A method and system for analyzing aquatic biological resources based on big data

Abstract

This invention relates to the field of aquatic organism management technology, specifically disclosing a method and system for aquatic biological resource analysis based on big data. This invention involves planning multiple monitoring points for interconnected monitoring; performing data cleaning and standardization; calculating and statistically analyzing relatively important indicators; conducting comparative analysis of ecological health based on big data technology; and interactively displaying relatively important information and ecological health information. It enables the planning of multiple monitoring points for interconnected monitoring of aquatic organisms, calculation and statistical analysis of relatively important indicators, comparative analysis of ecological health, and interactive display of relatively important information and ecological health information. This allows for high-precision and diverse sampling, effectively and accurately acquiring basic data, improving the comprehensiveness and accuracy of resource analysis, fully reflecting the ecological health characteristics of aquatic ecosystems, and providing a foundation for accurately assessing the potential for sustainable resource utilization.

Description

Technical Field

[0001] This invention belongs to the field of aquatic organism management technology, and in particular relates to a method and system for aquatic biological resource analysis based on big data. Background Technology

[0002] Aquatic life management is the systematic management of biological resources and their ecological environment in aquatic bodies (such as rivers, lakes, reservoirs, and oceans) through scientific planning, monitoring, protection, regulation, and rational utilization. Its core objective is to maintain the balance and health of aquatic ecosystems, protect biodiversity, and promote the sustainable use of water resources.

[0003] Aquatic biological resource analysis is one of the most common applications in aquatic biological management.

[0004] In existing technologies, the analysis of aquatic organism resources is hampered by insufficient sampling precision and limited monitoring methods, making it difficult to obtain basic data effectively and accurately. This can lead to incomplete and inaccurate resource analysis, failing to fully reflect the ecological health characteristics of aquatic ecosystems and making it difficult to accurately assess the potential for sustainable resource utilization. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for analyzing aquatic biological resources based on big data, aiming to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] A method for analyzing aquatic biological resources based on big data, the method specifically includes the following steps:

[0008] Acquire basic information about the water area and plan multiple monitoring points. Conduct interconnected monitoring of aquatic organisms at the multiple monitoring points to obtain aquatic monitoring data.

[0009] The aquatic monitoring data is cleaned and standardized to generate standard monitoring data;

[0010] From the standard monitoring data, relevant data of the indicators are extracted, and based on the relevant data of the indicators, the relatively important indicators are calculated and statistically analyzed to generate relatively important information;

[0011] Based on big data technology, the standard monitoring data is compared and analyzed for ecological health to generate ecological health information;

[0012] The relatively important information and the ecological health information are displayed interactively.

[0013] A big data-based aquatic biological resource analysis system includes a point-to-point interconnected monitoring unit, a data standard processing unit, a key indicator calculation unit, a data comparison and analysis unit, and an information interaction and display unit, wherein:

[0014] The interconnected monitoring unit is used to acquire basic information about the water area and plan multiple monitoring points. At these multiple monitoring points, interconnected monitoring of aquatic organisms is carried out to acquire aquatic monitoring data.

[0015] The data standard processing unit is used to perform data cleaning and standardization processing on the aquatic monitoring data to generate standard monitoring data.

[0016] The important indicator calculation unit is used to extract indicator-related data from the standard monitoring data, and to calculate and statistically analyze the relatively important indicators based on the indicator-related data to generate relatively important information.

[0017] The data comparison and analysis unit is used to perform ecological health comparison and analysis on the standard monitoring data based on big data technology, and generate ecological health information;

[0018] The information interaction and display unit is used to interactively display the relatively important information and the ecological health information.

[0019] Compared with the prior art, the beneficial effects of the present invention are:

[0020] This invention, through the planning of multiple monitoring points for interconnected monitoring, data cleaning and standardization, calculation and statistics of relatively important indicators, comparative analysis of ecological health based on big data technology, and interactive display of relatively important information and ecological health information, enables the planning of multiple monitoring points for interconnected monitoring of aquatic organisms, calculation and statistics of relatively important indicators, comparative analysis of ecological health, and interactive display of relatively important information and ecological health information. It achieves high-precision and diverse sampling, thereby effectively and accurately acquiring basic data, improving the comprehensiveness and accuracy of resource analysis, fully reflecting the ecological health characteristics of aquatic ecosystems, and providing a foundation for accurately assessing the potential for sustainable resource utilization. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention.

[0022] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0023] Figure 2A flowchart illustrating the planning of multiple monitoring points in the method provided by an embodiment of the present invention is shown.

[0024] Figure 3 A flowchart of interconnected monitoring of aquatic organisms in the method provided by an embodiment of the present invention is shown.

[0025] Figure 4 A flowchart of data cleaning and standardization in the method provided by an embodiment of the present invention is shown.

[0026] Figure 5 A flowchart illustrating the calculation and statistics of relatively important indicators in the method provided by the embodiments of the present invention is shown.

[0027] Figure 6 A flowchart illustrating the comparative analysis of ecological health in the method provided by an embodiment of the present invention is shown.

[0028] Figure 7 A flowchart illustrating the information interaction display method provided in the embodiments of the present invention is shown.

[0029] Figure 8 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0030] Figure 9 The diagram shows the structural block diagram of the important indicator calculation unit in the system provided by the embodiment of the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0032] Understandably, aquatic biological resource analysis is one of the most common applications in aquatic life management. However, current technologies for aquatic biological resource analysis suffer from insufficient sampling precision and limited monitoring methods, making it difficult to obtain basic data effectively and accurately. This often leads to incomplete and inaccurate resource analysis, failing to fully reflect the ecological health characteristics of aquatic ecosystems and making it difficult to accurately assess the potential for sustainable resource utilization.

[0033] To address the aforementioned issues, this invention acquires basic water area information and plans multiple monitoring points. At these points, interconnected monitoring of aquatic organisms is conducted to obtain aquatic monitoring data. This data is then cleaned and standardized to generate standard monitoring data. From this standard data, relevant indicator data is extracted, and based on this data, the relative importance of indicators is calculated and statistically analyzed to generate relative importance information. Using big data technology, a comparative analysis of the ecological health of the standard monitoring data is performed to generate ecological health information. Finally, the relative importance information and ecological health information are interactively displayed. This approach allows for the planning of multiple monitoring points, interconnected monitoring of aquatic organisms, calculation and statistical analysis of relative importance indicators, comparative analysis of ecological health, and interactive display of relative importance and ecological health information. It enables high-precision and diverse sampling, thereby effectively and accurately acquiring basic data, improving the comprehensiveness and accuracy of resource analysis, fully reflecting the ecological health characteristics of the aquatic ecosystem, and providing a foundation for accurately assessing the potential for sustainable resource utilization.

[0034] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0035] Specifically, a method for analyzing aquatic biological resources based on big data includes the following steps:

[0036] Step S101: Obtain basic information about the water area and plan multiple monitoring points. Conduct interconnected monitoring of aquatic organisms at the multiple monitoring points to obtain aquatic monitoring data.

[0037] In this embodiment of the invention, basic water area information is acquired, and an electronic map of the water area is extracted from the basic water area information. Monitoring planning is carried out based on the electronic map of the water area to determine multiple monitoring points. Monitoring instructions are generated and sent to multiple monitoring points. Multiple direct monitoring data are received. By identifying and analyzing the sending addresses of multiple direct monitoring data, multiple feedback points corresponding to the sending of direct monitoring data are determined. Monitoring points without feedback are marked as abnormal points, thereby dividing multiple monitoring points into multiple feedback points and multiple abnormal points. According to preset point interconnection information, auxiliary points corresponding to multiple abnormal points are selected from multiple feedback points (multiple auxiliary points are interconnected with multiple corresponding feedback points through wired communication or other communication methods). Then, through multiple auxiliary points, indirect monitoring data of multiple abnormal points are obtained. Multiple direct monitoring data and multiple indirect monitoring data are comprehensively sorted to obtain aquatic monitoring data, which includes water quality data, fish data, plankton data, and benthic animal data.

[0038] Understandably, water quality data can be monitored and collected through satellite remote sensing, drone inspections, and other methods; fish data can be monitored and collected through sonar detection, electronic tag identification, and other methods; plankton data can be monitored and collected through microscopic examination, flow cytometry, and other methods; and benthic animal data can be monitored and collected through bottom sediment sampling, sediment analysis, and other methods.

[0039] Specifically, Figure 2 A flowchart illustrating the planning of multiple monitoring points in the method provided by an embodiment of the present invention is shown.

[0040] In a preferred embodiment of the present invention, the steps of acquiring basic water area information, planning multiple monitoring points, and conducting interconnected monitoring of aquatic organisms at the multiple monitoring points to acquire aquatic monitoring data specifically include the following steps:

[0041] Step S1011: Obtain basic water area information;

[0042] Step S1012: Extract the electronic map of the water area from the basic water area information;

[0043] Step S1013: Based on the electronic map of the water area, plan multiple monitoring points;

[0044] Step S1014: Conduct interconnected monitoring of aquatic organisms at multiple monitoring points to obtain aquatic monitoring data, including water quality data, fish data, plankton data, and benthic animal data.

[0045] In a preferred embodiment of the present invention, the step of planning multiple monitoring points based on the electronic map of the water area specifically includes the following steps:

[0046] Electronic map data is extracted from basic water area information, and the number of monitoring points to be planned is determined based on project monitoring needs and resource constraints.

[0047] Based on the planned number of monitoring points and the suitable environmental areas in the electronic map, candidate areas that meet the installation and monitoring conditions are selected.

[0048] Based on water quality sensitive areas, fish habitat distribution, and biodiversity hotspots, the coverage utility of each potential monitoring point in the candidate area is evaluated to obtain the candidate points and the corresponding coverage utility value for each candidate point;

[0049] Calculate the construction and maintenance costs of each candidate site to obtain the monitoring cost of each candidate site;

[0050] Calculate the spatial distances between all candidate points and generate a distance matrix;

[0051] Based on specific monitoring objectives and resource budgets, set coverage utility weight and cost weight parameters;

[0052] A multi-objective optimization model is constructed based on the coverage utility value corresponding to each candidate point, the monitoring cost of each candidate point, the distance matrix, and the coverage utility weight and cost weight parameters.

[0053] To maximize overall coverage effectiveness while satisfying the constraints of the number and distance of monitoring points, and with the lowest total monitoring cost as the optimization objective, an optimization algorithm is used to solve the multi-objective optimization model, resulting in a set of monitoring points that meet the constraints and achieve a balance between coverage and cost.

[0054] In the above scheme, this invention introduces two major indicators—coverage utility and monitoring cost—and balances them using weighted parameters, achieving multi-objective optimization of monitoring point planning. Compared to methods that solely pursue coverage rate or cost minimization, this approach better aligns with the comprehensive requirements of actual projects regarding effectiveness and budget. Furthermore, the planning process fully considers the minimum distance constraint between points, effectively avoiding data redundancy and coverage gaps caused by overly concentrated monitoring points, ensuring uniform spatial distribution, and improving the representativeness and accuracy of monitoring data. To ensure transparency and standardization in the planning process and avoid subjective judgment, the complex ecological environment and economic factors are quantified into calculable indicators by calculating the coverage utility and monitoring cost of each candidate point, providing a quantitative basis for the optimization model.

[0055] Specifically, Figure 3 A flowchart of interconnected monitoring of aquatic organisms in the method provided by an embodiment of the present invention is shown.

[0056] In a preferred embodiment of the present invention, the interconnected monitoring of aquatic organisms at multiple monitoring points to obtain aquatic monitoring data specifically includes the following steps:

[0057] Step S10141: Generate and send monitoring instructions to multiple monitoring points;

[0058] Step S10142: Receive multiple direct monitoring data;

[0059] Step S10143: Analyze the multiple direct monitoring data and divide the multiple monitoring points into multiple feedback points and multiple abnormal points;

[0060] Step S10144: Based on the preset interconnection information, select auxiliary points corresponding to multiple abnormal points from multiple feedback points;

[0061] Step S10145: Using multiple auxiliary points, indirectly monitor data of multiple abnormal points is obtained.

[0062] Step S10146: The multiple direct monitoring data and multiple indirect monitoring data are comprehensively processed to obtain aquatic monitoring data.

[0063] In a preferred embodiment of the present invention, the step of analyzing the multiple direct monitoring data and dividing the multiple monitoring points into multiple feedback points and multiple abnormal points specifically includes the following steps:

[0064] Step S101431: Obtain direct monitoring data from multiple monitoring points;

[0065] Step S101432: Calculate the mean vector of direct monitoring data from all locations to quantify the statistical relationship between monitoring indicators and obtain the mean level of all monitoring indicators.

[0066] Step S101433: Calculate the degree of deviation between the direct monitoring data of each monitoring point and the mean level of all monitoring indicators to obtain the individual abnormality score corresponding to each monitoring point.

[0067] Step S101434: Based on the actual geographic spatial location of the monitoring points, construct an adjacency relationship network between the points, and form an adjacency matrix by calculating the spatial proximity between the points and normalizing it to obtain a normalized spatial adjacency weight matrix between the points.

[0068] Step S101435: Use the normalized spatial adjacency weight matrix between monitoring points to perform weighted correction on the individual anomaly score corresponding to each monitoring point, and obtain the comprehensive anomaly score of each monitoring point.

[0069] Step S101436: Divide the direct monitoring data into different ecological categories to obtain monitoring data for different ecological categories. Repeat steps S101431 to S101435 with the monitoring data of different ecological categories as input to obtain the comprehensive anomaly score of different categories. Given the ecological category weight, the comprehensive anomaly scores of different categories are weighted and combined using the ecological category weight to obtain the final anomaly score with ecological category weight adjustment.

[0070] In the above scheme, this invention establishes a global data distribution benchmark by calculating the overall mean and covariance, and then determines the degree of anomaly at individual points. This ensures that anomaly detection considers both the overall ecological environment and individual differences, balancing global and local information. Furthermore, it introduces spatial adjacency relationships, incorporating the geographical and ecological spatial connections between points into the anomaly scoring calculation. Through weighted anomalous propagation from neighboring areas, it reflects the spatial correlation within the ecosystem, avoiding isolated judgments and more closely reflecting the actual situation of aquatic ecosystems. Different ecological categories have varying impacts on aquatic health. This invention fully utilizes data from multiple ecological categories, such as water quality, fish, plankton, and benthic animals, avoiding the bias caused by single indicators. Through joint analysis of multidimensional data, it improves the accuracy of anomaly detection.

[0071] Furthermore, the big data-based aquatic biological resource analysis method also includes the following steps:

[0072] Step S102: Perform data cleaning and standardization on the aquatic monitoring data to generate standard monitoring data.

[0073] In this embodiment of the invention, abnormal monitoring data is identified and removed from aquatic monitoring data to generate normal monitoring data. Then, missing data is identified and supplemented from the normal monitoring data to generate supplementary monitoring data. Multiple standardized features are determined, and then the supplementary monitoring data is standardized according to the multiple standardized features to generate standard monitoring data. Specifically, the multiple standardized features may be time, spatial coordinates, etc.

[0074] Specifically, Figure 4 A flowchart of data cleaning and standardization in the method provided by an embodiment of the present invention is shown.

[0075] In a preferred embodiment of the present invention, the step of cleaning and standardizing the aquatic monitoring data to generate standard monitoring data specifically includes the following steps:

[0076] Step S1021: Anomaly identification and removal are performed on the aquatic monitoring data to generate normal monitoring data;

[0077] Step S1022: Identify and supplement missing data in the normal monitoring data to generate supplementary monitoring data;

[0078] Step S1023: Determine multiple standardized features;

[0079] Step S1024: Standardize the supplementary monitoring data according to the multiple standardized features to generate standard monitoring data.

[0080] In a preferred embodiment of the present invention, the step of identifying and supplementing missing data in the normal monitoring data to generate supplementary monitoring data specifically includes the following steps:

[0081] Identify missing data in normal monitoring data, and extract valid observations from the historical and future neighboring time periods of the same ecological category at the corresponding monitoring points based on the monitoring points and time points corresponding to the missing data, forming a time series context dataset of missing values, so as to obtain the time series neighboring data corresponding to the missing values;

[0082] Time series modeling methods are used to learn and fit the time series neighboring data corresponding to the missing values ​​to predict the ecological category value of the missing time point, and the time series predicted value of each missing point is obtained.

[0083] Based on the spatial location information of the monitoring points, the set of spatially adjacent points of the missing points is determined, and the effective observation data of the spatially adjacent points corresponding to the ecological categories at the missing time points are extracted to obtain the observation data of the spatially adjacent points corresponding to the missing points.

[0084] The spatial influence weight of spatially neighboring observation data on missing values ​​is calculated by spatial variogram, and the spatial influence weight is used to spatially weight the predicted values ​​of time series to conform to the spatial distribution characteristics, so as to obtain the missing value estimation results after spatial weight correction.

[0085] Extract observations of other relevant ecological categories besides the ecological category of the missing point at the same time point from the normal monitoring data to obtain the observation data of other ecological categories of the missing point at that time point;

[0086] Based on multivariate statistical analysis, by combining observational data of other ecological categories at the current missing time point with the historical statistical relationships between various ecological categories, we estimate the reasonable value of the missing ecological category and obtain the missing value estimation result of multi-indicator collaborative inference.

[0087] The missing value estimation results of time series forecast, spatially weighted correction, and multi-indicator collaborative inference are weighted and fused to form the final supplementary value of the missing data.

[0088] The final supplementary values ​​of the missing data are filled back into the corresponding missing positions of the normal monitoring data to obtain the supplementary monitoring data.

[0089] In the above scheme, this invention captures continuous temporal trends by predicting historical and future time-point data of missing points. Simultaneously, it introduces spatial variability functions and adjacent point data to weight and correct spatial distribution characteristics, reflecting the spatiotemporal continuity and spatial heterogeneity of the aquatic ecosystem and effectively improving the ecological rationality of the supplementary results. Furthermore, ecological monitoring involves multiple types of indicators, which often exhibit complex correlations and interactions. Therefore, by using multivariate statistical analysis methods to incorporate observational data from other indicators into the missing value estimation, the supplementary results take into account the intrinsic relationships between indicators, improving the comprehensiveness and reliability of the inference.

[0090] In summary, this method not only incorporates time series information but also spatially adjacent data and the correlation between multiple indicators, forming a supplementary model that integrates time, space, and indicators. This model can fully explore the potential correlation features in the data, significantly improve the accuracy of missing data estimation, and avoid the possible biases and distortions of traditional single imputation methods.

[0091] Furthermore, the big data-based aquatic biological resource analysis method also includes the following steps:

[0092] Step S103: Extract indicator-related data from the standard monitoring data, and calculate and statistically analyze the relatively important indicators based on the indicator-related data to generate relatively important information.

[0093] In this embodiment of the invention, multiple fish species are identified by analyzing standard monitoring data. Then, for each fish species, relevant indicator data is extracted from the standard monitoring data. Fish release data and catch data corresponding to the multiple fish species are also obtained. Based on the relevant indicator data, fish release data, and catch data, the relative importance indicators for the multiple fish species are calculated. Finally, these relatively important indicators are statistically analyzed to generate relative importance information. Specifically, the calculation formula for the relative importance indicators of the multiple fish species is as follows:

[0094] ;

[0095] in, Representing the 100 species of fish For the first Relative important indicators for each fish species For the first The proportion of each fish species released. For the first The proportion of catch by each fish species This represents the proportion of monitored quantities.

[0096] Specifically, Figure 5A flowchart illustrating the calculation and statistics of relatively important indicators in the method provided by the embodiments of the present invention is shown.

[0097] In a preferred embodiment of the present invention, the step of extracting indicator-related data from the standard monitoring data, and calculating and statistically analyzing relatively important indicators based on the indicator-related data to generate relatively important information specifically includes the following steps:

[0098] Step S1031: Identify the standard monitoring data to determine multiple fish species;

[0099] Step S1032: Extract indicator-related data from the standard monitoring data according to the multiple fish species;

[0100] Step S1033: Obtain fish release data and catch data for multiple fish species;

[0101] Step S1034: Calculate the relative importance indicators of multiple fish species based on the relevant data of the indicators, the fish release data, and the catch data;

[0102] Step S1035: Statistical analysis is performed on multiple relatively important indicators to generate relatively important information.

[0103] Furthermore, the big data-based aquatic biological resource analysis method also includes the following steps:

[0104] Step S104: Based on big data technology, perform comparative analysis of the ecological health of the standard monitoring data to generate ecological health information.

[0105] In this embodiment of the invention, based on big data technology, the basic information of the water area is matched according to standards to obtain reference biological data. Then, the standard monitoring data is compared with the reference biological data, the comparison results are recorded, and then the ecological health analysis of the water area is performed according to the comparison results to generate ecological health information.

[0106] Specifically, Figure 6 A flowchart illustrating the comparative analysis of ecological health in the method provided by an embodiment of the present invention is shown.

[0107] In a preferred embodiment of the present invention, the step of performing comparative analysis of the standard monitoring data on ecological health based on big data technology to generate ecological health information specifically includes the following steps:

[0108] Step S1041: Based on big data technology, standard matching is performed on the basic information of the water area to obtain reference biological data;

[0109] Step S1042: Compare the standard monitoring data with the reference biological data and record the comparison results;

[0110] Step S1043: Based on the comparison results, perform ecological health analysis and generate ecological health information.

[0111] In a preferred embodiment of the present invention, the step of performing ecological health analysis and generating ecological health information based on the comparison results specifically includes the following steps:

[0112] Environmental impact factors and environmental pressure indicators extracted from basic water area information;

[0113] Based on historical ecological monitoring data and experimental research results, obtain the response parameters of the ecosystem;

[0114] Using environmental impact factors and environmental pressure indicators, the weights of each ecological indicator are dynamically calculated through multi-factor analysis.

[0115] A multi-layer neural network model is used to fuse the time series information of ecological indicators in the standard monitoring data and the weights of ecological indicators in the comparison results. During the fusion process, the spatial distribution characteristics of the monitoring points and the spatial variation of environmental pressure are considered to obtain the fused feature vector.

[0116] Based on the fused feature vector and ecosystem response parameters, an ecosystem dynamic model is established to simulate the trend of ecological indicators changing over time, predict the future state of the ecosystem under continuous environmental pressure, and obtain prediction results.

[0117] The prediction results are classified to obtain health status labels and risk levels;

[0118] The comprehensive ecological health index is calculated by weighting and fusing environmental stress indicators, ecosystem response parameters, the weights of each ecological indicator, the fused feature vector, prediction results, health status labels, and risk levels, thereby generating ecological health information.

[0119] In the above-described scheme, this invention, by fusing time-series and spatial distribution data, can automatically capture the complex nonlinear relationships and potential impact mechanisms among ecological indicators, greatly improving the accuracy and reliability of ecological health status assessment. Furthermore, by simulating and predicting the ecosystem evolution process through an ecological dynamics model, the system can not only assess the current health status but also predict potential risks and recovery trends of the ecosystem under environmental stress. Moreover, by utilizing the comparison results of standard monitoring data and reference biological data, and integrating environmental impact factors, environmental stress indicators, and ecosystem response parameters, it fully leverages multi-dimensional and multi-source ecological and environmental information, avoiding the potential bias of a single data source and improving the comprehensiveness of the analysis.

[0120] Furthermore, the big data-based aquatic biological resource analysis method also includes the following steps:

[0121] Step S105: Interactively display the relatively important information and the ecological health information.

[0122] In this embodiment of the invention, a brief framework information is extracted from relatively important information and ecological health information. Based on the brief framework information, a framework introduction interface is created. The framework introduction interface receives user interaction operations and responds to user interaction operations. Interaction requirement information is extracted from relatively important information and / or ecological health information and interactively displayed.

[0123] Specifically, Figure 7 A flowchart illustrating the information interaction display method provided in the embodiments of the present invention is shown.

[0124] In a preferred embodiment of the present invention, the interactive display of the relatively important information and the ecological health information specifically includes the following steps:

[0125] Step S1051: Extract brief framework information from the relatively important information and the ecological health information;

[0126] Step S1052: Create a framework introduction interface based on the brief framework information;

[0127] Step S1053: Receive user interaction operations in the framework introduction interface;

[0128] Step S1054: Based on the interactive operation, extract the interactive requirement information from the relatively important information and / or the ecological health information and display it interactively.

[0129] Furthermore, Figure 8 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0130] In another preferred embodiment of the present invention, a big data-based aquatic biological resource analysis system includes:

[0131] The interconnected monitoring unit 101 is used to acquire basic information about the water area and plan multiple monitoring points. At the multiple monitoring points, interconnected monitoring of aquatic organisms is carried out to acquire aquatic monitoring data.

[0132] In this embodiment of the invention, the point-to-point interconnection monitoring unit 101 acquires basic water area information, extracts an electronic map of the water area from the basic water area information, performs monitoring planning based on the electronic map of the water area, determines multiple monitoring points, generates monitoring instructions, sends the monitoring instructions to multiple monitoring points, receives multiple direct monitoring data, identifies and analyzes the sending addresses of multiple direct monitoring data, determines multiple feedback points corresponding to the sending of direct monitoring data, and marks monitoring points without feedback as abnormal points, thereby dividing multiple monitoring points into multiple feedback points and multiple abnormal points. According to preset point-to-point interconnection information, it selects auxiliary points corresponding to multiple abnormal points from multiple feedback points (multiple auxiliary points are interconnected with multiple corresponding feedback points through wired communication or other communication methods), and then uses multiple auxiliary points to assist in acquiring indirect monitoring data of multiple abnormal points. It integrates and sorts multiple direct monitoring data and multiple indirect monitoring data to obtain aquatic monitoring data, which includes water quality data, fish data, plankton data, and benthic animal data.

[0133] The data standard processing unit 102 is used to perform data cleaning and standardization processing on the aquatic monitoring data to generate standard monitoring data.

[0134] In this embodiment of the invention, the data standard processing unit 102 generates normal monitoring data by identifying and removing anomalies in aquatic monitoring data, then identifies and supplements missing data in the normal monitoring data to generate supplementary monitoring data, and determines multiple standardized features. Then, according to the multiple standardized features, the supplementary monitoring data is standardized to generate standard monitoring data. Specifically, the multiple standardized features may be time, spatial coordinates, etc.

[0135] The important indicator calculation unit 103 is used to extract indicator-related data from the standard monitoring data, and to calculate and statistically analyze the relatively important indicators based on the indicator-related data to generate relatively important information.

[0136] In this embodiment of the invention, the important indicator calculation unit 103 identifies multiple fish species by analyzing standard monitoring data. Then, according to the multiple fish species, it extracts indicator-related data from the standard monitoring data and obtains fish release data and catch data corresponding to the multiple fish species. Based on the indicator-related data, fish release data, and catch data, it calculates the relative importance indicators for the multiple fish species. Finally, it statistically organizes the multiple relatively important indicators to generate relative importance information. Specifically, the calculation formula for the relative importance indicators of the multiple fish species is as follows:

[0137] ;

[0138] in, Representing the 100 species of fish For the first Relative important indicators for each fish species For the first The proportion of each fish species released. For the first The proportion of catch by each fish species This represents the proportion of monitored quantities.

[0139] Specifically, Figure 9 The diagram shows the structure of the important indicator calculation unit 103 in the system provided in the embodiment of the present invention.

[0140] In a preferred embodiment provided by the present invention, the important indicator calculation unit 103 specifically includes:

[0141] Data identification module 1031 is used to identify the standard monitoring data and determine multiple fish species;

[0142] Data extraction module 1032 is used to extract indicator-related data from the standard monitoring data according to multiple fish species;

[0143] Data acquisition module 1033 is used to acquire fish release data and catch data of multiple fish species;

[0144] The relative importance indicator calculation module 1034 is used to calculate the relative importance indicators of multiple fish species based on the indicator-related data, the fish release data, and the catch data.

[0145] The relative importance indicator statistics module 1035 is used to perform statistics on multiple relative importance indicators and generate relative importance information.

[0146] Furthermore, the big data-based aquatic biological resource analysis system also includes:

[0147] The data comparison and analysis unit 104 is used to perform ecological health comparison and analysis on the standard monitoring data based on big data technology, and generate ecological health information.

[0148] In this embodiment of the invention, the data comparison and analysis unit 104 uses big data technology to perform standard matching on basic water information, obtain reference biological data, compare the standard monitoring data with the reference biological data, record the comparison results, and then perform ecological health analysis on the water area according to the comparison results to generate ecological health information.

[0149] The information interaction display unit 105 is used to interactively display the relatively important information and the ecological health information.

[0150] In this embodiment of the invention, the information interaction display unit 105 extracts brief framework information from relatively important information and ecological health information, creates a framework introduction interface based on the brief framework information, receives user interaction operations in the framework introduction interface, responds to user interaction operations, extracts interaction requirement information from relatively important information and / or ecological health information, and interactively displays the interaction requirement information.

[0151] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0153] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0154] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0155] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for analyzing aquatic biological resources based on big data, characterized in that, The method specifically includes the following steps: Acquire basic information about the water area and plan multiple monitoring points. Conduct interconnected monitoring of aquatic organisms at the multiple monitoring points to obtain aquatic monitoring data. The aquatic monitoring data is cleaned and standardized to generate standard monitoring data; From the standard monitoring data, relevant data of the indicators are extracted, and based on the relevant data of the indicators, the relatively important indicators are calculated and statistically analyzed to generate relatively important information; The formula for calculating the relatively important indicators is as follows: ； in, Representing the 100 species of fish For the first Relative important indicators for each fish species For the first The proportion of each fish species released. For the first The proportion of catch by each fish species For the proportion of monitored quantities; Based on big data technology, the standard monitoring data is compared and analyzed for ecological health to generate ecological health information; The relatively important information and the ecological health information are displayed interactively; The process of acquiring basic water area information, planning multiple monitoring points, and conducting interconnected monitoring of aquatic organisms at these multiple monitoring points to obtain aquatic monitoring data specifically includes the following steps: Obtain basic information about the water area; Extract the electronic map of the water area from the aforementioned basic water area information; Based on the aforementioned electronic map of the water area, multiple monitoring points were planned; Interconnected monitoring of aquatic organisms is carried out at multiple monitoring points to obtain aquatic monitoring data, including water quality data, fish data, plankton data, and benthic animal data. The interconnected monitoring of aquatic organisms at multiple monitoring points to obtain aquatic monitoring data specifically includes the following steps: Generate and send monitoring commands to multiple monitoring points; Receives multiple direct monitoring data; The multiple direct monitoring data are analyzed, and the multiple monitoring points are divided into multiple feedback points and multiple abnormal points; Based on the preset interconnection information, select auxiliary points corresponding to multiple abnormal points from multiple feedback points; By using multiple auxiliary points, indirect monitoring data of multiple abnormal points can be obtained. Aquatic monitoring data are obtained by comprehensively organizing and processing multiple direct monitoring data and multiple indirect monitoring data. The analysis of multiple direct monitoring data points, dividing the multiple monitoring points into multiple feedback points and multiple abnormal points, specifically includes the following steps: Step S101431: Obtain direct monitoring data from multiple monitoring points; Step S101432: Calculate the mean vector of direct monitoring data from all locations to quantify the statistical relationship between monitoring indicators and obtain the mean level of all monitoring indicators. Step S101433: Calculate the degree of deviation between the direct monitoring data of each monitoring point and the mean level of all monitoring indicators to obtain the individual abnormality score corresponding to each monitoring point. Step S101434: Based on the actual geographic spatial location of the monitoring points, construct an adjacency relationship network between the points, and form an adjacency matrix by calculating the spatial proximity between the points and normalizing it to obtain a normalized spatial adjacency weight matrix between the points. Step S101435: Use the normalized spatial adjacency weight matrix between monitoring points to perform weighted correction on the individual anomaly score corresponding to each monitoring point, and obtain the comprehensive anomaly score of each monitoring point. Step S101436: Divide the direct monitoring data into different ecological categories to obtain monitoring data for different ecological categories. Repeat steps S101431 to S101435 with the monitoring data of different ecological categories as input to obtain the comprehensive anomaly score of different categories. Given the ecological category weight, the comprehensive anomaly scores of different categories are weighted and combined using the ecological category weight to obtain the final anomaly score with ecological category weight adjustment.

2. The aquatic biological resource analysis method based on big data according to claim 1, characterized in that, The planning of multiple monitoring points based on the electronic map of the water area specifically includes the following steps: Electronic map data is extracted from basic water area information, and the number of monitoring points to be planned is determined based on project monitoring needs and resource constraints. Based on the planned number of monitoring points and the suitable environmental areas in the electronic map, candidate areas that meet the installation and monitoring conditions are selected. Based on water quality sensitive areas, fish habitat distribution, and biodiversity hotspots, the coverage utility of each potential monitoring point in the candidate area is evaluated to obtain the candidate points and the corresponding coverage utility value for each candidate point; Calculate the construction and maintenance costs of each candidate site to obtain the monitoring cost of each candidate site; Calculate the spatial distances between all candidate points and generate a distance matrix; Based on specific monitoring objectives and resource budgets, set coverage utility weight and cost weight parameters; A multi-objective optimization model is constructed based on the coverage utility value corresponding to each candidate point, the monitoring cost of each candidate point, the distance matrix, and the coverage utility weight and cost weight parameters. To maximize overall coverage effectiveness while satisfying the constraints of the number and distance of monitoring points, and with the lowest total monitoring cost as the optimization objective, an optimization algorithm is used to solve the multi-objective optimization model, resulting in a set of monitoring points that meet the constraints and achieve a balance between coverage and cost.

3. The aquatic biological resource analysis method based on big data according to claim 2, characterized in that, The process of cleaning and standardizing the aquatic monitoring data to generate standard monitoring data specifically includes the following steps: The aquatic monitoring data is anomaly identified and removed to generate normal monitoring data; The normal monitoring data is identified and supplemented to generate supplementary monitoring data; Determine multiple standardized features; The supplementary monitoring data is standardized according to several of the aforementioned standardized features to generate standard monitoring data.

4. The aquatic biological resource analysis method based on big data according to claim 3, characterized in that, The process of identifying and supplementing missing data in the normal monitoring data to generate supplementary monitoring data specifically includes the following steps: Identify missing data in normal monitoring data, and extract valid observations from the historical and future neighboring time periods of the same ecological category at the corresponding monitoring points based on the monitoring points and time points corresponding to the missing data, forming a time series context dataset of missing values, so as to obtain the time series neighboring data corresponding to the missing values; Time series modeling methods are used to learn and fit the time series neighboring data corresponding to the missing values ​​to predict the ecological category value of the missing time point, and the time series predicted value of each missing point is obtained. Based on the spatial location information of the monitoring points, the set of spatially adjacent points of the missing points is determined, and the effective observation data of the spatially adjacent points corresponding to the ecological categories at the missing time points are extracted to obtain the observation data of the spatially adjacent points corresponding to the missing points. The spatial influence weight of spatially neighboring observation data on missing values ​​is calculated by spatial variogram, and the spatial influence weight is used to spatially weight the predicted values ​​of time series to conform to the spatial distribution characteristics, so as to obtain the missing value estimation results after spatial weight correction. Extract observations from normal monitoring data of other relevant ecological categories besides the ecological category of the missing point at the same time point to obtain observation data of other ecological categories at the current missing time point; Based on multivariate statistical analysis, by combining observational data of other ecological categories at the current missing time point with the historical statistical relationships between various ecological categories, we estimate the reasonable value of the missing ecological category and obtain the missing value estimation result of multi-indicator collaborative inference. The missing value estimation results of time series forecast, spatially weighted correction, and multi-indicator collaborative inference are weighted and fused to form the final supplementary value of the missing data. The final supplementary values ​​of the missing data are filled back into the corresponding missing positions of the normal monitoring data to obtain the supplementary monitoring data.

5. The aquatic biological resource analysis method based on big data according to claim 4, characterized in that, The step of extracting indicator-related data from the standard monitoring data, and calculating and statistically analyzing the relatively important indicators based on the indicator-related data to generate relatively important information specifically includes the following steps: The standard monitoring data was used to identify multiple fish species. According to the various fish species, extract relevant data of the indicators from the standard monitoring data; Acquire fish release data and catch data for multiple fish species; Based on the relevant data of the indicators, the fish release data, and the catch data, calculate the relative importance indicators of multiple fish species; Statistical analysis is performed on multiple relatively important indicators to generate relatively important information.

6. The method for analyzing aquatic biological resources based on big data according to claim 5, characterized in that, The process of generating ecological health information by comparing and analyzing the standard monitoring data based on big data technology includes the following steps: Based on big data technology, standard matching is performed on basic water information to obtain reference biological data; Compare the standard monitoring data with the reference biological data and record the comparison results; Based on the comparison results, an ecological health analysis is performed to generate ecological health information; The step of performing ecological health analysis and generating ecological health information based on the comparison results specifically includes the following steps: Environmental impact factors and environmental pressure indicators extracted from basic water area information; Based on historical ecological monitoring data and experimental research results, obtain the response parameters of the ecosystem; Using environmental impact factors and environmental pressure indicators, the weights of each ecological indicator are dynamically calculated through multi-factor analysis. A multi-layer neural network model is used to fuse the time series information of ecological indicators in the standard monitoring data and the weights of ecological indicators in the comparison results. During the fusion process, the spatial distribution characteristics of the monitoring points and the spatial variation of environmental pressure are considered to obtain the fused feature vector. Based on the fused feature vector and ecosystem response parameters, an ecosystem dynamic model is established to simulate the trend of ecological indicators changing over time, predict the future state of the ecosystem under continuous environmental pressure, and obtain prediction results. The prediction results are classified to obtain health status labels and risk levels; The comprehensive ecological health index is calculated by weighting and fusing environmental stress indicators, ecosystem response parameters, the weights of each ecological indicator, the fused feature vector, prediction results, health status labels, and risk levels, thereby generating ecological health information.

7. The method for analyzing aquatic biological resources based on big data according to claim 6, characterized in that, The interactive display of the relatively important information and the ecological health information specifically includes the following steps: Extract a brief framework from the relatively important information and the ecological health information; Based on the brief framework information, create a framework introduction interface; The framework introduction interface receives user interaction operations; Based on the interactive operation, interactive requirement information is extracted from the relatively important information and / or the ecological health information and then interactively displayed.

8. A big data-based aquatic biological resource analysis system, wherein the system is applied to the big data-based aquatic biological resource analysis method according to any one of claims 1 to 7, characterized in that, The system includes a point-to-point interconnection monitoring unit, a data standard processing unit, a key indicator calculation unit, a data comparison and analysis unit, and an information interaction and display unit, wherein: The interconnected monitoring unit is used to acquire basic information about the water area and plan multiple monitoring points. At these multiple monitoring points, interconnected monitoring of aquatic organisms is carried out to acquire aquatic monitoring data. The data standard processing unit is used to perform data cleaning and standardization processing on the aquatic monitoring data to generate standard monitoring data. The important indicator calculation unit is used to extract indicator-related data from the standard monitoring data, and to calculate and statistically analyze the relatively important indicators based on the indicator-related data to generate relatively important information. The data comparison and analysis unit is used to perform ecological health comparison and analysis on the standard monitoring data based on big data technology, and generate ecological health information; The information interaction and display unit is used to interactively display the relatively important information and the ecological health information.

Images