Intelligent accounting platform and method for ocean industry data

Abstract

The invention relates to the technical field of ocean industry data accounting, in particular to an intelligent accounting platform and method for ocean industry data, and the method comprises the following steps: carrying out the multi-source data collection and preprocessing of the ocean industry data; performing nested analysis on multi-dimensional features in the marine industry data based on a deep learning algorithm, and constructing a marine resource utilization rate, ecological environment index and economic benefit ratio feature map; based on the feature map, constructing a comprehensive benefit scoring function, and meanwhile, fusing a spatial-temporal change rule of the data into the constructed function to realize comprehensive accounting of the ocean industry data; according to the method, the graph neural network model is introduced to perform feature nesting analysis, so that multi-dimensional features in ocean industry data can be deeply mined; the comprehensive benefit scoring function is constructed based on the adaptive weight coefficient, and the spatial and temporal change rule of the data is fused into the function, so that the intelligent accounting of the benefit change of each ocean region in different time periods is realized, and the timeliness and regional adaptability of the accounting are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of marine industry data accounting, and specifically to an intelligent accounting platform and method for marine industry data. Background Art

[0002] With the development of science and technology, the economy brought by marine industry data has become an important part of economic development. However, at this stage, the accounting of marine industry data faces the following challenges: In the process of calculating marine industry data, there are problems such as difficulty in aligning multi-source heterogeneous data, low data calculation accuracy, and lack of intelligent calculation methods. Traditional calculation methods often rely on manual operation and experience judgment, which cannot meet the complex and changeable needs of marine industry data; Traditional marine industry data accounting methods usually use static weights and fixed algorithms for comprehensive evaluation, but fail to fully consider temporal and spatial changes and regional differences. For example, the impact of seasonal factors, climate change, policy adjustments, etc. on resource utilization, ecological environment and economic benefits has not been dynamically adapted, resulting in limitations in accounting results. In addition, traditional models often lack flexible real-time feedback mechanisms and are difficult to cope with the rapidly changing marine environment and industry needs. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent accounting method for marine industry data, comprising the following steps: Multi-source data collection and preprocessing of marine industry data, specifically: Collect marine industry data in different formats through unified standards, and pre-process the collected data based on adaptive weighted dynamic fusion algorithm; Based on the deep learning algorithm, a nested analysis of the multi-dimensional features in the marine industry data is conducted to construct characteristic graphs of marine resource utilization rate, ecological environment index and economic benefit ratio, specifically: The fused marine industry data is used as a node set input into the graph neural network model, and a node feature matrix is ​​constructed. At the same time, feature nesting analysis is performed based on the graph neural network. In the layer-by-layer analysis process of graph convolution, an attention mechanism is introduced to eliminate the influence of neighbor nodes in the data propagation process, and a feature graph is constructed based on the calculated importance weights. Based on the characteristic graph, a comprehensive benefit scoring function is constructed. At the same time, the temporal and spatial variation patterns of the data are integrated into the constructed function to achieve comprehensive accounting of marine industry data.

[0005] As a preferred solution of the intelligent accounting method for marine industry data of the present invention, the marine industry data of different formats collected by unified standards are specifically as follows: Set the marine industry data source to , ,in, Indicates Marine industry data sources, Indicates of the marine industry data sources Item data; And mark the feature dimensions for each data source, including time features, spatial features, and attribute features, specifically:

[0006]

[0007]

[0008] in, Indicates The time characteristics corresponding to each marine industry data source represent the timestamp of the data record. Indicates of the marine industry data sources The timestamp corresponding to the data. Indicates The spatial features corresponding to the marine industry data sources represent the regional labels of the data records. Indicates of the marine industry data sources The regional label corresponding to the data. Indicates The attribute characteristics corresponding to the marine industry data source represent the data fields of the data record. Indicates of the marine industry data sources The data field corresponding to the data item.

[0009] As a preferred solution of the intelligent accounting method for marine industry data described in the present invention, the adaptive weighted dynamic fusion algorithm is specifically as follows: For each time point The corresponding attribute features of different data sources are used for data fusion based on adaptive weights, as follows:

[0010] in, Indicates Data sources in The attribute characteristics of Indicates the total number of data sources. Indicated in The fused data Indicates Data sources in The weight coefficient is as follows:

[0011] in, Indicates Data sources in The attribute characteristics of Indicated in is the average value of the attribute feature values ​​of all data sources. Indicates the total number of data sources. Indicates Data sources in The weight coefficient when Indicates The noise parameter of a data source is used to reflect the overall noise level of the current data source.

[0012] As a preferred solution of the intelligent accounting method for marine industry data described in the present invention, the graph neural network model is specifically as follows: According to the constructed graph neural network model, the marine industry data is used as a node set input into the graph neural network model, including different dimensional features of the marine industry data as a node set , the time series correlation between data is used as the edge set ,in, express nodes, Representation Node With Node The edge relationship between them is determined; Construct the feature matrix of the node, then we have, ,in, represents the constructed node feature matrix, Indicates the number of nodes, Represents feature dimensions, including resource utilization, ecological environment index, economic benefit ratio, ocean temperature and pollution index. At the same time, a node adjacency matrix is ​​constructed. ,and, Representation Node With Node The relationship between the edges can be determined, including the mutual influence of data between adjacent sea areas, the industrial connection between fishery production centers and ports, and the impact of pollution in a certain area on surrounding areas. Otherwise, it is 0.

[0013] As a preferred solution of the intelligent accounting method for marine industry data described in the present invention, the feature nesting analysis based on graph neural network is specifically as follows: Initialize node features ; Based on the graph convolution layer, the data is propagated layer by layer, then,

[0014] in, Indicates The node feature matrix of the layer, Indicates The weight matrix of the layer, represents the adjacency matrix, Indicates The node feature matrix of the layer;

[0015] in, represents the attention vector, represents the transposed matrix, represents the introduced transformation matrix, , Respectively represent nodes With Node The characteristic vector of Represents the calculated importance weight, which is the influence weight of the neighboring node.

[0016] As a preferred solution of the intelligent accounting method for marine industry data of the present invention, the feature graph constructed according to the calculated importance weight is as follows: The utilization rate of marine resources indicates the degree of development of marine resources in each region, including fishery resources and mineral development, specifically:

[0017] in, represents the importance weight of the calculation, Indicates the amount of fish caught, Indicates the total amount of resources available for development in the current area. Indicates the utilization rate of marine resources in the current area; The Ecological Environment Index indicates the environmental health of each region, including pollution index and water quality data, specifically:

[0018] in, represents the importance weight of the calculation, represents the pollutant concentration, Indicates the current regional environmental carrying capacity, Indicates the ecological environment index of the current area; The economic benefit ratio indicates the ratio of industry input to income, specifically:

[0019] in, represents the importance weight of the calculation, Indicates the total industrial income of the current region, including fisheries, tourism and port economy. Represents the total industry cost of the current region, including labor costs, resource consumption, and environmental governance. Represents the economic benefit ratio of the current region.

[0020] As a preferred solution of the intelligent accounting method for marine industry data described in the present invention, the comprehensive benefit score function is as follows: The comprehensive benefit score function is constructed based on the adaptive weight coefficient, then:

[0021] in, , , are adaptive weight coefficients, Represents the resource utilization characteristic graph, Represents the characteristic graph of ecological environment index, Represents the economic benefit characteristic diagram, Indicates the comprehensive benefit score corresponding to the current area; Based on the constructed comprehensive benefit score function, the calculation of marine industry data is realized, specifically:

[0022] in, represents the importance weight of the calculation, Indicates the comprehensive benefit score corresponding to the current area, represents the total number of ocean areas, It represents the accounting results of all ocean areas and is a comprehensive accounting result of marine industry data.

[0023] As a preferred solution of the intelligent accounting method for marine industry data of the present invention, the function of integrating the temporal and spatial variation law of data into the construction is as follows: Adaptive weight coefficient , as well as , affected by the temporal characteristics of marine industry data And spatial characteristics Dynamic control, specifically: Time characteristics of regulation,

[0024] in, Represents the seasonal change factor, which is the seasonal change time node in the time feature. The shorter the time from seasonal change, The smaller the seasonal variation factor, represents the basic adaptive weight coefficient, Represents the adjusted adaptive weight coefficient; Spatial characteristics of regulation,

[0025]

[0026]

[0027] in, , , represents the adaptive weight coefficient before adjustment, , , represents the adjusted adaptive weight coefficient, Indicates the resource density of the current area. Indicates the pollution concentration in the current area. Indicates the intensity of economic activity in the current region.

[0028] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of an intelligent accounting method for marine industry data when executing the computer program.

[0029] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of an intelligent accounting method for marine industry data.

[0030] Beneficial effects of the present invention: Marine industry data in different formats are collected through unified standards, and the data is pre-processed based on an adaptive weighted dynamic fusion algorithm, which enables the alignment and fusion of multi-source heterogeneous data and improves the accuracy and reliability of the data. The introduction of graph neural network model for feature nesting analysis can deeply explore the multi-dimensional features in marine industry data, construct characteristic graphs of marine resource utilization rate, ecological environment index and economic benefit ratio, and provide more comprehensive data support for accounting; A comprehensive benefit scoring function is constructed based on adaptive weight coefficients, and the temporal and spatial variation patterns of the data are integrated into the function, which enables intelligent calculation of benefit changes in various ocean regions in different time periods and improves the timeliness and regional adaptability of the calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 It is a schematic diagram of the overall method steps structure of the intelligent accounting method for marine industry data of the present invention. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0033] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0034] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0035] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0036] Meanwhile, in the description of the present invention, it should be noted that the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0037] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0038] Example 1 Reference Figure 1 , as an embodiment of the present invention, provides an intelligent accounting method for marine industry data, comprising the following steps: S1: Multi-source data collection and preprocessing of marine industry data.

[0039] Specifically, the multi-source data collection and preprocessing of the marine industry data is to collect marine industry data from different sources and in different formats through unified standardization, and preprocess the collected data based on the adaptive weighted dynamic fusion algorithm and time series algorithm. The specific implementation is as follows: Set the marine industry data source to , ,in, Indicates Marine industry data sources, Indicates of the marine industry data sources Item data; And mark the feature dimensions for each data source, including time features, spatial features, and attribute features, specifically:

[0040]

[0041]

[0042] in, Indicates The time characteristics corresponding to each marine industry data source represent the timestamp of the data record. Indicates of the marine industry data sources The timestamp corresponding to the data. Indicates The spatial features corresponding to the marine industry data sources represent the regional labels of the data records. Indicates of the marine industry data sources The regional label corresponding to the data. Indicates The attribute characteristics corresponding to the marine industry data source represent the data fields of the data record. Indicates of the marine industry data sources The data field corresponding to the data item; The data of different feature dimensions are converted as follows: Set a global reference timeline , and each data source Time characteristics Mapped to the global reference time axis, thus completing the temporal unification of data of different time dimensions; At the same time, each data Spatial characteristics Mapped into a unified spatial network, completing the spatial unification of data of different spatial dimensions; And the attribute characteristics of all data Perform normalization processing to complete the attribute standardization of data with different attribute dimensions; For each time point The corresponding attribute features of different data sources are used for data fusion based on adaptive weights, as follows:

[0043] in, Indicates Data sources in The attribute characteristics of Indicates the total number of data sources. Indicated in The fused data Indicates Data sources in The weight coefficient is as follows:

[0044] in, Indicates Data sources in The attribute characteristics of Indicated in is the average value of the attribute feature values ​​of all data sources. Indicates the total number of data sources. Indicates Data sources in The weight coefficient when Indicates The noise parameter of a data source is used to reflect the overall noise level of the current data source and is determined by the characteristics of the data source itself.

[0045] It should be noted that by combining the noise level of the data source and the time-dynamic adjustment weight, the robustness and accuracy of the fusion structure can be improved, and the unification of different feature dimensions of the data can solve the alignment problem of multi-source heterogeneous data.

[0046] S2: Based on the deep learning algorithm, a nested analysis is conducted on the multi-dimensional features in the marine industry data to construct characteristic graphs of marine resource utilization rate, ecological environment index and economic benefit ratio.

[0047] Specifically, the nested analysis of multi-dimensional features in marine industry data based on deep learning algorithms is for the integrated marine industry data. By building a graph neural network model and taking the marine industry data as the input of the model, the marine resource utilization rate, ecological environment index and economic benefit ratio feature map are constructed according to the output results of the model. The specific implementation is as follows: According to the constructed graph neural network model, the marine industry data is used as a node set input into the graph neural network model, including different dimensional features of the marine industry data as a node set , the time series correlation between data is used as the edge set ,in, Indicates nodes, Representation Node With Node The edge relationship between them is determined; Construct the feature matrix of the node, then we have, ,in, represents the constructed node feature matrix, Indicates the number of nodes, Represents feature dimensions, including resource utilization, ecological environment index, economic benefit ratio, ocean temperature and pollution index. At the same time, a node adjacency matrix is ​​constructed. ,and, Representation Node With Node The relationship between the edges can be determined, including the mutual influence of data between adjacent sea areas, the industrial connection between fishery production centers and ports, and the impact of pollution in a certain area on surrounding areas. Otherwise, it is 0; Feature nesting analysis based on graph neural network is as follows: Initialize node features ; Based on the graph convolution layer, the data is propagated layer by layer, then,

[0048] in, Indicates The node feature matrix of the layer, Indicates The weight matrix of the layer, represents the adjacency matrix, Indicates The node feature matrix of the layer; When data is propagated layer by layer through the graph convolution layer, the influence of neighbor nodes in the process of data propagation is eliminated by introducing the attention mechanism. Specifically, the attention mechanism is used to calculate the influence of each node on the data propagation process. With neighbor nodes The importance weights are:

[0049] in, represents the attention vector, represents the transposed matrix, represents the introduced transformation matrix, , Respectively represent nodes With Node The characteristic vector of Represents the calculated importance weight, which is the influence weight of the neighboring node; According to the calculated importance weights, characteristic graphs of marine resource utilization rate, ecological environment index and economic benefit ratio are constructed respectively, as follows: The utilization rate of marine resources indicates the degree of development of marine resources in each region, including fishery resources and mineral development, specifically:

[0050] in, represents the importance weight of the calculation, Indicates the amount of fish caught, Indicates the total amount of resources available for development in the current area. Indicates the utilization rate of marine resources in the current area; The Ecological Environment Index indicates the environmental health of each region, including pollution index and water quality data, specifically:

[0051] in, represents the importance weight of the calculation, represents the pollutant concentration, Indicates the current regional environmental carrying capacity, Indicates the ecological environment index of the current area; The economic benefit ratio indicates the ratio of industry input to income, specifically:

[0052] in, represents the importance weight of the calculation, Indicates the total industrial income of the current region, including fisheries, tourism and port economy. Represents the total industry cost of the current region, including labor costs, resource consumption, and environmental governance. Represents the economic benefit ratio of the current region.

[0053] It should be noted that the calculated marine resource utilization rate, ecological environment index and economic benefit ratio are constructed as corresponding characteristic maps to provide a data basis for subsequent intelligent accounting.

[0054] S3: Based on the constructed feature map, a multi-objective optimization model is introduced to comprehensively evaluate the relationship between resource utilization, ecological and environmental impact, and economic benefits, and realize the intelligent accounting of marine industry data.

[0055] Specifically, the multi-objective optimization model constructs a comprehensive benefit score function based on the characteristic graph through adaptive weight coefficients. At the same time, the temporal and spatial variation law of the data is integrated into the constructed function to analyze the benefit changes of each marine area in different time periods and realize the comprehensive accounting of marine industry data. The specific implementation is as follows: The comprehensive benefit score function is constructed based on the adaptive weight coefficient, then:

[0056] in, , , are adaptive weight coefficients, Represents the resource utilization characteristic graph, Represents the characteristic graph of ecological environment index, Represents the economic benefit characteristic diagram, Indicates the comprehensive benefit score corresponding to the current area; Based on the constructed comprehensive benefit score function, the calculation of marine industry data is realized, specifically:

[0057] in, represents the importance weight of the calculation, Indicates the comprehensive benefit score corresponding to the current area, represents the total number of ocean areas, It represents the accounting results of all ocean areas and is a comprehensive accounting result of marine industry data.

[0058] It should be noted that the adaptive weight coefficient in the process of constructing the comprehensive benefit score function is regulated based on the temporal and spatial variation law of ocean data. The specific regulation process is as follows: Adaptive weight coefficient , as well as , affected by the temporal characteristics of marine industry data And spatial characteristics Dynamic control, specifically: Time characteristics of regulation,

[0059] in, Indicates the seasonal change factor, which is the seasonal change time node in the time feature. The shorter the time from seasonal change, the smaller the seasonal change factor. The specific value is set by the implementer according to the actual application scenario. represents the basic adaptive weight coefficient, Represents the adjusted adaptive weight coefficient; Spatial characteristics of regulation,

[0060]

[0061]

[0062] in, , , represents the adaptive weight coefficient before adjustment, , , represents the adjusted adaptive weight coefficient, Indicates the resource density of the current area, including fishery resources and mineral resources. Indicates the pollution concentration in the current area. Indicates the intensity of current economic activities in the region, including tourism.

[0063] It should be noted that by introducing an adaptive weight coefficient control mechanism and combining temporal and spatial characteristics, not only the accuracy of marine industry data accounting is improved, but also the weight coefficient can be dynamically adjusted for different time periods and regions to ensure that the accounting results are timely and regionally adaptable.

[0064] Furthermore, if the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0065] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0066] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0067] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those features that are not relevant to implementing the invention).

[0068] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0069] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent accounting method for marine industry data, characterized by: The following steps are included: Multi-source data collection and preprocessing of marine industry data, specifically: Collect marine industry data in different formats through unified standards, and pre-process the collected data based on adaptive weighted dynamic fusion algorithm; Based on the deep learning algorithm, a nested analysis of the multi-dimensional features in the marine industry data is conducted to construct characteristic graphs of marine resource utilization rate, ecological environment index and economic benefit ratio, specifically: The fused marine industry data is used as a node set input into the graph neural network model, and a node feature matrix is ​​constructed. At the same time, feature nesting analysis is performed based on the graph neural network. In the layer-by-layer analysis process of graph convolution, an attention mechanism is introduced to eliminate the influence of neighbor nodes in the data propagation process, and a feature graph is constructed based on the calculated importance weights. Based on the characteristic graph, a comprehensive benefit scoring function is constructed. At the same time, the temporal and spatial variation patterns of the data are integrated into the constructed function to achieve comprehensive accounting of marine industry data.

2. The intelligent accounting method for marine industry data according to claim 1, characterized in that: The specific methods of collecting marine industry data in different formats through unified standards are as follows: Set the marine industry data source to , ,in, Indicates Marine industry data sources, Indicates of the marine industry data sources Item data; And mark the feature dimensions for each data source, including time features, spatial features, and attribute features, specifically: ； ； ； in, Indicates The time characteristics corresponding to each marine industry data source represent the timestamp of the data record. Indicates of the marine industry data sources The timestamp corresponding to the data. Indicates The spatial features corresponding to the marine industry data sources represent the regional labels of the data records. Indicates of the marine industry data sources The regional label corresponding to the data. Indicates The attribute characteristics corresponding to the marine industry data source represent the data fields of the data record. Indicates of the marine industry data sources The data field corresponding to the data item.

3. The intelligent accounting method for marine industry data according to claim 2, characterized in that: The adaptive weighted dynamic fusion algorithm is specifically as follows: For each time point The corresponding attribute features of different data sources are used for data fusion based on adaptive weights, as follows: ； in, Indicates Data sources in The attribute characteristics of Indicates the total number of data sources. Indicated in The fused data Indicates Data sources in The weight coefficient is as follows: ； in, Indicates Data sources in The attribute characteristics of Indicated in is the average value of the attribute feature values ​​of all data sources. Indicates the total number of data sources. Indicates Data sources in The weight coefficient when Indicates The noise parameter of a data source is used to reflect the overall noise level of the current data source.

4. The intelligent accounting method for marine industry data according to claim 3 is characterized by: The graph neural network model is specifically as follows: According to the constructed graph neural network model, the marine industry data is used as a node set input into the graph neural network model, including different dimensional features of the marine industry data as a node set , the time series correlation between data is used as the edge set ,in, express nodes, Representation Node With Node The edge relationship between them is determined; Construct the feature matrix of the node, then we have, ,in, represents the constructed node feature matrix, Indicates the number of nodes, Represents feature dimensions, including resource utilization, ecological environment index, economic benefit ratio, ocean temperature and pollution index. At the same time, a node adjacency matrix is ​​constructed. ,and, Representation Node With Node The relationship between the edges can be determined, including the mutual influence of data between adjacent sea areas, the industrial connection between fishery production centers and ports, and the impact of pollution in a certain area on surrounding areas. Otherwise, it is 0.

5. The intelligent accounting method for marine industry data according to claim 4 is characterized in that: The feature nesting analysis based on graph neural network is specifically as follows: Initialize node features ; Based on the graph convolution layer, the data is propagated layer by layer, then, ； in, Indicates The node feature matrix of the layer, Indicates The weight matrix of the layer, represents the adjacency matrix, Indicates The node feature matrix of the layer; ； in, represents the attention vector, represents the transposed matrix, represents the introduced transformation matrix, , Respectively represent nodes With Node The characteristic vector of Represents the calculated importance weight, which is the influence weight of the neighboring node.

6. The intelligent accounting method for marine industry data according to claim 5 is characterized in that: The construction of the feature map according to the calculated importance weight is as follows: The utilization rate of marine resources indicates the degree of development of marine resources in each region, including fishery resources and mineral development, specifically: ； in, represents the importance weight of the calculation, Indicates the amount of fish caught, Indicates the total amount of resources available for development in the current area. Indicates the utilization rate of marine resources in the current area; The Ecological Environment Index indicates the environmental health of each region, including pollution index and water quality data, specifically: ； in, represents the importance weight of the calculation, represents the pollutant concentration, Indicates the current regional environmental carrying capacity, Indicates the ecological environment index of the current area; The economic benefit ratio indicates the ratio of industry input to income, specifically: ； in, represents the importance weight of the calculation, Indicates the total industrial income of the current region, including fisheries, tourism and port economy. Represents the total industry cost of the current region, including labor costs, resource consumption, and environmental governance. Represents the economic benefit ratio of the current region.

7. The intelligent accounting method for marine industry data according to claim 6 is characterized in that: The comprehensive benefit score function is as follows: The comprehensive benefit score function is constructed based on the adaptive weight coefficient, then: ； in, , , are adaptive weight coefficients, Represents the resource utilization characteristic graph, Represents the characteristic graph of ecological environment index, Represents the economic benefit characteristic diagram, Indicates the comprehensive benefit score corresponding to the current area; Based on the constructed comprehensive benefit score function, the calculation of marine industry data is realized, specifically: ； in, represents the importance weight of the calculation, Indicates the comprehensive benefit score corresponding to the current area, represents the total number of ocean areas, It represents the accounting results of all ocean areas and is a comprehensive accounting result of marine industry data.

8. The intelligent accounting method for marine industry data according to claim 7, characterized in that: The function of integrating the temporal and spatial variation law of data into the construction is specifically as follows: Adaptive weight coefficient , as well as , affected by the temporal characteristics of marine industry data And spatial characteristics Dynamic control, specifically: Time characteristics of regulation, ； in, Represents the seasonal change factor, which is the seasonal change time node in the time feature. The shorter the time from seasonal change, the smaller the seasonal change factor. represents the basic adaptive weight coefficient, Represents the adjusted adaptive weight coefficient; Spatial characteristics of regulation, ； ； ； in, , , represents the adaptive weight coefficient before adjustment, , , represents the adjusted adaptive weight coefficient, Indicates the resource density of the current area. Indicates the pollution concentration in the current area. Indicates the intensity of economic activity in the current region.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images