Network construction methods, devices, electronic devices and storage media

Abstract

This disclosure provides a network construction method, apparatus, electronic device, vehicle, and storage medium, relating to the field of artificial intelligence technology, particularly network construction and big data analysis, and applicable to smart city scenarios. The specific implementation scheme is as follows: when a jump relationship exists between a first node and a second node, the root node to which the first node belongs and the root node to which the second node belongs are found in the node network set; if the root nodes to which the first node belongs and the second node belong are different, the first node network and the second node network are merged in the node network set; wherein, the first node network is the network to which the first node resides, and the second node network is the network to which the second node resides. Using the technical solution of this disclosure can improve the speed of network construction.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and more particularly to the fields of network construction and big data analysis, with applications in smart city scenarios. Specifically, this disclosure relates to a network construction method, apparatus, electronic device, and storage medium. Background Technology

[0002] In big data analytics scenarios, data typically involves multiple nodes, and these nodes may have interrelationships, such as navigation from node A to node B, or from node B to node C. Building a node network based on these relationships and then using that network for big data analysis is a common approach in big data analytics. Therefore, the node network can significantly impact the effectiveness of big data analysis. Summary of the Invention

[0003] This disclosure provides a network construction method, apparatus, electronic device, and storage medium.

[0004] According to one aspect of this disclosure, a network construction method is provided, comprising:

[0005] If there is a jump relationship between the first node and the second node, search for the root node to which the first node belongs and the root node to which the second node belongs in the node network set.

[0006] If the root nodes to which the first node belongs and the root nodes to which the second node belongs are different, the first node network and the second node network are merged in the node network set.

[0007] Wherein, the first node network is the network where the first node is located, and the second node network is the network where the second node is located.

[0008] According to another aspect of this disclosure, a network construction apparatus is provided, comprising:

[0009] The root node lookup module is used to find the root node to which the first node belongs and the root node to which the second node belongs in the node network set when there is a jump relationship between the first node and the second node.

[0010] A network merging module is used to merge a first node network and a second node network in the node network set when the root nodes to which the first node belongs and the second node belong are different.

[0011] Wherein, the first node network is the network where the first node is located, and the second node network is the network where the second node is located.

[0012] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0013] At least one processor; and

[0014] The memory is communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the network construction methods in the embodiments of this disclosure.

[0016] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform any network construction method according to an embodiment of this disclosure.

[0017] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements any network construction method according to an embodiment of this disclosure.

[0018] According to the technology disclosed herein, when there is a jump relationship between the first node and the second node, the root node to which the first node belongs and the root node to which the second node belongs are searched in the node network set; when the root nodes to which the first node belongs and the root nodes to which the second node belongs are different, the networks containing the first node and the second node are merged in the node network set. Therefore, the solution disclosed herein can quickly construct a node network when there are a large number of nodes.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0020] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0021] Figure 1 This is a flowchart of a network construction method according to an embodiment of the present disclosure;

[0022] Figure 2 This is a schematic diagram of a network construction process according to an embodiment of the present disclosure;

[0023] Figure 3 This is a flowchart of a method for combating black market activities according to an embodiment of this disclosure;

[0024] Figure 4 This is a structural block diagram of a network construction apparatus according to an embodiment of the present disclosure;

[0025] Figure 5 This is a structural block diagram of a network construction apparatus according to another embodiment of the present disclosure;

[0026] Figure 6 This is a block diagram of an electronic device used to implement the network construction method of the embodiments of this disclosure. Detailed Implementation

[0027] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0028] The solutions disclosed herein can be applied to communication scenarios. For example, a communication network can be constructed using the methods disclosed herein. For a given communication node, the source node corresponding to that node can be obtained by tracing back layer by layer in the communication network. Alternatively, for a given node, the target node to be reached can be obtained by jumping forward in the communication network from that node.

[0029] The disclosed solution can also be applied to economic or financial analysis scenarios. For example, for multiple nodes involved in fund transfers, the disclosed solution can be used to construct a node network, and economic or financial analysis can be performed based on the node network.

[0030] Figure 1 This is a flowchart of a network construction method according to an embodiment of the present disclosure.

[0031] like Figure 1 As shown, the network construction method may include:

[0032] S110, if there is a jump relationship between the first node and the second node, find the root node to which the first node belongs and the root node to which the second node belongs in the node network set.

[0033] S120, if the root nodes to which the first node belongs are different from the root nodes to which the second node belongs, merge the first node network and the second node network in the node network set.

[0034] The first node network is the network where the first node is located, and the second node network is the network where the second node is located.

[0035] For example, the network construction scheme provided in this disclosure can be applied to smart city scenarios.

[0036] For example, in a communication scenario, the first node and the second node can be communication nodes. The hop relationship can include an access relationship from the first node to the second node, or a data forwarding relationship from the first node to the second node.

[0037] For example, in a fund transfer scenario, the first node and the second node can be fund accounts. The redirection relationship can include transferring funds from the account corresponding to the first node to or making payments to the account corresponding to the second node, or transferring funds from the account corresponding to the second node to or making payments to the account corresponding to the first node.

[0038] For example, the set of node networks includes one or more tree-shaped node networks. Each node network includes one or more nodes. Each node network includes a root node and non-root nodes, where non-root nodes are directly connected to the root node, or non-root nodes are connected to the root node through one or more intermediate non-root nodes.

[0039] For example, if the network containing the first node consists of only one node, then the root node of the first node is the first node. If the network containing the second node consists of only one node, then the root node of the second node is the second node.

[0040] For example, if the root node of the first node and the root node of the second node are the same, the node network in which the first node and the node network in which the second node are located can be considered as the same network. In this case, there is no need to merge the networks.

[0041] For example, if the root node of the first node and the root node of the second node are different, the node network containing the first node and the node network containing the second node can be considered as two different networks, that is, the first node network and the second node network are not the same network. In this case, it is necessary to merge these two networks.

[0042] For example, merging a first node network and a second node network in a set of node networks includes: determining, based on the number of nodes in the first node network and the number of nodes in the second node network, whether to merge the first node network into the second node network or to merge the second node network into the first node network.

[0043] For example, merging a first node network and a second node network in a set of node networks includes: determining, based on the network depth of the first node network and the network depth of the second node network, whether to merge the first node network into the second node network or the second node network into the first node network.

[0044] In a tree network, network depth refers to the number of nodes from the leaf node to the root node. A leaf node is a node in the tree network that has no further branches; it is also called the terminal node of the tree network. The root node is a node in the tree network that has no parent node; it is also called the apex node of the tree network. The parent node of a given node is the node preceding it in the tree network.

[0045] Therefore, when a tree network includes multiple branches from leaf nodes to the root node, the network depth of different branches in the tree network may be different. Thus, the network depth can be the maximum network depth of the tree network.

[0046] For example, merging a first node network and a second node network in a set of node networks includes: incorporating the first node network into the second node network in the set of node networks.

[0047] For example, merging a first node network and a second node network in a set of node networks includes: incorporating the second node network into the first node network in the set of node networks.

[0048] According to the above implementation, when there is a jump relationship between the first node and the second node, and the root nodes of the first node and the second node are different in the node network set, the networks containing the first node and the second node are merged in the node network set. Therefore, this implementation can improve the construction speed of the node network when the number of nodes is large.

[0049] In practical applications, the embodiments disclosed herein can be used in combating illicit activities. For example, in economic crimes involving financial transactions, criminals are highly vigilant and often transfer funds between multiple accounts during the process of transferring illicit proceeds to launder illegal assets and evade law enforcement. Such money laundering networks often have multiple hidden money laundering nodes. If a particular node is targeted, criminals, due to their strong counter-surveillance capabilities, can quickly detect that the money laundering node has been targeted and rapidly switch to another money laundering node. Therefore, it is difficult to completely dismantle the money laundering network.

[0050] In some technologies, the approach to quickly trace money laundering networks involves first mapping a node network based on the records of fund transfers between nodes, then analyzing this network to identify the money laundering network, and finally simultaneously targeting all nodes within the network. However, this approach has the following problems:

[0051] 1. This money laundering network was drawn manually, heavily reliant on human experience, and lacks scalability.

[0052] 2. The nodes in an illegal money laundering network are often nested in layers, and each node is connected to its superior node in a single line. Even if several layers of nodes are destroyed, it is difficult to find the final money laundering root node. This allows criminals to quickly restore the destroyed money laundering network.

[0053] 3. Money laundering networks have complex structures, requiring a large amount of computation during the investigation process. Manual analysis is costly.

[0054] In contrast, the network construction solution provided in this disclosure can solve the above problems.

[0055] According to the embodiments of this disclosure, the constructed network structure, when used to find a specific node or the root node to which a node belongs, guarantees that the time complexity of the search is the logarithm of N to the base 2, where N is the number of nodes in the node network set. This improves the efficiency of node searching. In scenarios involving the analysis and mining of black market nodes, it significantly enhances analysis and mining efficiency.

[0056] In one exemplary implementation, merging a first node network and a second node network in a set of node networks includes: determining a merging method for the first node network and the second node network based on the network parameters of the first node network and the second node network, and merging the first node network and the second node network in the set of node networks based on the merging method.

[0057] For example, network parameters may include the number of nodes and network depth.

[0058] For example, merging a first node network and a second node network in a set of node networks includes: determining a merging method for the first node network and the second node network based on the number of nodes in the first node network and the number of nodes in the second node network, and / or the network depth of the first node network and the network depth of the second node network; and merging the first node network and the second node network in the set of node networks based on the merging method.

[0059] For example, the merging method of the first node network and the second node network is determined based on the number of nodes in the first node network and the number of nodes in the second node network. For example, the node network with fewer nodes is merged into the node network with more nodes, or the node network with more nodes is merged into the node network with fewer nodes.

[0060] For example, the merging method of the first node network and the second node network is determined based on the network depth of the first node network and the network depth of the second node network. For example, the network with shallower network depth is merged into the network with deeper network depth, or the network with deeper network depth is merged into the network with shallower network depth.

[0061] For example, the merging method of the first node network and the second node network is determined based on the number of nodes in the first node network and the number of nodes in the second node network, as well as the network depth of the first node network and the network depth of the second node network. For example, a network with fewer nodes and shallower network depth is merged into a network with more nodes and deeper network depth, and a network with more nodes and deeper network depth is merged into a network with fewer nodes and shallower network depth.

[0062] For example, the merging method may include merging the first node network into the second node network, and merging the second node network into the first node network.

[0063] For example, the merging method may further include determining which node in the second node network the root node of the first node network is connected to when the first node network is merged into the second node network, and determining which node in the second node network the root node of the second node network is connected to when the second node network is merged into the first node network.

[0064] According to the above implementation method, the merging method of two node networks is determined by the number of nodes and the network depth of the two node networks. Thus, under the premise of accurately determining the networks to be merged, the network depth and the number of nodes of each network in the network set can be adjusted.

[0065] In one exemplary implementation, the network parameters include the number of nodes. Based on the network parameters of the first node network and the second node network, the method of merging the first node network and the second node network is determined, including: if the number of nodes in the first node network is less than the number of nodes in the second node network, the method of merging the first node network and the second node network is determined to be merging the first node network into the second node network.

[0066] For example, in the merged second node network, the parent node of the third node is the fourth node, where the third node is the root node in the first node network before the merger, and the fourth node is the root node in the second node network.

[0067] According to the above implementation method, a network with fewer nodes is merged into a network with more nodes. Furthermore, during the merge, the root node of the network with fewer nodes is connected to the root node of the network with more nodes. This merging method avoids the merged network becoming too deep, thereby improving the efficiency of node lookup.

[0068] In one exemplary implementation, the network parameters include network depth. Based on the network parameters of the first node network and the second node network, the method of merging the first node network and the second node network is determined, including: if the network depth of the first node network is less than the network depth of the second node network, the method of merging the first node network and the second node network is determined to be merging the first node network into the second node network.

[0069] For example, in the merged second node network, the parent node of the third node is the fourth node, where the third node is the root node in the first node network before the merger, and the fourth node is the root node in the second node network.

[0070] According to the above implementation method, networks with shallower depths are merged into networks with deeper depths. During the merge, the root node of the shallower network is connected to the root node of the deeper network. In this merging method, the network depth of the deeper network can cover the network depth of the shallower network, which avoids the merged network being too deep, thereby improving the efficiency of node lookup.

[0071] Figure 2 This is a schematic diagram of a network construction process according to an embodiment of the present disclosure.

[0072] The following combination Figure 2 The process of network merging is described exemplarily as follows:

[0073] like Figure 2 As shown, taking nodes 5 and 0 as an example, the node network set in the sixth row is the node network set before the merge, and the node network set in the seventh row is the node network set after the merge. Assuming that nodes 5 and 0 have a jump relationship, we can see from the node network set in the sixth row that the root node of node 5 is node 6, and the root node of node 0 is node 0. Therefore, since the root node of node 5 is different from the root node of node 0, we can merge the network B1 containing node 5 and the network A containing node 0.

[0074] During the merging process, in the set of node networks, network A is merged into network B1, and node 0 in network A is connected to node 6 in network B1, resulting in network B2 consisting of node 0, node 5, and node 6.

[0075] As shown in the example above, before merging, network A has 1 node and a tree depth of 1; network B1 has 2 nodes and a tree depth of 2. After merging, the resulting new network B2 has 3 nodes and a tree depth of 2. Therefore, this network merging method does not increase the tree depth of the new network relative to the tree depth of the old network.

[0076] According to the above implementation method, merging networks with fewer nodes into networks with more nodes, or merging networks with shallower depths into networks with deeper depths, can avoid the merged network becoming too deep, thereby improving the efficiency of node lookup.

[0077] In one exemplary embodiment, the method may further include: if a first node cannot be found in a node network in a node network set, adding a first node network to the node network set, wherein the root node of the first node network is the first node, and the number of nodes in the first node network is 1.

[0078] For example, when a node is found in a node network within a set of node networks, it is not necessary to add a first node network to the set of node networks.

[0079] In one exemplary embodiment, the method may further include: if a second node cannot be found in a node network in a node network set, adding a second node network to the node network set, wherein the root node of the second node network is the first node, and the number of nodes in the second node network is 1.

[0080] For example, when a node is found in a node network within a set of node networks, it is not necessary to add a first node network to the set of node networks.

[0081] like Figure 2 As shown, taking nodes 3 and 4 as examples, the node network set in the first row is the node network set before the merge, and the node network set in the second row is the node network set after the merge. Before the merge, if nodes 3 and 4 are found in the node network set in the first row, then it is not necessary to add the network consisting of node 3 as the root node and the network consisting of node 4 as the root node to the node network set in the first row.

[0082] If node 3 is not included in the node network set in the first row, then node 3 needs to be added to the node network set, and node 3 should be set as the root node, with the number of nodes in the network containing node 3 being 1.

[0083] According to the above implementation method, when searching for the root node of a certain node, the node itself is searched first. If the node cannot be found in the node network set, a new node network is added to the node network set, with the root node being the specified node, and the number of nodes in this new node network is 1. This avoids situations where the specified node cannot be found in the node network set.

[0084] In one exemplary embodiment, the method may further include: searching for a jump record in a jump record set based on a first node and a second node; if a first jump record and / or a second jump record are found in the jump record set, determining that a jump relationship exists between the first node and the second node; wherein the first jump record includes jump information from the first node to the second node, and the second jump record includes jump information from the second node to the first node.

[0085] For example, the jump record set includes one or more jump records, each jump record including a jump relationship between at least two nodes.

[0086] For example, in a communication scenario, the first node and the second node can be communication nodes. The first hop record may include an access record of accessing the second node from the first node, or a data stream record of forwarding data from the first node to the second node. The second hop record may include an access record of accessing the first node from the second node, or a data stream record of forwarding data from the second node to the first node.

[0087] For example, in a fund transfer scenario, the first node and the second node can be transaction accounts. The first redirect record may include fund flow information of transfers from the account corresponding to the first node to or payments to the account corresponding to the second node. The second redirect record may include fund flow information of transfers from the account corresponding to the second node to or payments to the account corresponding to the first node.

[0088] According to the above implementation method, based on the jump record between the first node and the second node, it is possible to accurately determine whether there is a jump relationship between the first node and the second node, so as to improve the accuracy of subsequent node network construction.

[0089] In one exemplary embodiment, the above method may further include: determining a node set based on the nodes in each jump record in the jump record set; and adding a third node network to the node network set if a third node in the node network set cannot be found, wherein the root node of the third node network is the third node and the number of nodes in the third node network is 1.

[0090] For example, a node set includes one or more nodes.

[0091] For example, duplicate nodes are removed from each jump record in the jump record set to obtain a node set. For instance, duplicate nodes are deleted.

[0092] like Figure 2 As shown, assuming there are 10 nodes in the node set, each node is assigned a unique number, such as a number from 0 to 9, so that in Figure 2The first row of the node network set adds nodes 0 to 9. Each node is the root node, and the number of nodes in the network of each node is 1.

[0093] According to the above implementation method, a set of nodes is collected, and the set of nodes is used to initialize the network in the node network set, which facilitates subsequent network merging and improves the speed of network construction.

[0094] In one exemplary embodiment, the method may further include: determining a set of node combinations based on any two nodes in the node set; filtering node combinations in the node combination set based on search records for each node combination in the node combination set to obtain a first node combination; and determining a first node and a second node based on the first node combination.

[0095] For example, a node combination set includes one or more node combinations. Each node combination includes two nodes.

[0096] For example, the lookup record for a node combination includes information on whether a jump record has been searched in the jump record set for two nodes in the node combination.

[0097] For example, in the set of node combinations, node combinations that have not been searched for a jump record are filtered to obtain the first node combination, thereby obtaining the first node and the second node. For the first node and the second node, a jump record is searched in the set of jump records to determine whether there is a jump relationship between the two nodes, and further to determine whether the networks containing these two nodes should be merged.

[0098] According to the above implementation method, for any two nodes for which no jump record has been found, it is determined whether the networks to which these two nodes belong need to be merged, which can improve the speed of network construction.

[0099] Figure 3 This is a flowchart of a method for combating cybercrime according to an embodiment of the present disclosure.

[0100] The following will combine Figure 2 and Figure 3 Taking the fight against cybercrime as an example, the process of network construction is described in detail below:

[0101] 1. Data Preprocessing Stage. Obtain financial transaction records that may be involved in illicit activities. Collect account information from these records, deduplicate accounts, and obtain an account set. Uniquely number each account in the account set. For example, if the account set contains 10 accounts, number them from 0 to 9.

[0102] 2. Initialize the tree network.

[0103] like Figure 2 As shown, in the tree network set in the first row, add nodes 0 to 9, and set each node as the root node. The number of nodes in the tree network of each node is 1.

[0104] 3. Merging tree networks.

[0105] For any two nodes, check the fund transfer records to see if there are any fund transfer records between them. If so, search the tree network set for the root nodes to which each node belongs. If the two root nodes to which each node belongs are different, merge the networks to which these two nodes belong, and merge the network with fewer nodes into the network with more nodes. The parent node of the root node of the network with fewer nodes becomes the root node of the network with more nodes, thus avoiding excessive network depth and improving node search efficiency.

[0106] like Figure 2 As shown, for nodes 3 and 4, the first row represents the node network set before merging, and the second row represents the node network set after merging. In the fund flow records, a transfer or transaction record is found between nodes 3 and 4. In the node network set, node 3 belongs to root node 3, and node 4 belongs to root node 4; their root nodes are different. Therefore, the networks of nodes 3 and 4 are merged. Since the number of nodes in the network of node 3 is the same as the number of nodes in the network of node 4, we can choose to connect node 3 to node 4 and make it a child node of node 4, or connect node 4 to node 3 and make it a child node of node 3. Figure 2 For example, connect node 3 to node 4 and make it a child node of node 4.

[0107] For nodes 3 and 8, the node network set in the second row is the node network set before merging, and the node network set in the third row is the node network set after merging.

[0108] The fund flow records show a transfer or transaction record between node 3 and node 8. In the node network set, node 3 belongs to root node 4, and node 8 belongs to root node 8; their root nodes are different. Therefore, the networks of node 3 and node 8 are merged. Since the network of node 3 has 2 nodes and the network of node 8 has 1 node, the network of node 8 is merged into the network of node 3, and node 8 is connected to root node 4 as a child node of root node 4.

[0109] For nodes 6 and 5, the node network set in the third row is the set of node networks before merging, and the node network set in the fourth row is the set of node networks after merging. The process of merging the networks for nodes 6 and 5 is similar to the process of merging the networks for nodes 3 and 4, and can be referred to the detailed introduction above, which will not be elaborated here.

[0110] For nodes 9 and 4, the node network set in the fourth row is the set of node networks before merging, and the node network set in the fifth row is the set of node networks after merging. The process of merging the networks for nodes 9 and 4 is similar to the process of merging the networks for nodes 3 and 8, and can be referred to the detailed introduction above, which will not be elaborated here.

[0111] For nodes 2 and 1, the node network set in the fifth row is the set of node networks before merging, and the node network set in the sixth row is the set of node networks after merging. The process of merging the networks for nodes 2 and 1 is similar to the process of merging the networks for nodes 3 and 4, and can be referred to the detailed introduction above, which will not be elaborated here.

[0112] The merging process for nodes 5 and 0 has been described previously; for details, please refer back to the previous implementation methods. It will not be elaborated here.

[0113] For nodes 7 and 2, the node network set in the seventh row is the set of node networks before merging, and the node network set in the eighth row is the set of node networks after merging. The process of merging the networks for nodes 7 and 2 is similar to the process of merging the networks for nodes 3 and 8, and can be referred to the detailed introduction above, which will not be elaborated here.

[0114] For nodes 6 and 1, the node network set in the eighth row is the set of node networks before merging, and the node network set in the ninth row is the set of node networks after merging. The process of merging the networks for nodes 6 and 1 is similar to the process of merging the networks for nodes 3 and 8, and can be referred to the detailed introduction above, which will not be elaborated here.

[0115] Similarly, by merging any two nodes in the account set using the above method, a node network can be quickly constructed. Furthermore, merging networks with fewer nodes into networks with more nodes, and ensuring that the parent node of the root node of the network with fewer nodes is the root node of the network with more nodes, avoids excessive network depth and thus improves node search efficiency.

[0116] 3. Based on tree network sets, analyze and mine other nodes or networks associated with the node involved.

[0117] In the tree network set, find the node involved, as well as other nodes or networks associated with the node involved.

[0118] According to the above implementation method, the constructed network structure, when used to find a specific node or the root node to which a node belongs, ensures that the time complexity of node search is the logarithm of N to the base 2, where N is the number of nodes in the node network set. This low time complexity improves the efficiency of node search. In scenarios involving the analysis and mining of black market nodes, it also significantly improves analysis and mining efficiency. This not only accurately and quickly identifies other nodes associated with the node in question but also uncovers the entire black market network associated with that node, greatly improving the efficiency of combating black market networks. Therefore, the embodiments of this disclosure can demonstrate significant practical value in the fields of economics and network information.

[0119] Figure 4 This is a structural block diagram of a network construction apparatus according to an embodiment of the present disclosure.

[0120] like Figure 4 As shown, the network construction apparatus includes:

[0121] The root node lookup module 410 is used to find the root node to which the first node belongs and the root node to which the second node belongs in the node network set when there is a jump relationship between the first node and the second node.

[0122] The network merging module 420 is used to merge a first node network and a second node network in the node network set when the root nodes to which the first node belongs and the root nodes to which the second node belongs are different, wherein the first node network is the network to which the first node is located, and the second node network is the network to which the second node is located.

[0123] Figure 5 This is a structural block diagram of a network construction apparatus according to another embodiment of the present disclosure.

[0124] like Figure 4 and Figure 5 As shown, Figure 5 The root node search module 510 and the network merging module 520 are respectively connected with Figure 4 The root node search module 410 and the network merging module 420 have the same function or role, which will not be described in detail here.

[0125] In one exemplary embodiment, the network merging module 520 includes:

[0126] The merging method determination unit 521 is used to determine the merging method of the first node network and the second node network based on the network parameters of the first node network and the network parameters of the second node network.

[0127] The network merging unit 522 is used to merge the first node network and the second node network in the node network set based on the merging method.

[0128] In one exemplary embodiment, the network parameters include node data, and the merging method determination unit 521 is specifically used for:

[0129] If the number of nodes in the first node network is less than the number of nodes in the second node network, the method for merging the first node network and the second node network is determined to be to merge the first node network into the second node network.

[0130] In one exemplary embodiment, the network parameters include network depth, and the merging method determination unit 521 is specifically used for:

[0131] If the network depth of the first node network is less than the network depth of the second node network, the method for merging the first node network and the second node network is determined to be to merge the first node network into the second node network.

[0132] In one exemplary implementation, in the merged second node network, the parent node of the third node is the fourth node; wherein the third node is the root node in the first node network before the merger, and the fourth node is the root node in the second node network.

[0133] In one exemplary implementation, such as Figure 5 As shown, the device also includes:

[0134] The first network adding module 530 is used to add the first node network to the node network set when no node network containing the first node can be found in the node network set, wherein the root node of the first node network is the first node, and the number of nodes in the first node network is 1.

[0135] In one exemplary implementation, such as Figure 5 As shown, the device also includes:

[0136] The second network adding module 540 is used to add a second node network to the node network set when no node network containing the second node can be found in the node network set, wherein the root node of the second node network is the first node, and the number of nodes in the second node network is 1.

[0137] In one exemplary implementation, such as Figure 5 As shown, the device also includes:

[0138] The jump record lookup module 550 is used to search for jump records in the jump record set based on the first node and the second node;

[0139] The jump relationship determination module 560 is used to determine that there is a jump relationship between the first node and the second node when the first jump record and / or the second jump record are found in the jump record set;

[0140] The first jump record includes jump information from the first node to the second node, and the second jump record includes jump information from the second node to the first node.

[0141] In one exemplary implementation, such as Figure 5 As shown, the device also includes:

[0142] The node set determination module 570 is used to determine the node set based on the nodes in each jump record in the jump record set;

[0143] The third network addition module 580 is used to add a third node network to the node network set when the third node in the node network set cannot be found, wherein the root node of the third node network is the third node, and the number of nodes in the third node network is 1.

[0144] In one exemplary implementation, such as Figure 5 As shown, the device also includes:

[0145] The node group set determination module 590 is used to determine a node combination set based on any two nodes in the node set;

[0146] The node group filtering module 591 is used to filter node combinations in the node combination set based on the search records for each node combination in the node combination set to obtain the first node combination.

[0147] The search record includes information on whether a jump record has been searched in the jump record set. If the search record of the first node combination includes information on whether a jump record has been searched in the jump record set, the first node combination includes the first node and the second node.

[0148] The specific functions and examples of each module and submodule of the apparatus in this disclosure can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0149] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0150] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0151] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0152] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded into random access memory (RAM) 603 from storage unit 608. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0153] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0154] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a network construction method. For example, in some embodiments, a network construction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of a network construction method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform a network construction method by any other suitable means (e.g., by means of firmware).

[0155] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0156] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0157] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0158] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0159] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0160] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0161] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0162] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A network construction method, comprising: If there is a jump relationship between the first node and the second node, find the root node to which the first node belongs and the root node to which the second node belongs in the node network set. When the root nodes to which the first node belongs and the root nodes to which the second node belongs are different, merging the first node network and the second node network in the node network set includes: merging the first node network into the second node network. Wherein, the first node network is the network where the first node is located, the second node network is the network where the second node is located, and in the merged second node network, the parent node of the third node is the fourth node. The third node is the root node in the first node network before the merger, and the fourth node is the root node in the second node network.

2. The method according to claim 1, wherein, The merging of the first node network and the second node network in the node network set includes: Based on the network parameters of the first node network and the network parameters of the second node network, determine the merging method of the first node network and the second node network; Based on the merging method, the first node network and the second node network are merged in the node network set.

3. The method according to claim 2, wherein, The network parameters include the number of nodes. Determining the merging method of the first node network and the second node network based on the network parameters of the first node network and the second node network includes: If the number of nodes in the first node network is less than the number of nodes in the second node network, the method for merging the first node network and the second node network is determined to be to merge the first node network into the second node network.

4. The method according to claim 2, wherein, The network parameters include network depth. Determining the merging method of the first node network and the second node network based on the network parameters of the first node network and the second node network includes: If the network depth of the first node network is less than the network depth of the second node network, the method for merging the first node network and the second node network is determined to be to merge the first node network into the second node network.

5. The method according to any one of claims 1-4, further comprising: If the first node cannot be found in the node network set, the first node network is added to the node network set, wherein the root node of the first node network is the first node, and the number of nodes in the first node network is 1.

6. The method according to any one of claims 1-4, further comprising: If the second node cannot be found in the node network set, the second node network is added to the node network set, wherein the root node of the second node network is the first node, and the number of nodes in the second node network is 1.

7. The method according to any one of claims 1-4, further comprising: Based on the first node and the second node, search for the jump record in the jump record set; If a first jump record and / or a second jump record are found in the jump record set, it is determined that there is a jump relationship between the first node and the second node; The first jump record includes jump information from the first node to the second node, and the second jump record includes jump information from the second node to the first node.

8. The method according to claim 7, further comprising: Based on the nodes in each jump record in the jump record set, determine the node set; If a third node cannot be found in the node network set, a third node network is added to the node network set, wherein the root node of the third node network is the third node, and the number of nodes in the third node network is 1.

9. The method according to claim 8, further comprising: Determine a set of node combinations based on any two nodes in the node set; Based on the search records for each node combination in the node combination set, the node combinations are filtered in the node combination set to obtain the first node combination; Based on the first node combination, the first node and the second node are determined.

10. A network construction apparatus, comprising: The root node lookup module is used to find the root node to which the first node belongs and the root node to which the second node belongs in the node network set when there is a jump relationship between the first node and the second node. A network merging module is used to merge a first node network and a second node network in the node network set when the root nodes to which the first node belongs and the second node belong are different, including merging the first node network into the second node network. Wherein, the first node network is the network where the first node is located, the second node network is the network where the second node is located, and in the merged second node network, the parent node of the third node is the fourth node. The third node is the root node in the first node network before the merger, and the fourth node is the root node in the second node network.

11. The apparatus according to claim 10, wherein, The network merging module includes: The merging method determination unit is used to determine the merging method of the first node network and the second node network based on the network parameters of the first node network and the network parameters of the second node network. A network merging unit is used to merge the first node network and the second node network in the set of node networks based on the merging method.

12. The apparatus according to claim 11, wherein, The network parameters include node data, and the merging method determination unit is specifically used for: If the number of nodes in the first node network is less than the number of nodes in the second node network, the method for merging the first node network and the second node network is determined to be to merge the first node network into the second node network.

13. The apparatus according to claim 11, wherein, The network parameters include network depth, and the merging method determination unit is specifically used for: If the network depth of the first node network is less than the network depth of the second node network, the method for merging the first node network and the second node network is determined to be to merge the first node network into the second node network.

14. The apparatus according to any one of claims 10-13, further comprising: The first network adding module is used to add the first node network to the node network set when the first node cannot be found in the node network set, wherein the root node of the first node network is the first node, and the number of nodes in the first node network is 1.

15. The apparatus according to any one of claims 10-13, further comprising: The second network adding module is used to add a second node network to the node network set when the second node cannot be found in the node network set, wherein the root node of the second node network is the first node, and the number of nodes in the second node network is 1.

16. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

17. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-9.

18. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-9.

Images