Intelligent collection method and system for ocean multi-dimensional information and storage medium

Abstract

The invention relates to the technical field of marine environment monitoring, and discloses an intelligent collection method and system for marine multi-dimensional information and a storage medium. The method comprises the following steps: synchronously acquiring environmental parameters at a plurality of measuring points and a depth layer, and constructing a hydrological characteristic data set; calculating spatial correlation and dividing a high variation region and a low variation region; constructing an equipment spacing model based on an information density classification result, and generating a point distribution scheme by adopting an optimization algorithm; combining real-time monitoring data to judge significant changes and dynamically updating layout parameters; and issuing an instruction to the equipment through the main and standby wireless channels to complete deployment. According to the invention, the adaptability and layout efficiency of marine environment perception are improved, and the method is suitable for intelligent monitoring application of complex and changeable sea areas.

Description

Technical Field

[0001] The present invention relates to the technical field of marine environment monitoring and information collection, and specifically to an intelligent collection method, system and storage medium for multi-dimensional marine information based on dynamic analysis of spatial correlation and information density. The invention belongs to the interdisciplinary technical field of marine information perception, environmental monitoring, spatial optimization layout and intelligent communication control. Background Art

[0002] The growing demand for marine resource development, marine disaster warning, and climate change research has placed higher demands on the real-time, accurate collection of multidimensional information about the marine environment. Traditional oceanographic information collection relies primarily on fixed measurement equipment, deployed vessels, or remote sensing systems, primarily collecting hydrological parameters such as temperature, salinity, current velocity, and water depth. While these methods have played an important role in basic ocean observations, they have gradually exposed problems such as rigid deployment, insufficient sampling resolution, and delayed response in large-scale, multi-dimensional, and high-frequency dynamic monitoring.

[0003] In recent years, with the advancement of wireless communications, spatial data modeling, and optimization algorithms, academic and engineering communities have attempted to incorporate technologies such as sensor networks, adaptive control, and machine learning into marine environmental monitoring systems. One strand of research focuses on improving data acquisition frequency and node deployment flexibility, such as dynamic node placement methods based on mobile observation platforms (such as AUVs and buoys). Another strand of research focuses on establishing spatial optimization models, attempting to identify key areas and implement precise node placement using methods such as information entropy, kriging interpolation, and autocorrelation coefficients.

[0004] However, there is currently a lack of a complete methodology that can simultaneously consider spatial correlation analysis, information density modeling, and resource optimization. Existing systems often have the following major technical problems: 1. The deployment plan is static and generalized: The collection points are often divided based on experience or rules, which makes it difficult to adapt to the characteristics of the ocean hydrological environment that change dramatically over time and space. This leads to insufficient monitoring in key areas and waste of resources in redundant areas. 2. Lack of dynamic adaptive adjustment mechanism: Most existing deployments are one-time deployments, lacking the ability to update and optimize based on real-time data feedback; Large number of devices and low deployment efficiency: To ensure both coverage accuracy and monitoring range, a large number of data collection nodes are often required, increasing deployment costs and system maintenance pressure. 4. Separation of acquisition control and communication systems, lack of intelligent linkage: Existing solutions mostly rely on manual intervention and adjustment, making it difficult to achieve real-time response and closed-loop control.

[0005] Therefore, there is an urgent need for a dynamic optimization deployment technology solution based on real-time data-driven technology, which can combine key environmental characteristics such as spatial correlation and information density distribution to adaptively adjust the deployment mode of collection equipment, so as to reduce the number of equipment, improve deployment efficiency and system intelligence level while ensuring monitoring accuracy. This is the core technical problem that the present invention intends to solve. Summary of the Invention

[0006] To address the problems of existing ocean information collection methods, such as strong point rigidity, lack of dynamic adaptability, and low deployment efficiency, the present invention provides an intelligent collection method, system, and storage medium for multi-dimensional ocean information. These methods, combined with the spatial variation characteristics and information density differences of the ocean environment, enable intelligent optimization and dynamic adjustment of equipment deployment while ensuring monitoring accuracy.

[0007] In a first aspect, the present invention provides a method for intelligently collecting multi-dimensional ocean information, the method comprising the following steps: S1. Synchronously collect environmental parameters at multiple measuring points and multiple depth layers in the sea area, including temperature, salinity, current velocity, and water depth, to form a hydrological characteristic dataset with time series and spatial coordinates; S2. Based on the hydrological characteristic data set, calculate the spatial autocorrelation coefficient between each measuring point and generate a spatial correlation matrix using a spatial interpolation algorithm; S3. Dividing the sea area into high-variability areas and low-variability areas based on the spatial correlation matrix; S4, calculating the information density index of the high-variability region and the low-variability region, and classifying them into information-intensive regions and information-sparse regions; S5. Build an inverse proportional relationship model between device spacing and information density, and set smaller device spacing for high-variability and information-dense areas; S6. Use optimization algorithms to optimize the number of devices and layout coordinates while meeting monitoring coverage requirements and generate a layout plan; S7. Acquire real-time marine environment monitoring data. If significant changes in hydrological characteristics are detected, recalculate the device spacing and update the deployment plan. S8. Send updated working parameters and position instructions to the acquisition equipment through the wireless communication system to complete the dynamic optimization layout.

[0008] In combination with the first aspect, in a first implementation of the first aspect of the present application, S1 includes a data anomaly detection mechanism. When a parameter of a certain measuring point continuously exceeds a preset threshold in a time or depth dimension, high-frequency sampling of the measuring point is triggered, and the sampling results are used to update the hydrological characteristic dataset; In S2, the spatial correlation calculation uses the Moran index or the Geary-C index as an evaluation method to measure the degree of synchronous change of hydrological parameters between adjacent measuring points; The spatial interpolation algorithm is the Kriging interpolation method, which performs local smoothing in areas with large parameter gradient changes. Based on the known parameter values ​​of the measuring points and their spatial coordinates, the Kriging interpolation method is used to interpolate and estimate the unmeasured areas. The Kriging interpolation method calculates the predicted values ​​of the hydrological parameters at the target location based on the known measuring point weights and spatial variation function, realizing the spatial reconstruction of the parameter field.

[0009] In combination with the first aspect, in a second implementation of the first aspect of the present application, in S4, based on the division results of the high-variability area and the low-variability area, a two-dimensional grid structure covering the entire monitored sea area is constructed, each grid cell is used as a calculation unit, hydrological parameter data in any grid cell is extracted, the statistical characteristics of the hydrological parameter data are used as input, and an information entropy calculation method is used to evaluate the data distribution uncertainty of any of the grid cells, and the data distribution uncertainty is used as an information density indicator of any of the grid cells; Clustering algorithms are used to cluster all information density indicators. Based on the clustering results, all grid cells are divided into different information density categories to obtain preliminary classification results. The information density index difference and category consistency relationship between each grid unit and multiple directly adjacent grid units are detected. If the information density index of any grid unit is close to that of any adjacent grid unit but the category is inconsistent, the grid unit is reclassified and merged into the main category of the adjacent grid unit.

[0010] In combination with the first aspect, in the third implementation method of the first aspect of the present application, in S5, the inverse proportional relationship model between the device spacing and the information density satisfies d = k / ρ, wherein d is the device spacing, ρ is the information density index, and k is a proportional constant set according to the target coverage.

[0011] In combination with the first aspect, in the fourth implementation method of the first aspect of the present application, the high-variability and information-intensive areas are identified, and the corresponding device spacing is compared with the preset minimum layout spacing threshold. If the device spacing is less than the minimum layout spacing threshold, the parameter optimization mechanism is triggered, and the current information density index value is used as input to automatically iteratively update the proportional constant of the inverse proportional relationship model.

[0012] In combination with the first aspect, in a fifth implementation of the first aspect of the present application, in S6, the sea area division result, the device spacing parameter, the information density weight, and the boundary constraint condition are input into the optimization algorithm, and the coordinate set corresponding to the minimum number of devices is searched in the deployment space, specifically including: A genetic algorithm is used as a global search tool to generate multiple layout combination schemes by initializing the population. The fitness of each scheme is evaluated based on the total number of devices, coverage area integrity, spacing rationality, and connectivity as evaluation dimensions. The layout combination with the least number of devices and the best coverage is selected. Based on the layout combination, the layout structure is continuously iteratively evolved through crossover and mutation operations, and the local optimal solution is dynamically updated in each round of iteration until the global optimal solution is reached or the convergence condition is met, and the final solution output is used as the layout solution.

[0013] In conjunction with the first aspect, in a sixth implementation of the first aspect of the present application, in S7, any hydrological parameter is extracted, its time series data is obtained, a parameter change trend for the current period and multiple historical change trends are extracted using a sliding window mechanism, a change threshold is generated based on the average and standard deviation of the multiple historical change trends, and if the parameter change trend exceeds the change threshold, it is determined that the hydrological characteristics have changed significantly; If the monitoring data of any area show significant changes in hydrological characteristics over multiple consecutive periods, the area will be marked as a highly dynamic state; A priority parameter is assigned to each region based on its environmental sensitivity, hydrological change frequency, and monitoring target weight, and a release point update process is triggered for highly dynamic regions where the priority parameter is greater than a preset value.

[0014] In combination with the first aspect, in the seventh implementation method of the first aspect of the present application, in S8, the wireless communication system includes a main communication channel and a backup communication channel. If the main communication channel fails to send parameters, it automatically switches to the backup communication channel for retransmission until the device confirms successful reception.

[0015] In a second aspect, the present application provides an intelligent collection system for multi-dimensional ocean information, the system comprising: Hydrological sensor network module, used to collect hydrological parameters at multiple depth layers and perform anomaly detection and data update; Data processing and analysis module, used to construct hydrological characteristic datasets, generate spatial correlation matrices and information density classification maps; The layout optimization module is used to output the optimal equipment layout plan based on the inverse proportional relationship model and optimization algorithm; Real-time monitoring and adaptive update module, used to analyze hydrological trends and dynamically trigger point updates; The communication management module is used to send updated parameters and location information to the acquisition device and complete the receipt confirmation.

[0016] A third aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned method for intelligently collecting multi-dimensional ocean information.

[0017] Compared with the prior art, the beneficial effects of the technical solution of this application are at least as follows: 1. Dynamic and adaptive point distribution to improve monitoring accuracy and response capability: Based on the real-time changes in spatial autocorrelation and information density, this invention constructs a spatial characteristic model of the marine environment, so that the collection points can be flexibly adjusted according to changes in sea conditions, significantly improving the monitoring coverage capability of key areas and the overall response capability of the system.

[0018] 2. Optimize the configuration of equipment resources and reduce deployment costs: By establishing an inversely proportional relationship model between device spacing and information density, and combining it with an optimization algorithm to control the number and location of points, the total number of collection devices is reduced while ensuring coverage, thereby reducing equipment investment, operation and maintenance costs, and energy consumption.

[0019] 3. Intelligent collection strategy to achieve closed-loop control throughout the entire life cycle: Combining real-time data monitoring and anomaly identification mechanisms, the present invention can automatically trigger the update of the configuration plan and parameter reconfiguration, and achieve remote dynamic control of the collection nodes with the help of the communication system, thereby improving the intelligence level and operational stability of the entire system.

[0020] 4. Versatility and scalability: The proposed technical framework has good versatility and can be used for fixed platforms and buoy systems, as well as for the deployment planning of mobile platforms such as AUVs. It has the ability to be expanded to multiple types of ocean monitoring systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of a method for intelligently collecting multi-dimensional ocean information according to the present invention;

[0022] Figure 2 This is a schematic diagram of an intelligent collection system for multi-dimensional ocean information according to the present invention. DETAILED DESCRIPTION

[0023] The specific implementation methods of the present invention are described in detail below with reference to the accompanying drawings and examples. However, it should be understood by those skilled in the art that these examples are only used to illustrate the present invention and do not constitute a limitation on the scope of protection of the present invention.

[0024] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1In this embodiment, a method for intelligently collecting multi-dimensional ocean information may specifically include: Step S1: synchronously collect environmental parameters at multiple measuring points and multiple depth layers in the sea area, wherein the environmental parameters include temperature, salinity, flow velocity and water depth, to form a hydrological characteristic data set with time series and spatial coordinates.

[0025] In a specific embodiment, S1 includes a data anomaly detection mechanism. When a parameter of a measuring point continuously exceeds a preset threshold in the time or depth dimension, high-frequency sampling of the measuring point is triggered, and the sampling results are used to update the hydrological characteristic dataset.

[0026] Specifically, in one embodiment of the present invention, a sensor network is deployed at multiple measurement points and depths in the ocean. Each node is used to synchronously collect environmental parameters such as temperature, salinity, current velocity, and water depth. The collected data is recorded in a time series format with accompanying three-dimensional spatial coordinate information, forming a structured hydrological characteristic dataset. Each data record contains a measurement point number, spatial location, timestamp, and corresponding parameter value.

[0027] The hydrological characteristic dataset is dynamically updated based on a pre-set anomaly detection mechanism. The system establishes a judgment logic based on time-varying trends and depth differences for the various parameters collected, and sets a preset anomaly threshold. When it is detected that the environmental parameters of a certain measuring point continuously exceed the threshold in a time series, or when the parameter difference between the depth layer where it is located and the adjacent depth layer at the same time point exceeds the set threshold, the system determines that the measuring point is in an abnormal state. When the trigger condition is met, the control module adjusts the sampling frequency of the measuring point, performs high-frequency sampling, and obtains multiple sets of continuous data within its short period.

[0028] The newly triggered data is merged with the original dataset to form an updated dataset containing data from the anomaly phase. This updated dataset is directly used by the spatial correlation calculation module and the interpolation processing module to improve the accuracy of determining the continuity of anomaly regions in the spatial model. A closed-loop control link is formed between the anomaly detection module and the sampling control module, enabling adaptive adjustments to sampling behavior based on dynamic data changes.

[0029] In this implementation, the anomaly detection mechanism and high-frequency sampling strategy functionally form an integrated data feedback control mechanism within the hydrological data acquisition system. This mechanism dynamically adjusts the sampling frequency of target measurement points by identifying data changes, enabling the system to prioritize sampling accuracy and temporal density in areas of high variation under resource-constrained conditions. The high-frequency data sampling results support subsequent site optimization and information density modeling, forming a core approach to addressing insufficient monitoring and data asymmetry in key areas.

[0030] Step S2: Based on the hydrological characteristic data set, the spatial autocorrelation coefficient between each measuring point is calculated, and a spatial correlation matrix is ​​generated using a spatial interpolation algorithm.

[0031] In a specific embodiment, in S2, the spatial correlation calculation uses the Moran index or the Geary-C index as an evaluation method to measure the degree of synchronous change of hydrological parameters between adjacent measuring points; The spatial interpolation algorithm is the Kriging interpolation method, which performs local smoothing in areas with large parameter gradient changes. Based on the known parameter values ​​of the measuring points and their spatial coordinates, the Kriging interpolation method is used to interpolate and estimate the unmeasured areas. The Kriging interpolation method calculates the predicted values ​​of the hydrological parameters at the target location based on the known measuring point weights and spatial variation function, realizing the spatial reconstruction of the parameter field.

[0032] Specifically, based on the constructed hydrological characteristic dataset, the spatial structural relationship between each measuring point is analyzed and processed to obtain a spatial correlation matrix that reflects the continuity of hydrological parameters in the sea area and the variability of the regional environment. The hydrological characteristic dataset is a structured data set that contains parameter values ​​such as temperature, salinity, flow rate, water depth, etc. at multiple measuring points at different time and depth positions, and is accompanied by corresponding timestamps and spatial coordinates. The system extracts data fields with spatial correlation attributes from the dataset and calculates spatial autocorrelation based on the geographical location relationship between the measuring points and the trend of parameter value changes. Spatial autocorrelation calculation uses the Moran index or the Geary-C index as an evaluation method to measure the degree of synchronous change of hydrological parameters between adjacent measuring points. The Moran index is used to reflect the global correlation characteristics, and the Geary-C index is used to highlight the local difference performance. Either of the two can be selected for analysis based on the selected parameter type and analysis objectives.

[0033] During the autocorrelation calculation process, the system establishes the adjacency relationship between measuring points in a grid-like manner, and calculates the similarity index based on the difference in parameter values. By statistically analyzing the similarity level between measuring points in each region, the spatial distribution pattern of correlation strength is identified. Based on the correlation coefficient results, a preliminary spatial structure representation matrix is ​​generated to express the degree of spatial coupling of hydrological characteristics between different measuring point areas. To further obtain the continuous parameter distribution between various locations within the sea area, the system uses the Kriging interpolation method to interpolate and estimate the unmeasured areas based on the known parameter values ​​of the measuring points and their spatial coordinates. The Kriging interpolation method calculates the predicted values ​​of the hydrological parameters at the target location based on the known measuring point weights and spatial variation functions, thereby realizing the spatial reconstruction of the parameter field.

[0034] When performing interpolation processing, the system sets the interpolation window size and covariance function type based on the spatial variability model to ensure that the interpolation process can fully reflect the correlation structure of the surrounding measurement points and reduce local error interference. During the interpolation process, the system synchronously calculates the spatial gradient changes, performs gradient scanning and identification on the parameter field formed by the interpolation results, and marks the areas where the gradient change amplitude exceeds the preset range as high variation areas. In order to reduce the impact of numerical mutations in such areas on continuity judgment, the system implements local smoothing processing on such areas, and adjusts the interpolation results by introducing edge point weighting adjustment, smoothing kernel convolution and other means to keep it in a balanced state between spatial continuity and abnormal sensitivity.

[0035] The entire spatial correlation calculation and interpolation reconstruction process forms a linkage relationship with the data acquisition module and the point distribution optimization module in the system architecture. By analyzing the spatial correlation matrix, the system can identify areas of drastic changes in the sea area in subsequent steps and assign them higher point distribution density weights, providing a basis for the distribution strategy. The combination of spatial interpolation algorithms and data structures ensures the dual requirements of parameter estimation accuracy and regional representativeness. The kriging method's adaptive response to the measurement point distribution structure and parameter variance meets the requirements of processing the rapid changes, multi-source, and multi-scale characteristics of the marine environment. The results of spatial autocorrelation calculations can also be directly input into the information density assessment model to support regional clustering and the construction of dynamic allocation strategies for acquisition resources.

[0036] Taking the nearshore waters during a typhoon as an example, the system received several hours of high-frequency sampling data and found that the consistency of salinity change trends at certain measuring points at the water depth level had significantly increased. After calculating the Moran index, it was determined that their regional correlation had increased. The interpolation results formed a high-gradient strip structure, which the system classified as a key collection area and, on this basis, triggered a reduction in the spacing between the measuring points. This process reflects the mutual support and synergy between algorithmic and technical features at the functional level. Through these technical means, the system comprehensively solves the problems of existing technologies such as insufficient spatial model accuracy, delayed point distribution in variable areas, and local jumps affecting interpolation stability.

[0037] Step S3: Divide the sea area into high-variability areas and low-variability areas based on the spatial correlation matrix.

[0038] Specifically, based on the spatial correlation matrix constructed in step S2, the sea area division operation is performed to divide the target monitoring sea area into high-variability areas and low-variability areas to guide the differentiated implementation of the subsequent point optimization strategy. The spatial correlation matrix is ​​a structured data result constructed based on the spatial position relationship and the consistency of the changes in hydrological characteristic parameters of the collected measurement points. Each element in the matrix represents the degree of spatial similarity of the hydrological parameters between any two measurement points. By analyzing the distribution of correlation coefficients in the matrix, the system extracts the parameter response characteristics of each measurement point in the spatial dimension, thereby establishing a corresponding relationship between the measurement point and the regional variability.

[0039] To achieve regional division, the system sets a correlation coefficient threshold based on the continuity requirements of the hydrological environment. The threshold can be set based on historical statistical laws, water area types and monitoring accuracy requirements. When the correlation coefficient between a measuring point and multiple measuring points in its spatial neighborhood is lower than the set threshold, the system determines that the hydrological characteristics in the area where the measuring point is located are spatially discontinuous, that is, it is determined to be a high-variance area. On the contrary, if the correlation between the measuring points in the area is generally higher than the threshold and the change trend is consistent, the system marks the area as a low-variance area. This judgment process is not for a single measuring point, but forms a local analysis window with the measuring point as the center, and combines the statistical characteristics of its spatial neighborhood to form the basis for regional division. The system performs a point-by-point sliding window analysis on the entire monitoring area to form a preliminary regional classification label matrix, and merges spatially adjacent grids with similar labels to generate connected high-variance area and low-variance area layers.

[0040] In practical applications, such as during nearshore storms, salinity and current velocity change rapidly and are spatially localized. Consequently, the spatial correlation matrix collected by the system will show multiple regions with low correlation. In these cases, the aforementioned regionalization method can accurately identify these regions as high-variability areas, increasing the system's sampling density and triggering adjustments to the distribution strategy. To enhance the stability of the demarcation boundaries and the clarity of the regional structure, the system introduces boundary connectivity rules based on the initial demarcation results, merging fragmented regions. Principal component analysis is then used to extract the dominant hydrological characteristic variables for each region, which are then used to determine the rationality of the demarcation boundaries and the dominant parameter attributes.

[0041] The spatial correlation matrix construction algorithm and region division logic in the above technical solution are closely integrated functionally. The algorithmic features quantitatively describe spatial continuity, and then the region division operation is completed by technical means, achieving structure identification and layout guidance driven by collected data. This process not only serves as an important reference for setting point density, but also provides a spatial structural foundation for subsequent information density modeling and equipment spacing adjustment. The linkage between the spatial correlation matrix and the identification of variable regions plays a central role in the entire technical solution. Its ability to identify the dynamic characteristics of the monitoring area directly affects the accuracy and adaptability of the system's layout response.

[0042] The present invention integrates the quantitative calculation results with the deployment decision logic in the above-mentioned way, solving the technical problems in the existing technology such as the lack of spatial differentiation adjustment capability of the acquisition strategy, the rigid regional deployment structure, and the insufficient monitoring density in key variation areas. It has beneficial technical effects such as enhancing the adaptability of deployment, improving the monitoring accuracy of key areas, and supporting the optimal allocation of resources, and meets the comprehensive requirements of dynamics, efficiency and controllability in marine environmental monitoring.

[0043] Step S4: Calculate the information density index of the high-variability region and the low-variability region and classify them into information-intensive regions and sparse regions.

[0044] In a specific embodiment, in S4, based on the division results of the high-variability area and the low-variability area, a two-dimensional grid structure covering the entire monitored sea area is constructed, each grid unit is used as a calculation unit, the hydrological parameter data in any grid unit is extracted, the statistical characteristics of the hydrological parameter data are used as input, and the information entropy calculation method is used to evaluate the data distribution uncertainty of any grid unit, and the data distribution uncertainty is used as the information density indicator of any grid unit; Clustering algorithms are used to cluster all information density indicators. Based on the clustering results, all grid cells are divided into different information density categories to obtain preliminary classification results. The information density index difference and category consistency relationship between each grid unit and multiple directly adjacent grid units are detected. If the information density index of any grid unit is close to that of any adjacent grid unit but the category is inconsistent, the grid unit is reclassified and merged into the main category of the adjacent grid unit.

[0045] The information density classification is based on the information entropy calculation results of the sea area grid cells. The K-means clustering algorithm is used to divide each grid into different information density categories, and the cluster boundaries are optimized through neighborhood density similarity verification. Specifically, based on the spatial division results of high-variability and low-variability areas, the system constructs a two-dimensional grid structure covering the entire monitored sea area. Using each grid cell as a calculation unit, the hydrological parameter data contained therein is extracted to calculate the information density index. This information density index quantifies the comprehensive complexity and variation level of each region in multidimensional hydrological parameters, reflecting the importance of each region to environmental monitoring results. The system uses the statistical characteristics of hydrological parameter data such as temperature, salinity, flow velocity, and water depth collected within each grid as input and uses the information entropy calculation method to assess the distribution uncertainty of the data within each grid cell. Higher information entropy values ​​indicate more complex parameter variations in the area and more information contained. As a direct indicator of information density, the information entropy value has a direct corresponding relationship with the priority setting of the unit during the site optimization process.

[0046] After calculating information density, the system compiles the information entropy values ​​of all grid cells into a set of density feature vectors, which are then fed into the cluster analysis module. The K-means clustering algorithm is then used to classify the information density values. Based on the minimum variance principle, the K-means algorithm constructs several cluster centers within the sample space. The system then classifies all grid cells according to a preset number of cluster categories, minimizing information density differences within the same category and ensuring significant differences between different categories. The classification results are presented as density level labels. The system automatically determines the relative density level of each category based on the size of the cluster centers, forming a continuous density classification system from information-dense areas to information-sparse areas.

[0047] In order to further improve the spatial continuity and regional connectivity of the clustering results, the system performs neighborhood density similarity verification on the preliminary classification results and optimizes the cluster boundaries. The system detects the density value difference and category consistency relationship between each grid unit and multiple units directly adjacent to it. If it is found that the density value of a unit is close to the adjacent area but the category label is inconsistent, the system performs a reclassification operation on the unit and merges it into the adjacent main category to avoid unreasonable spatial segmentation problems caused by isolated points, boundary disturbances or initial cluster center distribution. In addition, if a cluster category presents a broken or non-connected structure in space, the system will mark the non-connected part of the category separately or merge it into the main area according to the grid topology and connectivity requirements to ensure that the density classification layer has spatial interpretability and continuity.

[0048] In the marine environment monitoring application scenarios involved in the present invention, such as coastal tidal mutation areas or frontal junction areas, there are often problems of superposition of local hydrological structure mutations and intensive disturbances. The parameter distribution in this area is complex, the spatial variation is drastic, and the information density distribution presents discontinuous characteristics. It is difficult for traditional acquisition systems to distinguish density levels based on parameter change trends, resulting in the inability of equipment deployment strategies to achieve regional adaptation. The present invention introduces an information entropy model to measure the complexity of information within the sea area, combines cluster analysis with neighborhood verification optimization mechanisms, and constructs a complete information density level classification system. The system can allocate the number of acquisition devices and the spacing between distribution points according to the differences in information density in different regions, and realize resource optimization configuration driven by information value.

[0049] In this technical approach, the information entropy calculation algorithm and clustering classification technology functionally support each other, forming a joint solution for expressing regional information features and structured modeling. The results of density index calculation and spatial structure identification directly serve the subsequent device placement parameter generation module. The algorithm characteristics and placement structure form a stable data interface and control foundation. This comprehensively solves the problems of existing technologies such as the lack of density stratification for placement, the rigidity of regional deployment structures, and the mismatch between device distribution and information value. This improves the monitoring system's adaptability to spatially heterogeneous environments and enhances the relevance and effectiveness of the overall placement plan.

[0050] Step S5: construct an inverse proportional relationship model between device spacing and information density, and set a smaller device spacing for high-variability and dense areas.

[0051] In a specific embodiment, in S5, the inverse proportional relationship model between the device spacing and the information density satisfies d = k / ρ, where d is the device spacing, ρ is the information density index, and k is a proportional constant set according to the target coverage.

[0052] Specifically, after completing the information density classification, the system constructs an inversely proportional relationship model between device spacing and information density based on the corresponding information density index for each region. This model is used to determine the spacing parameters for different regions, thereby achieving spatially differentiated control of device deployment. The information density index is a density value calculated for each grid cell based on the changes in multidimensional hydrological parameters. It reflects the data carrying capacity and environmental complexity of that cell in the overall monitoring network. A larger value indicates a more sensitive region and a greater need for high-frequency sampling and intensive monitoring.

[0053] To enable quantitative control of the device deployment strategy, the system sets the device spacing as an inverse function of the density index. The spacing parameter d and the density index ρ are set to satisfy the functional relationship d = k / ρ, where k is a proportional constant related to target coverage, regional deployment capabilities, and system constraints. This proportional constant can be preset based on engineering parameters such as the total area of ​​the target sea area, the device quantity budget, and the minimum deployment tolerance, and dynamically adjusted during subsequent optimization calculations. This inverse proportional relationship logically establishes a functional mapping between information value and resource allocation, enabling the monitoring system to automatically allocate deployment spacing based on the changing characteristics of each area, achieving adaptive matching of monitoring density with environmental changes.

[0054] Based on this model, the system calculates the target device spacing for each grid cell in the entire sea area, and compiles all the calculation results into a spacing distribution matrix. During the processing, the system refers to the model for high-variability areas and low-variability areas respectively, and sets a lower limit for spacing in areas with high variation and high density to avoid deployment conflicts caused by abnormal convergence of spacing due to excessively high density indicators. In low-variability areas or sparse areas, the system automatically enlarges the device spacing based on the lower density value, thereby reducing invalid deployment points and saving resource allocation. In some boundary transition areas, the system introduces a smoothing function to perform difference processing on the spacing changes between consecutive units to ensure layout continuity and system stability.

[0055] In typical scenarios such as the typhoon front or areas with sudden changes in seabed terrain, the hydrological change gradient is large and densely distributed, and the calculated information density value in this area is significantly higher than that in the background sea area. In traditional point distribution strategies, the equipment spacing is usually arranged in an average manner, making it difficult to maintain sampling accuracy in key areas. The present invention significantly reduces the point spacing in such areas through a spacing control strategy based on an inverse proportional model, forming a high-density mesh layout structure, enhancing the system's ability to monitor local mutations, and appropriately expanding the spacing in low-variability areas far away from the impact area, thereby maximizing the overall resource utilization efficiency of the system.

[0056] The inverse-proportional model construction and information density index calculation in the above technical solution are functionally tightly coupled. The former uses the latter as a direct input parameter, while the latter's calculation logic remains consistent with the spatial feature modeling mechanism. By embedding the spatial feature evaluation results into the equipment deployment rules, this technical solution forms a linkage mechanism that integrates data analysis, parameter modeling, and control execution. This solves the problems of existing technologies such as the lack of quantitative expression of point placement strategies, rigid spacing adjustment, and inability to dynamically match regional characteristics. It has clear engineering practicality and system adaptability, and has significant technical effects in improving monitoring efficiency, reducing deployment costs, and enhancing coverage capabilities in key areas.

[0057] In a preferred embodiment, the process of executing step S5 may further specifically include the following steps: identifying the high-variability and information-dense areas, comparing the corresponding device spacing with a preset minimum layout spacing threshold, and if the device spacing is less than the minimum layout spacing threshold, triggering a parameter optimization mechanism, using the current information density index value as input, and automatically iterating and updating the proportional constant of the inverse proportional relationship model.

[0058] If an area is of high variation and information-intensive type, and the device spacing calculated according to the inverse proportional relationship model is lower than the preset minimum layout spacing threshold, the parameter optimization mechanism is triggered to readjust the model constants. Specifically, during the execution of the inverse proportional relationship model between device spacing and information density, the system compares the device spacing value calculated for each high variation and information-intensive area with the preset minimum layout spacing threshold. If the calculated spacing of a certain area is less than the threshold, the system automatically triggers the parameter optimization mechanism to adjust the proportional constant in the model, thereby avoiding deployment conflicts, coverage redundancy or hardware deployment infeasibility problems caused by too small device layout spacing. The inverse proportional relationship model is constructed based on the inverse relationship between device spacing d and information density ρ. In high-density areas or areas with severe variation, the ρ value increases significantly, resulting in a significant decrease in the d value output by the model. In order to ensure that the operability of actual deployment matches physical limitations, the system sets a reasonable minimum spacing threshold. This threshold is set based on a comprehensive set of parameters such as device perception range, communication interference distance, and physical fixed distance, as the acceptable lower limit of spacing.

[0059] The system executes this threshold comparison logic simultaneously during the point-to-point parameter generation phase, individually checking all spacing values ​​calculated based on d = k / ρ. If a spacing is less than the threshold, the system does not directly use the result. Instead, it uses the current density value as input, reversely adjusts the value of the proportional constant k, regenerates the spacing value, and re-verifies whether the updated spacing meets the constraint. The parameter optimization mechanism automatically iteratively updates k through recursive adjustment. While maintaining relative point density differences, it increases all spacing values ​​to a value no less than the threshold. It also controls the spacing gradient between high- and low-density areas to maintain a smooth gradient, avoiding sudden changes in the layout structure or density discontinuities caused by local corrections.

[0060] In this process, the algorithm module and the deployment logic form a linkage relationship. Information density serves as a model input parameter to drive spacing calculations. Comparison of spacing with a threshold triggers model parameter updates. The updated model applies uniformly to all regions, forming a unified deployment rule system. This mechanism is suitable for areas in the sea with localized mutations, extremely high boundary density, or drastically fluctuating historical sampling data. It can automatically identify small spacing caused by a single model scaling factor and prevent global model structure collapse through local corrections, thereby improving the stability of the deployment strategy and engineering controllability.

[0061] For example, in the tidal shear zone at the mouth of a river, the density of hydrological information reaches extremely high peaks due to the coupling of complex terrain and flow velocity. Directly applying the standard inverse proportional model will produce spacing values ​​in this area that are far smaller than the equipment deployment capacity. Without parameter correction, this will lead to excessive concentration of equipment in this area, mutual interference, or difficulty in deployment. This invention introduces a linkage scheme of minimum deployment spacing thresholds and parameter optimization mechanisms, enabling the system to automatically improve the spacing calculation results after identifying such areas. This not only ensures monitoring accuracy in densely populated areas, but also avoids unnecessary deployment redundancy, achieving a balanced control of model sensitivity and deployment feasibility.

[0062] Step S6: Use an optimization algorithm to optimize the number of devices and layout coordinates while meeting the monitoring coverage requirements, and generate an accurate layout plan.

[0063] Specifically, based on the previously completed information density classification results and the device spacing configuration model, the system uses an optimization algorithm to jointly solve the number of collection devices deployed and the corresponding spatial coordinates, generating a deployment plan that meets coverage constraints. This optimization process aims to improve resource utilization efficiency, ensure monitoring integrity, and enhance deployment feasibility. The results of the sea area division, device spacing parameters, information density weights, and boundary constraints are input into the optimization algorithm. The algorithm searches for the coordinate set corresponding to the minimum number of devices within the deployment space, ensuring that the monitoring coverage rate in each area meets the preset requirements and that the spatial distribution of devices conforms to the spacing constraints derived from the density model.

[0064] The system introduces a feasible solution space for layout into the deployment model, limiting constraints such as the minimum spacing between devices, boundary buffers, and signal interference distances to ensure that the optimization results are physically feasible. In terms of algorithm selection, the system uses a genetic algorithm as a global search tool, generating multiple layout combination schemes by initializing the population, and performing a fitness evaluation on each scheme. The fitness function uses the total number of devices, coverage area integrity, spacing rationality, and connectivity as evaluation dimensions, prioritizing the layout combination with the least number of devices and the best coverage within the constraints. The system continuously iteratively evolves the layout structure through crossover and mutation operations, dynamically updating the local optimal solution in each round of iteration until the global optimal solution is reached or the convergence conditions are met, and outputting the final layout solution.

[0065] During the optimization process, the system incorporates the information-dense and sparse area distribution layers generated in the previous stage into the population initialization strategy, increasing the density of candidate points in information-dense areas and reducing the frequency of point searches in sparse areas to improve population quality and optimization efficiency, while ensuring that the optimization results prioritize coverage of dense areas. In each round of point evaluation, the system maps each candidate solution to the spatial grid model and calculates its degree of adaptation to the information density layer. If a point solution fails to cover all density level areas, its fitness value is reduced. The system uses this to suppress the retention rate of non-balanced layout structures and gradually converges to the optimal layout structure with strong spatial continuity and high local density matching.

[0066] In typical application scenarios, such as complex intertidal zones or within the deployment zone of marine environmental observation platforms, the irregular spatial structure, rapidly changing hydrodynamic characteristics, and limited deployment costs of measurement points mean that adopting a fixed deployment pattern will result in redundant equipment or gaps in regional coverage. This invention solves deployment coordinates through an optimization algorithm, dynamically adjusting the number of devices to meet the deployment requirements of various areas of variable intensity, while ensuring that monitoring within the area is non-overlapping, non-missing, and non-overloaded, significantly reducing system deployment costs and maintenance intensity.

[0067] In this technical solution, the optimization algorithm structure and information density modeling results are directly functionally linked. The former relies on the spatial attribute inputs of the latter to drive device placement priorities and structural control, while the latter completes placement feasibility verification through optimization algorithm feedback. The two together form a closed-loop deployment strategy scheduling system, addressing the existing problems of fixed-point deployment methods in areas of environmental heterogeneity, such as insufficient response, low deployment efficiency, and high local redundancy. This technical solution is suitable for large-scale, highly variable, and highly structurally sensitive marine environmental monitoring scenarios, improving the system's global coverage performance and deployment cost control capabilities.

[0068] In a preferred embodiment, in step S6, the sea area division result, device spacing parameters, information density weight and boundary constraints are input into the optimization algorithm, and the coordinate set corresponding to the minimum number of devices is searched in the deployment space, specifically including: (1) Genetic algorithm is used as a global search tool to generate multiple layout combination schemes by initializing the population. The fitness evaluation of each scheme is performed using the total number of devices, coverage area integrity, spacing rationality and connectivity as evaluation dimensions, and the layout combination with the least number of devices and the best coverage is selected.

[0069] (2) Based on the layout combination, the layout structure is continuously iterated and evolved through crossover and mutation operations, and the local optimal solution is dynamically updated in each round of iteration until the global optimal solution is reached or the convergence condition is met, and the final solution output is used as the layout solution.

[0070] The optimization algorithm is a genetic algorithm, which includes population initialization, fitness evaluation, crossover and mutation operations, and generates a minimum equipment deployment plan that meets coverage requirements through iterative calculations. Specifically, the algorithm is based on the genetic evolution mechanism and realizes global search and optimization of the solution space through iterative evolution of multiple deployment plans, thereby solving problems that traditional deployment strategies are difficult to deal with, such as uneven equipment deployment density in high-variability areas and low-variability areas, and complex spatial constraints. The input parameters of the algorithm include the spatial boundary of the target monitoring sea area, the hydrological information density layer, the regional classification results, the minimum equipment spacing constraint, the perception coverage radius, and the total number of deployments. The output is a set of equipment deployment coordinates and their feasibility marks in space.

[0071] During the population initialization phase, the system randomly generates several placement solutions based on the density distribution of high-variability regions. Each placement solution is represented as an individual, consisting of a set of coordinate points. The population initialization strategy considers the spatial gradient of information density distribution, with a high probability of placement in high-density regions and a low probability in sparse regions. This density-weighted approach improves the feasibility of the initial solution, providing an effective starting point for iterative optimization.

[0072] During the fitness evaluation process, the system calculates constraints and monitoring coverage for each individual deployment point, using a fitness function to comprehensively score it across multiple dimensions, including spatial coverage within the target area, total device usage, and reasonable spacing between adjacent points. Plans with insufficient coverage or exceeding the upper limit for device usage are assigned lower fitness values. Plans with uniform deployment structures, satisfactory spacing requirements, and the smallest number of devices are prioritized for subsequent crossover and mutation phases.

[0073] The crossover operation generates new individuals by interleaving the parent generation's layout solutions, increasing population diversity by exchanging some coordinate sets. The mutation operation randomly replaces some of the layout coordinates in the offspring, introducing perturbations in the solution space to escape local optima. After each round of evolution, the system retains the solutions with the highest fitness to form the new generation of populations. This operation is repeated until the fitness function converges or the maximum number of iterations is reached, outputting the optimal layout solution.

[0074] In specific applications, such as long-term monitoring of hydrological parameters in complex offshore seafloor geomorphic areas, traditional equally spaced deployments cannot achieve a balanced balance between monitoring accuracy and equipment cost due to the constraints of seafloor structure and the influence of multi-parameter coupled disturbances. This invention uses a genetic algorithm to perform multi-constrained optimization, dynamically searching for the optimal bit combination within a continuous space. This achieves high-density information coverage in key areas while minimizing equipment in non-key areas under resource-constrained conditions, effectively alleviating the problem of redundant deployment.

[0075] In this technical solution, the genetic algorithm's structural design and the marine environment information density model form a functional closed-loop logic. The algorithm input relies on density classification results to generate the initial point distribution. The optimization objective reflects the relationship between information variation characteristics and equipment deployment. The evaluation index system is directly weighted by the front-end model. The two functions support each other and form a feedback loop. This point optimization mechanism integrates the algorithm's structural design with the actual physical deployment capability constraints to form an automatically adjustable deployment parameter control system capable of resolving existing issues such as poor regional adaptability, low deployment efficiency, and high redundancy.

[0076] Step S7: Acquire real-time marine environment monitoring data. If significant changes in hydrological characteristics are detected, recalculate the equipment spacing and update the deployment plan.

[0077] In a specific embodiment, in S7, any hydrological parameter is extracted, its time series data is obtained, and a parameter change trend in the current period and multiple historical change trends are extracted using a sliding window mechanism. A change threshold is generated based on the average value and standard deviation of the multiple historical change trends. If the parameter change trend exceeds the change threshold, it is determined that the hydrological characteristics have changed significantly. If the monitoring data of any area show significant changes in hydrological characteristics over multiple consecutive periods, the area will be marked as a highly dynamic state; A priority parameter is assigned to each region based on its environmental sensitivity, hydrological change frequency, and monitoring target weight, and a release point update process is triggered for highly dynamic regions where the priority parameter is greater than a preset value.

[0078] In real-time environmental monitoring, a trend analysis is performed on the changes in hydrological characteristics. The basis for judging significant changes is whether the amplitude of parameter changes exceeds the dynamic threshold set according to the historical change pattern, and the update process of the release points can be triggered according to the priority of the regional risk level. Specifically, after the deployment is completed, the system continuously obtains real-time monitoring data of the marine environment. The collected objects include key hydrological parameters such as temperature, salinity, flow rate, and water depth, and the monitoring data is identified for trend changes based on the time series analysis mechanism. During the processing process, the system continuously updates the hydrological characteristic database according to the preset monitoring period and sampling frequency, and extracts the current parameter change trend through the sliding window mechanism, and compares and analyzes it with the change pattern in the historical period to determine whether the current environment has changed significantly. The judgment standard for significant changes is that the amplitude of change of one or more hydrological parameters in a specified period exceeds the change threshold dynamically generated by the system based on the historical mean and standard deviation. The threshold is dynamically set in combination with the parameter type and the heterogeneous characteristics of the marine environment, and has time-varying and regional adaptability.

[0079] The system classifies and processes the trend change results. If the monitoring data of a certain area fluctuates outside the threshold for multiple consecutive cycles, the system automatically marks the area as a highly dynamic state and starts the spacing update process. In this process, the system calls the inverse proportional model of equipment spacing and information density built in the early stage, recalculates the target spacing for the current high-variability area, and links the trigger point optimization module to generate an adjusted layout recommendation plan. In order to avoid waste of resources caused by frequent system recalculations, the system introduces a risk level mechanism, which assigns priority parameters according to the environmental sensitivity, hydrological change frequency and monitoring target weight of each area. When a trend change signal is detected, the distribution point update process is triggered only for high-priority areas, and the changes in the remaining areas are recorded but no structural update operations are performed.

[0080] For example, in the front area affected by storm surges, flow velocity and salinity parameters change dramatically and have the characteristics of rapid spatial migration. The system continuously analyzes the changes in flow velocity gradients in real-time monitoring data, identifies the area with continuous abnormal changes and exceeds the dynamic threshold standard, and thus determines it as a significant environmental disturbance area. It automatically recalculates the spacing and adjusts the equipment deployment strategy so that the deployment results adapt to the changed information distribution structure, thereby improving the system's response capability to environmental mutations and the robustness of the deployment strategy.

[0081] The parameter trend analysis algorithm and dynamic deployment adjustment mechanism in this technical solution form a data-driven control closed loop. The algorithm relies on monitoring data to model parameter fluctuations, and the control module uses the analysis results as a trigger to dynamically modify the deployment structure. These two functional components support each other, forming a linked feedback loop, solving the problem of static, unadjustable deployment points and a lack of dynamic environmental responsiveness in traditional deployment models. This mechanism is particularly suitable for monitoring key areas with sudden, highly variable hydrodynamic conditions or disaster risk, enhancing the adaptability and system stability of the deployment solution.

[0082] Step S8: Send updated working parameters and position instructions to the acquisition device via the wireless communication system to complete the dynamic optimization layout.

[0083] In a specific embodiment, in S8, the wireless communication system includes a primary communication channel and a backup communication channel. If the primary communication channel fails to send parameters, it automatically switches to the backup communication channel for retransmission until the device confirms successful reception.

[0084] Specifically, after completing the dynamic update of the deployment plan, the system sends control information containing the latest working parameters and position instructions to each acquisition device distributed in the sea area through the wireless communication system, realizing real-time adjustment of the deployment structure and remote command response. The wireless communication system includes a two-level architecture of a main communication channel and a backup communication channel, in which the main channel takes priority for normal communication tasks, and the backup channel serves as a fault switching path to ensure the continuity and reliability of remote command transmission. Based on the real-time deployment optimization results, the control center automatically generates new configuration instructions for each acquisition device. The instructions include target working coordinates, water depth range, sampling frequency, interval duration, power consumption level, etc., and encodes this information and sends it to the corresponding device's unique identification address through the main communication channel.

[0085] During the communication process, the system monitors the receipt information in real time and verifies the device response status within the specified time window. If the device does not return a successful reception confirmation signal within the response window, the system determines that the main channel communication has failed and automatically enables the backup communication channel to execute the instruction retransmission process. The backup channel can use a low-power wide area network, satellite link or shortwave wireless channel. It automatically matches the optimal transmission path based on the current network environment and the device's receiving capability, and enhances the reception robustness in environments with poor channel quality through multi-frame reconstruction technology. The system continues to monitor the device's reception status during the retransmission cycle until valid confirmation is obtained or it determines that the communication link has completely failed. In the event of a communication failure, an abnormal record will be made and sent to the scheduling platform to prompt manual intervention.

[0086] The above describes an intelligent collection method of ocean multi-dimensional information in an embodiment of the present application. The following describes an intelligent collection system of ocean multi-dimensional information in an embodiment of the present application. Figure 2 In an embodiment of the present application, an intelligent system for collecting multi-dimensional ocean information includes: The hydrological sensor network module 10 is used to collect hydrological parameters at multiple depth layers and perform anomaly detection and data update.

[0087] The data processing and analysis module 20 is used to construct a hydrological characteristic data set, generate a spatial correlation matrix and an information density classification map.

[0088] The layout optimization module 30 is used to output the optimal equipment layout plan based on the inverse proportional relationship model and optimization algorithm.

[0089] The real-time monitoring and adaptive updating module 40 is used to analyze the hydrological change trend and dynamically trigger the update of the distribution points.

[0090] The communication management module 50 is used to send updated parameters and location information to the acquisition device and complete the receipt confirmation.

[0091] The present application also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the steps of the method for intelligently collecting multi-dimensional ocean information.

[0092] The above is only a preferred embodiment of the present invention. It should be pointed out that ordinary technicians in this technical field can make several improvements and supplements without departing from the principles of the present invention. These improvements and supplements should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent method for collecting multi-dimensional ocean information, characterized in that: The steps include: S1. Synchronously collect environmental parameters at multiple measuring points and multiple depth layers in the sea area, including temperature, salinity, current velocity, and water depth, to form a hydrological characteristic dataset with time series and spatial coordinates; S2. Based on the hydrological characteristic data set, calculate the spatial autocorrelation coefficient between each measuring point and generate a spatial correlation matrix using a spatial interpolation algorithm; S3. Dividing the sea area into high-variability areas and low-variability areas based on the spatial correlation matrix; S4, calculating the information density index of the high-variability region and the low-variability region, and classifying them into information-intensive regions and information-sparse regions; S5. Build an inverse proportional relationship model between device spacing and information density, and set smaller device spacing for high-variability and information-dense areas; S6. Use optimization algorithms to optimize the number of devices and layout coordinates while meeting monitoring coverage requirements and generate a layout plan; S7. Acquire real-time marine environment monitoring data. If significant changes in hydrological characteristics are detected, recalculate the device spacing and update the deployment plan. S8. Send updated working parameters and position instructions to the acquisition equipment through the wireless communication system to complete the dynamic optimization layout.

2. The method according to claim 1, wherein Said S1 includes a data anomaly detection mechanism. When a parameter of a certain measuring point continuously exceeds a preset threshold in the time or depth dimension, high-frequency sampling of the measuring point is triggered, and the sampling results are used to update the said hydrological characteristic dataset; In S2, the spatial correlation calculation uses the Moran index or the Geary-C index as an evaluation method to measure the degree of synchronous change of hydrological parameters between adjacent measuring points; The spatial interpolation algorithm is the Kriging interpolation method, which performs local smoothing in areas with large parameter gradient changes. Based on the known parameter values ​​of the measuring points and their spatial coordinates, the Kriging interpolation method is used to interpolate and estimate the unmeasured areas. The Kriging interpolation method calculates the predicted values ​​of the hydrological parameters at the target location based on the known measuring point weights and spatial variation function, realizing the spatial reconstruction of the parameter field.

3. The method according to claim 1, wherein In S4, based on the division results of the high-variability area and the low-variability area, a two-dimensional grid structure covering the entire monitored sea area is constructed, each grid cell is used as a calculation unit, the hydrological parameter data in any grid cell is extracted, the statistical characteristics of the hydrological parameter data are used as input, and the information entropy calculation method is used to evaluate the data distribution uncertainty of any grid cell, and the data distribution uncertainty is used as the information density indicator of any grid cell; Clustering algorithms are used to cluster all information density indicators. Based on the clustering results, all grid cells are divided into different information density categories to obtain preliminary classification results. The information density index difference and category consistency relationship between each grid unit and multiple directly adjacent grid units are detected. If the information density index of any grid unit is close to that of any adjacent grid unit but the category is inconsistent, the grid unit is reclassified and merged into the main category of the adjacent grid unit.

4. The method according to claim 1, wherein In S5, the inverse proportional relationship model between the device spacing and the information density satisfies d = k / ρ, where d is the device spacing, ρ is the information density index, and k is a proportional constant set according to the target coverage.

5. The method according to claim 4, wherein Identify the high-variability and information-dense areas, and compare the corresponding device spacing with a preset minimum layout spacing threshold. If the device spacing is less than the minimum layout spacing threshold, trigger a parameter optimization mechanism, and use the current information density index value as input to automatically iterate and update the proportional constant of the inverse proportional relationship model.

6. The method according to claim 1, wherein In S6, the sea area division result, device spacing parameters, information density weight and boundary constraints are input into the optimization algorithm, and the coordinate set corresponding to the minimum number of devices is searched in the layout space, specifically including: A genetic algorithm is used as a global search tool to generate multiple layout combination schemes by initializing the population. The fitness of each scheme is evaluated based on the total number of devices, coverage area integrity, spacing rationality, and connectivity as evaluation dimensions. The layout combination with the least number of devices and the best coverage is selected. Based on the layout combination, the layout structure is continuously iteratively evolved through crossover and mutation operations, and the local optimal solution is dynamically updated in each round of iteration until the global optimal solution is reached or the convergence condition is met, and the final solution output is used as the layout solution.

7. The method according to claim 6, wherein In S7, any hydrological parameter is extracted, its time series data is obtained, and a parameter change trend in the current period and multiple historical change trends are extracted using a sliding window mechanism. A change threshold is generated based on the average value and standard deviation of the multiple historical change trends. If the parameter change trend exceeds the change threshold, it is determined that the hydrological characteristics have changed significantly; If the monitoring data of any area show significant changes in hydrological characteristics over multiple consecutive periods, the area will be marked as a highly dynamic state; A priority parameter is assigned to each region based on its environmental sensitivity, hydrological change frequency, and monitoring target weight, and a release point update process is triggered for highly dynamic regions where the priority parameter is greater than a preset value.

8. The method according to claim 1, wherein In S8, the wireless communication system includes a main communication channel and a backup communication channel. If the main communication channel fails to send parameters, it automatically switches to the backup communication channel for retransmission until the device confirms successful reception.

9. An intelligent collection system for implementing the method for intelligent collection of multi-dimensional ocean information according to any one of claims 1 to 8, characterized in that: include: Hydrological sensor network module, used to collect hydrological parameters at multiple depth layers and perform anomaly detection and data update; Data processing and analysis module, used to construct hydrological characteristic datasets, generate spatial correlation matrices and information density classification maps; The layout optimization module is used to output the optimal equipment layout plan based on the inverse proportional relationship model and optimization algorithm; Real-time monitoring and adaptive update module, used to analyze hydrological trends and dynamically trigger point updates; The communication management module is used to send updated parameters and location information to the acquisition device and complete the receipt confirmation.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the computer program is used to execute the steps of the method for intelligently collecting multi-dimensional ocean information according to any one of claims 1 to 8.

Images