A method and system for fusion processing of enteromorpha data

Abstract

The present invention relates to the field of enteromorpha monitoring technology, and specifically to a method and system for fusion processing of enteromorpha data, including: obtaining multi-source heterogeneous information of enteromorpha; using standardized data sets to perform data analysis and reorganization to obtain standardized information; using fusion algorithms to fuse the standardized information; and presetting hybrid storage strategies and data automatic warehousing mechanisms to store the standardized information. The present invention ensures the format consistency and content accuracy of data by presetting standardized data sets. Using a preset fusion algorithm, the standardized multi-source information is organically fused to more comprehensively reflect the actual situation and changing trend of enteromorpha. The preset hybrid storage strategies and data automatic warehousing mechanisms ensure the efficient storage and convenient management of the fused data.

Description

Technical Field

[0001] The present invention relates to the technical field of enteromorpha monitoring, and in particular to an enteromorpha data fusion processing method and system. Background Art

[0002] Since the large-scale outbreak of Enteromorpha in the Yellow Sea in the summer of 2008, large-scale Enteromorpha disasters have occurred in the Yellow Sea every summer. Large-scale, high-density floating Enteromorpha will block the light on the sea surface, reduce phytoplankton photosynthesis, change the primary production process and material energy flow of the ocean, and affect the structure and function of the marine ecosystem.

[0003] The Enteromorpha green tide has a period of rapid growth in the early stage of the outbreak. During this period, the duration of the Enteromorpha green tide between the radiation sandbar and 35°N and the amount of biomass have a direct impact on the final scale of the Enteromorpha green tide outbreak. Monitoring data show that in the early stage of the green tide outbreak, because the conditions of nutrients, water temperature, light, etc. in the sea area are very suitable, the algae strains themselves are also in a rapid growth stage, and the overall scale of the Enteromorpha green tide has explosive growth, which can increase 10 times in a week. Real-time monitoring of Enteromorpha and pre-salvage to block its natural outbreak process will have a multiplier effect on controlling the final scale of the Enteromorpha green tide outbreak.

[0004] Existing technologies for real-time monitoring of Ulva include traditional methods that rely on manual on-site observation and recording. Data are usually collected and stored separately by department or task type. There is a lack of complex data fusion and application in predictive models. Data storage may rely on local hard drives or simple network sharing. There is a lack of centralized and large-scale data centers, and the degree of automation is low, making it difficult to cope with the efficient processing and management needs of large-scale data. Summary of the invention

[0005] 1. Purpose of the invention

[0006] The purpose of the present invention is to provide a method and system for fusion processing of Enteromorpha data which can integrate and utilize Enteromorpha monitoring data from multiple sources, improve the degree of automation of data storage, and meet the needs of efficient processing and management of large-scale data.

[0007] (II) Technical solution

[0008] In order to solve the above problems, the present invention provides a method for fusion processing of enteromorpha data, comprising:

[0009] Obtain multi-source heterogeneous information of Enteromorpha;

[0010] Presetting a standardized data set, wherein the standardized data set includes a data category and a data format;

[0011] Using the standardized data set, performing data parsing and reorganization on the multi-source heterogeneous information to obtain standardized information;

[0012] Using a preset fusion algorithm to fuse the standardized information to obtain fused information;

[0013] The standardized information is stored using a preset hybrid storage strategy and an automatic data storage mechanism.

[0014] In another aspect of the present invention, preferably, the data categories include: spatial data, real-time dynamic data, monitoring data, meteorological environment data, and personnel and management data;

[0015] The spatial data includes: pre-salvage spatial data and basic geographic data;

[0016] The real-time dynamic data includes: ship dynamic information AIS data, on-site salvage data and on-site supervision data;

[0017] The monitoring data include: multi-method enteromorpha monitoring data and enteromorpha distribution and drift data;

[0018] The meteorological environment data include: marine meteorological environment observation and forecast data;

[0019] The personnel and management data include: personnel information and breeding area prevention and control supervision data.

[0020] In another aspect of the present invention, preferably, using the standardized data set to perform data parsing and reorganization on the multi-source heterogeneous information to obtain standardized information includes:

[0021] Performing data cleaning on the multi-source heterogeneous information to obtain cleaned information;

[0022] Unifying the format of the cleaned information according to a preset standardized data set to obtain information in a unified format;

[0023] Performing data conversion on the information after the format is unified, converting the unstructured data into structured data, and obtaining the information after the data conversion;

[0024] The information after the data conversion is subjected to numerical standardization processing to obtain standardized information.

[0025] In another aspect of the present invention, preferably, the standardized information is fused using the fusion algorithm to obtain the fused information, which includes:

[0026] Performing time-space registration on the standardized information, matching the time series data of the standardized information with the spatial data, and obtaining time-space matched information;

[0027] Setting corresponding weights for the information after the time-space matching according to data categories to obtain first information;

[0028] The first information is represented by a Bayesian network to represent the dependency relationship between the data categories, thereby obtaining the second information.

[0029] In another aspect of the present invention, preferably, using the fusion algorithm to fuse the standardized information to obtain the fused information further comprises:

[0030] performing feature extraction on the second information to obtain distribution information of Enteromorpha;

[0031] The distribution information of the Enteromorpha is integrated with the meteorological environment data to predict the dynamics of the Enteromorpha.

[0032] In another aspect of the present invention, preferably, performing feature extraction on the second information to obtain the distribution information of Enteromorpha includes:

[0033] Cropping the remote sensing image in the second information into a fixed size and performing data enhancement;

[0034] Use convolutional neural networks for feature extraction;

[0035] The convolutional layers of the convolutional neural network are used to capture local patterns in remote sensing images;

[0036] The pooling layer of the convolutional neural network is used to reduce the size of the feature map;

[0037] The fully connected layer of the convolutional neural network is used to connect the output of the convolutional layer to perform classification or regression to obtain extracted features;

[0038] The extracted features are used to classify or locate the area covered by Enteromorpha.

[0039] In another aspect of the present invention, preferably, the distribution information of Enteromorpha is integrated with meteorological environment data, and the dynamics of Enteromorpha are predicted to include:

[0040] According to the scale information in the distribution information of the enteromorpha and the light and temperature in the meteorological environment data, using a growth model, predicting the enteromorpha growth information in the enteromorpha dynamics;

[0041] According to the positioning information in the distribution information of the enteromorpha and the wind direction information in the meteorological environment data, the position information of the enteromorpha in the enteromorpha dynamics is predicted by using a drift model.

[0042] In another aspect of the present invention, preferably, the preset hybrid storage strategy and data automatic warehousing mechanism for storing the standardized information includes:

[0043] Establishing a database and a file system, wherein the database includes a Enteromorpha monitoring database, a prevention and control supervision database, a ship information database, a personnel information database, and a salvage supervision database, and the file system includes a salvage supervision file system;

[0044] storing the structured data in the fused information in a database, and storing the unstructured data in the fused information in a file system;

[0045] The database is set to select a relational database;

[0046] The data automatic warehousing mechanism is set as an ETL process, and uses Kafka message queue technology to buffer real-time data streams.

[0047] In another aspect of the present invention, preferably, the preset hybrid storage strategy includes:

[0048] The metadata of the unstructured data is stored in the database, and the actual files of the unstructured data are stored in the file system, and the actual locations in the file system are pointed to by the links in the database;

[0049] Preset data access frequency thresholds and use cache technology to speed up access to frequently accessed database records or files;

[0050] According to the data access frequency threshold, the storage medium is divided into different storage levels.

[0051] In another aspect of the present invention, preferably, a system for fusion processing of enteromorpha data comprises:

[0052] Acquisition module: Acquisition of multi-source heterogeneous information of Enteromorpha;

[0053] Preset module: preset a standardized data set, wherein the standardized data set includes a data category and a data format;

[0054] Parsing and reorganization module: using the standardized data set, performing data parsing and reorganization on the multi-source heterogeneous information to obtain standardized information;

[0055] Fusion module: using the preset fusion algorithm to fuse the standardized information to obtain fused information;

[0056] Storage module: uses a preset hybrid storage strategy and data automatic warehousing mechanism to store the standardized information.

[0057] (III) Beneficial effects

[0058] The above technical solution of the present invention has the following beneficial technical effects:

[0059] The present invention uniformly analyzes and reorganizes multi-source heterogeneous Enteromorpha data by presetting standardized data sets, thereby ensuring the format consistency and content accuracy of the data. This standardized processing eliminates format differences and potential data conflicts between different data sources, and provides a high-quality data basis for subsequent data analysis and application. Using a preset fusion algorithm, the standardized multi-source information is organically integrated to more comprehensively reflect the actual situation and change trend of Enteromorpha. This fusion not only improves the richness and comprehensiveness of the data, but also helps to discover the laws and characteristics that are difficult to reveal from a single data source. The preset hybrid storage strategy and data automatic warehousing mechanism ensure the efficient storage and convenient management of the fused data. The hybrid storage strategy can flexibly select the most suitable storage method according to the characteristics and access requirements of the data. At the same time, the data automatic warehousing mechanism reduces manual intervention, reduces the error rate, and improves the overall efficiency of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is an overall flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0062] Obviously, the described embodiments are only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] In the description of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0064] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0065] Embodiment 1

[0066] A method for fusion processing of enteromorpha data, Figure 1 FIG. 1 shows an overall flow chart of an embodiment of the present invention, as shown in FIG. Figure 1 As shown, including:

[0067] Obtain multi-source heterogeneous information on Enteromorpha; in this embodiment, the multi-source heterogeneous information on Enteromorpha includes data such as marine meteorological environment observation and forecast data and Enteromorpha drift path prediction data; ship dynamic information, salvage volume, Enteromorpha green tide discovery data and other data; reported cruise ship Enteromorpha green tide discovery, salvage, disposal data, supervisory personnel work progress data and other data; Enteromorpha remote sensing interpretation data; aquaculture area prevention and control supervision data; data formats include shapefile, picture, video, excel, word, pdf, netcdf, service interface and other data formats.

[0068] Furthermore, the multi-source heterogeneous information of Enteromorpha includes: pre-salvage spatial data: Enteromorpha salvage focus areas, Jiangsu key salvage areas, prevention and control areas, release areas, salvage zones, tidal gully garrison zones, Shandong's first and second lines of defense, video monitoring points, and ship garrison points; on-site salvage data: ship dynamic information, salvage volume, and Enteromorpha green tide discovery; on-site supervision data: Enteromorpha green tide discovery, salvage and disposal data of cruise ships, and supervisory personnel's work progress data; ship AIS data: Jiangsu Province and Shandong Province salvage ship information and real-time information data; multi-means monitoring data: Enteromorpha monitoring data such as ship cruises, drones, satellite remote sensing, and video monitoring; marine atmospheric Environmental observation and forecast data: including daily large-scale marine meteorological environment observation and forecast, severe weather forecast data such as strong winds and fog, detailed observation and forecast of local hydrological and meteorological conditions, early warning information and other data; Enteromorpha distribution and drift data: remote sensing and on-site supervision found Enteromorpha green tide areas, Enteromorpha drift path prediction data; Personnel information: Joint command headquarters, on-site command headquarters, Jiangsu Province, Shandong Province Enteromorpha pre-salvage and East China Sea Bureau, North Sea Bureau on-site supervision staff information data; Aquaculture area prevention and control supervision data: to achieve integrated display of aquaculture enterprise distribution, new algae prevention technology and new material test pilot, bamboo pole drift and labeling, algae removal and prevention effect, aquaculture facility recovery supervision data. Basic geographic data: electronic nautical charts, marine functional zoning, ecological red lines, salvage area divisions, exercise areas, important locations and provincial and municipal surface data and other base map data.

[0069] A standardized data set is preset, and the standardized data set includes data categories and data formats. In this embodiment, different data formats are set for different data categories. The data categories in this embodiment include: spatial data, real-time dynamic data, monitoring data, meteorological environment data, and personnel and management data; spatial data include: pre-salvage spatial data and basic geographic data; real-time dynamic data include: ship dynamic information AIS data, on-site salvage data and on-site supervision data; monitoring data include: multi-means Enteromorpha monitoring data and Enteromorpha distribution and drift data; meteorological environment data include: marine meteorological environment observation and forecast data; personnel and management data include: personnel information and aquaculture area prevention and control supervision data.

[0070] The standardized data set is used to perform data analysis and reorganization on the multi-source heterogeneous information to obtain standardized information. The specific content of data analysis and reorganization is not limited here, and can be automatic processing such as automatic reception of multi-source data, fusion of multi-means Enteromorpha monitoring data, dated archiving of Enteromorpha distribution and drift prediction data, dated archiving of salvage supervision data, merging of salvaged ships, generation of standard slices of marine meteorological forecast data, and digitization of basic geographic data.

[0071] In this embodiment, using the standardized data set to perform data parsing and reorganization on the multi-source heterogeneous information to obtain standardized information includes:

[0072] Data cleaning is performed on the multi-source heterogeneous information to obtain the cleaned information; the purpose of data cleaning is to remove invalid and duplicate data, fill missing values, and use technologies such as Apache Kafka, Apache Storm or Apache Flink to realize real-time data stream processing for real-time dynamic data. Use time series databases such as InfluxDB and TimescaleDB to store and query data, and apply time series analysis algorithms such as ARIMA and state space models to identify trends and outliers, implement cleaning and time series analysis, and ensure the freshness and accuracy of data.

[0073] The cleaned information is formatted in accordance with a preset standardized data set to obtain information in a formatted manner; ensuring that all data follow the same data structure and format;

[0074] Performing data conversion on the information after the unified format, converting the unstructured data into structured data, and obtaining the converted information, so as to facilitate subsequent comparative analysis;

[0075] The information after the data conversion is numerically standardized to obtain standardized information, which is convenient for subsequent comparative analysis.

[0076] The standardized information is fused using a preset fusion algorithm to obtain fused information; in this embodiment, the fusion includes:

[0077] Performing time-space registration on the standardized information, matching the time series data of the standardized information with the spatial data, and obtaining time-space matched information;

[0078] Setting corresponding weights for the information after the time-space matching according to data categories to obtain first information;

[0079] The first information is represented by a Bayesian network to represent the dependency relationship between the data categories, thereby obtaining the second information.

[0080] Furthermore, in this embodiment, the fusion further includes:

[0081] Extracting features from the second information to obtain the distribution information of Enteromorpha; including: cropping the remote sensing image in the second information into a fixed size and performing data enhancement;

[0082] Use convolutional neural networks for feature extraction;

[0083] The convolutional layers of the convolutional neural network are used to capture local patterns in remote sensing images;

[0084] The pooling layer of the convolutional neural network is used to reduce the size of the feature map;

[0085] The fully connected layer of the convolutional neural network is used to connect the output of the convolutional layer to perform classification or regression to obtain extracted features;

[0086] The extracted features are used to classify or locate the area covered by Enteromorpha.

[0087] The distribution information of Enteromorpha is integrated with the meteorological environment data to predict the dynamics of Enteromorpha, including:

[0088] According to the scale information in the distribution information of the enteromorpha and the light and temperature in the meteorological environment data, using a growth model, predicting the enteromorpha growth information in the enteromorpha dynamics;

[0089] The growth model is expressed using the following formula:

[0090] ;

[0091] Among them, N(t) represents the growth information of Enteromorpha in the predicted Enteromorpha dynamics, represents the scale of Enteromorpha at a specific time t, and u max represents the maximum growth rate of Enteromorpha, which means the maximum growth rate that Enteromorpha can achieve under the most ideal conditions (e.g., sufficient light and nutrition and no other limiting factors); I represents the light intensity, k s represents the light saturation coefficient of Enteromorpha, indicating that when the light intensity exceeds this value, the growth rate of Enteromorpha no longer increases with the increase of light intensity; r represents the growth rate corresponding to light intensity I, t represents time, T represents temperature, A and B represent the adjustment coefficients of growth rate and death rate at temperature T, E 1 represents the growth activation energy coefficient, which indicates the minimum energy threshold required for the growth of Enteromorpha at a given temperature; E 2 represents the death activation energy coefficient, which indicates the minimum energy threshold for the death of Enteromorpha at a given temperature, X represents the initial scale, u d Abnormal mortality rate of Enteromorpha, such as being eaten by animals.

[0092] According to the positioning information in the distribution information of the enteromorpha and the wind direction information in the meteorological environment data, the position information of the enteromorpha in the enteromorpha dynamics is predicted by using a drift model.

[0093] ;

[0094] Where D(t) represents the position of Enteromorpha at time t, D 0 Indicates the initial positioning information of Enteromorpha, v cx

[0095] and v cy are the velocity components of the ocean current in the east-west and north-south directions, V w represents wind speed and θ w Indicates wind direction, measured clockwise from due north. is the drift velocity vector caused by the ocean current, is the wind-induced drift velocity vector.

[0096] Furthermore, the integrated information also provides data-driven decision support for salvage operations, resource allocation, emergency response, etc. Develop interactive maps and dashboards to intuitively display the status of Enteromorpha, salvage results and meteorological impacts. Analyze the salvage efficiency and the effectiveness of regulatory measures, and continuously optimize salvage strategies and resource allocation.

[0097] The standardized information is stored using a preset hybrid storage strategy and an automatic data storage mechanism, including:

[0098] Establishing a database and a file system, wherein the database includes a Enteromorpha monitoring database, a prevention and control supervision database, a ship information database, a personnel information database, and a salvage supervision database, and the file system includes a salvage supervision file system;

[0099] The structured data in the fused information is stored in a database, and the unstructured data in the fused information is stored in a file system; structured data, such as monitoring data, ship dynamics, personnel information, etc., are suitable for storage in a database for fast query, indexing and transaction processing. Unstructured data, such as large files such as on-site pictures, video surveillance recordings, electronic charts, etc., are more suitable for storage in a file system because the file system is more efficient in processing large files and streaming data.

[0100] The database is set to select a relational database; for the Enteromorpha monitoring database, prevention and control supervision database, ship information database, personnel information database, and salvage supervision database, a relational database (such as MySQL, PostgreSQL) or a NoSQL database (such as MongoDB, especially for complex or semi-structured data) can be selected to meet different query and expansion requirements. Optimize the indexing strategy to ensure query efficiency. Use a high-performance file system (such as EXT4, ZFS, or a file system designed for cloud storage) to store unstructured data. Consider using a distributed file system (such as HDFS) to increase storage capacity and fault tolerance, especially when the amount of data is huge.

[0101] The data automatic storage mechanism is set as an ETL process, and Kafka message queue technology is used to buffer real-time data streams. Design the ETL (Extract, Transform, Load) process to automatically extract data from various sources, perform necessary transformations (such as data cleaning and format standardization), and then load it into the corresponding database or file system. Kafka and other message queue technologies can be used to buffer real-time data streams to ensure stable and efficient data ingestion.

[0102] The preset hybrid storage strategy includes:

[0103] The metadata of the unstructured data, such as the file name, path, size, creation time, etc., is stored in the database, and the actual files of the unstructured data are stored in the file system, and the links in the database point to the actual locations in the file system;

[0104] Preset data access frequency thresholds and use caching technology to speed up access to frequently accessed database records or files; Use caching technology (such as Redis) to speed up access to frequently accessed database records or files, especially for data with high requirements for real-time monitoring and query response.

[0105] According to the data access frequency threshold, the storage media are divided into different storage tiers. According to the data access frequency and importance, the data is distributed on storage media of different tiers, such as hot data is stored in SSD, and cold data is migrated to HDD or low-cost cloud storage.

[0106] The Ulva data fusion processing method of this embodiment can be applied to the comprehensive information processing of ships. Aiming at the problem of efficient management of different types of ships such as salvage ships, supervision ships, and monitoring ships in the pre-salvage work of Ulva green tide, a comprehensive ship information processing system is developed to realize ship information processing functions such as real-time request for salvage ship and supervision ship data, dynamic request for ship historical data, storage management of fishing vessel detailed information, one-click generation of multiple ship trajectories, automatic calculation of ship sailing distance, and one-click export of daily ship data.

[0107] Real-time data requests from salvage and supervision vessels are processed by setting up a real-time data receiving interface, integrating AIS or BeiDou systems, and continuously monitoring the location and status information sent by the ship through WebSocket. After the data arrives, it is immediately parsed, verified, and stored in a real-time database to ensure the immediate availability of information.

[0108] Dynamically request historical ship data, build a historical data query system, and use efficient database technology to store archived data. Develop a flexible query API to support users to retrieve data based on parameters such as timestamps and ship identification. After processing, the search results are intuitively displayed in the front-end interface in the form of charts.

[0109] Detailed information of fishing vessels is stored in the database, and the database structure is designed to store the overall information of fishing vessels, and the management background is created to enter and edit these details. The data verification process is implemented to ensure the accuracy and completeness of the stored information, and the ORM technology is used to simplify the database interaction process.

[0110] Generate multiple ship trajectories with one click, integrate map API, develop functions to receive a list of selected ships, extract trajectory data from real-time and historical databases. Apply algorithms to optimize trajectory display, eliminate redundancy, and generate and display the movement paths of all selected ships on the map with one click.

[0111] The ship's sailing distance is automatically calculated, and the algorithm automatically processes the ship's positioning sequence, calculates the distance between two consecutive points and accumulates them to obtain the total sailing distance. The calculation results can be updated in real time and can also be provided to users on demand to assist in navigation analysis and decision-making.

[0112] Daily ship data can be exported with one click, and an export function module has been added to allow users to customize the date range and data dimensions. The backend extracts the data accordingly, converts it into CSV, Excel or PDF format, and provides it to users through a secure download link, enabling convenient offline analysis and archiving of data.

[0113] The enteromorpha data fusion processing method of this embodiment can be applied to weather forecast data processing, including:

[0114] The numerical forecast data of wind field, flow field, waves, etc. uploaded by the central station are monitored in real time, and the original NetCDF format files are preprocessed. After a series of preprocessing operations such as data parsing, feature, extraction, data cleaning, quality control, coordinate conversion, contour line generation, data clipping, compression encryption, time and space slicing, and service distribution, the output is a standard standardized feature service. First, a receiving service compatible with the central station data transmission protocol needs to be deployed, and a real-time monitoring mechanism based on event-driven or message queues needs to be configured to ensure that new file uploads can be responded to immediately. Once a file upload in NetCDF format is detected, the system will automatically perform file integrity and format verification. The verified files will be registered in the database and detailed logs will be recorded, and the notification mechanism will be triggered to confirm receipt. Subsequently, these files will be compiled into the preprocessing task queue and prepared to enter a series of standardized processing processes including parsing, cleaning, and conversion according to the predetermined priority, thus laying a solid foundation for the subsequent feature service output. The whole process ensures the efficiency, real-time and traceability of data processing.

[0115] The data fusion processing method of the present embodiment can be applied to the processing of drift and buoy data. In order to respond to the owner's demand for drift and buoy data storage, a drift and buoy data processing system is designed to automatically integrate and store the real-time data of drift and buoy, and store the historical trajectory and monitoring data of drift and buoy to achieve efficient storage of drift and buoy data. Among them, drift monitoring elements include longitude and latitude, voltage, water temperature, time, etc.; buoy monitoring elements include current, waves, weather, status, comprehensive, etc.

[0116] First, we deeply analyze the needs and design the system architecture, covering all aspects of data reception, processing, storage and display; then, we develop a real-time data reception interface to ensure the safe acquisition of field data through a reliable network protocol; after the data is decoded, verified and cleaned in the pre-processing stage, we implement real-time integration technology to quickly import the processed real-time data into real-time and relational databases. The system further tracks and stores the detailed historical trajectories of the drift and buoy, and uses advanced analytical methods to mine trends and anomalies in the monitoring data. By building an intuitive data visualization module, users can intuitively view key information such as location trajectory and changes in environmental parameters, and have flexible data export and report generation capabilities. In addition, we strengthen system security measures, implement user authority management, and continuously monitor and maintain the system to finally complete the processing of drift and buoy data.

[0117] The present invention uniformly analyzes and reorganizes multi-source heterogeneous Enteromorpha data by presetting standardized data sets, thereby ensuring the format consistency and content accuracy of the data. This standardized processing eliminates format differences and potential data conflicts between different data sources, and provides a high-quality data basis for subsequent data analysis and application. Using a preset fusion algorithm, the standardized multi-source information is organically integrated to more comprehensively reflect the actual situation and change trend of Enteromorpha. This fusion not only improves the richness and comprehensiveness of the data, but also helps to discover the laws and characteristics that are difficult to reveal from a single data source. The preset hybrid storage strategy and data automatic warehousing mechanism ensure the efficient storage and convenient management of the fused data. The hybrid storage strategy can flexibly select the most suitable storage method according to the characteristics and access requirements of the data. At the same time, the data automatic warehousing mechanism reduces manual intervention, reduces the error rate, and improves the overall efficiency of data processing.

[0118] Embodiment 2

[0119] A system for fusion processing of enteromorpha data, comprising:

[0120] Acquisition module: Acquisition of multi-source heterogeneous information of Enteromorpha;

[0121] Preset module: preset a standardized data set, wherein the standardized data set includes a data category and a data format;

[0122] Parsing and reorganization module: using the standardized data set, performing data parsing and reorganization on the multi-source heterogeneous information to obtain standardized information;

[0123] Fusion module: using a preset fusion algorithm to fuse the standardized information to obtain fused information;

[0124] Storage module: uses a preset hybrid storage strategy and data automatic warehousing mechanism to store the standardized information.

[0125] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

[0126] The present invention has been described above with reference to the embodiments of the present invention. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. The scope of the present invention is defined by the appended claims and their equivalents. Without departing from the scope of the present invention, a person skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

[0127] Although the embodiments of the present invention have been described in detail, it should be understood that the various changes, substitutions, and alterations could be made hereto without departing from the spirit and scope of the invention.

[0128] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A method for fusion processing of Enteromorpha data, characterized in that: include: Obtain multi-source heterogeneous information of Enteromorpha; Presetting a standardized data set, wherein the standardized data set includes a data category and a data format; Using the standardized data set, performing data parsing and reorganization on the multi-source heterogeneous information to obtain standardized information; Using a preset fusion algorithm to fuse the standardized information to obtain fused information; The standardized information is stored using a preset hybrid storage strategy and an automatic data storage mechanism; The standardized information is fused by using the fusion algorithm to obtain the fused information, which includes: Performing time-space registration on the standardized information, matching the time series data of the standardized information with the spatial data, and obtaining time-space matched information; Setting corresponding weights for the information after the time-space matching according to data categories to obtain first information; For the first information, using a Bayesian network to represent the dependency relationship between the data categories, to obtain second information; performing feature extraction on the second information to obtain distribution information of Enteromorpha; The distribution information of Enteromorpha is integrated with the meteorological environment data to predict the dynamics of Enteromorpha; The distribution information of Enteromorpha is integrated with the meteorological environment data to predict the dynamics of Enteromorpha, including: According to the scale information in the distribution information of the enteromorpha and the light and temperature in the meteorological environment data, using a growth model, predicting the enteromorpha growth information in the enteromorpha dynamics; The growth model is expressed using the following formula: Among them, N(t) represents the growth information of Enteromorpha in the predicted Enteromorpha dynamics, represents the scale of Enteromorpha at a specific time t, and u max represents the maximum growth rate of Enteromorpha, I represents the light intensity, k s represents the light saturation coefficient of Enteromorpha, r represents the growth rate corresponding to the light intensity I, t represents time, T represents temperature, A and B represent the adjustment coefficients of growth rate and death rate at temperature T, E1 represents the growth activation energy coefficient, E2 represents the death activation energy coefficient, X represents the initial scale, u d The abnormal mortality of Enteromorpha ; According to the positioning information in the distribution information of the enteromorpha and the wind direction information in the meteorological environment data, using a drift model, predicting the position information of the enteromorpha in the enteromorpha dynamics; The drift model is expressed using the following formula: Where D(t) represents the position of Enteromorpha at time t, D0 represents the initial positioning information of Enteromorpha, and v cx and v cy are the velocity components of the ocean current in the east-west and north-south directions, V w represents wind speed and θ w Indicates wind direction, measured clockwise from due north. is the drift velocity vector caused by the ocean current, is the wind-induced drift velocity vector.

2. The method according to claim 1, characterized in that The data categories include: spatial data, real-time dynamic data, monitoring data, meteorological environment data, and personnel and management data; The spatial data includes: pre-salvage spatial data and basic geographic data; The real-time dynamic data includes: ship dynamic information AIS data, on-site salvage data and on-site supervision data; The monitoring data include: multi-method enteromorpha monitoring data and enteromorpha distribution and drift data; The meteorological environment data include: marine meteorological environment observation and forecast data; The personnel and management data include: personnel information and breeding area prevention and control supervision data.

3. The method according to claim 2, characterized in that Using the standardized data set, parsing and reorganizing the multi-source heterogeneous information to obtain standardized information includes: Performing data cleaning on the multi-source heterogeneous information to obtain cleaned information; Unifying the format of the cleaned information according to a preset standardized data set to obtain information in a unified format; Performing data conversion on the information after the format is unified, converting the unstructured data into structured data, and obtaining the information after the data conversion; The information after the data conversion is subjected to numerical standardization processing to obtain standardized information.

4. The method according to claim 3, characterized in that Performing feature extraction on the second information to obtain the distribution information of Enteromorpha includes: Cropping the remote sensing image in the second information into a fixed size and performing data enhancement; Use convolutional neural networks for feature extraction; The convolutional layers of the convolutional neural network are used to capture local patterns in remote sensing images; The pooling layer of the convolutional neural network is used to reduce the size of the feature map; The fully connected layer of the convolutional neural network is used to connect the output of the convolutional layer to perform classification or regression to obtain extracted features; The extracted features are used to classify or locate the area covered by Enteromorpha.

5. The method according to claim 4, characterized in that The preset hybrid storage strategy and data automatic warehousing mechanism for storing the standardized information include: Establishing a database and a file system, wherein the database includes a Enteromorpha monitoring database, a prevention and control supervision database, a ship information database, a personnel information database and a salvage supervision database, and the file system includes a salvage supervision file system; storing the structured data in the fused information in a database, and storing the unstructured data in the fused information in a file system; The database is set to select a relational database; The data automatic warehousing mechanism is set as an ETL process, and uses Kafka message queue technology to buffer real-time data streams.

6. The method according to claim 5, characterized in that The preset hybrid storage strategy includes: The metadata of the unstructured data is stored in the database, and the actual files of the unstructured data are stored in the file system, and the actual locations in the file system are pointed to by the links in the database; Preset data access frequency thresholds and use cache technology to speed up access to frequently accessed database records or files; According to the data access frequency threshold, the storage medium is divided into different storage levels.

7. A Enteromorpha data fusion processing system, characterized in that: include: Acquisition module: Acquisition of multi-source heterogeneous information of Enteromorpha; Preset module: preset a standardized data set, wherein the standardized data set includes a data category and a data format; Parsing and reorganization module: using the standardized data set, performing data parsing and reorganization on the multi-source heterogeneous information to obtain standardized information; Fusion module: using a preset fusion algorithm to fuse the standardized information to obtain fused information; Storage module: uses a preset hybrid storage strategy and data automatic warehousing mechanism to store the standardized information; The standardized information is fused by using the fusion algorithm to obtain the fused information, which includes: Performing time-space registration on the standardized information, matching the time series data of the standardized information with the spatial data, and obtaining time-space matched information; Setting corresponding weights for the information after the time-space matching according to data categories to obtain first information; For the first information, using a Bayesian network to represent the dependency relationship between the data categories, to obtain second information; performing feature extraction on the second information to obtain distribution information of Enteromorpha; The distribution information of Enteromorpha is integrated with the meteorological environment data to predict the dynamics of Enteromorpha; The distribution information of Enteromorpha is integrated with the meteorological environment data to predict the dynamics of Enteromorpha, including: According to the scale information in the distribution information of the enteromorpha and the light and temperature in the meteorological environment data, using a growth model, predicting the enteromorpha growth information in the enteromorpha dynamics; The growth model is expressed using the following formula: Among them, N(t) represents the growth information of Enteromorpha in the predicted Enteromorpha dynamics, represents the scale of Enteromorpha at a specific time t, and u max represents the maximum growth rate of Enteromorpha, I represents the light intensity, k s represents the light saturation coefficient of Enteromorpha, r represents the growth rate corresponding to the light intensity I, t represents time, T represents temperature, A and B represent the adjustment coefficients of growth rate and death rate at temperature T, E1 represents the growth activation energy coefficient, E2 represents the death activation energy coefficient, X represents the initial scale, u d The abnormal mortality of Enteromorpha ; According to the positioning information in the distribution information of the enteromorpha and the wind direction information in the meteorological environment data, using a drift model, predicting the position information of the enteromorpha in the enteromorpha dynamics; The drift model is expressed using the following formula: Where D(t) represents the position of Enteromorpha at time t, D0 represents the initial positioning information of Enteromorpha, and v cx and v cy are the velocity components of the ocean current in the east-west and north-south directions, V w represents wind speed and θ w Indicates wind direction, measured clockwise from due north. is the drift velocity vector caused by the ocean current, is the wind-induced drift velocity vector.

Images