A satellite network international cooperation relationship mining method and system

Abstract

The application provides a satellite network international cooperation relationship mining method and system, the method is based on a satellite network data database, a satellite network correlation relationship network is constructed, and a Louvain algorithm and a PageRank algorithm are used to mine satellite network country cooperation relationships; the country cooperation relationships include community distribution of the cooperation relationship network, importance of the countries in cooperation, and cooperation business types of the countries in satellite network engineering. The application applies graph theory to satellite network international cooperation relationship mining, can automatically analyze hidden cooperation relationships between countries from the ITU satellite network data database through the graph algorithm without prior knowledge, saves manpower, and has good effects on mining implicit cooperation relationships.

Description

Technical Field

[0001] This invention belongs to the field of satellite network application data mining and satellite network international cooperation relationship mining and analysis, specifically involving a method and system for mining satellite network international cooperation relationships. Background Technology

[0002] In recent years, countries around the world have been collaborating on satellite network data submissions. For example, OneWeb has submitted multiple satellite network data submissions with the help of countries such as France, the UK, and Canada, while SpaceX has also partnered with Norway to obtain two Ku and Ka band data sets. However, many of these collaborations are relatively confidential, and most satellite network operators do not publicly disclose their cooperation with other countries.

[0003] The analysis of international cooperation relationships in satellite networks aims to infer and analyze hidden cooperative relationships between countries from existing data, including the overall overview of the cooperative relationships and the specific types of cooperative business. The International Telecommunication Union (ITU) Satellite Network Data Database (SRS database) is currently the main source of satellite network information. Current research and analysis of this database largely relies on manual methods. However, the SRS database has a complex structure, and the data is growing exponentially. Relying on manual correlation analysis of existing data is neither flexible nor time-consuming. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of human analysis of satellite network data databases, which are not flexible enough and are time-consuming and labor-intensive.

[0005] To achieve the above objectives, this invention proposes a method for mining international cooperation relationships in satellite networks. This method uses a satellite network database to construct a network of satellite network relationships and employs the Louvain and PageRank algorithms to mine national cooperation relationships within the satellite network. These national cooperation relationships include: the community distribution of the cooperation network, the importance of each country in the cooperation, and the types of cooperative business among countries in satellite network projects.

[0006] As an improvement to the above method, the method includes:

[0007] Step 1: Construct a satellite network relationship network; the relationship network includes two types of nodes and two types of relationships. The two types of nodes are country names and satellite network data, and the two types of relationships are the link relationships between data and the relationship between data and its country.

[0008] Step 2: Explore national cooperation relationships in satellite networks;

[0009] Based on the content of the national cooperation relationships uncovered, step 2 is further divided into:

[0010] Step 2a: Coarse-grained mining of national cooperation relationships; obtaining information on the community distribution of national cooperation networks and the importance of each country in the cooperation;

[0011] Step 2b: Fine-grained mining of national cooperation relationships; obtaining the types of cooperative business among countries in satellite network engineering.

[0012] As an improvement to the above method, step 1 specifically includes:

[0013] Step 1a: Query the satellite network data database to obtain the names of all non-deprecated satellite network data and the names of the countries that submitted the data;

[0014] Step 1b: Query the satellite network data database, determine the direction of the inter-satellite link association based on the link direction, and obtain the inter-satellite link association between satellite network data.

[0015] As an improvement to the above method, step 2a specifically includes:

[0016] Step 2a-1: Construct a network of national cooperation relationships; treat each country as a node, traverse each pair of satellite-related data nodes in the satellite network relationship network, if the two data belong to different countries, the edge weight between the two countries is increased by 1, and the final edge weight between nodes is the number of satellite network data sets that are related between the two countries;

[0017] Step 2a-2: Divide the cooperative relationship network into communities; view the national cooperative relationship network as a social relationship network. Initially, each country is a node, and each node is a community. Calculate the modularity Q of each community:

[0018]

[0019] in, v , w For two connected nodes, For nodes v , w The weight of the connecting edges, They are nodes v and w Community ID, if ,function Otherwise, it is 0. m It is the sum of the weights of all connected edges in the network. For nodes v The sum of the weights of all connected edges. For nodes w The sum of the weights of all connected edges;

[0020] Steps 2a-3: Calculate the modularity gain of the mobile node; each node is treated as a separate community, and for each node...i Move it into any connected node j The modularity gain of the community C represented is calculated afterward. :

[0021]

[0022] in Let the sum of the edge weights within community C be the sum of the edge weights. This is the sum of the weights of all connected edges to nodes within community C. It is a point i The sum of the weights of all connected edges. For nodes i The sum of the edge weights between nodes in community C, m It is the sum of the weights of all connected edges in the network; if it exists , will node i Move to command The largest node resides in community C; repeat this step until moving any node no longer results in any modularity gain. ;

[0023] Step 2a-4: Treat each community obtained in Step 2a-3 as a new node. Consider the sum of edge weights within a community as the self-connection weight of the new node. The edge weight between two adjacent new nodes is the sum of the edge weights between nodes in the two communities. Calculate the modularity gain according to Step 2a-3. ;

[0024] Step 2a-5: Repeat steps 2a-3 and 2a-4 until the community no longer changes, and obtain the distribution map of the international cooperation community of the satellite network;

[0025] Step 2a-6: Evaluate cooperability centrality; calculate the cooperability centrality PR value for each node, i.e., each country:

[0026]

[0027] in, It is the first i 1 node It is the first j 1 node It points to a node All nodes, It is a node The number of links to which it points, where N is the total number of nodes; This is the damping factor, with a value of 0.85;

[0028] Each country's cooperation centrality (PR) value is directly proportional to its importance in cooperation.

[0029] As an improvement to the above method, step 2b specifically includes:

[0030] Step 2b-1: Use the connected graph partitioning algorithm to cluster the nodes of the satellite network association network to obtain the connected subgraph of the satellite network association relationship;

[0031] Step 2b-2: For each pair of related data in the satellite network interconnection subgraph, query the satellite network data database to obtain the specific cooperative business types between the related data.

[0032] As an improvement to the above method, the connected graph partitioning algorithm uses the networkx.connected_components function in Python.

[0033] This invention also provides a system for mining international cooperation relationships in satellite networks, the system comprising:

[0034] The relational network module is used to build a network of relationships between satellite networks.

[0035] The "Explore Partnerships" module is used to explore national partnerships within satellite networks.

[0036] As an improvement to the above system, the module for mining cooperative relationships includes:

[0037] The coarse-grained relationship mining module is used to obtain the community distribution of national cooperation networks and the importance of each country in the cooperation; and

[0038] The fine-grained relationship mining module is used to obtain the types of cooperative business between countries in satellite network engineering.

[0039] The present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method as described in any of the preceding claims.

[0040] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the method described in any of the preceding claims.

[0041] Compared with the prior art, the advantages of the present invention are:

[0042] This technical solution applies graph theory to the mining of international cooperation relationships in satellite networks. Based on the characteristics of satellite network data, a satellite network relationship model is defined, which links the originally independent satellite network data through inter-satellite links. Without prior knowledge, the graph algorithm can automatically analyze the hidden cooperation relationships between countries from the ITU satellite network data database, saving manpower and achieving good results in mining implicit cooperation relationships. Attached Figure Description

[0043] Figure 1 The diagram shown is the overall flowchart for mining international cooperation relationships in satellite networks;

[0044] Figure 2 The diagram shows the ontology definition and construction module for satellite network relationships;

[0045] Figure 3 The image shows a distribution map of international cooperation communities in satellite networks.

[0046] Figure 4 The diagram shown is a network diagram of cooperative relationships. Detailed Implementation

[0047] This invention employs social network analysis to mine and analyze the ITU satellite network data database, uncovering hidden overall profiles of international cooperation relationships and specific types of cooperative business. This helps to understand the development of international satellite networks and provides suggestions for satellite network application and planning.

[0048] The technical solution of the present invention will now be described in detail with reference to the accompanying drawings.

[0049] like Figure 1 As shown, the present invention mainly includes two steps for mining international cooperation relationships in satellite networks: constructing a network of satellite network relationships and mining national cooperation relationships. The mining of national cooperation relationships is further divided into coarse-grained national cooperation relationship mining and fine-grained national cooperation relationship mining.

[0050] 1. Construct a satellite network of interconnected relationships.

[0051] Graph theory is used to analyze the relationships between satellite network data, linking independent satellite network data to derive cooperation relationships between countries. The relationships between satellite network data in the ITU database are highly complex, primarily manifested in link relationships. These links exist not only between satellites but also between satellites and ground stations. However, the ITU database contains different ground stations with the same name. Linking two sets of satellite network data solely based on related ground station names is not feasible, and most related ground station data is merely paper data used by satellite network companies to gain an advantage in resource acquisition, lacking practical significance. Therefore, having a common ground station name does not necessarily mean that two satellites belong to the same constellation.

[0052] This invention, based on inter-satellite links in satellite network data, links satellite network data to construct a satellite network association network. For example... Figure 2 As shown, the relationship network contains two types of nodes: countries and satellite network data (including GSO data and NGSO data), and two types of relationships: link relationships between data and relationships between data and the country to which the competent authority belongs.

[0053] First, use SQL statements to query the SRS2948 database to obtain the data names, country names, and inter-satellite link directions between different data sets for Geostationary Orbit (GSO) and Non-Geostationary Orbit (NGSO) satellites.

[0054] 1) Use SQL statements to query the SRS database to obtain the names of all non-decommissioned satellite network data, "sat_name", the reporting country "adm", and the triple (GSO / NGSO, belong to, adm). This includes GSO data (select distinct adm,sat_name as GSO FROM geo,notice where notice.ntc_id=geo.ntc_id and notice.ntf_rsn!='U') and NGSO data (select distinct adm,sat_name as NGSO FROM non_geo,notice where notice.ntc_id=non_geo.ntc_id and notice.ntf_rsn!='U').

[0055] 2) Use SQL statements to query the SRS database. Based on the link direction "grp.emi_rcp", determine the direction of the inter-satellite link association, obtaining the inter-satellite link association triplet (sat_name, link, sat_name) between satellite network data: GSO data inter-link (select distinct geo.sat_name, geo2.sat_name, grp.emi_rcp from notice as n1, geo, grp, notice as n2, s_as_stn, geo as geo2 where n1.ntc_id=geo.ntc_id and n2.ntc_id=geo2.ntc_id and n1.ntc_id=grp.ntc_id and grp.grp_id=s_as_stn.grp_id and s_as_stn.sat_name=geo2.sat_name and n1.ntf_rsn!='U' and n2.ntf_rsn!='U' and n1.ntc_id!=n2.ntc_id), link between GSO and NGSO data (select distinctgeo.sat_name,non_geo.sat_name,grp.emi_rcp from notice as n1,geo,grp,notice asn2,s_as_stn,non_geo where n1.ntc_id=geo.ntc_id and n2.ntc_id=non_geo.ntc_id and n1.ntc_id=grp.ntc_id and grp.grp_id=s_as_stn.grp_id and s_as_stn.sat_name=non_geo.sat_name and n1.ntf_rsn!='U' and n2.ntf_rsn!='U' and n1.ntc_id!=n2.ntc_id、select distinct non_geo.sat_name,geo.sat_name,grp.emi_rcp fromnotice as n1,non_geo,grp,notice as n2,s_as_stn,geo where n1.ntc_id=non_geo.ntc_id and n2.ntc_id=geo.ntc_id and n1.ntc_id=grp.ntc_id and grp.grp_id=s_as_stn.grp_id and s_as_stn.sat_name=geo.sat_name and n1.ntf_rsn!='U' andn2.ntf_rsn!='U' and n1.ntc_id!=n2.ntc_id), link between NGSO data (select distinct non_geo.sat_name,non_geo2.sat_name,grp.emi_rcp from notice as n1,non_geo,grp,notice as n2,s_as_stn,non_geo as non_geo2 where n1.ntc_id=non_geo.ntc_id andn2.ntc_id=non_geo2.ntc_id and n1.ntc_id=grp.ntc_id and grp.grp_id=s_as_stn.grp_id and s_as_stn.sat_name=non_geo2.sat_name and n1.ntf_rsn!='U' andn2.ntf_rsn!='U'and n1.ntc_id!=n2.ntc_id). .

[0056] Ultimately, 3430 GSO network data nodes, 2025 NGSO network data nodes, and 93 national nodes were obtained; 2475 relationships between GSO network data, 375 relationships between NGSO network data, and 2026 relationships between GSO and NGSO network data were obtained. All nodes and relationships were stored in the neo4j database.

[0057] 2. Explore national cooperation relationships

[0058] (1) Mining of coarse-grained national cooperation relationships

[0059] The purpose of coarse-grained cooperation relationship mining is to classify the overall trends of cooperation relationships among countries in satellite network projects and analyze the cooperation centrality of each country in the cooperation. The specific process is as follows:

[0060] 1) Building a network of national cooperation relationships

[0061] Quantifying national cooperation relationships: Each country is treated as a node. Each pair of related data nodes in the satellite network association network is traversed. If two data points belong to different countries, the edge weight between the two countries is increased by 1. The final edge weight between nodes represents the number of satellite network data sets related to the two countries. Experiments revealed 4876 directly related satellite network data sets in the SRS2948 database. Among these, 70 sets belong to different countries and involve the relevant authorities of 13 countries / regions: Belgium, the United Kingdom, Singapore, Cyprus, Sweden, New Zealand, the United States, France, Germany, Japan, Luxembourg, Australia, and Italy.

[0062] 2) Divide the communities into cooperative relationships

[0063] This invention views the network of national cooperation relationships as a social relationship network and employs the Louvain graph partitioning algorithm to divide the network into communities, analyzing the overall clustering of countries in cooperation. Initially, each country is treated as a node, and each node as a community. The Louvain algorithm is a community detection algorithm model based on modularity, where modularity Q is used to measure the quality of the community partitioning results, as shown in Equation 1.

[0064] (1)

[0065] in Let be the weight of the edge connecting nodes v and w. These are the community IDs of nodes v and w, respectively. ,function Otherwise, it is 0, where m is the sum of the weights of all edges in the network. The sum of the weights of all edges connecting to node v. Let w be the sum of the weights of all edges connected to node w. This represents the probability that an edge exists between vertices v and w in the case of a random graph. Generally, a Q value greater than 0.3 is considered to indicate good community partitioning performance. The Louvain algorithm consists of two phases:

[0066] Phase 1:

[0067] Initially, each node operates as a separate community.

[0068] For each node i, calculate the modularity gain after moving it into the community C represented by any connected node j according to Equation 2. If it exists Move node i to let The largest node is located in community C. Let the sum of the edge weights within community C be the sum of the edge weights. This is the sum of the weights of all connected edges to nodes within community C. It is the sum of the weights of all edges connected to point i. It is the sum of the edge weights between node i and nodes within community C.

[0069] (2)

[0070] Repeat the above steps until moving any node no longer results in any modularity gain. Then the first phase ends.

[0071] Phase 2: Treat each community obtained in Phase 1 as a new node, the sum of edge weights within the same community as the node's self-connection weight, and the edge weight between two adjacent new nodes as the sum of the edge weights between the nodes in the two communities.

[0072] Repeat the above two phases until the algorithm is stable and the community no longer changes.

[0073] Taking the ITU's SRS2948 database as an example, the distribution map of international cooperation communities in satellite networks is as follows: Figure 3 As shown, two major cooperative groups have formed, centered on the United States and the United Kingdom, respectively. It can be seen that the main partners of the United States are countries such as Japan, France, and Australia, while the main partners of the United Kingdom are countries such as Singapore and Sweden. Furthermore, there are 18 interconnected satellite network data sets between the United Kingdom and the United States. Apart from this, the two cooperative communities are clearly defined, with no overlap in the countries cooperating between the two communities.

[0074] 3) Assess the degree of cooperative centrality

[0075] This invention employs the PageRank algorithm to evaluate the cooperative centrality of nodes in a network. The PageRank algorithm, proposed by the founders of Google, is used to measure the importance of web pages and rank websites based on their importance. The PageRank formula is shown in Equation 3. It calculates the PageRank value of a web page by measuring its in-degree and the quality of the links reaching it. The higher the PageRank value, the higher the website's ranking.

[0076] (3)

[0077] in It points to a webpage. All web pages It's a webpage. The number of links pointing to the page, where N is the total number of web pages considered. This represents the probability of being redirected to various web pages upon first browsing. The damping factor, i.e., the probability of remaining on the current webpage in the next step, is set in the experiments of this invention. It is 0.85.

[0078] (2) Mining of fine-grained national cooperation relationships

[0079] The goal of fine-grained cooperation relationship mining is to obtain details of cooperation among countries in satellite network engineering, i.e., specific types of cooperative business. The specific process is as follows:

[0080] 1) A connected component graph algorithm is used to cluster and partition the nodes of the satellite network relationship network, resulting in a connected subgraph of the satellite network relationship. Each piece of data within a subgraph has a direct or indirect relationship with other data. In this invention, the `networkx.connected_components` function in Python is used to partition the connected component graph, and the input satellite network relationship network is a directed graph.

[0081] 2) Following step 1), a connectivity map of all satellite network data is obtained. Figure 4 For example, Figure 4 This is a connected subgraph containing nodes from multiple countries, where larger nodes represent countries and smaller nodes represent satellite network data. The connected subgraph involving data from multiple different countries exhibits inter-country cooperation relationships. For each pair of related data, an SQL query is used to query the ITU database to obtain the specific cooperative service type "stn_cls" between the related data. An example query (cooperative service type between satellite networks 'APOG' and 'ANDROMEDA-A') is as follows:

[0082] select distinct stn_cls from non_geo,grp,s_as_stn,srv_cls where s_as_stn.sat_name='APOG' and non_geo.sat_name='ANDROMEDA-A' and non_geo.ntc_id=grp.ntc_id and grp.grp_id=s_as_stn.grp_id and grp.grp_id=srv_cls.grp_id

[0083] Return as Figure 4 The diagram shows the network of cooperative relationships, and Table 1 shows the types of cooperative business.

[0084] Table 1. Types of Cooperative Business

[0085]

[0086] This invention defines a network ontology model of satellite network relationships and applies social network analysis to the mining of international cooperation relationships in satellite networks, providing a new approach to satellite network intelligence data analysis.

[0087] The present invention also provides a computer device comprising: at least one processor, a memory, at least one network interface, and a user interface. The various components of this device are coupled together via a bus system. It is understood that the bus system is used to enable communication between these components. In addition to a data bus, the bus system also includes a power bus, a control bus, and a status signal bus.

[0088] The user interface may include a display, keyboard, or clicking device (e.g., mouse, trackball, touchpad, or touchscreen).

[0089] It is understood that the memory in the embodiments disclosed in this application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memories described herein are intended to include, but are not limited to, these and any other suitable types of memory.

[0090] In some implementations, the memory stores elements such as executable modules or data structures, or subsets thereof, or extended sets thereof: operating systems and applications.

[0091] The operating system includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application programs include various applications, such as media players and browsers, used to implement various application functions. Programs implementing the methods of the embodiments of this disclosure can be included in the application programs.

[0092] In the above embodiments, the processor can also invoke programs or instructions stored in memory, specifically programs or instructions stored in an application program, for the following purposes:

[0093] Follow the steps described above.

[0094] The above methods can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above methods can be completed by integrated logic circuits in the processor's hardware or by software instructions. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the disclosed methods, steps, and logic block diagrams. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the disclosed methods can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above methods.

[0095] It is understood that the embodiments described in this invention can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in this application, or combinations thereof.

[0096] For software implementation, the technology of this invention can be implemented by executing the functional modules (e.g., procedures, functions, etc.) of this invention. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or externally.

[0097] The present invention may also provide a non-volatile storage medium for storing a computer program. When the computer program is executed by a processor, it can implement the steps in the above method embodiments.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the embodiments, those skilled in the art should understand that modifications or equivalent substitutions to the technical solutions of the present invention do not depart from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for mining international cooperation relationships in satellite networks, wherein the method constructs a satellite network relationship network based on a satellite network data database, and uses the Louvain algorithm and PageRank algorithm to mine the international cooperation relationships in satellite networks; The aforementioned national cooperation relationships include: The community distribution of the cooperative relationship network, the importance of countries in the cooperation, and the types of cooperative business among countries in satellite network projects; The method includes: Step 1: Construct a satellite network relationship network; the relationship network includes two types of nodes and two types of relationships. The two types of nodes are country names and satellite network data, and the two types of relationships are the link relationships between data and the relationship between data and its country. Step 2: Explore national cooperation relationships in satellite networks; Based on the content of the national cooperation relationships uncovered, step 2 is further divided into: Step 2a: Coarse-grained mining of national cooperation relationships; obtaining information on the community distribution of national cooperation networks and the importance of each country in the cooperation; Step 2b: Fine-grained mining of national cooperation relationships; obtaining the types of cooperative business among countries in satellite network engineering; Step 2a specifically includes: Step 2a-1: Construct a network of national cooperation relationships; treat each country as a node, traverse each pair of satellite-related data nodes in the satellite network relationship network, if the two data belong to different countries, the edge weight between the two countries is increased by 1, and the final edge weight between nodes is the number of satellite network data sets that are related between the two countries; Step 2a-2: Divide the cooperative relationship network into communities; view the national cooperative relationship network as a social relationship network. Initially, each country is a node, and each node is a community. Calculate the modularity Q of each community: ； in, v , w For two connected nodes, For nodes v , w The weight of the connecting edges, They are nodes v and w Community ID, if ,function Otherwise, it is 0. m It is the sum of the weights of all connected edges in the network. For nodes v The sum of the weights of all connected edges, For nodes w The sum of the weights of all connected edges; Steps 2a-3: Calculate the modularity gain of the mobile node; each node is treated as a separate community, and for each node... i Move it into any connected node j The modularity gain of the community C it represents is calculated. ; ； in, Let the sum of the edge weights within community C be the sum of the edge weights. This is the sum of the weights of all connected edges to nodes within community C. It is a point i The sum of the weights of all connected edges. For nodes i The sum of the edge weights between nodes in community C, m It is the sum of the weights of all connected edges in the network; if it exists , will node i Move to command The largest node resides in community C; repeat this step until moving any node no longer results in any modularity gain. ; Step 2a-4: Treat each community obtained in Step 2a-3 as a new node. Consider the sum of edge weights within a community as the self-connection weight of the new node. The edge weight between two adjacent new nodes is the sum of the edge weights between nodes in the two communities. Calculate the modularity gain according to Step 2a-3. ; Step 2a-5: Repeat steps 2a-3 and 2a-4 until the community no longer changes, and obtain the distribution map of the international cooperation community of the satellite network; Steps 2a-6: Evaluate cooperability centrality; calculate the cooperability centrality PR value for each node, i.e., each country: ； in, It is the first i 1 node It is the first j 1 node It points to a node All nodes, It is a node The number of links to which it points, where N is the total number of nodes; This is the damping factor, with a value of 0.85; Each country's cooperation centrality (PR) value is directly proportional to its importance in cooperation; Step 2b specifically includes: Step 2b-1: Use the connected graph partitioning algorithm to cluster the nodes of the satellite network association network to obtain the connected subgraph of the satellite network association relationship; Step 2b-2: For each pair of related data in the satellite network interconnection subgraph, query the satellite network data database to obtain the specific cooperative business types between the related data.

2. The method for mining international cooperation relationships in satellite networks according to claim 1, characterized in that, Step 1 specifically includes: Step 1a: Query the satellite network data database to obtain the names of all non-deprecated satellite network data and the names of the countries that submitted the data; Step 1b: Query the satellite network data database, determine the direction of the inter-satellite link association based on the link direction, and obtain the inter-satellite link association between satellite network data.

3. The method for mining international cooperation relationships in satellite networks according to claim 1, characterized in that, The connected component graph algorithm is implemented using the networkx.connected_components function in Python.

4. A satellite network international cooperation relationship mining system, used to implement the method as described in claim 1, the system comprising: The relational network module is used to build a network of relationships between satellite networks. The "Explore Partnerships" module is used to explore national partnerships within satellite networks.

5. The satellite network international cooperation relationship mining system according to claim 4, characterized in that, The module for mining cooperative relationships includes: The coarse-grained relationship mining module is used to obtain the community distribution of national cooperation networks and the importance of each country in the cooperation; and The fine-grained relationship mining module is used to obtain the types of cooperative business between countries in satellite network engineering.

6. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 3.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the method as described in any one of claims 1 to 3.

Images