Seabed data organization method and system based on space entity object

Abstract

The invention provides a seabed data organization method and system based on a space entity object, and the method comprises the steps: constructing a multi-dimensional data layer structure which comprises a space object layer, a storage structure layer, an unstructured data layer and a verification and extension layer, and the data in each layer is composed of nodes; data nodes are created in a data layer, and a systematic, convenient, efficient, verifiable and expandable data organization form is carried out on data by adopting a heterogeneous graph neural network with data generation information in the layers and among the layers based on the nodes. Wherein the data generation information is participated by a large number of social ships, and the efficiency of data generation and further data organization is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to a seabed data organization method and system, in particular to a seabed data organization method and system based on spatial entity objects, and belongs to the field of geographic data processing. BACKGROUND

[0002] The research on the nearshore seabed area needs to integrate multi-source heterogeneous data for analysis, including geological and geomorphological data, geophysical data, hydrological and hydrodynamic data, marine biology and ecological data, legal and political data, and related mineral environmental and resource data. How to organically organize these multi-element data to solve the technical problems of convenient retrieval, real-time update, and expansion. The data needs to be reorganized and the logical relationship between them. On this basis, a unified data organization model structure is designed, and multi-source heterogeneous data (such as satellite remote sensing, seabed exploration, seismic exploration, etc.) are integrated through hierarchical classification. The fused data is applied to the formulation and optimization of the nearshore seabed area scheme, supports accurate decision-making and international law compliance evaluation, and provides strong technical support for marine rights maintenance and resource development. SUMMARY

[0003] To solve the above problems, the present application is designed from the following points, so as to find a real-time multi-source heterogeneous data organization method, the first data type classification, relationship, storage structure design, and verifiability; the second data fusion; the third data update scheme.

[0004] Based on the above design points, the present application provides a seabed data organization method based on spatial entity objects, comprising the following steps:

[0005] S1, a multi-dimensional data layer structure is constructed, including a spatial object layer, a storage structure layer, an unstructured data layer, and a verification and expansion layer, and the data in each layer is composed of nodes;

[0006] S2, a heterogeneous graph neural network H i (V i ,E i ,R i ,T i ,D i ) and an inter-layer heterogeneous graph neural network H int (V int ,E int ,R int ,T int ,D int ) are respectively established in the layers and between the layers of the data layer structure, wherein V i , V int , E i , E int , R i , Rint ,T i T int D i D int Five sets of variables represent the network node set, path set, node relationship set, data type set, and data information set of both entities, respectively. The data information set includes data content and data generation information. Let v be two nodes in the multidimensional data layer structure. m ,v n If m and n are node codes, then the path E between the two nodes is... mn =(v m ,r mn ,v n The path E between the data type set and the data information set. TD =(t m ,r m ,d m )∪(t n ,r n ,d n )∪(X m ,r′ mn ,Y n ),X m =t m ∪d m ,Y n =t n ∪d n ,t n ∈T i ,t m ∈T i This includes the path between the data type sets and data information sets of the two nodes, the path between the data type sets and data information sets of the two nodes, and the path E between the node and the data type sets and data information sets. vTD =(v k ,r vTD ,T i )∪(v k ,r vTD D i ), (E mn ∪E TD ∪E vTD )=(E i ∪E int ), , node v k For T i and D i For nodes in or outside the specified layer, k represents the node v. k The encoding includes data generation information such as the method of data generation, the time of data generation, and the update history;

[0007] It should be understood that the heterogeneous graph neural network is a framework of data fusion, after the construction is completed, only the corresponding nodes in the data layer are stored therein, and the path, relationship, type, data information are defined, the fusion is completed, the data retrieval reversible mapping between nodes is completed through the path, and convenient retrieval is completed.

[0008] The fusion of S3 data is firstly cleaned and standardized through data preprocessing on the multi-dimensional data layer structure; then, the data of each layer of S1 is filled into the nodes of S2, and the fusion of three-dimensional vector data, grid data, marine hydrological and meteorological data, and real scene three-dimensional data is completed.

[0009] Optionally, the spatial object layer includes data belonging to the data type set in the layer, and determines the features and uses of the data content belonging to the data information set of each data type as follows (for the naming of the tables appearing later, the following is in the order of table number Chinese character ranking, for example, the second, the third, etc.):

[0010]

[0011]

[0012] The storage structure layer is a storage structure of the nodes and their mutual relationship in the construction layer, including a metadata storage structure, a geometric information storage structure, a link object storage structure, an attribute storage structure, a material, texture, picture data storage structure, a geometric template storage structure, and an extended content storage structure, which are respectively represented by the following seven tables:

[0013]

[0014]

[0015] The source object and the target object belong to two nodes in the layer

[0016]

[0017] The path between the spatial object nodes and the path between the field names are established through the description in the link object storage structure The path between them is established through the relationship between the data types and the descriptions in the seven tables in the foregoing The path between them is established through the relationship between the data types and the descriptions in the seven tables in the foregoing The path between them is established through the relationship between the data types and the descriptions in the seven tables in the foregoing The path between them is established through the relationship between the data types and the descriptions in the seven tables in the foregoing The path between them is established through the relationship between the data types and the descriptions in the seven tables in the foregoing

[0018] ​An unstructured data layer is configured to store policies and regulations, biological and ecological resource videos, and marine protection right and interest documents, and includes an association mechanism between the unstructured data and the spatial object layer and the unstructured data layer, which are represented by tables as follows:

[0019]

[0020]

[0021] According to the description in the association mechanism , a path is established between a spatial node and a data type and description in the unstructured data layer

[0022] A verification and expansion layer is configured to verify the insertion of new data in other layers and establish new relationships between the new data and other existing data, verify the insertion of new data, and verify whether the insertion can be accurately completed, including verifying nodes and expansion nodes, verifying nodes by establishing path links with nodes in other layers to achieve the insertion, query, and update of data, and deleting any data in the verification node after the verification is completed, and the expansion nodes include the addition of data nodes in other layers and the update of corresponding data information in the nodes, and the addition and update are also achieved by the path links of the heterogeneous graph neural network.

[0023] It should be understood that the nodes, path sets, and node relationship sets of the present application are mathematical abstract representations of data, the data type sets, and the data information sets are specific data corresponding to the abstract nodes, and the specific data is also abstracted as nodes in the neural network, that is, although the data types descriptions descriptions relationship types and the like are indicated in the above tables, the data types, descriptions, relationship types, and the like are all nodes in the heterogeneous graph neural network. In other words, the data types descriptions descriptions relationship types and the like in the tables represent the data to which the specific contents of the nodes belong. When the path between the nodes belongs to the path in the inter-layer heterogeneous graph neural network, the nodes at both ends of the path respectively belong to V int , and the corresponding path set, node relationship set, data type set, and data information set are respectively denoted as E int , R int , T int , and D int , with i as the subscript to distinguish the case in the layer.

[0024] E mn = (v m , rmn ,v n The nodes in the E mn may be nodes abstracted from the five types of data, i.e., data characteristics, data use, field name, data type and description in the above-mentioned nine tables in the spatial object layer, the storage structure layer and the unstructured data layer. In this case, the paths between the nodes are represented as E TD and the paths between the data information are represented as E vTD Therefore, there are That is, when at least one of the nodes in the E mn is represented by the specific data information, the corresponding relationship subset r m r n r′ mn r vTD are all subsets of r mn The data related to time in the above-mentioned nine tables belong to the data generation information, and the addition and update of other data types, as well as the generation and update time of the description itself in the table, all belong to the time of data generation and the update history in the data generation information.

[0025] The data generation method includes the following steps:

[0026] For the data in the spatial object layer, the following steps are included:

[0027] Q1 installing a detector and a satellite positioning system on a social ship, or on a social ship, a detection ship and / or a diving ship,

[0028] Q2 recording the detection signal at a regular time when the ship is sailing,

[0029] Q3 combining the detection signal and the satellite positioning at the detection time to draw a shallow seabed image;

[0030] Q4 obtaining middle and deep sea detection data, drawing a middle and deep sea seabed image, splicing the shallow seabed image to form a spliced image, and marking the data in the spatial object layer to form three-dimensional real scene data;

[0031] For the storage structure layer and the unstructured data layer, a computer system is arranged on the social ship or the social ship and the detection ship or the diving ship to obtain the corresponding data for storage in the corresponding storage structure layer and the unstructured data layer in the remote server.

[0032] It can be understood that, therefore, the generation efficiency of the shallow sea layer detection data is improved through the participation of a large number of social ships and frequent detection practices.

[0033] Optionally, the fusion method of three-dimensional vector data, grid data, marine hydro-meteorological data and real scene three-dimensional data comprises the following steps:

[0034] The fusion method of three-dimensional vector data comprises:

[0035] S3-1-1 stores the obtained three-dimensional vector data containing three-dimensional spatial coordinates (i.e. the first type of data of the label weight, the composite data formed by mapping the three types of data of data adjustment and data use to the three-dimensional spatial coordinates) into the spatial object layer, and fills the data into the nodes of the corresponding metadata storage structure, the geometric information storage structure, the linking object storage structure, the attribute storage structure, the material, texture and picture data storage structure, the geometric template storage structure, the extended content storage structure and the unstructured data layer;

[0036] It is easy to understand that the three-dimensional vector data is actually the data in the spatial object layer labeled on the mapping image with three-dimensional spatial coordinates.

[0037] S3-1-2 completes the path link between the nodes filled with data by the heterogeneous graph neural network model constructed by S2 to realize the fusion of data; the fusion method of grid data comprises:

[0038] S3-2-1 performs fixed resolution grid division on the spliced image, and encodes the grid unit by using a preset encoding rule;

[0039] S3-2-2 stores each encoding into the nodes in the spatial object layer, and completes the path link between the nodes in the spatial object layer, each storage structure and the nodes filled with data in the unstructured data layer according to the heterogeneous graph neural network model constructed by S2 to realize the fusion of data;

[0040] The fusion method of marine hydro-meteorological data comprises:

[0041] S3-3-1 obtains and analyzes marine environmental information field data, and classifies the information field data with the same or similar characteristics into a field node;

[0042] S3-3-2 obtains the distribution of the field nodes in the spatial object layer and the storage structure layer and the unstructured data layer;

[0043] For example, the distribution of the field nodes on the spatial object elements (such as shallow sea area, deep sea area, trench, etc.) in different grid nodes in the spatial object layer, the distribution of the field nodes on the surface elements and the boundary line elements in different regions in the storage structure layer, the distribution of the field nodes on different time elements and the distribution of the field nodes on mixed elements in the unstructured data layer.

[0044] S3-3-3 For all the distributions, each field node in all layers is taken as the node described in S2, and the heterogeneous graph neural network model constructed according to S2 is also used to complete the path link between the information field data in the nodes in the spatial object layer, each storage structure layer and unstructured data layer, so as to realize the fusion of data.

[0045] The fusion method of real three-dimensional data comprises the following steps:

[0046] S3-4-1 Obtain large-scale three-dimensional model data 3DTiles specification;

[0047] S3-4-2 Fuse the three-dimensional real scene data under the 3DTiles specification.

[0048] Optionally, the preset encoding rule comprises a Morton traversal order rule, the information field comprises temperature, density, salt composition, sea luminescence, ocean current vector velocity, transparency, water color and sea surface wind composition, and the three-dimensional real scene data comprises at least one of osgb, gltf and b3dm.

[0049] Another object of the present application is to provide a seabed data organization system based on spatial entity objects, which comprises a social ship, or a social ship, a detection ship and / or a diving ship, and a remote server, wherein the social ship and the detection ship are provided with a detector for making three-dimensional real scene data, and a corresponding computer system is arranged for obtaining corresponding data and storing the data into a corresponding storage structure layer and an unstructured data layer of the remote server, the remote server receives signals from the detector and the detection device, constructs a spatial object layer, processes the signals, completes the making of the three-dimensional real scene data, and realizes the seabed data organization method of the spatial entity objects through the installed software system.

[0050] Advantages

[0051] By arranging the data in a multi-dimensional data layer structure and involving the specific data structure of each layer, the data is organized in a systematic, convenient, verifiable and expandable manner by using data node means and a heterogeneous graph neural network with data producing information in the layer and between layers based on the data nodes. In addition, a large number of social ships are involved in seabed data detection, which improves the efficiency of data generation and further data organization. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 The data organization general diagram constructed for the seabed data organization method based on spatial entity objects in embodiment 1 of the present application;

[0053] Figure 2 The data organization general diagram constructed for the seabed data organization method based on spatial entity objects in embodiment 1 of the present application; Figure 1 The data organization general diagram constructed for the seabed data organization method based on spatial entity objects in embodiment 1 of the present application;

[0054] Figure 3 A program interface schematic diagram for verifying data insertion;

[0055] Figure 4 A program interface schematic diagram for verifying data query;

[0056] Figure 5 A program interface schematic diagram for verifying data update;

[0057] Figure 6a A schematic diagram of a ship sailing in different near-shore seabed area sea areas for verifying the data generation method in the spatial object layer of Embodiment 1 of the present application;

[0058] Figure 6b A flowchart of three-dimensional real scene data making;

[0059] Figure 6c A flowchart of grid data division and fusion method in Embodiment 2 of the present application;

[0060] Figure 6d A flowchart of marine hydro-meteorological data fusion method in Embodiment 2 of the present application;

[0061] Figure 7 A flowchart of three-dimensional vector data fusion method in Embodiment 2 of the present application. DETAILED DESCRIPTION

[0062] Embodiment 1

[0063] This embodiment will illustrate a seabed data organization method based on spatial entity objects, as shown in FIG. 1, including the following steps: Figure 1

[0064] S1, constructing a multi-dimensional data layer structure, including a spatial object layer, a storage structure layer, an unstructured data layer, and a verification and expansion layer, and the data in each layer is composed of nodes;

[0065] S2, constructing a heterogeneous graph neural network in each layer and between layers, and the network forms a reversible path between nodes in each layer and between layers, and the heterogeneous graph neural network in each layer and between layers is respectively represented as H i (V i ,E i ,R i ,T i ,D i ) and H int (V int ,E int ,R int ,T int ,D int ).

[0066] ​Firstly, the node relationship and path are described, which is developed around the node set, relationship set, data type set, and data generation information set, and is divided into three categories, as shown in Figure 2 .

[0067] Since the verification nodes in the verification and expansion layer and the expansion layer nodes, and the paths between other layers in the heterogeneous graph neural network are described in the same way, for the convenience of description, Figure 2 only the spatial object layer, the storage structure layer, and the unstructured layer are listed to construct the description of the heterogeneous graph neural network in each layer and between layers.

[0068] The spatial object layer includes three types of data, data types, data characteristics, and data purposes as described in the first table, and the layer data set to which it belongs can be referred to the first table. The storage structure layer data has seven categories, which correspond to the seven tables described above, and the layer data set to which it belongs can be referred to the second to seventh tables, and each category of table contains three types of nodes, field name, data type, and description. The heterogeneous graph neural network constructed between the nodes in the layer is the heterogeneous graph neural network in the layer, and the one constructed between the layers is the inter-layer heterogeneous graph neural network.

[0069] For the three types of data in the spatial object layer, the path representation between the nodes is a proper subset of E mn , and the relationship set of the nodes at both ends of the path is r mn . The corresponding heterogeneous graph neural network belongs to the layer. Taking the metadata storage structure in the storage structure layer as an example, the heterogeneous graph neural network constructed between the field name node and the node in the spatial object layer belongs to the inter-layer, and the field name node between the material and the texture, picture data storage structure belongs to the intra-layer.

[0070] For data types and data information as nodes, the network node path representation constructed is a proper subset of E TD , and the relationship set of the nodes at both ends of the path is r m , r n , r′ mn , which is a proper subset of the relationship set r mn . The description of the relationship set between the nodes in the spatial object layer links the “description” type data in the object storage structure, which is also a proper subset of the relationship set r mn .

[0071] Taking the field name, data type, and description between the unstructured data in the unstructured data layer, the data purpose and the description of the unstructured data in the spatial object layer, and the data type and the data type in the association mechanism in the spatial object layer as examples, the heterogeneous graph neural network constructed between the three groups of nodes belongs to the inter-layer, and the path representation between the nodes is a proper subset of E vTD , and the relationship set of the nodes at both ends of the path is rvTD It is also a relation set r mn A proper subset of .

[0072] Therefore, in heterogeneous graph neural networks, nodes involving both data types and descriptions from non-spatial object layers are represented by their path relation sets with subscripts ending in TD. Furthermore, if a node with a field name is also a node on the path, its subscript is uniformly represented with vTD (note that data types and descriptions do not need to be fully included; since this invention defines a path with only two nodes, it is still represented by a path set with vTD. For multi-node paths, it is considered as a concatenation of two or more paths). The relation set subscript for the corresponding path node is also vTD. If a node does not belong to either the data type or description category from the non-spatial object layer, then the corresponding path set and relation set subscript representation is mn, resulting in three main categories.

[0073] The heterogeneous graph neural network constructed in this way facilitates subsequent data fusion, data querying, updating, and verification. It can also be used for other research work based on the data access history.

[0074] Secondly, the paper introduces data verification, testing the integrity and performance of the storage structure using real-world data (such as seabed mining areas and mining boundaries). Figure 3 A program was developed to insert metadata, geometric information, and attribute data for a seabed mining area. For example... Figure 4 As shown, the metadata, geometric information, and attribute data hierarchy of mining area A were queried. Figure 5 A program to update the resource reserve attributes of mining area A.

[0075] To verify the effectiveness of the unstructured data linking mechanism, it is first necessary to ensure that unstructured data (such as policies and regulations, videos of biological and ecological resources, and approvals for marine protection rights) can be accurately associated with corresponding spatial objects (such as seabed mining areas and mining boundaries). By inserting test data and establishing relationships, it is necessary to check whether the association table (such as unstructured_data_links) can correctly record the relationship between unstructured data and spatial objects, and to verify whether query operations can efficiently retrieve unstructured data associated with specific spatial objects.

[0076] The compatibility of the storage structure for new data types, such as newly added marine ecological data, is mainly to verify whether the database can flexibly support the possible addition of new data types and formats in the future. By inserting new types of data (such as marine ecological monitoring data) in the extension content table (such as extension_content), and checking whether the storage, query and update operations are normal, the expansion capability of the storage structure is evaluated. For example, a marine ecological monitoring record can be inserted, including species distribution, ecological environment change and other data, and it is verified whether these data can be correctly stored and associated with related spatial objects. In addition, the compatibility of new data types with existing data needs to be tested to ensure that the addition of new data does not affect the integrity and performance of existing data.

[0077] Finally, the data generation information in the heterogeneous graph neural network includes the method of data generation, the time of data generation, and the update history, which reflects the real-time nature of data organization. The data generation method includes the following steps:

[0078] In combination with Figures 6a to 6d As shown in the figure, the data in the spatial object layer includes the following steps:

[0079] Q1 as Figure 6a , gives the three levels of shallow sea, middle layer, and deep sea in the nearshore seabed area. On the social ship, the detection ship, and the two groups of diving ships, install the detector and the satellite positioning system (not shown in the figure), the social ship sails in the shallow sea, the detection ship sails in the middle layer, one group of diving ships sails underwater in the middle layer, and the other group of diving ships sails underwater in the deep sea.

[0080] As shown below Figure 6b Q2, when various ships are sailing, record the detection signal at regular intervals,

[0081] Q3 combines the detection signal and the satellite positioning at the detection time to draw the shallow seabed image;

[0082] Q4 obtains the middle layer and deep sea detection data, draws the middle layer and deep sea seabed image, and splices it with the shallow seabed image to form a spliced image, and marks the data in the spatial object layer to form three-dimensional real scene data;

[0083] For the storage structure layer and the unstructured data layer, corresponding detection devices are installed on the social ship, or on the social ship and the detection ship or the diving ship, to obtain corresponding data for storage in the corresponding storage structure layer and the unstructured data layer.

[0084] S3 data fusion, first, through data preprocessing, the multi-dimensional data layer structure is cleaned and standardized; then, the data of each layer of S1 is filled into the nodes of S2, and the fusion of three-dimensional vector data, grid data, marine hydrological and meteorological data, and real scene three-dimensional data is completed respectively.

[0085] Embodiment 2

[0086] This embodiment will be specifically explained for the fusion of data in Embodiment 1.

[0087] The fusion method of three-dimensional vector data, as shown in Figure 7 specifically includes:

[0088] S3-1-1 stores the obtained three-dimensional vector data containing three-dimensional space coordinates into the space object layer, and fills in data in the nodes in the corresponding metadata storage structure, geometry information storage structure, linked object storage structure, attribute storage structure, material, texture, picture data storage structure, geometry template storage structure, extended content storage structure (seven types of storage structures), and unstructured data layer;

[0089] S3-1-2 completes the path link between the nodes filled with data through the heterogeneous graph neural network model (including layers and interlayers) constructed by S2, so as to realize the fusion of data;

[0090] The fusion method of grid data includes, as shown in Figure 6c

[0091] S3-2-1 divides the fixed resolution grid into rectangular grid cells, and encodes the grid cells using the Morton traversal order rule;

[0092] Among them, the fixed resolution gridding is a standard method for generating point data sets by setting a resolution or grid spacing, and then calculating the value of each grid according to the single attribute of the point group contained in each cell;

[0093] The size of the grid cell is variable, and the area where the marine environmental elements change greatly is represented by small grid cells; the area where the change is small is represented by large grid cells. To ensure that the grid mosaic partition can still cover the bounded area, and the traversal method must be able to organize the cells in order. Each cell carries several attribute values. Adjacent cells can be aggregated to greatly reduce the amount of data. Small cells only exist in places where the attribute between cells changes very quickly, such as shoals, coastlines and obstacles. Relatively stable or flat areas, such as the bottom of the strait, will result in some aggregated cells.

[0094] Morton order encoding is to traverse each cell from left to right, from bottom to top, regardless of the size of the cell. It first increases the X coordinate, and then the Y coordinate. This can also be extended to the case of multiple dimensions, first increasing the X coordinate, then the Y coordinate, then the Z coordinate, and so on to more dimensions.

[0095] ​S3-2-2 stores the path links between the nodes in the spatial object layer, the unstructured data layer and the storage structure layer according to the heterogeneous graph neural network model constructed in S2, so as to realize the fusion of data.

[0096] The marine hydro-meteorological data fusion method comprises the following steps as shown in the figure: Figure 6d

[0097] S3-3-1 obtains and analyzes marine environmental information field data, including temperature, density, salt composition, sea luminescence, ocean current vector velocity, transparency, water color, and sea surface wind composition, and groups information field data with the same characteristics into a field node.

[0098] S3-3-2 obtains the distribution of the field node in the spatial object layer, the storage structure layer and the unstructured data layer.

[0099] S3-3-3, for all the distributions, takes each field node in all layers as the node in S2, and according to the heterogeneous graph neural network model constructed in S2, completes the path links between the information field data in the nodes in the spatial object layer, the storage structure layer and the unstructured data layer, so as to realize the fusion of data.

[0100] The fusion method of real three-dimensional data comprises the following steps:

[0101] S3-4-1 obtains large-scale three-dimensional model data 3DTiles specification.

[0102] S3-4-2 fuses three-dimensional real scene data osgb under the 3DTiles specification.

[0103] Embodiment 3

[0104] The embodiment provides a seabed data organization system based on spatial entity objects, which comprises a social ship, a detection ship, two groups of diving ships and a remote server (not shown in the figure), as shown in the figure. Figure 6a The social ship, the detection ship and the two groups of diving ships are provided with detectors for three-dimensional real scene data production, and corresponding computer systems are arranged for obtaining corresponding data and storing the data into the corresponding storage structure layer and the unstructured data layer of the remote server. The remote server receives signals from the detectors and detection devices, constructs a spatial object layer, processes the signals, completes the production of three-dimensional real scene data, and realizes the seabed data organization method of spatial entity objects through the installed software system.​

Claims

1. A method for organizing seabed data based on spatial entity objects, characterized in that, Includes the following steps: S1 constructs a multi-dimensional data layer structure, including a spatial object layer, a storage structure layer, an unstructured data layer, and a verification and extension layer. The data in each layer is composed of nodes. S2 establishes heterogeneous graph neural networks H within and between layers of the data layer structure. i (V i E i ,R i ,T i D i ) and interlayer heterogeneous graph neural network H int (V int E int ,R int ,T int D int ), where V i V int E i E int ,R i R int ,T i T int D i D int Five sets of variables represent the network node set, path set, node relationship set, data type set, and data information set of both entities, respectively. The data information set includes data content and data generation information. Let v be two nodes in the multidimensional data layer structure. m ,v n If m and n are node codes, then the path E between the two nodes is... mn =(v m ,r mn ,v n The path E between the data type set and the data information set. TD =(t m ,r m ,d m )∪(t n ,r n ,d n )∪(X m ,r m ' n ,Y n ),X m =t m ∪d m ,Y n =t n ∪d n ,t n ∈T i ,t m ∈T i This includes the path between the data type sets and data information sets of the two nodes, the path between the data type sets and data information sets of the two nodes, and the path E between the node and the data type sets and data information sets. vTD =(v k ,r vTD ,T i )∪(v k ,r vTD ,D i ), (E mn ∪E TD ∪E vTD )=(E i ∪E int ), node v k For T i and D i For nodes in or outside the specified layer, k represents the node v. k The encoding, The data generation information includes the method of data generation, the time of data generation, and the update history; The fusion of S3 data first involves cleaning and standardizing the multidimensional data layer structure through data preprocessing; then, the data from each layer of S1 are filled into the nodes of S2, and the fusion of three-dimensional vector data, grid data, marine hydrological and meteorological data, and real-scene three-dimensional data is completed respectively.

2. The method according to claim 1, characterized in that, The spatial object layer includes data belonging to the data type set within the layer, and the characteristics and uses of the data content belonging to the data information set for each data type are defined in the following table: The storage structure layer is the storage structure for the nodes and their relationships in the construction layer. It includes the metadata storage structure, geometric information storage structure, linked object storage structure, attribute storage structure, material, texture, and image data storage structure, geometric template storage structure, and extended content storage structure, which are represented by the following seven tables: The source object and the target object belong to two nodes in the layer. By linking the description in the object storage structure The call establishes paths between spatial object nodes. and the path between field names The relationships between data types and descriptions within and between the preceding seven tables are illustrated by these relationships. Establish the path between them It also utilizes the relationships between nodes or field names in the spatial object layer and field names, data types, and descriptions in the preceding seven tables. Establish the path between them The unstructured data layer is used to store policies and regulations, videos of biological and ecological resources, and approvals for marine protection rights. It specifically includes unstructured data and the association mechanism between the spatial object layer and the unstructured data layer, as shown in the following tables: According to the description in the association mechanism The call establishes a path between the spatial node and the data types and descriptions in the unstructured data layer. The validation and extension layer is used to validate the insertion of new data into other layers, establish new relationships between new data and other existing data, validate queries for inserting new data, and verify whether the process can be completed accurately. It includes validation nodes and extension nodes. Validation nodes establish path links with nodes in other layers to realize data insertion, querying, and updating. After validation is completed, any data in the validation node is deleted. Extension nodes include the addition of data nodes in other layers and the updating of corresponding data information in the nodes. Similarly, the addition and updating are realized through heterogeneous graph neural network path links.

3. The method according to claim 1 or 2, characterized in that, The data generation method includes the following steps: For data in the spatial object layer, the following steps are involved: Q1 Install detectors and satellite positioning systems on social vessels, or on social vessels, exploration vessels and / or submarines; Q2 records the detection signals periodically while the ship is sailing; Q3 combines the detection signals and satellite positioning at the time of detection to create images of the shallow seabed; Q4. Acquire mid- and deep-sea exploration data, create mid- and deep-sea seabed images, and stitch them together with shallow seabed images to form a stitched image. Mark the data in the spatial object layer to form three-dimensional real-scene data. For the storage structure layer and unstructured data layer, the relevant data is obtained through computer systems installed on social vessels, or on social vessels, exploration vessels, or submarines, and then stored in the corresponding storage structure layer and unstructured data layer of the remote server.

4. The method according to claim 3, characterized in that, The method for fusing 3D vector data, grid data, marine hydrological and meteorological data, and real-scene 3D data includes the following steps: Methods for fusing 3D vector data include: S3-1-1 stores the acquired 3D vector data containing 3D spatial coordinates into the spatial object layer, and fills the data into the nodes of the corresponding metadata storage structure, geometric information storage structure, linked object storage structure, attribute storage structure, material, texture and image data storage structure, geometric template storage structure, extended content storage structure, and unstructured data layer. S3-1-2 uses the heterogeneous graph neural network model built through S2 to complete the path links between nodes that have been filled with data, thereby achieving data fusion; the methods for fusion of grid data include: S3-2-1 Divide the stitched image into a fixed-resolution grid, and encode the grid units using a preset encoding rule; For each encoded node stored in the spatial object layer, S3-2-2 uses the heterogeneous graph neural network model constructed in S2 to complete the path links between the nodes in the spatial object layer, the nodes in each storage structure and the nodes in the unstructured data layer that are filled with data, so as to achieve data fusion. Methods for fusing marine hydrological and meteorological data include: S3-3-1 Acquire and analyze marine environmental information field data, and group information field data with the same or similar characteristics into one field node; S3-3-2 Obtain the distribution of field nodes in the spatial object layer, storage structure layer, and unstructured data layer; For all the aforementioned distributions, each field node in all layers is treated as a node as described in S2. Based on the heterogeneous graph neural network model constructed in S2, the path links between information field data in nodes in the spatial object layer, each storage structure layer, and the unstructured data layer are also completed to achieve data fusion. Methods for fusing real-scene 3D data include: S3-4-1 Acquiring Large-Scale 3D Model Data: 3DTiles Specification; S3-4-2 integrates 3D reality data under the 3DTiles specification.

5. The method according to claim 4, characterized in that, The preset encoding rules include the Morton traversal order rules, and the information fields include various fields composed of temperature, density, salinity, marine luminescence, ocean current vector velocity, transparency, water color, and sea surface wind; the three-dimensional real-scene data includes at least one of osgb, gltf, and b3dm.

6. The method according to claim 4, characterized in that, Fixed-resolution gridding is a standard method for generating point datasets. It involves setting a resolution or grid spacing and then calculating the value of each grid cell based on the single attribute of the point group contained in each cell. The size of the grid cells is variable. Areas with large variations in marine environmental elements are represented by small grid cells, while areas with smaller variations are represented by large grid cells.

7. A seabed data organization system based on spatial entity objects, characterized in that, The method includes social vessels, or social vessels, exploration vessels, and / or submarines, as well as a remote server. The social vessels and exploration vessels are equipped with detectors for creating 3D reality data and corresponding computer systems for acquiring relevant data and storing it in the corresponding storage structure layer and unstructured data layer of the remote server. The remote server receives signals from the detectors and exploration devices, constructs a spatial object layer, processes the signals, completes the creation of 3D reality data, and implements the seabed data organization method for spatial entity objects as described in any one of claims 1-6 through the installed software system.

Images