A knowledge graph-based method for evaluating the navigability of Arctic routes

Abstract

The embodiment of the present application discloses a method for evaluating the navigability of an Arctic route based on a knowledge graph, and relates to the field of knowledge graph technology. The method includes: obtaining data to be analyzed in the Arctic region; extracting multiple triples through a constructed knowledge graph of Arctic route evaluation indicators and an Arctic route navigability knowledge graph, determining associated triples based on the position coordinates of each pixel unit on the remote sensing image, and generating a graph chain corresponding to the pixel unit; determining the navigability evaluation value of each graph chain based on the constructed knowledge graph, determining the navigability evaluation result of each pixel unit, and outputting a distribution map of the navigability evaluation results of the Arctic region. The present application can quantify the navigability of each graph chain through the knowledge graph, obtain an navigability evaluation value, and then quickly obtain the navigability evaluation result of each pixel unit, and efficiently output a distribution map of the navigability evaluation results of the Arctic region.

Description

Technical Field

[0001] The present application relates to the field of knowledge graph technology, and in particular to a method for evaluating the navigability of Arctic routes based on knowledge graphs. Background Art

[0002] The Arctic route refers to the sea route that crosses the Arctic Ocean and connects the Atlantic and Pacific Oceans. It mainly includes three main sections: the Northeast Passage, the Northwest Passage, and the Central Passage. Global climate change has led to a continuous reduction in the area covered by sea ice in the Arctic Ocean, especially in summer, which has greatly increased the possibility of navigation on the Arctic route in summer. However, due to the special geographical location of the Arctic route, the changeable coastal ice environment, and the complex meteorological and hydrological conditions, it is crucial to accurately assess the navigability of the Arctic route in summer in order to ensure navigation safety and environmental sustainability.

[0003] In the relevant technologies, the assessment of the navigability of the Arctic route is generally based on the changes in sea ice density on the route, the economic feasibility of navigation, and the interpretation of relevant geopolitical policies. There is a lack of quantitative analysis that comprehensively considers sea ice, meteorological and hydrological environments, which can easily lead to unstable assessment results of navigability. In addition, the factors that affect the navigability of the Arctic route are mostly large, multi-source, heterogeneous, and complex, and only a small part of them can be effectively converted into useful information for analyzing navigability.

[0004] The relevant technology only uses a small number of factors to evaluate the airworthiness, and the factors considered are not comprehensive enough, which will lead to unstable risk assessment results of the Arctic route given by the relevant technology, and it is easy to give biased assessment results. Specifically, if the airworthiness of the route is overestimated, it may lead to actual navigation difficulties, and there will be potential navigation risks during the voyage. If the route is changed, the time cost of navigation will increase; if the airworthiness of the route is underestimated, it may lead to missing good navigation conditions and missed passage opportunities, and it may lead to missing the time window for scientific research and resource collection, causing immeasurable economic losses.

[0005] Therefore, there is currently a lack of an Arctic route navigability assessment method that can comprehensively consider multi-source and multi-modal data. Summary of the invention

[0006] The embodiment of the present application provides a method for evaluating the navigability of an Arctic route based on a knowledge graph, which is used to solve the defects in the related art that the navigability evaluation is performed only by a small number of factors, the factors considered are not comprehensive enough, and the risk assessment results of the Arctic route are unstable. The technical solution is as follows:

[0007] In a first aspect, an embodiment of the present application provides a method for evaluating the navigability of an Arctic route based on a knowledge graph, comprising:

[0008] Acquire data to be analyzed in the Arctic region; wherein the data to be analyzed at least includes a remote sensing image of the Arctic region;

[0009] A plurality of triples are obtained by extracting data based on the data to be analyzed through the constructed Arctic waterway evaluation index knowledge graph and Arctic waterway navigability knowledge graph; wherein the triples include two entities and an association relationship between the two entities, and the types of the entities include influencing factors and waterway information;

[0010] Determine the triplet associated with the pixel unit based on the position coordinates of each pixel unit on the remote sensing image, and generate a graph chain corresponding to the pixel unit based on the associated triplet; wherein each node of the graph chain is an influence factor extracted from the associated triplet, and the edge between each two nodes is an association relationship between corresponding influence factors;

[0011] Determine the navigability evaluation value of each graph chain based on the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph;

[0012] The airworthiness assessment results of each pixel unit are determined based on the airworthiness assessment values ​​of each of the atlas chains, and a distribution map of the airworthiness assessment results of the Arctic region is output.

[0013] In an optional solution of the first aspect, the construction process of the constructed Arctic waterway assessment index knowledge graph and the Arctic waterway navigability knowledge graph includes:

[0014] Obtain multi-modal and multi-source data in the Arctic region;

[0015] Extracting multiple entities from the multi-source data and extracting the association relationship between every two entities; wherein the multi-source multi-modal data at least includes document text data, remote sensing image data and meteorological data, and the entities at least include influencing factors and waterway information;

[0016] A triple is constructed based on every two of the entities and the association relationship between every two of the entities, a knowledge graph of Arctic waterway evaluation indicators is constructed based on the triples containing only the influencing factors, and a knowledge graph of Arctic waterway navigability is constructed based on all the triples.

[0017] In an optional solution of the first aspect, the acquiring multimodal multi-source data of the Arctic region, extracting a plurality of entities from the multimodal multi-source data, and extracting an association relationship between every two of the entities includes:

[0018] Based on a plurality of preset basic data types, N Arctic region data in the multi-modal multi-source data are obtained as entities; the preset basic data types include at least the following types: influencing factors and waterway information;

[0019] Determine whether there is at least one association relationship between the N Arctic region data, and add the association relationship between the Arctic region data having the association relationship; the association relationship is any one of the at least one association relationship, and N is an integer greater than 1.

[0020] In an optional solution of the first aspect, determining a triplet associated with each pixel unit based on the position coordinates of each pixel unit on the remote sensing image, and generating a graph chain corresponding to the pixel unit based on the associated triplet, includes:

[0021] rasterizing the remote sensing image of the Arctic region into a plurality of pixel units;

[0022] Determine a plurality of triplets associated with the position coordinates according to the position coordinates of each pixel unit;

[0023] Determine, based on the associated multiple triplets, an influence factor associated with a corresponding pixel unit and an association relationship between every two of the influence factors;

[0024] Using each of the influencing factors as a node and the association relationship corresponding to each node as a connecting edge, at least one graph chain corresponding to the pixel unit is generated;

[0025] Get the atlas chain of each pixel unit.

[0026] In an optional solution of the first aspect, the determining the navigability evaluation value of each graph chain based on the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph includes:

[0027] Determine the weight of the influencing factor and the corresponding navigation parameter corresponding to each node in each of the graph chains based on the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph;

[0028] For each of the graph chains, the airworthiness evaluation value of the corresponding graph chain is obtained by weighted calculation based on the weight of the influencing factor corresponding to each node and the corresponding airworthiness parameter.

[0029] In an optional solution of the first aspect, determining the airworthiness assessment result of each pixel unit based on the airworthiness assessment value of each of the atlas chains, and outputting the distribution of the airworthiness assessment results of the Arctic region, comprises:

[0030] Compare the airworthiness assessment value of each of the graph chains with a plurality of airworthiness assessment value ranges respectively, and determine the airworthiness assessment value range into which the airworthiness assessment value of each of the graph chains falls; wherein each of the airworthiness assessment value ranges does not overlap;

[0031] Generate a graph chain cluster based on graph chains falling into the same airworthiness assessment value range;

[0032] Determine the distribution area corresponding to each atlas chain in each atlas chain cluster on the North Pole region based on the position information of the pixel unit corresponding to each atlas chain;

[0033] The distribution area corresponding to each of the atlas chain clusters is marked on the remote sensing image, and a distribution map of the airworthiness assessment results of the Arctic region is output.

[0034] In an optional solution of the first aspect, determining the airworthiness assessment result of each pixel unit based on the airworthiness assessment value of each of the atlas chains, and outputting the distribution of the airworthiness assessment results of the Arctic region, comprises:

[0035] Obtain graph chain clusters within each preset time period;

[0036] Respectively determine the distribution area corresponding to each atlas chain in the atlas chain cluster in the Arctic region within each preset time period, and output a distribution map of the airworthiness assessment results of the Arctic region within the corresponding preset time period;

[0037] The average value of the distribution of the airworthiness assessment results of the Arctic region in each of the preset time periods is calculated to obtain a distribution map of the average airworthiness assessment results of the Arctic region in the total period of all the preset time periods.

[0038] In a second aspect, the embodiment of the present application further provides an Arctic waterway navigability assessment device based on a knowledge graph, comprising:

[0039] A data acquisition module, used to acquire data to be analyzed in the Arctic region; wherein the data to be analyzed at least includes a remote sensing image of the Arctic region;

[0040] An information extraction module, used for extracting data based on the data to be analyzed through the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph to obtain a plurality of triples; wherein the triples include two entities and an association relationship between the two entities, and the types of the entities include influencing factors and waterway information;

[0041] A graph chain construction module, used to determine the triplet associated with each pixel unit based on the position coordinates of each pixel unit on the remote sensing image, and generate a graph chain corresponding to the pixel unit based on the associated triplet; wherein each node of the graph chain is an influence factor extracted from the associated triplet, and the edge between each two nodes is an association relationship between corresponding influence factors;

[0042] An airworthiness assessment module, used to determine the airworthiness assessment value of each of the graph chains based on the constructed Arctic waterway assessment index knowledge graph and the Arctic waterway airworthiness knowledge graph;

[0043] The airworthiness assessment module is also used to determine the airworthiness assessment results of each pixel unit based on the airworthiness assessment value of each of the atlas chains, and output a distribution map of the airworthiness assessment results of the Arctic region.

[0044] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method provided in the first aspect of the embodiment of the present application or any one of the implementation methods of the first aspect is implemented.

[0045] In a fourth aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided by the first aspect of the embodiment of the present application or any one of the implementations of the first aspect.

[0046] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0047] An embodiment of the present application provides an Arctic waterway navigability assessment method based on a knowledge graph. The knowledge graph is used to analyze and obtain data related to influencing factors and waterway information, and integrates all structured data represented in the form of triples related to the corresponding position coordinates at the position of each pixel unit in the remote sensing image, so that all relevant information of the Arctic region can be integrated with the position information, and further analyzed separately through the graph chain corresponding to each pixel unit. The knowledge graph can be used to quantify the navigability of each graph chain to obtain an navigability assessment value, and then the navigability assessment result of each pixel unit can be quickly obtained, and the distribution map of the navigability assessment results of the Arctic region can be efficiently output. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 It is a flow chart of a method for evaluating the navigability of an Arctic route based on a knowledge graph provided in an embodiment of the present application;

[0050] Figure 2 It is a structural schematic diagram of an Arctic waterway assessment index knowledge graph of an Arctic waterway navigability assessment method based on a knowledge graph provided in an embodiment of the present application;

[0051] Figure 3 It is a structural schematic diagram of an Arctic waterway navigability knowledge graph of an Arctic waterway navigability assessment method based on a knowledge graph provided in an embodiment of the present application;

[0052] Figure 4 It is a diagram of a graph chain of a method for evaluating the navigability of an Arctic route based on a knowledge graph provided in an embodiment of the present application;

[0053] Figure 5 It is a schematic diagram of a distribution map of the navigability assessment results of an Arctic waterway navigability assessment method based on a knowledge graph provided in an embodiment of the present application;

[0054] Figure 6 It is a structural schematic diagram of an Arctic waterway navigability assessment device based on a knowledge graph provided in an embodiment of the present application;

[0055] Figure 7 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] The terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0058] It should be noted that the terms "first\second" involved in the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that "first\second" can be interchanged with a specific order or sequence where permitted. It should be understood that the objects distinguished by "first\second" can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those described or illustrated herein.

[0059] It should be noted that the knowledge graph-based Arctic route navigability assessment method provided in the embodiment of the present application can be applied to the navigability analysis of the Arctic region. It can comprehensively evaluate the navigability of various locations in the Arctic region according to various existing parameters, and can provide accurate and effective data support for route planning, resource exploitation, etc.

[0060] Understandably, the Knowledge Graph (KG), known as knowledge domain visualization or knowledge domain mapping map in the library and information industry, is a series of various graphics that show the development process and structural relationship of knowledge, using visualization technology to describe knowledge resources and their carriers, and to mine, analyze, construct, draw and display knowledge and their mutual connections. The Knowledge Graph is a modern theory that combines the theories and methods of applied mathematics, graphics, information visualization technology, information science and other disciplines with methods such as metrology citation analysis and co-occurrence analysis, and uses visualized graphs to vividly display the core structure, development history, frontier fields and overall knowledge architecture of the discipline to achieve the purpose of multidisciplinary integration. It can provide practical and valuable references for disciplinary research.

[0061] The present application is described in detail below with reference to specific embodiments.

[0062] Next, combine Figure 1 , taking the terminal executing the Arctic waterway navigation assessment method based on the knowledge graph as an example, the Arctic waterway navigation assessment method based on the knowledge graph provided by the embodiment of the present application is introduced. For details, please refer to Figure 1 , Figure 1 A schematic diagram of a process of evaluating the navigability of an Arctic waterway based on a knowledge graph provided in an embodiment of the present application is shown. The method comprises the following steps:

[0063] S101, obtaining data to be analyzed in the Arctic region.

[0064] S102, extracting data based on the data to be analyzed by constructing the Arctic route evaluation index knowledge graph and the Arctic route navigability knowledge graph to obtain multiple triples.

[0065] S103, determining a triplet associated with each pixel unit on the remote sensing image based on the position coordinates of each pixel unit, and generating a graph chain corresponding to the pixel unit based on the associated triplet.

[0066] S104, determining the navigability assessment value of each of the graph chains based on the constructed Arctic waterway assessment index knowledge graph and the Arctic waterway navigability knowledge graph.

[0067] S105, determining the airworthiness assessment result of each pixel unit based on the airworthiness assessment value of each of the atlas chains, and outputting a distribution map of the airworthiness assessment results of the Arctic region.

[0068] Specifically, in S101, the data to be analyzed at least include remote sensing images of the Arctic region, so that the constructed Arctic waterway assessment index knowledge graph and Arctic waterway navigability knowledge graph can perform navigability analysis based on the provided remote sensing images, and provide other navigability-related data such as Arctic region literature related to remote sensing images and Arctic region meteorological analysis data through the corresponding knowledge graph.

[0069] Optionally, relevant literature materials, meteorological analysis data, etc. can be actively provided in the data to be analyzed. In some embodiments, a large language model can also be used to retrieve various types of data related to the Arctic region, so that the constructed Arctic waterway assessment index knowledge graph and Arctic waterway navigability knowledge graph can perform navigability analysis based on the provided data to be analyzed.

[0070] Optionally, if the originally constructed knowledge graph does not contain all or part of the data to be analyzed, the corresponding data can be processed into structured triple data and then added to the knowledge graph.

[0071] In some embodiments, the process of constructing the Arctic waterway assessment index knowledge graph and the Arctic waterway navigability knowledge graph may include the following steps:

[0072] Access multimodal and multi-source data for the Arctic region.

[0073] A plurality of entities are extracted from the multi-source data, and an association relationship between every two of the entities is extracted.

[0074] A triple is constructed based on every two of the entities and the association relationship between every two of the entities, a knowledge graph of Arctic waterway evaluation indicators is constructed based on the triples containing only the influencing factors, and a knowledge graph of Arctic waterway navigability is constructed based on all the triples.

[0075] It can be understood that multi-source multi-modal data may include data from multiple sources, such as survey data, images taken by satellites, text materials recorded on the Internet, etc., and each type of data may have different forms of expression, such as text data, image data, vectorized data, etc.

[0076] Specifically, the multi-source and multi-modal data include at least literature text data, remote sensing image data and meteorological data. Large language models can also be used to search and crawl other data related to the airworthiness of the Arctic region.

[0077] In some embodiments, the entity obtained based on the multimodal data extraction includes at least influencing factors and waterway information. The influencing factors may include various influencing factors affecting the navigability, such as ocean parameters, geographical environment, meteorological parameters, etc., and the waterway parameters may include the geographical location of the waterway, the distribution of natural resources near the waterway, etc.

[0078] It can be understood that no matter whether it is ocean parameters, geographical environment or meteorological parameters, the influencing factors all have a mapping relationship with the coordinates of a certain location. It can be understood that each ocean parameter, geographical environment, meteorological parameter and other influencing factors are used to characterize the corresponding related parameters at a certain location, such as the wind speed at a certain coordinate position, the sea ice density at another coordinate position, the channel depth at another coordinate position, etc.

[0079] Specifically, N Arctic region data in the multimodal multi-source data can be obtained as entities based on two basic data types of influencing factors and waterway information. Further, it is determined whether there is at least one association relationship between the N Arctic region data, and the association relationship is added between the Arctic region data with the association relationship, thereby obtaining a corresponding triple, where N is an integer greater than 1.

[0080] Specifically, the association relationship may include an inclusion relationship, a mapping relationship, a characterization relationship between specific parameters and influencing factors, an influence relationship between influencing factors and airworthiness, a relative position relationship between a waterway and other targets, etc., which is not limited in the embodiments of the present application.

[0081] Exemplarily, the obtained triplet may include <influencing factor, including, sea ice factor>, <influencing factor, including, meteorological factor>, <influencing factor, affecting, navigability>, <sea ice factor, characterized by..., sea ice density>, <sea ice density, belonging to, sea ice factor>, <meteorological factor, including, wind speed>, <Arctic route, including, central route>, etc., and the embodiments of the present application are not limited to this.

[0082] Specifically, based on all entities and all triples obtained from the association relationship between every two entities with an association relationship, an Arctic waterway navigability knowledge graph containing waterway information and information on factors affecting navigability can be constructed.

[0083] For example, reference may be made to Figure 2 The structure diagram of the Arctic route assessment indicator knowledge graph shown in the figure illustrates some of the association relationships between various influencing factor entities. For example, the influencing factors can be divided into multiple levels, such as primary influencing factors and secondary influencing factors.

[0084] For example, the influencing factors include primary influencing factors and secondary influencing factors, wherein the primary influencing factors include geographical factors, regulatory factors, sea ice factors, meteorological factors, facility factors, hydrological factors, etc., and the secondary influencing factors include sea ice density, ocean division, channel depth, channel width, temperature, wind speed, current velocity, sea surface temperature, port facilities, etc. Figure 2 As shown, the specific entities in the secondary impact factors can also have an inclusion relationship with the corresponding entities in the primary impact factors. For example, the regulatory factors in the primary impact factors include the ocean zoning in the secondary impact factors, and the port facilities in the secondary impact factors belong to the facility factors in the primary impact factors.

[0085] For example, reference may be made to Figure 3 The structure diagram of the Arctic route navigability knowledge graph shown in the figure illustrates some of the associations between various entities. For example, the route information entity can include the geographical location of the route connection (including Asia, Europe, and North America), the main routes (Central Passage, Northwest Passage, and Northeast Passage), resource distribution information (such as water resources, biological resources, and exploitable minerals), the economic benefits of the route, and the sailing time. The influencing factor entity is related to Figure 2 The contents of the knowledge graph of Arctic waterway evaluation indicators shown are the same and will not be repeated here. The correlation between the influencing factors and waterway information can be summarized as follows: the influencing factors will affect the navigability of the corresponding waterway, and the navigability of the waterway is obtained by a comprehensive evaluation of the influencing factors.

[0086] It should be noted that Figure 2 , Figure 3It is only an example of entities corresponding to waterway information and impact factors, and does not reveal the full content of the knowledge graph. Figure 2-Figure 3 The specific data of various entities stored in the knowledge graph are not shown. The specific data can be stored in a plain text format CSV (Comma Separated Values) file as structured data in the form of triples.

[0087] In some embodiments, in S102, the constructed Arctic route evaluation index knowledge graph and Arctic route navigability knowledge graph can extract all relevant entities and relationships based on the provided data to be analyzed to obtain multiple triples, wherein the triple includes two entities and the association relationship between the two entities, and the type of the entity includes influencing factors and route information.

[0088] In some embodiments, for data in text form, data extraction can be performed using methods such as domain ontology construction and entity classification disambiguation; for data in vector form, information extraction can be performed based on the time, space, and attributes of point, line, and surface data; for data in the form of remote sensing images, relationships and entities are extracted based on the metadata, attributes, and basic units of the remote sensing images, and finally stored in a plain text format CSV (Comma Separated Values) file as a structured data type, which is not limited to the embodiments of the present application.

[0089] In some embodiments, by executing step S103, a graph chain for each pixel unit is constructed based on structured data using the constructed knowledge graph.

[0090] Specifically, the remote sensing image of the Arctic region may be rasterized into a plurality of pixel units, a pixel unit may be composed of at least one pixel, and each pixel unit may contain the same or different numbers of pixels, which is not limited in this embodiment of the present application.

[0091] It can be understood that the range of geographical locations corresponding to each pixel unit depends on the resolution of the remote sensing image. The finer the resolution of the image, the smaller the range of geographical locations that a single pixel unit can correspond to. It also depends on the rasterization division of the image, which is not limited in the embodiments of the present application.

[0092] Specifically, a plurality of triplets associated with the position coordinates of each pixel unit can be determined according to the position coordinates of the pixel unit, and an influencing factor associated with the corresponding pixel unit and an association relationship between every two influencing factors can be determined based on the associated plurality of triplets; at least one graph chain corresponding to the pixel unit is generated with each influencing factor as a node and the association relationship corresponding to each node as a connecting edge.

[0093] Based on the above steps, the atlas chain of each pixel unit can be obtained respectively.

[0094] Specifically, the data of pixel units at the same position can be extracted from multiple rasterized remote sensing images, and the correspondence between the triplet and the pixel unit can be determined based on the information related to the position coordinates corresponding to the entity in the triplet, so as to extract the influencing factors at each pixel unit position. For example, the ocean surface velocity is the velocity corresponding to a certain coordinate, and the correspondence with the pixel unit is determined by the coordinate; the sea ice density is the sea ice distribution density corresponding to a certain coordinate range, and the correspondence with the pixel unit is determined by the coordinate range; based on these correspondences, these influencing factors can be determined as the influencing factors within the corresponding pixel unit, which can be used to evaluate the navigability within the corresponding pixel unit.

[0095] For example, Figure 4 As shown, 9 types of influencing factors related to the location can be extracted from the corresponding pixel unit, including sea ice density, ocean zoning, channel depth, channel width, temperature, wind speed, ocean current velocity, sea surface temperature, and port settings. These 9 types of influencing factors are respectively used as 9 nodes of the atlas chain. The 9 types of influencing factors can be arranged according to the value of the influencing weight, or according to the degree of mutual correlation between the 9 types of influencing factors, or randomly arranged to determine the edge of the atlas chain, thereby forming the atlas chain of the pixel unit according to the nodes and the edges between two nodes.

[0096] It can be understood that each atlas chain is equivalent to filling all the data related to the corresponding pixel unit position into the corresponding pixel unit, and taking all the related data as the pixel value of the pixel unit. For example, the necessary processing steps such as resampling of remote sensing images can be performed with the help of open source libraries such as GDAL, Py2neo, and Pandas in Python, so as to extract the pixel values ​​of the same pixel unit position on various remote sensing images.

[0097] In some embodiments, the triples obtained in S102 and the graph chain data obtained in S103 may be stored and managed through a Neo4j graph database.

[0098] Further, in S104, the weights of the influencing factors and the corresponding airworthiness parameters corresponding to each node in each graph chain can be determined according to the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph, and the corresponding weights and airworthiness parameters can be stored as node information in the Neo4j graph database.

[0099] Specifically, for each of the graph chains, the airworthiness evaluation value of the corresponding graph chain is obtained by weighted calculation based on the weight of the influencing factor corresponding to each node and the corresponding airworthiness parameter.

[0100] Further, step S105 may be performed to determine the airworthiness assessment result of each pixel unit based on the airworthiness assessment value of each of the atlas chains, and output a distribution map of the airworthiness assessment results of the Arctic region.

[0101] In some embodiments, the airworthiness assessment value of each of the graph chains may be compared with the airworthiness assessment value ranges corresponding to a plurality of airworthiness assessment rules to determine the airworthiness assessment value range within which the airworthiness assessment value of each of the graph chains falls;

[0102] Generate a graph chain cluster based on the graph chains that fall into the airworthiness evaluation value range corresponding to the same airworthiness evaluation rule;

[0103] Determine the distribution area corresponding to each atlas chain in each atlas chain cluster on the North Pole region based on the position information of the pixel unit corresponding to each atlas chain;

[0104] The distribution area corresponding to each of the atlas chain clusters is marked on the remote sensing image, and a distribution map of the airworthiness assessment results of the Arctic region is output.

[0105] For example, GraphChainLibrary represents a graph chain library, which contains all graph chains, GraphChain represents one of the graph chains, GraphChainCluster represents a graph chain cluster, and node n (a, b, c, d, e, f, g, h, i) represents the nodes contained in the nth graph chain, a, b, c…i represent the nine influencing factors of the Arctic route, edge n (ab, bc, cd, ef, fg, gh, hi) represents the edges ab, cd…hi contained in the nth graph chain, representing the relationship between the nodes of the nine evaluation index elements. represents the weight of the kth node, T n Represents the airworthiness assessment value range corresponding to the airworthiness assessment rules, including:

[0106] (1)GraphChainLibrary={GraphChain(1,2,3…m)};

[0107] GraphChain={node n (a,b,c,d,e,f,g,h,i),edge n (ab,bc,cd,ef,fg,gh,hi)};

[0108] W(k)=weight for k, k a,b,c…i;

[0109] T=threshold value for rule

[0110] (2)Rule=Select(m) <where ∈T n |=>returnGraphChainCluster(m)

[0111] Specifically, through the above steps, a weighted calculation can be performed on each of the m graph chains in the graph chain library to obtain the corresponding airworthiness evaluation value, and it can be determined whether the airworthiness evaluation value falls within the airworthiness evaluation value range T corresponding to the relevant airworthiness evaluation rules. n If it falls within the scope of the relevant airworthiness evaluation rules, the corresponding graph chain is output and added to the graph chain cluster of the relevant airworthiness evaluation rules.

[0112] Specifically, the navigable area corresponding to the atlas chain cluster can be determined based on the same atlas chain cluster, and the airworthiness assessment results corresponding to the atlas chain cluster can be filled into the map of the Arctic region to obtain a distribution map of the airworthiness assessment results corresponding to the atlas chain cluster.

[0113] For example, a plurality of different airworthiness assessment rules may be set, each corresponding to a different airworthiness assessment value range, such as Figure 5 As shown, five airworthiness assessment rules can be set, corresponding to five airworthiness assessment value ranges, namely, the safe navigable area falling within the airworthiness assessment value range 1, the relatively safe navigable area falling within the airworthiness assessment value range 2, the generally navigable area falling within the airworthiness assessment value range 3, the risky navigable area falling within the airworthiness assessment value range 4, and the non-navigable area falling within the airworthiness assessment value range 5.

[0114] Among them, Rule 1 can set the airworthiness assessment value range 1 to (0, T1), Rule 2 can set the airworthiness assessment value range 2 to (T1, T2), Rule 3 can set the airworthiness assessment value range 3 to (T2, T3), Rule 4 can set the airworthiness assessment value range 4 to (T3, T4), and Rule 5 can set the airworthiness assessment value range 5 to (T4, T5). It can realize quantitative screening of the atlas chains that meet the safe navigable areas, relatively safe navigable areas, generally navigable areas, risky navigable areas, and non-navigable areas, and obtain the atlas chain clusters corresponding to Rules 1-5, and then obtain the distribution map of airworthiness assessment results in the Arctic region based on each atlas chain cluster.

[0115] In some embodiments, the graph chain can also be divided according to the time period corresponding to the graph chain to obtain the graph chain cluster corresponding to each preset time period. For example, five preset time periods from 2017 to 2021 are selected.

[0116] The distribution area corresponding to each atlas chain in the atlas chain cluster in each preset time period on the Arctic region is determined respectively, and a distribution map of the airworthiness assessment results of the Arctic region in the corresponding preset time period is output.

[0117] For example, Figure 5 As shown, according to the atlas chain library from 2017 to 2021, corresponding atlas chain clusters are obtained based on the five types of airworthiness assessment rules, and then step S105 is executed respectively according to the atlas chains of each year in each type of atlas chain cluster to obtain the navigable area distribution map of the corresponding year, that is, the distribution map of the airworthiness assessment results of the Arctic region in the corresponding year.

[0118] In some embodiments, the average value of the distribution of the airworthiness assessment results of the Arctic region in each of the preset time periods may also be calculated to obtain a distribution map of the average airworthiness assessment results of the Arctic region in the total period of all the preset time periods.

[0119] For example, Figure 5 As shown in the figure, the mean value of the airworthiness evaluation value of each pixel unit can be calculated based on the five-year atlas chain and atlas chain cluster, and then the following is obtained: Figure 5 The distribution map of average airworthiness assessment results in the Arctic region from 2017 to 2021 is shown.

[0120] In some embodiments, it is also possible to further adjust the constructed Arctic waterway assessment index knowledge graph and Arctic waterway navigability knowledge graph by adjusting the content of the data to be analyzed in S101, adding real-time remote sensing images, hydrological data, literature materials, meteorological observation data, etc., thereby achieving near real-time Arctic waterway navigability assessment, and obtaining an accurate distribution map of navigability assessment results in the Arctic region, providing effective data support for route planning, scientific research planning, etc.

[0121] The following are device embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0122] See next Figure 6 , which is a schematic diagram of the structure of an Arctic waterway navigability assessment device based on a knowledge graph provided by an exemplary embodiment of the present application. The device can be implemented as all or part of a terminal through software, hardware, or a combination of both, and can also be integrated on a server as an independent module. The Arctic waterway navigability assessment device based on a knowledge graph in the embodiment of the present application can be applied to a terminal or a cloud. The device 60 includes a graph chain construction module 601, an information extraction module 602, a graph chain construction module 603, and a navigability assessment module 604, wherein:

[0123] A data acquisition module, used to acquire data to be analyzed in the Arctic region; wherein the data to be analyzed at least includes a remote sensing image of the Arctic region;

[0124] An information extraction module, used for extracting data based on the data to be analyzed through the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph to obtain a plurality of triples; wherein the triples include two entities and an association relationship between the two entities, and the types of the entities include influencing factors and waterway information;

[0125] A graph chain construction module, used to determine the triplet associated with each pixel unit based on the position coordinates of each pixel unit on the remote sensing image, and generate a graph chain corresponding to the pixel unit based on the associated triplet; wherein each node of the graph chain is an influence factor extracted from the associated triplet, and the edge between each two nodes is an association relationship between corresponding influence factors;

[0126] An airworthiness assessment module, used to determine the airworthiness assessment value of each of the graph chains based on the constructed Arctic waterway assessment index knowledge graph and the Arctic waterway airworthiness knowledge graph;

[0127] The airworthiness assessment module is also used to determine the airworthiness assessment results of each pixel unit based on the airworthiness assessment value of each of the atlas chains, and output a distribution map of the airworthiness assessment results of the Arctic region.

[0128] It should be noted that the device 60 provided in the above embodiment only uses the division of the above functional modules as an example when executing the Arctic waterway navigability assessment method based on the knowledge graph. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device provided in the above embodiment and the embodiment of the Arctic waterway navigability assessment method based on the knowledge graph belong to the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0129] An embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the program.

[0130] See also Figure 7 , which is a structural block diagram of an electronic device provided in an embodiment of the present application.

[0131] like Figure 7 As shown, the electronic device 700 includes: a processor 701 and a memory 702 .

[0132] In the embodiment of the present application, the processor 701 is the control center of the computer system, which can be a processor of a physical machine or a processor of a virtual machine. The processor 701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 701 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array).

[0133] The processor 701 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also called a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state.

[0134] The memory 702 may include one or more computer-readable storage media, which may be non-transitory. The memory 702 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments of the present application, the non-transitory computer-readable storage medium in the memory 702 is used to store at least one instruction, which is used to be executed by the processor 701 to implement the method in the embodiment of the present application.

[0135] In some embodiments, the electronic device 700 further includes: a peripheral device interface 703 and at least one peripheral device 704. The processor 701, the memory 702 and the peripheral device interface 703 can be connected via a bus or a signal line. Each peripheral device 704 can be connected to the peripheral device interface 703 via a bus, a signal line or a circuit board. Specifically, the peripheral device 704 includes: a display screen, a camera and an audio circuit. The peripheral device interface 703 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 701 and the memory 702.

[0136] In some embodiments of the present application, the processor 701, the memory 702, and the peripheral device interface 703 are integrated on the same chip or circuit board; in some other embodiments of the present application, any one or two of the processor 701, the memory 702, and the peripheral device interface 703 can be implemented on a separate chip or circuit board. This embodiment of the present application does not specifically limit this.

[0137] The electronic device structure block diagram shown in the embodiment of the present application does not constitute a limitation on the electronic device 700. The electronic device 700 may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0138] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the method of any of the above embodiments are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0139] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A knowledge graph-based method for evaluating the navigability of Arctic waterways, characterized in that: include: Acquire data to be analyzed in the Arctic region; wherein the data to be analyzed at least includes a remote sensing image of the Arctic region; A plurality of triples are obtained by extracting data based on the data to be analyzed through the constructed Arctic waterway evaluation index knowledge graph and Arctic waterway navigability knowledge graph; wherein the triples include two entities and an association relationship between the two entities, and the types of the entities include influencing factors and waterway information; Determine the triplet associated with the pixel unit based on the position coordinates of each pixel unit on the remote sensing image, and generate a graph chain corresponding to the pixel unit based on the associated triplet; wherein each node of the graph chain is an influence factor extracted from the associated triplet, and the edge between each two nodes is an association relationship between corresponding influence factors; Determine the navigability evaluation value of each graph chain based on the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph; The airworthiness assessment results of each pixel unit are determined based on the airworthiness assessment values ​​of each of the atlas chains, and a distribution map of the airworthiness assessment results of the Arctic region is output.

2. According to claim 1, a method for evaluating the navigability of Arctic waterways based on knowledge graph is characterized in that: The construction process of the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph includes: Obtain multi-modal and multi-source data in the Arctic region; Extracting multiple entities from the multi-source data and extracting the association relationship between every two entities; wherein the multi-source multi-modal data at least includes document text data, remote sensing image data and meteorological data, and the entities at least include influencing factors and waterway information; A triple is constructed based on every two of the entities and the association relationship between every two of the entities, a knowledge graph of Arctic waterway evaluation indicators is constructed based on the triples containing only the influencing factors, and a knowledge graph of Arctic waterway navigability is constructed based on all the triples.

3. The method for evaluating the navigability of Arctic waterways based on knowledge graph according to claim 2 is characterized in that: The step of acquiring multimodal multi-source data of the Arctic region, extracting a plurality of entities from the multimodal multi-source data, and extracting an association relationship between every two of the entities includes: Based on a plurality of preset basic data types, N Arctic region data in the multi-modal multi-source data are obtained as entities; the preset basic data types include at least the following types: influencing factors and waterway information; Determine whether there is at least one association relationship between the N Arctic region data, and add the association relationship between the Arctic region data having the association relationship; the association relationship is any one of the at least one association relationship, and N is an integer greater than 1.

4. The method for evaluating the navigability of Arctic waterways based on knowledge graph according to claim 1 is characterized in that: The step of determining a triplet associated with each pixel unit based on the position coordinates of each pixel unit on the remote sensing image, and generating a graph chain corresponding to the pixel unit based on the associated triplet, comprises: rasterizing the remote sensing image of the Arctic region into a plurality of pixel units; Determine a plurality of triplets associated with the position coordinates according to the position coordinates of each pixel unit; Determine, based on the associated multiple triplets, an influence factor associated with a corresponding pixel unit and an association relationship between every two of the influence factors; Using each of the influencing factors as a node and the association relationship corresponding to each node as a connecting edge, at least one graph chain corresponding to the pixel unit is generated; Get the atlas chain of each pixel unit.

5. The method for evaluating the navigability of Arctic waterways based on knowledge graph according to claim 4 is characterized in that: The determining of the navigability evaluation value of each graph chain based on the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph includes: Determine the weight of the influencing factor and the corresponding navigation parameter corresponding to each node in each of the graph chains based on the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph; For each of the graph chains, the airworthiness evaluation value of the corresponding graph chain is obtained by weighted calculation based on the weight of the influencing factor corresponding to each node and the corresponding airworthiness parameter.

6. The method for evaluating the navigability of Arctic waterways based on knowledge graph according to claim 1 or 5, characterized in that: The airworthiness evaluation result of each pixel unit is determined based on the airworthiness evaluation value of each of the atlas chains, and the airworthiness evaluation result distribution map of the Arctic region is output, including: Compare the airworthiness assessment value of each of the graph chains with a plurality of airworthiness assessment value ranges respectively, and determine the airworthiness assessment value range into which the airworthiness assessment value of each of the graph chains falls; wherein each of the airworthiness assessment value ranges does not overlap; Generate a graph chain cluster based on graph chains falling into the same airworthiness assessment value range; Determine the distribution area corresponding to each atlas chain in each atlas chain cluster on the North Pole region based on the position information of the pixel unit corresponding to each atlas chain; The distribution area corresponding to each of the atlas chain clusters is marked on the remote sensing image, and a distribution map of the airworthiness assessment results of the Arctic region is output.

7. The method for evaluating the navigability of Arctic waterways based on knowledge graph according to claim 6 is characterized in that: The airworthiness evaluation result of each pixel unit is determined based on the airworthiness evaluation value of each of the atlas chains, and the airworthiness evaluation result distribution map of the Arctic region is output, including: Obtain graph chain clusters within each preset time period; Respectively determine the distribution area corresponding to each atlas chain in the atlas chain cluster in the Arctic region within each preset time period, and output a distribution map of the airworthiness assessment results of the Arctic region within the corresponding preset time period; The average value of the distribution of the airworthiness assessment results of the Arctic region in each of the preset time periods is calculated to obtain a distribution map of the average airworthiness assessment results of the Arctic region in the total period of all the preset time periods.

8. An Arctic waterway navigation assessment device based on knowledge graph, characterized in that: include: A data acquisition module, used for acquiring data to be analyzed in the Arctic region; wherein the data to be analyzed at least includes a remote sensing image of the Arctic region; An information extraction module, used for extracting data based on the data to be analyzed through the constructed Arctic waterway evaluation index knowledge graph and the Arctic waterway navigability knowledge graph to obtain a plurality of triples; wherein the triples include two entities and an association relationship between the two entities, and the types of the entities include influencing factors and waterway information; A graph chain construction module, used to determine the triplet associated with each pixel unit based on the position coordinates of each pixel unit on the remote sensing image, and generate a graph chain corresponding to the pixel unit based on the associated triplet; wherein each node of the graph chain is an influence factor extracted from the associated triplet, and the edge between each two nodes is an association relationship between corresponding influence factors; An airworthiness assessment module, used to determine the airworthiness assessment value of each of the graph chains based on the constructed Arctic waterway assessment index knowledge graph and the Arctic waterway airworthiness knowledge graph; The airworthiness assessment module is also used to determine the airworthiness assessment results of each pixel unit based on the airworthiness assessment value of each of the atlas chains, and output a distribution map of the airworthiness assessment results of the Arctic region.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A non-transitory 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 7 are implemented.

Images