS equipment, and the navigation process must be started particularly during the entering and leaving port, so compared with the traditional maritime statistical method, the method provided by the invention reduces the situations of report refusing, report missing, report withholding and report missing of statistical data in manual reporting, and also reduces the possible artificial errors in intermediate links such as step-by-step reporting.
(3) Improving the timeliness of statistical data
The ship AIS data is generated in real time, the method provided by the invention can access the real-time AIS data, can process and analyze the data in real time, can generate an instant marine statistical index product, can provide any statistical period, particularly high-frequency (month, ten days, weather, day and the like) index product, greatly shortens the production period of the statistical data, and greatly improves the timeliness of the statistical data.
Drawings
FIG. 1 is a flow chart of a prior art marine statistical method;
FIG. 2 is a technical roadmap of the AIS big data based marine statistical method of the present invention;
FIG. 3 is a general architecture diagram of the AIS big data platform of the present invention;
FIG. 4 is a diagram of the AIS big data platform data architecture of the present invention.
Detailed Description
For a further understanding of the contents, features and effects of the present invention, reference will now be made to the following examples, which are illustrated in the accompanying drawings. It should be noted that the present embodiment is illustrative, not restrictive, and the scope of the invention should not be limited thereby.
The invention provides a maritime transportation statistical system based on AIS big data and a statistical method thereof, which apply big data mining analysis technology to develop the generation of statistical indexes of maritime transportation external trade, ports and bulk goods around the core content of the statistics of the maritime transportation industry, and the specific implementation steps comprise:
(1) Big data platform construction
The AIS big data platform is constructed as a technical basis for realizing marine big data statistics, and aims to form a specific basic database and a data analysis model by combining a digging knowledge base such as ship archives, port data, research data and the like based on real-time and historical AIS data and assisting with online processing through continuous data digging and experience accumulation. Finally, statistical indexes such as ports, sea channels, goods transportation volume and the like and dynamic information related to various commodities and ships are automatically and regularly output, and open type editing operation, visual interactive display and report form export are supported.
1) Platform architecture
The AIS big data platform comprises an infrastructure layer, a data resource layer, a data analysis layer and a service encapsulation layer.
Infrastructure layer: the system consists of a network, a host, storage, safety and other equipment, provides basic software and hardware support for storage and calculation of a big data platform, and also provides a basic support environment for operation of various application systems based on the big data platform. Data resource layer: the method comprises the steps of collecting, extracting, converting and cleaning real-time AIS data and historical AIS data, and meets the requirements of storage management, query retrieval and the like of various basic data, process data and result data based on a big data storage architecture. Data analysis layer: and integrating a big data analysis model algorithm, generating ship navigation events, voyage times, tracks and the like through mining analysis based on various data in the data storage layer, and finally forming various shipping statistical indexes. Service encapsulation layer: and the system is responsible for packaging various big data processing and analyzing functions according to different requirements and providing services for the outside.
2) Platform data architecture
Based on the overall architecture of the big data platform, the data flow design of the big data platform is realized by combining an AIS marine statistics technology route, and as shown in fig. 4, the data flow design comprises five parts, namely a data source, data access processing, data storage management, data calculation analysis and data display application.
A data source: the system comprises real-time AIS data, historical AIS data, and basic support data such as ship files, ports, berths, offshore channels, electronic charts and the like.
Data access processing: for real-time AIS data, firstly, a streaming data processing frame is built, an external real-time AIS data source is accessed through a TCP protocol, and is uniformly delivered to a Kafka message middleware for storage (Kafka realizes high throughput and can ensure accurate transmission to a Flink streaming data processing engine, so that the problem of data loss caused by failure of Flink is avoided), and the data is distributed to the Flink for multi-machine multi-thread processing. The flight stream data processing engine firstly needs to finish the cleaning work of the AIS data, including removing invalid data and repeated data, integrating position, draught, destination and the like, and comparing the integrated data with the previous AIS data to complement navigation related data, meanwhile, the flight also stores the processed AIS data into an AIS log file, and a flight log collector regularly acquires the AIS log file and merges the AIS log file into an AIS month log file; and for historical AIS data, an ETL tool button is adopted to execute batch tasks to extract message files, batch operations such as cleaning, duplicate removal, invalidation removal and the like are carried out, files to be processed in a uniform format are formed, and processing results are stored in an AIS log file.
Data storage management: on one hand, the real-time AIS data processed by the flash is stored into a Redis memory database by taking MMSI + date as a Key for real-time analysis work such as navigation event generation, sea channel access judgment and the like of Spark offline tasks; on the other hand, the latest position of the ship is recorded in the spatial memory database H2GIS, and the requirement of displaying the current position of the ship in real time in the later period is met. Form AIS log file after washing, through the automatic leading-in of fluorine to Hive data warehouse, make things convenient for later stage problem backtracking to for data calculation analysis provides the support. And storing a navigation track line, a navigation event, navigation information and a data mart formed by data calculation and analysis based on the HBase. Basic support data such as ship archives, ports and berths are small in overall data volume, and need to be frequently called when data mining analysis is carried out, so that the data are stored on the basis of a relational database MySQL.
Calculating and analyzing data: firstly, AIS track point data is extracted from a Redis memory database and Hive in batches by utilizing a Spark event analysis task, ship files, ports, berths and other basic support data in MySQL are combined for analysis to form navigation event data and stored in HBase, and then navigation events to be analyzed are obtained from the HBase through the Spark event analysis task, are analyzed to form navigation event data and are stored in the HBase. The data mart is a statistical index table and a dimension table which are finally presented, the statistical index table comprises port statistics, channel statistics, goods statistics and the like, multi-dimensional data statistics and query are achieved through an interface provided by an analytical data warehouse Kylin, hive and HBase serve the Kylin to provide data for the Kylin, and HBase is used for storing Cube generated by the Kylin. By utilizing a Geomesa space-time big data processing engine, a space-time index is established by reading AIS data stored in HBase and Hive, calculation analysis is carried out based on Spark, further space big data analysis such as single-ship track playback, multi-ship track thermodynamic diagram, track fitting and the like is realized, and the system has OGC standard service interface data access capability and meets the requirement of later-stage data display application.
Data presentation application: and the data storage and the analysis and calculation service are used as supports to realize the visual display of the statistical chart, the statistical report and the map of the analysis result. And reading the voyage data and the statistical index data stored in the HBase based on a URreport 2 report engine and an ECharts visual library to realize report service and chart visual service. The method is characterized in that real-time AIS point location data in an H2GIS and trajectory data in HBase are taken as the basis, a Geomesa space analysis service is combined, a Geoserver map server is used for issuing and forming a standard map service, and a map visual analysis service of mass ship AIS trajectory points and trajectories is realized based on an OpenLayers map library.
(2) AIS data access
And on the basis of the constructed big data platform, the real-time AIS data and the historical AIS data are acquired. Real-time AIS data refers to streaming AIS big data generated in real-time and dynamically added at short time intervals (generally not more than 10 minutes), which is accessed via TCP protocol based stream data processing engine of big data platform. The historical AIS data refers to AIS data sent by all ships in a certain period of time in the past, the AIS data is stored in a file form, the data format is a standard AIS original message, and the historical AIS data is accessed in a mode that an ETL tool button executes batch tasks to extract.
(3) AIS data cleansing
Cleaning the acquired real-time and historical AIS data, including removing invalid data and repeated data, integrating position, draught, destination and the like, and comparing the acquired real-time and historical AIS data with the previous AIS data sorted according to time to complement navigation related data; and storing the cleaned AIS data into an AIS log file, and regularly acquiring the AIS log file by a flash log collector and merging the AIS log file into an AIS monthly log file.
(4) Data warehouse construction
The cleaned AIS data is stored and managed on the basis of a big data platform, meanwhile, aiming at global port and berth data, an electronic fence is constructed by manually carrying out on-site investigation or drawing on the basis of remote sensing images and drawing a circle according to a specified radius on the basis of a central coordinate, a foundation is laid for later-stage navigation event analysis and voyage excavation, and finally, the port, the berth and the electronic fence thereof as well as ship archive data are also brought into the big data platform for storage and management, so that construction of a data warehouse is completed.
(5) Big data mining analysis model construction
And constructing an AIS big data mining analysis model comprising model algorithms such as electronic fence analysis, berth completion, berth commodity identification, navigation event analysis, navigation frequency mining, navigation frequency cargo capacity calculation and the like. The electronic fence analysis is to judge the intersection of the electronic fences of the port and the berth and the AIS track point, and is the basis for analyzing the navigation event; the berth completion algorithm is based on massive long-time sequence static AIS data, and utilizes a clustering analysis algorithm in Hadoop to identify berth positions so as to supplement a berth database for complete commercial purchase and manual investigation; the berth commodity identification is used for conjecturing the loading, unloading and goods type labels of other berths through the ship berth and part of the loading, unloading and goods type labels of the known berths by utilizing a neural network and an association rule algorithm; the navigation event analysis algorithm comprises 4 steps, namely firstly judging the navigation state and the navigation speed of the AIS track point data of the ship, then carrying out intersection calculation with electronic fences of ports and berths, secondly judging the loading and unloading states and the goods types of the ship according to loading and unloading identifiers of the ports and the berths and ship draft values, and finally forming a ship navigation event which comprises 8 middle navigation states and is arranged in a time ascending order; the voyage excavation is used for analyzing ship events according to ascending order of time and corresponding each voyage period of the ship to different transportation voyages; calculating the cargo capacity of the voyage ship by calculating the draft difference before and after loading and unloading certain voyage of the ship and combining the full-load draft and the load ton in the ship file to calculate the cargo capacity of the voyage ship.
(6) Analysis of voyage events
AIS track point data, ship archives, harbors, berths and electronic fence data stored in a data warehouse based on a big data platform, the ships are divided according to MMSI in the AIS data as the identity identification of the ships, the AIS track point data of each ship are arranged according to the ascending order of time, then a big data mining analysis model constructed in the steps is utilized, each AIS track point of the ships corresponds to a pre-installation sailing state, a loading preparation state, a loading completion state, a unloading preparation state, a unloading state and an unloading completion state through mining analysis, and finally a sailing state identification is added to each AIS track point.
(7) Voyage excavation
On the basis of analysis of a navigation event, the AIS data of each ship is firstly arranged according to the ascending order of time, then the navigation state identification of each AIS data is analyzed, the ship navigation is divided into navigation periods from pre-installation navigation to unloading completion, and finally the time of arrival, the time of departure, information such as a loading port, an unloading port, an approach marine route, a cargo type and a cargo capacity of each navigation period are analyzed and recorded to form navigation time data which is used as a basis for generating statistical indexes.
(8) Statistical indicator generation
On the basis of voyage data formed by voyage excavation, firstly, dividing voyages into different ports according to loading and unloading ports of the voyages, then screening voyages of departure and arrival time in a preset statistical period (such as months, seasons, half years, years and the like), and finally forming a multi-dimensional port statistical index according to information of loading ports, unloading ports, routes on sea, cargo carrying types, cargo carrying amounts and the like of the voyage data and ship archive data; on the basis of port statistics, the external trade statistics firstly take the voyage number of the unloading port which is a coastal port in China and the loading port which is a port in other countries as the content of import statistics, then take the voyage number of the loading port which is a coastal port in China and the loading port which is a port in other countries as the content of export statistics, finally summarize the import statistics and export statistics results of all ports in China, and form the statistics indexes of the quantity of imported and exported goods, the quantity of the imported and exported goods passing through a sea route, the country of import and export sources and the like; bulk goods statistics is established on the basis of port statistics and foreign trade statistics, statistics result indexes of all ports are summarized according to goods types (such as iron ores, coal, crude oil, soybeans, LNG, LPG and the like), and export and import, internal trade and external trade are distinguished for statistics.
To more clearly illustrate the particular mode of use of the invention, an example is provided below:
the invention researches a set of marine statistical method based on AIS big data, provides a construction method and systematic application of a marine statistical AIS big data platform, constructs a marine statistical AIS big data mining analysis model, forms a whole set of technical solutions of AIS data access, cleaning, storage management, mining analysis, index product generation and the like, and can provide high-quality, timely and accurate marine transportation industry statistical index products for marine economic management.
(1) Efficient and automatic maritime big data statistics realization method and system
Aiming at the problems of multiple intermediate links, low efficiency, difficult guarantee of data quality, long production period of statistical data, low timeliness and the like of the traditional marine statistics, the method for developing the marine statistics based on AIS big data is provided, and a complete technical process and a technical scheme including big data platform construction, data access, data cleaning, data warehouse construction, big data mining analysis model, navigation event analysis, navigation frequency mining and statistical index generation are provided, and the process and the scheme are applied systematically, so that the real-time and accurate marine transportation industry big data statistical index and product support are provided for marine economic management.
(2) AIS big data platform construction technical method for marine big data statistics
In order to realize the AIS-based marine big data statistics, a 4-layer system architecture of a data acquisition processing layer, a data storage layer, a data analysis layer and a service encapsulation layer is adopted based on a distributed storage and calculation framework, and a technical construction method of an AIS big data platform is provided, so that the requirements of real-time AIS flow data acquisition, historical AIS file extraction, data cleaning, data storage management, data mining analysis, statistical analysis, visual display and application service are met.
(3) AIS big data mining analysis model for realizing marine statistics
An AIS big data mining analysis model containing model algorithms such as electronic fence analysis, berth completion, berth commodity identification, navigation event analysis, navigation frequency mining, navigation frequency cargo capacity calculation and the like is constructed and integrated into a big data platform, and the requirements of AIS big data mining analysis and statistical analysis are met.
Finally, the invention preferably adopts mature products and mature technical means in the prior art.
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined in the appended claims.

Claims (8)

1. The utility model provides a marine statistics system based on AIS big data which characterized in that: the statistical system comprises a data source module, a data access processing module, a data storage management module, a data calculation and analysis module and a data display application module, wherein the data source module provides real-time AIS data and historical AIS data for the data access processing module, and the data source module provides basic support data for the data storage management module; the data access processing module cleans and screens real-time AIS data and historical AIS data and stores the data into the data storage management module; the data calculation and analysis module calls real-time AIS data of the data management module and feeds information after calculation processing back to the data storage management module for storage; the data display application module provides analysis service by a data analysis module and provides data support by basic support data of a data storage management module;
the statistical method of the marine statistical system based on the AIS big data comprises the following steps: step 1, constructing a big data platform; step 2, AIS data access; step 3, AIS data cleaning; step 4, constructing a data warehouse; step 5, constructing a big data mining analysis model; step 6, analyzing a navigation event; step 7, carrying out navigation excavation; step 8, generating statistical indexes;
the big data platform in the step 1 comprises an infrastructure layer, a data resource layer, a data analysis layer and a service encapsulation layer, wherein the infrastructure layer manages basic support data of a data source module; the data resource layer manages real-time AIS data and historical AIS data of the data source module and the data storage management module; the data analysis layer manages a data calculation analysis module; the service encapsulation layer manages a data display application module;
the step 1 comprises the following substeps:
step 1.1, constructing a data source module, wherein the data source module comprises real-time AIS data, historical AIS data and basic support data of ship files, ports, berths, offshore channels and electronic sea charts;
step 1.2, constructing a data access processing module, wherein the data access processing module comprises a flash stream data processing engine and a flash log collector; for real-time AIS data, firstly, a streaming data processing frame is built, an external real-time AIS data source is accessed through a TCP protocol, and the external real-time AIS data source is uniformly delivered to a Kafka message middleware for storage and is distributed to a flight streaming data processing engine for multi-machine multi-thread processing; the flight stream data processing engine firstly needs to complete the cleaning work of AIS data, remove the integrated position, eat water, and the invalid data and the repeated data of the destination, and compares the invalid data and the repeated data with the previous AIS data to complement the navigation related data, and simultaneously, the flight stream data processing engine also stores the processed AIS data into an AIS log file, and a flight log collector regularly acquires the AIS log file and merges the AIS log file into an AIS month log file; for historical AIS data, an ETL tool button is adopted to execute batch tasks to extract message files, and batch operations of cleaning, duplicate removal and invalidation are carried out to form files to be processed in a uniform format, and processing results are stored in an AIS log file;
step 1.3, constructing a data storage management module, wherein the data storage management module comprises a Redis and H2GIS memory database, a Hive, HBase and MySQL, and for real-time AIS data processed by a Flink stream data processing engine, on one hand, MMSI + date is used as a Key to be stored in the Redis memory database for real-time analysis work of navigation event generation and judgment of an access sea channel of a Spark offline task; on the other hand, the latest position of the ship is recorded in the H2GIS memory database, the requirement of displaying the current position of the ship in real time in the later period is met, an AIS log file is formed after cleaning, the AIS log file is automatically guided into a Hive data warehouse through Flume, the problem backtracking in the later period is facilitated, and support is provided for data calculation and analysis; storing a navigation track, a navigation event, navigation information and a data mart formed by data calculation and analysis based on HBase; basic support data of ship archives, ports and berths need to be frequently called when data mining analysis is carried out, and are stored by a relational database MySQL (MySQL system);
step 1.4, a data calculation module is constructed, wherein the data calculation module comprises a Spark event analysis method, a Geomesa space-time big data processing engine and Kylin, AIS track data is extracted from a Redis memory database and Hive in batches by utilizing a Spark event analysis task, the AIS track data is analyzed to form navigation event data and stored in HBase by combining with basic support data of MySQL (structured query language), ports and berths, and then the navigation event to be analyzed is obtained from the HBase by the Spark track event analysis task and analyzed to form navigation event data and stored in the HBase of the data storage management module; the data mart is a statistical index table and a dimension table which are finally presented, and comprises port statistics, channel statistics and goods statistics, the multidimensional data statistics and query are realized through an interface provided by an analytic data warehouse Kylin, hive and HBase serve the Kylin to provide data for the Kylin, and HBase is used for storing Cube generated by the Kylin; by utilizing a Geomesa space-time big data processing engine, a space-time index is established by reading AIS data stored in HBase and Hive, calculation analysis is carried out based on Spark, and further single-ship track playback, multi-ship track thermodynamic diagram and track line fitting space big data analysis are realized, and the method has OGC standard service interface data access capability and meets the requirement of later-stage data display application;
step 1.5, constructing a data display application module, wherein the data display application module comprises a statistical chart, a statistical report and map visual display, and reads the voyage data and statistical index data stored in HBase based on a UReport2 report engine and an ECharts visual library to realize report service and chart visual service; the method is based on real-time AIS point location data in an H2GIS and flight path line data in HBase, combines the space analysis service of a Geomesa space-time big data processing engine, utilizes a Geoserver map server to publish and form a standard map service, and achieves map visual analysis service of mass ship AIS flight path points and flight path lines based on an OpenLayers map library.
2. The AIS big data-based marine statistical system of claim 1, wherein: step 2, acquiring and acquiring real-time AIS data and historical AIS data on the basis of the constructed big data platform, wherein the real-time AIS data is streaming AIS big data which is generated in real time and is dynamically increased at short time intervals, and the real-time AIS data is accessed through a TCP (transmission control protocol) based on a streaming data processing engine of the big data platform; the historical AIS data refers to AIS data sent by all ships in a certain period of time in the past, the AIS data is stored in a file form, the data format is a standard AIS original message, and the historical AIS data is accessed in a mode that an ETL tool button executes batch tasks to extract.
3. The AIS big data-based marine statistical system of claim 1, wherein: step 3, cleaning the acquired real-time and historical AIS data, including removing invalid data and repeated data of the integration position, the draft and the destination, and comparing the invalid data and the repeated data with the previous AIS data sequenced according to time to complement navigation related data; and storing the cleaned AIS data into an AIS log file, and regularly acquiring the AIS log file by a flash log collector and merging the AIS log file into an AIS monthly log file.
4. The AIS big data-based marine statistical system of claim 1, wherein: and 4, storing and managing the cleaned AIS data based on a big data platform, meanwhile, aiming at global port and berth data, establishing an electronic fence by manually performing on-site investigation or drawing based on a remote sensing image and a method of drawing a circle according to a specified radius based on a central coordinate, laying a foundation for later-stage navigation event analysis and voyage mining, and finally, bringing the port, the berth and the electronic fence thereof as well as ship archive data into the big data platform for storage and management to complete data warehouse establishment.
5. The AIS big data-based marine statistical system of claim 1, wherein: and 5, constructing an AIS big data mining analysis model including a model algorithm of electronic fence analysis, berth completion, berth commodity identification, navigation event analysis, navigation frequency mining and navigation frequency cargo capacity calculation.
6. The AIS big data-based marine statistics system according to claim 1, wherein: step 6, based on the AIS track point data, ship files, ports, berths and electronic fence data stored in the data warehouse of the big data platform, the ships are divided according to the MMSI in the AIS data as the identity of the ships, the AIS track point data of each ship are arranged according to the ascending order of time, then, by using the big data mining analysis model constructed in the steps, each AIS track point of the ship is correspondingly in a pre-loading voyage, ready to load, in-loading completion, in-unloading voyage, in-preparation to unload, in-unloading, and in-unloading completion 8 voyage states, and finally, a voyage state identifier is added to each AIS track point.
7. The AIS big data-based marine statistical system of claim 1, wherein: and 7, on the basis of analysis of navigation events, firstly arranging AIS data of each ship according to time ascending sequence, then analyzing navigation state identification of each AIS data, dividing the ship navigation into a navigation time section from a pre-installed navigation to a finished unloading, and finally analyzing and recording the arrival time and departure time of each navigation, as well as information of a loading port, an unloading port, an approach marine route, a cargo type and cargo capacity to form navigation time data serving as a basis for generating statistical indexes.
8. The AIS big data-based marine statistical system of claim 1, wherein: and 8, on the basis of the voyage number data formed by voyage number mining, firstly dividing voyage numbers into different ports according to loading and unloading ports of the voyages, then screening the voyage numbers of the voyage times and the departure times in a preset statistical period, and finally forming a multi-dimensional port statistical index according to the information of the loading ports, the unloading ports, the routes on the sea, the cargo carrying types and the cargo carrying quantity of the voyage number data and the ship file data.
CN202110182609.5A 2021-02-08 2021-02-08 Ocean transportation statistical system based on AIS big data and statistical method thereof Active CN112862321B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110182609.5A CN112862321B (en) 2021-02-08 2021-02-08 Ocean transportation statistical system based on AIS big data and statistical method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110182609.5A CN112862321B (en) 2021-02-08 2021-02-08 Ocean transportation statistical system based on AIS big data and statistical method thereof

Publications (2)

Publication Number Publication Date
CN112862321A CN112862321A (en) 2021-05-28
CN112862321B true CN112862321B (en) 2023-01-17

Family

ID=75989692

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110182609.5A Active CN112862321B (en) 2021-02-08 2021-02-08 Ocean transportation statistical system based on AIS big data and statistical method thereof

Country Status (1)

Country Link
CN (1) CN112862321B (en)

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113407281B (en) * 2021-06-23 2022-11-11 重庆卡歌科技有限公司 Dynamic visual three-dimensional display method for new land and sea channel service based on data application
CN113434622A (en) * 2021-06-28 2021-09-24 大连海事大学 gPC-based distributed electronic chart information system and information interaction method
CN113610412B (en) * 2021-08-13 2024-01-26 重庆允丰科技有限公司 Equipment maintenance business index statistical method and system based on big data model
CN113672569B (en) * 2021-09-01 2024-05-07 上海太科舟智能科技有限公司 Method and device for automatically recording electronic navigation log
CN113822630B (en) * 2021-09-14 2022-04-12 中远海运科技股份有限公司 AIS-based LNG ship transport tracking method and system
CN113780952B (en) * 2021-09-16 2024-03-15 上海船舶运输科学研究所有限公司 Container airliner line capacity analysis method and system
CN113837801B (en) * 2021-09-24 2024-05-28 中远海运科技股份有限公司 Ship identification method
CN114005302B (en) * 2021-10-15 2023-07-07 中远海运科技股份有限公司 Coastal ship empty ship index generation method and system
CN113961660B (en) * 2021-10-22 2024-04-05 中远海运科技股份有限公司 Global route thermodynamic diagram generation method and system
CN113793075A (en) * 2021-10-28 2021-12-14 中远海运科技股份有限公司 Method and system for generating and analyzing shipping big data dynamic indexes
CN114020535B (en) * 2021-11-05 2024-04-09 中远海运科技股份有限公司 Backtracking analysis system based on shipping data snapshot
CN114969014A (en) * 2022-06-20 2022-08-30 交通运输部规划研究院 AIS data-based port resource visual intelligent evaluation method and system
CN115239242B (en) * 2022-07-25 2023-07-28 广东马泰找船科技有限公司 International trade shipping bill intelligent management method based on digital twinning
CN116719806A (en) * 2023-08-11 2023-09-08 尚特杰电力科技有限公司 Big data calculation analysis system
CN116775753B (en) * 2023-08-25 2023-11-17 北明成功软件(山东)有限公司 Data asset visualization method and system
CN117455201A (en) * 2023-12-22 2024-01-26 合肥三物信息技术有限公司 Port access scheduling management system
CN117636690B (en) * 2024-01-24 2024-03-29 亿海蓝（北京）数据技术股份公司 Ship voyage generation method and device, electronic equipment and readable storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130093245A (en) * 2012-02-14 2013-08-22 (주)지엠티 Suspected smuggling vessel ais analysis system and it's analysis method on the basis of multi-sensors and sailing pattern analysis
KR20170092804A (en) * 2016-02-04 2017-08-14 (주) 지씨에스씨 System For Generating Standard Sea Route And Supporting Decision of A Ship

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106295983A (en) * 2016-08-08 2017-01-04 烟台海颐软件股份有限公司 Power marketing data visualization statistical analysis technique and system
CN106845875B (en) * 2017-03-28 2024-03-05 中华人民共和国青岛海事局 LNG ship remote supervision system
CN109766397A (en) * 2018-12-17 2019-05-17 深圳市睿智物联科技有限公司 Big data analysis statistics and method of real-time and system for wisdom illumination
CN109636225A (en) * 2018-12-21 2019-04-16 北京航天泰坦科技股份有限公司 A kind of wisdom ocean big data monitors system
CN110188093A (en) * 2019-05-21 2019-08-30 江苏锐天信息科技有限公司 A kind of data digging system being directed to AIS information source based on big data platform
CN110598154B (en) * 2019-09-16 2023-04-07 新疆银狐数据科技有限公司 Tourism comprehensive statistics big data system based on fusion multi-channel data

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130093245A (en) * 2012-02-14 2013-08-22 (주)지엠티 Suspected smuggling vessel ais analysis system and it's analysis method on the basis of multi-sensors and sailing pattern analysis
KR20170092804A (en) * 2016-02-04 2017-08-14 (주) 지씨에스씨 System For Generating Standard Sea Route And Supporting Decision of A Ship

Also Published As

Publication number Publication date
CN112862321A (en) 2021-05-28

Similar Documents

Publication Publication Date Title
CN112862321B (en) Ocean transportation statistical system based on AIS big data and statistical method thereof
CN112256782B (en) Hadoop-based power big data processing system
CN112381406A (en) Ship energy efficiency management big data system and method based on ship-shore cooperation
Štepec et al. Machine learning based system for vessel turnaround time prediction
CN110837625A (en) Port operation control method and device
CN111915099B (en) Freight traffic prediction system with visualized freight information
CN114662795A (en) Natural gas load prediction method and system based on EMD-ARIMA-LSTM model
CN114547376A (en) Airport message data intelligent processing method, device and medium based on big data
Bao et al. AIS big data framework for maritime safety supervision
CN116126926B (en) Intelligent management method and system for full life cycle dynamic data of ship
CN116109185A (en) Carbon measurement system applied to carbon emission accounting of power system
CN115936296A (en) Production and manufacturing data cockpit system of discrete manufacturing enterprise based on industrial internet big data lake
CN110045693A (en) A kind of grouping of the world economy aggregate production managing and control system
CN113408049A (en) Ship water pollution prediction method based on AIS data
Su et al. Artificial intelligence and machine learning applications in freight transport
CN112241428A (en) Digital decision-making method and system
Weiguo et al. Research on the application of smart logistics system based on big data: Taking jingdong logistics as an example
CN110689241A (en) Power grid physical asset evaluation system based on big data
Yang et al. The sustainable development of modern railway transportation planning and management under the guidance of COM technology
Xin et al. Research on the big data platform and its key technologies for the railway locomotive system
Worth et al. Online Analytical Processing of Port Calls for Decision Support
Chen et al. On the Quality Inspection Software System of Surveying and Mapping Geographic Information Achievements Under Multi-Dimension Synergy
Zhao et al. Research on shipping statistics method based on AIS big data mining analysis
Lv et al. Research on ship manning data analysis based on data warehouse
Wang et al. The optimal location of dry port: A case study of the hinterland of Western Side of the Taiwan Straits Port Group

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant