Cross-region environmental data sharing and analysis method and system based on big data deep learning

Abstract

The application discloses a cross-regional environmental data sharing and analysis method and system based on big data deep learning, and relates to the technical field of data processing. The method comprises the following steps: determining the linkage range of the target device for sharing and analyzing environmental data, so as to avoid invalid coverage and resource waste of cross-regional data transmission; acquiring the collection frequency of environmental data in the linkage range; and dynamically dividing the big data deep learning area in the region according to the linkage range and the collection frequency, so as to realize the spatial matching of the computing resources and the data value, and improve the data processing efficiency of the high-priority area. By defining the linkage range of the target device, the application accurately limits the data sharing boundary, avoids redundant coverage of cross-regional data transmission, significantly reduces invalid data storage and network bandwidth consumption, dynamically adjusts the collection frequency, further optimizes the data collection density, reduces the generation of redundant data, and thus reduces the overall resource waste.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a cross-regional environmental data sharing and analysis method and system based on big data deep learning. BACKGROUND

[0002] Cross-regional environmental data sharing is a technical means for solving the problem of regional environmental monitoring data island in the existing technical field. In order to further enhance the collaborative analysis capability of multi-source heterogeneous data, a cross-regional environmental data sharing and analysis method and system based on big data deep learning is needed.

[0003] After searching, the Chinese invention patent with the publication number "CN111680793A" discloses "a blockchain consensus method and system based on deep learning model training". This application can guide the investment of funds, computing power and energy into more meaningful work by introducing the excess computing power of blockchain into deep learning model training, solving the problem of insufficient computing power and high cost.

[0004] In addition, the Chinese invention patent with the publication number "CN113469370A" discloses "an industrial Internet of Things data sharing method based on federal incremental learning". This application proposes a federal incremental learning algorithm to solve the problem of fusion of a large number of newly added data of the factory sub-end and the original industry joint model, the purpose of which is to quickly fuse the newly added state data with the original industry joint model through the calculation of the incremental weighting of the factory sub-end, and to realize effective incremental learning of the newly added state data.

[0005] However, in the actual use process, the above-mentioned disclosed patent and similar patent methods do not consider the non-homogeneity and dynamic change characteristics of the spatial distribution of cross-regional environmental data, but use a fixed threshold to set the linkage range. This method is easy to cause data transmission redundancy and edge computing resource mismatch between regions. Therefore, the applicant proposes a cross-regional environmental data sharing and analysis method and system based on big data deep learning to solve the above-mentioned problems. SUMMARY

[0006] The purpose of the present application is to provide a cross-regional environmental data sharing and analysis method and system based on big data deep learning to solve the problems raised in the background art.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0008] In the first aspect, a cross-regional environmental data sharing and analysis method based on big data deep learning is proposed, comprising:

[0009] Determining the linkage range of the target device sharing and analyzing environmental data, which is used to avoid invalid coverage and resource waste of cross-regional data transmission;

[0010] a collection frequency of environment data in the linkage range;

[0011] dynamically dividing a big data deep learning area in the region according to the linkage range and the collection frequency, for realizing spatial matching of the computing resource and the data value, and improving the data processing efficiency of the high-priority area;

[0012] constructing a shared network based on the big data deep learning area;

[0013] After the target devices in different areas access the shared network, the target devices acquire the required environment data, and analyze and predict the environment data based on the big data deep learning algorithm.

[0014] As a further preferred embodiment of the technical solution, the linkage range acquisition method comprises:

[0015] determining the longitude and latitude coordinates of the center points of the areas;

[0016] calculating the Euclidean distance between the center points of two adjacent areas according to the longitude and latitude coordinates;

[0017] setting the linkage range according to the obtained Euclidean distance.

[0018] As a further preferred embodiment of the technical solution, the following distance calculation formula is used for the calculation of the Euclidean distance:

[0019] radian = angle × (π / 180), which is used for converting the angle into radian;

[0020] which is used for determining the actual distance between the center points of two adjacent areas through the longitude and latitude coordinates, so as to more accurately set the linkage range;

[0021] wherein is the Euclidean distance between the center points of two areas, is the difference between the latitudes of the center points of two areas, in radian, is the difference between the longitudes of the center points of two areas, is the average latitude of the center points of two areas, is the radius of the earth, taking the value of 6371km;

[0022] and and and respectively represent the longitude and latitude coordinates of the center points of two adjacent areas.

[0023] As a further preferred embodiment of the technical solution, the priority evaluation standard establishment method comprises:

[0024] dividing the data collection frequency into several gradient levels;

[0025] The spatial mapping relationship of the collection frequency in the visual environment feature matrix is established;

[0026] The environment feature data of the target position is acquired, and a frequency-feature space correlation atlas is constructed in combination with the corresponding frequency level;

[0027] The priority arrangement is determined based on the size of the product of the frequency parameter and the distribution weight of the environment feature in the linkage region.

[0028] As a further preferred embodiment of the technical solution, the construction method of the shared network comprises:

[0029] The network node cluster is deployed in the target region based on the linkage range parameter, for realizing the rapid transmission and sharing of cross-regional environment data;

[0030] The environment data sharing network based on spatial position encryption is established, for generating an irreversible 128-bit session key by taking the longitude and latitude coordinates of the regional center point as an initial vector and combining the real-time timestamp parameter, to prevent data interception or tampering in the cross-regional transmission process.

[0031] As a further preferred embodiment of the technical solution, the implementation method of the regionalized deep learning operation optimization comprises:

[0032] The calculation resources are dynamically allocated according to the priority of the divided regions, for adjusting the calculation resources according to the priority order of the divided regions, so as to ensure that the deep learning operation on different regional environment data can be efficiently carried out;

[0033] The multi-modal data fusion processing and feature extraction are implemented, for improving the comprehensive analysis capability of the cross-regional environment data.

[0034] As a further preferred embodiment of the technical solution, the division method of the big data deep learning region comprises:

[0035] The visual environment feature matrix of the target region is constructed;

[0036] The priority evaluation standard of the visual environment feature matrix is constructed based on the collection frequency;

[0037] The linkage region corresponding positions are dynamically divided in sequence according to the priority arrangement order;

[0038] The regionalized deep learning operation optimization is implemented based on the dynamic division result.

[0039] In order to ensure the integrity of the above technical solution, a cross-regional environment data sharing and analysis system based on big data deep learning is proposed, which uses the above-mentioned cross-regional environment data sharing and analysis method based on big data deep learning, and comprises:

[0040] A linkage range determination module is configured to determine a linkage range of the target device for sharing and analyzing environmental data;

[0041] A data acquisition frequency acquisition module is configured to acquire an acquisition frequency of the environmental data in the linkage range;

[0042] A dynamic region division engine is configured to dynamically divide a big data deep learning region in the region according to the linkage range and the acquisition frequency;

[0043] A secure sharing network construction unit is configured to realize dynamic encryption of a data channel through a composite manner of geographical coordinates and time stamps;

[0044] A distributed deep learning operation cluster is configured to execute a distributed operation task on each big data deep learning region;

[0045] A multi-modal data fusion processor adopts a heterogeneous data source cooperative processing architecture, integrates a multi-dimensional parameter space feature analysis unit of meteorological factors, pollutant concentrations and ecological indexes, realizes joint representation of time series data and spatial distribution data through construction of a multi-channel parallel feature extraction module, and establishes a space-time coupling characteristic analysis channel of cross-modal parameters;

[0046] A visual decision support interface is configured to provide a visual interface.

[0047] As a further preferred technical solution, the linkage range determination module comprises an IoT gateway, a GIS server and an SDN controller, wherein the IoT gateway is configured to manage a device connection range, the GIS server is configured to determine a linkage region through a geographic fence technology, and the SDN controller is configured to dynamically configure a network device cooperation range; the data acquisition frequency acquisition module comprises a wireless sensor node, a data acquisition device and an edge gateway; the dynamic region division engine comprises a stream processing server, an edge computing node and a cloud resource manager; the secure sharing network construction unit comprises a hardware security module, a dynamic encryption router and a blockchain node; the distributed deep learning operation cluster comprises a GPU cluster, a TPU cluster and an AI server; the multi-modal data fusion processor comprises an FPGA acceleration server, a multi-sensor fusion platform and a distributed storage system; and the visual decision support interface comprises a data large screen, an interactive touch terminal and a Web visual server.

[0048] Compared with the prior art, the present application has the following advantages:

[0049] The cross-regional environmental data sharing and analysis method and system based on big data deep learning define the linkage range of the target device, accurately limit the data sharing boundary, avoid redundant coverage of cross-regional data transmission, significantly reduce invalid data storage and network bandwidth consumption, combine dynamic adjustment of collection frequency, further optimize data collection density, reduce the generation of redundant data, and thus reduce overall resource waste.

[0050] In addition, the linkage range and the collection frequency are dynamically divided into deep learning regions to realize intelligent matching of computing resources and data value, build a cross-regional sharing network, integrate environmental data, and realize analysis and prediction of environmental trends by combining a deep learning algorithm. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 The step flowchart of the disclosed method is provided.

[0052] Figure 2 The step flowchart of the linkage range acquisition method is provided.

[0053] Figure 3 The flowchart of the priority evaluation standard establishment method is provided.

[0054] Figure 4 The system composition diagram is provided.

[0055] Figure 5 The frequency-feature space correlation diagram disclosed by the present application is provided.

[0056] Figure 6 The auxiliary description diagram of step S103 is provided. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0058] Before understanding the technical solutions proposed in the present application, it should be clear that big data deep learning is a technical means that improves the accuracy and efficiency of environmental data sharing through massive data mining and analysis. In the technical solutions proposed in the present application, it is mainly used for cross-regional data sharing and interaction, which can accurately match and efficiently analyze the corresponding environmental data, ensuring seamless connection of data between different regions, thereby greatly improving the timeliness of environmental monitoring and early warning.

[0059] In addition, it should be noted that the environmental data in the present application refers to a type of data, and the environmental data in the present application includes CO2 content, garbage number and vegetation density.

[0060] As shown in Figure 1 The present application provides a technical solution: a cross-regional environmental data sharing and analysis method based on big data deep learning, comprising steps S100-S500.

[0061] Step S100: Determine the linkage range of the target device sharing and analyzing environmental data.

[0062] It should be noted that the linkage range in step S100 in the present application refers to the minimum distance threshold value of the environmental data that can be shared and analyzed across regions in different regions, which ensures the stability and reliability of the data in the transmission process and avoids data distortion caused by too long distance.

[0063] As a preferred embodiment, in the scenario of cross-regional linkage of city networking devices, the sharing and analysis of environmental data between devices rely on short distance determination (1-10 kilometers), and traditional GPS ranging wastes computing resources to some extent and causes long response time of embedded devices, resulting in delay between pushing and sharing of environmental data. Therefore, a ranging method applied in short distance cross-regional ranging is proposed, which makes the linkage range determination more accurate, reduces the computing burden, and improves the response speed of environmental data sharing and analysis.

[0064] It should be noted that in the present embodiment, the method for obtaining the linkage range comprises steps S101-S103.

[0065] Step S101: Determine the longitude and latitude coordinates of the center point of each region.

[0066] It should be noted that the determination method of the longitude and latitude coordinates in step S101 is determined by using the GPS positioning technology in the prior art.

[0067] Step S102: Calculate the Euclidean distance between the center points of two adjacent regions according to the longitude and latitude coordinates.

[0068] It should be noted that in step S102, the following distance calculation formula is used to calculate the Euclidean distance, and the angle needs to be converted to radian during calculation. It should be noted that the conversion of the angle to radian is realized by using the trigonometric function formula in the prior art, and the specific conversion formula is: radian = angle × (π / 180).

[0069] Specifically, the distance calculation formula is: ; wherein Euclidean distance between the center points of two regions, latitude difference between the center points of two regions, longitude difference between the center points of two regions, average latitude of the center points of two regions, earth radius, 6371km.

[0070] It should be noted that in the present application and and and represent the longitude and latitude coordinates of the center points of two adjacent regions.

[0071] It should be noted that the distance calculation formula disclosed in step S102 is used in practice, assuming that A region and B region are adjacent regions, and the longitude and latitude coordinates of A region and B region are obtained by GPS, then the Euclidean distance between the center points of A region and B region can be accurately calculated according to the above formula.

[0072] Specifically, for the longitude and latitude coordinates of A region (31.2423°, 121.4903°), the longitude and latitude coordinates of B region (31.2385°, 121.5020°), the angles of the longitude and latitude coordinates are converted into interaction, , , and The values of , , , .

[0073] At this time , ,

[0074] ;

[0075] Through the above calculation, it is obtained that the Euclidean distance between the center points of A region and B region is about 2.1 kilometers, and in addition, it is supplemented that the value of the value in the above formula is in radian.

[0076] Step S103: setting the linkage range according to the obtained Euclidean distance.

[0077] It should be noted that reference Figure 6The setting of the linkage range threshold in step 103 is determined by adding the average of the maximum value and the minimum value within the Euclidean distance of all adjacent regions, and after determining the average value, a circular range is set as the specific linkage range with the position of the target device in the region as the center and the average value as the radius. It should be noted that this setting method eliminates the influence of extreme distance on the system through extreme value averaging, and avoids response delay caused by too large threshold or false linkage caused by too small threshold.

[0078] Step S200: Obtain the collection frequency of the environmental data in the linkage range.

[0079] It should be noted that the collection frequency of the environmental data in step S200 is used to provide data samples for deep learning of big data.

[0080] It should be further noted that in the present application, the method for obtaining the collection frequency is to access the environmental monitoring module in the target device through the current sensor, to monitor the working state of the target device in real time. When the target device is in the working state, the current sensor will detect the current change and convert it into a digital signal, and then determine the collection frequency of the environmental data. It should be noted that since the current sensor is accessed into the corresponding functional module to detect the execution frequency of the function, it is a common knowledge in the existing sensor detection field, and therefore the applicant does not make too much explanation and description on the specific linkage method between the current sensor and the environmental detection module.

[0081] Step S300: Dynamically divide the deep learning area of big data in the region according to the linkage range and the collection frequency.

[0082] It should be noted that the deep learning area of big data in step S300 is used to determine the high-risk range of environmental data sharing and analysis, to ensure that the deep learning algorithm can efficiently process and analyze data in a specific area.

[0083] As a preferred embodiment, in the scenario of device cross-regional linkage after city networking, since the regions in the city are complex, the algorithm of deep learning of big data is applied to the entire region, which will disperse the computing resources and reduce the data processing efficiency. Therefore, a method for dynamically dividing the deep learning area of big data is needed.

[0084] It should be noted that in the present embodiment, the reference Figure 2 It can be seen that the method for dividing the deep learning area of big data includes steps S301-S304.

[0085] Step S301: Construct a visual environmental feature matrix of the target region.

[0086] It should be noted that the method for constructing the visualization environment feature matrix in the present embodiment is as follows: first, map the linkage region to the two-dimensional electronic map of the target region, then collect the environmental data in the mapped region, and finally integrate the position features collected by the environmental data in the form of annotations in the linkage region of the electronic map.

[0087] Step S302: Construct the priority evaluation standard of the visualization environment feature matrix based on the collection frequency.

[0088] It should be noted that, with reference to Figure 3 In the present embodiment, the method for establishing the priority evaluation standard includes steps S302A-S302D.

[0089] Step S302A: Divide the data collection frequency into several gradient levels.

[0090] Specifically, the present scheme adopts a three-level division standard: high-frequency collection level (sampling interval ≤5 minutes), medium-frequency collection level (sampling interval 6-30 minutes), and low-frequency collection level (sampling interval >30 minutes). This grading system is established based on the magnitude difference of the sampling time threshold.

[0091] Step S302B: Establish the spatial mapping relationship of the collection frequency in the visualization environment feature matrix.

[0092] It should be particularly pointed out that the present step aims to analyze the spatial position between the collection frequency and the environmental feature parameters in the corresponding linkage region.

[0093] Step S302C: Obtain the environmental feature data of the target position, and construct a frequency-feature spatial correlation map in combination with the corresponding frequency level.

[0094] It should be noted that, with reference to Figure 5 It can be seen that the frequency-feature spatial correlation map is a two-dimensional electronic map containing all target position points and their corresponding environmental feature data. The distribution of environmental features under different frequency levels is intuitively displayed through color depth or pattern difference, which not only helps to quickly identify data-intensive or sparse areas, but also provides an important reference for subsequent data processing and regional division.

[0095] Step S302D: Determine the priority arrangement based on the size of the product of the distribution weight of the frequency parameter and the environmental feature in the linkage region.

[0096] Step S303: Dynamically divide the corresponding positions of the linkage region in order according to the priority arrangement order.

[0097] Step S304: Implement regional deep learning operation optimization based on the dynamic division result.

[0098] As a preferred embodiment, in the embodiment, in order to allocate computing resources according to the priority ranking of each divided region, so as to ensure that the deep learning operation of different regional environmental data can be efficiently carried out, an implementation method for optimizing regional deep learning operation is proposed, which specifically includes: step S304A-step S304B.

[0099] Step S304A: dynamically allocate computing resources according to the priority of the divided region.

[0100] It should be noted that the computing resources in step S304A specifically refer to the computing power allocated for performing big data deep learning.

[0101] Specifically, in step S304A, the high-frequency acquisition region is configured with a real-time stream processing engine and a GPU cluster, the medium-frequency acquisition region is configured with a medium-scale computing resource and a memory database, and the low-frequency acquisition region is allocated with a basic computing unit and a local storage.

[0102] Step S304B: implement multi-modal data fusion processing and feature extraction to improve the comprehensive analysis capability of cross-regional environmental data.

[0103] It should be noted that in this step, the existing convolutional neural network (ST-CNN) is used to perform feature fusion processing on environmental data. In specific implementation, lightweight real-time feature extraction is deployed for high-frequency regions, and intermittent feature extraction is performed through cloud computing nodes for medium and low-frequency regions.

[0104] Step S400: build a shared network based on a big data deep learning region.

[0105] It should be noted that the method for building a shared network in the present application includes: step S401-step S402.

[0106] Step S401: deploy a network node cluster in the target region based on the linkage range parameter.

[0107] Specifically, the network node cluster is uniformly configured at any position within the linkage range of the two-dimensional electronic map, for realizing the phased transmission of environmental data. In addition, it should be noted that in the present application, the network node cluster is a kind of existing computing node, which can realize fast processing and transmission of data. Each computing node has the functions of data receiving, storage, forwarding and preliminary processing, ensuring the integrity and accuracy of data in the transmission process.

[0108] Step S402: establish an environmental data sharing network based on spatial position encryption.

[0109] It should be noted that when the network node cluster transmits environmental data, a dynamic hash value is generated based on the latitude and longitude coordinates of the target area as an encryption key, and the data is encrypted using the AES-GCM algorithm in the prior art. It should be noted that the environmental data sharing network generates an irreversible 128-bit session key by using the latitude and longitude coordinates of the region center point (such as the values obtained in step S101) as an initial vector and combining a real-time timestamp parameter to prevent data interception or tampering during cross-regional transmission.

[0110] Step S500: After the target device in different regions accesses the shared network, the required environmental data is obtained, and the environmental data is analyzed and predicted based on the big data deep learning algorithm.

[0111] It is worth noting that in step S500, the big data deep learning algorithm is a neural network algorithm, a support vector machine algorithm, and a decision tree algorithm in the prior art. These algorithms mine potential correlations and regularities from massive environmental data, providing strong support for accurate analysis and prediction of environmental data.

[0112] As a preferred embodiment, reference is made to Figure 4 It is disclosed that a system is provided for a cross-regional environmental data sharing and analysis system based on big data deep learning. The disclosed "cross-regional environmental data sharing and analysis method based on big data deep learning" is used to realize the sharing and analysis of cross-regional environmental data.

[0113] Specifically, it includes:

[0114] A linkage range determination module for determining the linkage range of the target device for sharing and analyzing environmental data;

[0115] A data acquisition frequency acquisition module for acquiring the acquisition frequency of environmental data within the linkage range;

[0116] A dynamic region division engine for dynamically dividing big data deep learning regions within the region according to the linkage range and the acquisition frequency;

[0117] A secure sharing network construction unit for dynamically encrypting data channels through the composite method of geographic coordinates and timestamps;

[0118] A distributed deep learning operation cluster for performing distributed operation tasks on each big data deep learning region;

[0119] A multi-modal data fusion processor using a heterogeneous data source cooperative processing architecture, integrating a multi-dimensional parameter space feature analysis unit of meteorological factors, pollutant concentrations, and ecological indexes, and establishing a spatio-temporal coupling characteristic analysis channel of cross-modal parameters by constructing a multi-channel parallel feature extraction module to realize joint representation of time series data and spatial distribution data.

[0120] a visual decision support interface for providing a visual interface.

[0121] As a preferred embodiment, the system architecture proposed in this embodiment realizes hardware entity deployment through a modular mapping method. Specifically, the linkage range determination module, the data acquisition frequency acquisition module, the dynamic region division engine, the secure shared network construction unit, the distributed deep learning operation cluster, the multi-modal data fusion processor, and the visual decision support interface can be mapped to the following hardware entities:

[0122] At the hardware implementation level: the linkage range determination module is composed of an IoT gateway, a spatial location service (GIS) server, and a software-defined network (SDN) controller. The IoT gateway is responsible for device access range management, the GIS server realizes accurate delimitation of the linkage area based on the geographic fence technology, and the SDN controller realizes dynamic configuration of the network device collaboration domain; the data acquisition frequency acquisition module integrates wireless sensor nodes, data acquisition terminals, and edge gateways to realize adaptive adjustment of multi-dimensional data acquisition frequency; the dynamic region division engine architecture includes a streaming data processing server, an edge computing node, and a cloud resource manager to build an elastic computing resource scheduling system; the secure shared network construction unit integrates a hardware security module (HSM), a dynamic encryption routing device, and a blockchain consensus node to establish a trusted data exchange mechanism; the distributed deep learning operation cluster deploys a GPU parallel computing array, a TPU special acceleration unit, and an AI inference server to form a hierarchical intelligent computing architecture; the multi-modal data fusion processor configures a FPGA programmable accelerator, a multi-source sensor fusion platform, and a distributed object storage system to complete real-time heterogeneous data processing; the visual decision support interface integrates a large-screen display system, a multi-point touch interaction terminal, and a WebGL visualization server to build a multi-dimensional data presentation system.

[0123] Although the embodiments of the present application have been shown and described, it can be understood by those of ordinary skill in the art that various changes, modifications, replacements, and variations can be made to these embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended embodiments and their equivalents.

Claims

1. A method for cross-regional environmental data sharing and analysis based on big data deep learning, characterized in that: include: Determine the scope of the linkage between target devices and the analysis environment data to avoid ineffective coverage and resource waste in cross-regional data transmission; Obtain the frequency of environmental data collection within the linkage range; Based on the linkage range and collection frequency, the region is dynamically divided into big data deep learning areas to achieve spatial matching of computing resources and data value, and improve the data processing efficiency of high-priority areas. Building a shared network based on deep learning regions using big data; After accessing the shared network, target devices in different areas acquire the required environmental data and analyze and predict the environmental data based on big data deep learning algorithms.

2. The method for cross-regional environmental data sharing and analysis based on big data deep learning according to claim 1, characterized in that: Methods for obtaining the linkage range include: Determine the latitude and longitude coordinates of the center point of each region; Calculate the Euclidean distance between the center points of two adjacent regions based on latitude and longitude coordinates; The linkage range is set based on the obtained Euclidean distance.

3. The method for cross-regional environmental data sharing and analysis based on big data deep learning according to claim 2, characterized in that: The following distance calculation formula was used for Euclidean distance. include: Radius = angle × (π / 180), used to convert angles to radians; It is used to determine the actual distance between the center points of two adjacent areas using latitude and longitude coordinates, thereby setting the linkage range more accurately; in The Euclidean distance between the centers of the two regions is given by [the Euclidean distance]. This represents the difference in latitude between the center points of the two regions, expressed in radians. The difference in longitude between the center points of the two regions. The average latitude of the center points of the two regions. The radius of the Earth is taken as 6371 km. and as well as and These represent the latitude and longitude coordinates of the center points of two adjacent regions, respectively.

4. The method for cross-regional environmental data sharing and analysis based on big data deep learning according to claim 1, characterized in that: Methods for establishing priority evaluation criteria include: Data acquisition frequencies are divided into several frequency levels; Establish the spatial mapping relationship between the acquisition frequency and the visual environment feature matrix; Acquire environmental feature data of the target location and construct a frequency-feature space correlation map by combining the corresponding frequency levels; Priority ranking is determined based on the product of the distribution weights of frequency parameters and environmental characteristics within the linkage range.

5. The method for cross-regional environmental data sharing and analysis based on big data deep learning according to claim 1, characterized in that: Methods for constructing shared networks include: Based on the linkage range parameters, a network node cluster is deployed in the target area to enable rapid transmission and sharing of cross-regional environmental data. Establish an environmental data sharing network based on spatial location encryption. This network uses the latitude and longitude coordinates of the regional center point as an initial vector, combined with real-time timestamp parameters, to generate an irreversible 128-bit session key, preventing data interception or tampering during cross-regional transmission.

6. The method for cross-regional environmental data sharing and analysis based on big data deep learning according to claim 1, characterized in that: The implementation methods for optimizing regionalized deep learning computations include: Computing resources are dynamically allocated based on the priority of the divided regions. This is used to allocate computing resources according to the priority ranking of each divided region, thereby ensuring that deep learning operations on environmental data in different regions can be carried out efficiently. Implement multimodal data fusion processing and feature extraction to enhance the comprehensive analysis capabilities of cross-regional environmental data.

7. The method for cross-regional environmental data sharing and analysis based on big data deep learning according to claim 1, characterized in that: The method for dividing the big data deep learning region includes: Construct a visual environmental feature matrix for the target region; Priority evaluation criteria for constructing a visualized environmental feature matrix based on acquisition frequency; The corresponding positions of the linkage range are dynamically divided according to the priority order; Optimize regional deep learning operations based on dynamic partitioning results.

8. A cross-regional environmental data sharing and analysis system based on big data deep learning, using the cross-regional environmental data sharing and analysis method based on big data deep learning as described in any one of claims 1-7, characterized in that, include: The linkage range determination module is used to determine the linkage range of target devices in sharing and analyzing environmental data; The data acquisition frequency acquisition module is used to acquire the acquisition frequency of environmental data within the linkage range; A dynamic region partitioning engine is used to dynamically partition big data deep learning regions within a region based on the linkage range and collection frequency. The secure shared network building unit is used to achieve dynamic encryption of data channels through a combination of geographic coordinates and timestamps; A distributed deep learning computing cluster is used to perform distributed computing tasks on large datasets and deep learning regions. The multimodal data fusion processor adopts a heterogeneous data source collaborative processing architecture, integrates multi-dimensional parameter spatial feature analysis units of meteorological factors, pollutant concentrations and ecological indices, and realizes joint characterization of time series data and spatial distribution data by constructing a multi-channel parallel feature extraction module, and establishes a spatiotemporal coupling characteristic analysis channel for cross-modal parameters. A visual decision support interface, used to provide a visual interface.

9. The cross-regional environmental data sharing and analysis system based on big data deep learning according to claim 8, characterized in that: The linkage range determination module includes: an IoT gateway, a GIS server, and an SDN controller. The IoT gateway is used to manage the device connection range, the GIS server is used to determine the linkage range through geofencing technology, and the SDN controller is used to dynamically configure the network device collaboration range. The data acquisition frequency acquisition module includes: wireless sensor nodes, data collectors, and edge gateways. The dynamic region partitioning engine includes: stream processing servers, edge computing nodes, and cloud resource managers. The secure shared network construction unit includes: a hardware security module, a dynamic encrypted router, and blockchain nodes. The distributed deep learning computing cluster includes: a GPU cluster, a TPU cluster, and an AI server. The multimodal data fusion processor includes: an FPGA acceleration server, a multi-sensor fusion platform, and a distributed storage system. The visual decision support interface includes: a data dashboard, an interactive touch terminal, and a Web visualization server.

Images