Multi-role embedding representation method and system based on self network splitting

Abstract

The invention provides a multi-role embedding representation method and system based on self-network splitting, and the method comprises the steps: carrying out the self-network splitting and reconstruction of an enterprise network data set, and constructing a multi-role network; capturing an enterprise node migration sequence from the local angle and the global angle of the network through quantum migration for the multi-role network, and obtaining the structure information of the network; comparing the walk sequence to generate a node role identification matrix of the enterprise network; and fusing the role representation of the enterprise node with the neighborhood feature information of the enterprise node to obtain a multi-role embedded representation of the enterprise node. According to the method, multi-role identification and embedded representation are carried out on the enterprise nodes in the network based on a self-network splitting mode, so that the problem that the existing multi-role embedded representation method only carries out single role identification on the enterprise nodes in the enterprise network is radically solved; and the multi-role embedding representation accuracy of the enterprise node is low.

Description

Technical Field

[0001] The present invention belongs to the field of complex network data mining, and in particular relates to a multi-role embedding representation method, system and device based on self-network splitting. Background Art

[0002] Networks are everywhere, full of complexity and diversity. Enterprise networks are one of the most common networks. In enterprise networks, each node represents an enterprise, and an edge represents the relationship between two nodes. In order to better understand and analyze enterprise network data, network embedding technology has emerged and has become an important technology and method for downstream tasks such as node classification, network clustering, and link prediction.

[0003] Among the nodes in the enterprise network, a set of nodes with similar structural features or the same pattern is called a role. Specifically, roles include suppliers, dealers, and customers, etc. The network constructed by role nodes is called a role network. Most existing methods map the nodes in the network to a low-dimensional vector space to achieve a one-to-one correspondence between nodes and vectors.

[0004] Role network embedding aims to project nodes with similar roles in the network into a tighter low-dimensional vector space, becoming an effective tool for network analysis. However, existing multi-role representation methods are usually limited to a single role identification of enterprise nodes in the enterprise network, ignoring the different functions played by enterprise nodes in the enterprise network. Identifying the different roles of enterprise nodes in the network can better understand the structure and function of the enterprise network, reveal hidden patterns and laws, discover key nodes and paths, design more effective network management and control strategies, and predict the behavior and evolution of the network. That is, there are currently problems that the existing multi-role embedding representation methods only identify enterprise nodes in a single role in the enterprise network, and the multi-role embedding representation of the enterprise network has low accuracy.

[0005] Therefore, how to realize multi-role identification and multi-role embedding representation of enterprise nodes in an enterprise network and improve the accuracy of multi-role embedding representation is an urgent problem to be solved in this field. Summary of the invention

[0006] The purpose of the present invention is to provide a multi-role embedding representation method and system based on self-network splitting in view of the defects of the prior art. The multi-role embedding representation method based on self-network splitting of the present invention constructs a multi-role network by self-network splitting and reconstructing the enterprise network data set; the multi-role network is used to capture the enterprise node wandering sequence from both the local and global perspectives of the network through quantum walks to obtain the structural information of the network; the wandering sequence is compared to generate the node role identification matrix of the enterprise network; the role representation of the enterprise node is integrated with the neighborhood feature information of the enterprise node to obtain the multi-role embedding representation of the enterprise node. The present invention adopts a method for multi-role identification and embedding representation of enterprise nodes in the network based on self-network splitting, thereby fundamentally solving the problem that the existing multi-role embedding representation method only performs a single role identification on the enterprise node in the enterprise network, and the multi-role embedding representation of the enterprise node has low accuracy.

[0007] In order to achieve the above purpose, the present invention adopts the following technical solutions:

[0008] The present invention proposes a multi-role embedding representation method based on ego network splitting, which is characterized by comprising the steps of:

[0009] S1. Split and reconstruct the enterprise network dataset to build a multi-role network; specifically include:

[0010] S11. Based on the enterprise network data set, perform self-network splitting; wherein, in the enterprise network data set, nodes represent different enterprises, and edges represent the relationship between enterprise nodes;

[0011] S12. Reconstructing the network based on the split nodes to form a multi-role network; wherein, in the multi-role network, nodes represent different enterprises, edges represent the relationship between enterprise nodes, node characteristics include enterprise scale and business type, and node roles include supplier, distributor, and customer;

[0012] S2. Based on the multi-role network, capturing the enterprise node wandering sequence through quantum wandering; specifically including:

[0013] S21. During the global walk, a probability distribution matrix is ​​obtained under the current walk evolution times; based on the probability distribution matrix, a global role representation of the enterprise node and a global quantum walk sequence are generated;

[0014] S22. Based on the biased quantum walk, generate a local role representation and a local quantum walk sequence of the enterprise node;

[0015] S3. Compare the walk sequences and generate role identifiers; specifically, it includes:

[0016] S31, splicing the global quantum walk sequence and the local quantum walk sequence to obtain a complete walk sequence of the enterprise node;

[0017] S32, determining a similarity function of the complete walk sequences of two enterprise nodes;

[0018] S33, based on the similarity function, performing sequence alignment on all nodes in the entire network to construct a similarity matrix;

[0019] S34, obtaining a node role identification matrix of the enterprise network according to the similarity matrix;

[0020] S4. The role representation of the enterprise node is integrated with the neighborhood feature information of the enterprise node to obtain a multi-role embedded representation of the enterprise node; specifically, the steps include:

[0021] S41, splicing the global role representation and the local role representation of the enterprise node to obtain a complete role representation that integrates global and local role information;

[0022] S42, using the characteristic function to calculate all node features and evaluation points to obtain the neighborhood feature information of the enterprise node, and performing feature fusion on the probability distribution matrix obtained by quantum walking to obtain the feature representation of the enterprise node;

[0023] S43: Fusing the complete role representation and the feature representation of the enterprise node to obtain a multi-role embedded representation of the enterprise node.

[0024] Furthermore, in step S11, based on the enterprise network data set, self-network splitting is performed, specifically:

[0025] The enterprise network dataset is G = (V, E), where nodes represent different enterprises and edges represent the relationship between enterprise nodes. Traverse all nodes in the graph and perform the following steps for each node:

[0026] The neighbor nodes of node v are defined as Disconnect the edges between the target node v and all the surrounding one-hop neighbor nodes. The edge set at this moment is

[0027] Compute the connected subgraph in the disconnected network Among them C i Represents node v i By disconnecting the subgraph set from the surrounding neighbors, Represents node v i The sth subgraph in the generated set i sub-graphs, s i is the number of connected subgraphs;

[0028] Each of the subnetworks can represent a specific role of the central node; the central node is split into s i nodes, each node is assigned to its own subnet; that is, for each connected subgraph Create a new node Make the new node set make Finally, we get a set of nodes

[0029] During the node splitting process, the number of roles in the network is obtained

[0030] Further, S12, based on the split nodes, the network is reconstructed to form a multi-role network, specifically including:

[0031] External reconstruction: split each node Connect the node V on the original graph G to the target node v. i , traverse all its edges (v i ,u)∈E; for the connected subgraph set C after disconnecting the edges i , if u exists in the subgraph In the j ; Update the new edge set in For node v i In the corresponding subgraph The new nodes generated under this condition; therefore, the network after external reconstruction is G′=(V′, E″);

[0032] Internal reconstruction: Perform the following operations on the externally reconstructed network G′: traverse all nodes v in the original network G i , find its split node set V′ i ,in For the set V′ i All nodes in the , are connected to each other, building new edges where 1≤j≤k≤s i ; Update edge set Form a multi-role network.

[0033] Further, in step S21, during the global walk, a probability distribution matrix under the current walk evolution times is obtained; based on the probability distribution matrix, a global role representation of the enterprise node and a global quantum walk sequence are generated, specifically:

[0034]

[0035] Among them, d(v) represents the node degree of enterprise node v, A represents the adjacency matrix of the graph, Sum() is the row summation function, k g represents the number of global quantum walk evolutions; Indicates that enterprise node v is in the kth g The evolution sequence representation obtained under the quantum walk evolution times; Indicates that enterprise node v is in the kth g -The evolution sequence representation obtained under 1 quantum walk evolution times; Indicates that enterprise node w is in the kth g -The evolution sequence representation obtained under 1 quantum walk evolution times; Indicated by The kth row of concatenation g The evolution sequence matrix obtained under the quantum walk evolution times; M0(v, ) represents the initialization vector obtained by calculating according to the degree of different nodes v; M0 represents the initialization matrix spliced ​​by row according to M0(v, ); z global It is the global role representation of the enterprise node, which is the sum of the probability matrix under global walk;

[0036] z global The i-th row represents the enterprise node v i The global walk sequence of nodes obtained by summing the probability matrix is ​​z global The walk sequence of each enterprise node in the final global quantum walk sequence is arranged horizontally: q = {q(v1), q(v2), ..., q(v n )}.

[0037] Further, step S22 generates a local role representation and a local quantum walk sequence of the enterprise node based on the biased quantum walk, specifically: obtaining global role information through quantum walk, biasing the quantum walk to emphasize the local structure of the enterprise node, and using the bias probability p ratio The initial probability of each enterprise node is biased, and the local role representation z of the node is obtained by calculating the role proximity local ,

[0038]

[0039] Among them, M'0(v,·) represents the bias probability p ratio The initialization sequence is obtained by calculating the degrees of different nodes v; M'0 represents the initialization matrix spliced ​​row by row according to M'0(v, ·); z local It is expressed as the sum of the probability matrix under local walk, k l represents the number of local quantum walk evolutions; M′1 represents the probability matrix obtained under one evolution of the local quantum walk; represents the local quantum walk k l The probability matrix obtained under the second evolution;

[0040] z local The i-th row represents the enterprise node v i The local walk sequence of the node obtained by summing the probability matrix is ​​z local The walk sequence of each node in the latitudinal arrangement is spliced ​​in rows to obtain the final local quantum walk sequence: q′={q′(v1), q′(v2), ..., q′(v n )}.

[0041] Furthermore, step S3, comparing the walking sequence and generating a role identifier, specifically includes:

[0042] S31, concatenate the global quantum walk sequence and the local quantum walk sequence to obtain a complete walk sequence of the enterprise node, specifically: Q = concat (q, q'), where Q (v i ) represents node v i The walking sequence of

[0043] S32. Determine the similarity function of the complete walk sequences of the two enterprise nodes, specifically:

[0044]

[0045] S33, based on the similarity function, sequence alignment is performed on all nodes in the entire network to construct a similarity matrix; wherein the similarity matrix is ​​identified as M R ;

[0046] S34, obtaining a node role identification matrix of the enterprise network according to the similarity matrix; specifically comprising:

[0047] Set the initial threshold R threshold =0.5, if R similarity (v i , v j )≥R threshold , then v i , v j Marked as the same character;

[0048] According to the similarity matrix M R Mark all nodes to get the role matrix R at this time M ;

[0049] Set the parameter Δ = 0.05, and calculate the statistical R M The number of roles in rn, if rn≤numR, then let R threshold =R threshold+Δ, if rn≥numR, then let R threshold =R threshold -Δ; calculate the value of |numR-rn| under each parameter; repeat the steps to determine R similarity (v i ,v j ) and the new threshold R threshold If R similarity (v i , v j )≥R threshold , then v i , v j Mark as the same role and update the role matrix R at this time M At this time R M for:

[0050]

[0051] where r x Represents the xth character;

[0052] When R threshold =min(|numR-rn|), the role matrix R obtained by comparing the threshold at this moment M The node role identification matrix obtained for the final network.

[0053] Further, S4, the role representation of the enterprise node is integrated with the neighborhood feature information of the enterprise node to obtain a multi-role embedded representation of the enterprise node; the specific formula is:

[0054] S41, concatenating the global role representation and the local role representation of the enterprise node to obtain a complete role representation that integrates global and local role information; specifically: z′=concat{Z local , Z global};

[0055] S42, using the characteristic function to calculate all node features and evaluation points, to obtain the neighborhood feature information of the enterprise node, and to perform feature fusion on the probability distribution matrix obtained by quantum walking, to obtain the feature representation of the enterprise node, specifically:

[0056]

[0057] Among them, x w is the feature vector of the target node w; M kg (v,w) represents the probability value of enterprise node v wandering to enterprise node w in the probability matrix; parameter θ represents the evaluation point value, set θ∈[-6,6];

[0058] S43, fusing the complete role representation and the feature representation of the enterprise node to obtain a multi-role embedded representation of the enterprise node, specifically: Z = concat{z′, z feature}.

[0059] The present invention also proposes a multi-role embedding representation system based on self-network splitting, wherein the multi-role embedding representation system executes the multi-role embedding representation method based on self-network splitting, including: a multi-role network construction module, a node wandering sequence acquisition module, a role identification generation module and a multi-role embedding representation construction module;

[0060] The multi-role network construction module splits and reconstructs the enterprise network data set to construct a multi-role network;

[0061] The node walk sequence acquisition module captures the enterprise node walk sequence through quantum walk based on the multi-role network;

[0062] The role identification generation module compares the wandering sequence and generates a role identification;

[0063] The multi-role embedding representation construction module integrates the role representation of the enterprise node with the neighborhood feature information of the enterprise node to obtain the multi-role embedding representation of the enterprise node.

[0064] The present invention further provides a computer device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0065] Compared with the prior art, it has the following beneficial effects:

[0066] The multi-role embedding representation method based on self-network splitting of the present invention constructs a multi-role network by performing self-network splitting and reconstruction on an enterprise network data set; based on the multi-role network, the enterprise node walk sequence is captured from both local and global perspectives of the network through quantum walks to obtain the structural information of the network; the walk sequences are compared to generate a node role identification matrix of the enterprise network; the role representation of the enterprise node is integrated with the neighborhood feature information of the enterprise node to obtain a multi-role embedding representation of the enterprise node; the multi-role identification of the enterprise nodes in the network is realized, and the accuracy of the multi-role embedding representation of the enterprise nodes in the network is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0068] Figure 1 A schematic diagram of a multi-role embedding representation method based on ego network splitting provided in an embodiment of the present invention.

[0069] Figure 2 A framework diagram of a multi-role embedding representation method based on ego-network splitting provided in an embodiment of the present invention.

[0070] Figure 3 A schematic diagram of network node splitting provided in an embodiment of the present invention, wherein (a) is the original enterprise network, (b) is an example enterprise node self-network partitioning diagram, (c) is an example enterprise node disconnecting the edges around it, (d) is the node community divided according to the connected subgraph, (e) generates a corresponding number of nodes according to the number of partitions, and (f) divides the enterprise nodes generated by the split into corresponding communities.

[0071] Figure 4 A schematic diagram of the internal and external edge connection process of a split node provided in an embodiment of the present invention.

[0072] Figure 5 A schematic diagram of generating a final network embedding representation by combining feature functions provided in an embodiment of the present invention.

[0073] Figure 6 A schematic diagram of a multi-role embedding representation system based on ego network splitting provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0076] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.

[0077] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0078] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0079] This invention proposes a multi-role embedding representation method based on ego network splitting. Figure 1 As shown in FIG, the multi-role embedding representation method based on self-network splitting includes the following steps S1 to S4. The framework diagram of the multi-role embedding representation method based on self-network splitting is shown in FIG. Figure 2 shown.

[0080] S1. Split and reconstruct the enterprise network dataset to build a multi-role network; specifically include:

[0081] S11. Based on the enterprise network data set, perform self-network splitting, such as Figure 3 Specifically:

[0082] The enterprise network data set is G = (V, E), where nodes represent different enterprises and edges represent the relationship between enterprise nodes. Specifically, edges represent the affiliation or business dealings between enterprise nodes, which can be in the form of purchase, sale, cooperation, etc.

[0083] for Traverse all nodes in the graph and perform the following steps for each node:

[0084] The neighbor nodes of node v are defined as Disconnect the edges between the target node v and all the surrounding one-hop neighbor nodes. The edge set at this moment is

[0085] Compute the connected subgraph in the disconnected network Among them C i Represents node v i By disconnecting the subgraph set from the surrounding neighbors, Represents node v i The sth subgraph in the generated set i sub-graphs, s i is the number of connected subgraphs;

[0086] Each of the subnetworks can represent a specific role of the central node; the central node is split into si nodes, each node is assigned to its own subnet; that is, for each connected subgraph Create a new node Make the new node set make Finally, we get a set of nodes

[0087] During the node splitting process, the number of roles in the network is obtained

[0088] S12, based on the split nodes, reconstruct the network to form a multi-role network;

[0089] Among them, in the multi-role network, nodes represent different enterprises, edges represent the relationship between enterprise nodes, and further, edges represent the affiliation or business dealings between enterprise nodes, which can be in the form of purchase, sale, cooperation, etc.

[0090] The characteristics of a node include the attributes or information of each node, including enterprise size (such as the number of employees, annual revenue, market share), business type (such as the type of products or services provided by the company), etc. The roles of a node include suppliers, distributors, customers, etc. An enterprise can be a supplier and a customer at the same time. This multi-role feature makes enterprises have complex interactive relationships in the network.

[0091] Step S12 specifically includes:

[0092] External reconstruction: split each node Connect the node V on the original graph G to the target node v. i , traverse all its edges (v i ,u)∈E; for the connected subgraph set C after disconnecting the edges i , if u exists in the subgraph In the j ; Update the new edge set in For node v i In the corresponding subgraph The new nodes generated under this condition; therefore, the network after external reconstruction is G′=(V′, E″).

[0093] In a specific embodiment, if Figure 4 As shown in the figure, the three multi-role nodes generated by enterprise node 4 are numbered as 4′. While generating these three split nodes, the three sub-networks {v1, v2, v3}, {v5, v6, v7}, {v8, v9, v10}, {v11, v12, v13}, {v12, v14}, {v13, v15, v16, v17}, {v14, v17}, {v15, v18, v19, v20}, {v21, v22, v23}, {v22, v24}, {v25, v26, v27}, {v27, v28, v29, v3}, {v3, v3, v4}, {v4, v4, v5}, {v4, v4 10} is disconnected from the original node v4. At this time, the v4 node on the graph has no edges. In the external reconstruction stage, this method will connect v4′ with the nodes in the three sub-networks to which it belongs.

[0094] Internal reconstruction: Perform the following operations on the externally reconstructed network G′: traverse all nodes v in the original network G i , find its split node set v′ i ,in For the set v′ i All nodes in the , are connected to each other, building new edges where 1≤j≤k≤s i ; Update edge set Form a multi-role network.

[0095] After the new split multi-role node is generated, in the external reconstruction phase, only new edges are constructed between the multi-role node and the "old node" on the original graph. However, the newly split multi-role nodes from the same original node are still disconnected components. In order to keep the structural integrity of the entire input graph, new edges need to be constructed for these points. Figure 3 For example, as v4′ is generated by the original node v4, there is a strong correlation between them. Therefore, the present invention performs an internal reconstruction operation on the network G′ after external reconstruction.

[0096] S2. Based on the multi-role network, capturing the enterprise node wandering sequence through quantum wandering; specifically including:

[0097] S21. During the global walk, a probability distribution matrix is ​​obtained under the current number of walk evolutions; based on the probability distribution matrix, a global role representation of the enterprise node and a global quantum walk sequence are generated.

[0098] During the quantum walk, the probability distribution matrix under the current walk evolution times will be output during the global walk. All nodes participate in the evolution of quantum walks at the same time, and the probability distribution matrix of the graph is The final global quantum walk sequence q is obtained by multiple evolutions of the Grover operator U, namely: It contains the role structure information of the node for the entire network, represented as z global ;

[0099] Step S21 is specifically:

[0100]

[0101] Among them, d(v) represents the node degree of enterprise node v, A represents the adjacency matrix of the graph, Sum() is the row summation function, k g represents the number of global quantum walk evolutions; Indicates that enterprise node v is in the kth g The evolution sequence representation obtained under the quantum walk evolution times; Indicates that enterprise node v is in the kth g -The evolution sequence representation obtained under 1 quantum walk evolution times; Indicates that enterprise node w is in the kth g -The evolution sequence representation obtained under 1 quantum walk evolution times; Indicated by The kth row of concatenation g The evolution sequence matrix obtained under the quantum walk evolution times; M0(v, 2) represents the initialization vector obtained by calculating according to the degree of different nodes v; M0 represents the initialization matrix spliced ​​by row according to M0(v, 2); z global It is the global role representation of the enterprise node, which is the sum of the probability matrix under global walk;

[0102] When the initial state probabilities of all nodes are the same, all nodes evolve simultaneously on the entire network, and the model is distributed through the probability of quantum walks. To simulate the global evolution characteristics, to represent the role relevance of nodes in the global network, and to generate the global role representation z global .

[0103] z global The i-th row represents the enterprise node v i The global walk sequence of nodes obtained by summing the probability matrix is ​​z global The walk sequence of each enterprise node in the final global quantum walk sequence is arranged horizontally: q = {q(v1), q(v2), ..., q(v n )}.

[0104] S22. Based on the biased quantum walk, generate a local role representation and a local quantum walk sequence of the enterprise node.

[0105] Step S22, based on the biased quantum walk, generates the local role representation and local quantum walk sequence of the enterprise node, specifically: obtain global role information through quantum walk, bias the quantum walk to emphasize the local structure of the enterprise node, and use the bias probability p ratio The initial probability of each enterprise node is biased, and the local role representation z of the node is obtained by calculating the role proximity local ,

[0106]

[0107] Among them, M'0(v,·) represents the bias probability p ratio The initialization sequence is obtained by calculating the degrees of different nodes v; M'0 represents the initialization matrix spliced ​​row by row according to M'0(v, ·); z local It is expressed as the sum of the probability matrix under local walk, k l represents the number of local quantum walk evolutions; M′1 represents the probability matrix obtained under one evolution of the local quantum walk; represents the local quantum walk k l The probability matrix obtained under the second evolution;

[0108] By biasing the probability p ratio The initial probability of each node is biased to make the enterprise node obtain a higher probability proportion, and the local role representation z of the enterprise node is obtained through role proximity calculation local , thereby obtaining the feature representation of enterprise nodes from multiple aspects.

[0109] z local The i-th row represents the enterprise node v i The local walk sequence of the node obtained by summing the probability matrix is ​​z local The walk sequence of each node in the latitudinal arrangement is spliced ​​in rows to obtain the final local quantum walk sequence: q′={q′(v1), q′(v2), ..., q′(v n )}.

[0110] like Figure 2 As shown in the figure, in the biased quantum walk part of the framework, if the initial state probability of a certain node is higher, the evolution of the quantum walk will be biased, emphasizing the proximity of the local structure of the node. The obtained probability distribution is considered to be the correlation between the node and the neighboring nodes. Therefore, the node has a higher probability of walking within the neighborhood and a lower probability of walking outside the neighborhood. The biased quantum walk emphasizes the local structure of the node, learns the role proximity of the node, and thus generates a local role representation z local and the local quantum walk sequence q′.

[0111] S3. Compare the walk sequences and generate role identifiers; specifically, it includes:

[0112] S31, splicing the global quantum walk sequence and the local quantum walk sequence to obtain a complete walk sequence of the enterprise node;

[0113] S32, determining a similarity function of the complete walk sequences of two enterprise nodes;

[0114] S33, based on the similarity function, performing sequence alignment on all nodes in the entire network to construct a similarity matrix;

[0115] S34. Obtain a node role identification matrix of the enterprise network according to the similarity matrix.

[0116] Step S3, comparing the walking sequence and generating a role identification; specifically including:

[0117] S31, concatenate the global quantum walk sequence and the local quantum walk sequence to obtain a complete walk sequence of the enterprise node, specifically: Q = concat (q, q'), where Q (v i ) represents node v i The walking sequence of

[0118] S32. Determine the similarity function of the complete walk sequences of the two enterprise nodes, specifically:

[0119]

[0120] S33, based on the similarity function, sequence alignment is performed on all nodes in the entire network to construct a similarity matrix; wherein the similarity matrix is ​​identified as M R ;

[0121] S34, obtaining a node role identification matrix of the enterprise network according to the similarity matrix; specifically comprising:

[0122] Set the initial threshold R threshold =0.5, if R similarity (v i , v j )≥R threshold , then v i , v j Marked as the same character;

[0123] According to the similarity matrix M R Mark all nodes to get the role matrix R at this time M ;

[0124] Set the parameter Δ = 0.05, and calculate the statistical R M The number of roles in rn, if rn≤numR, then let R threshold =R threshold +Δ, if rn≥numR, then let R threshold =R threshold -Δ; calculate the value of |numR-rn| under each parameter; repeat the steps to determine R similarity (v i ,v j ) and the new threshold R thresholdIf R similarity (v i , v j )≥R threshold , then v i , v j Mark as the same role and update the role matrix R at this time M At this time R M for:

[0125]

[0126] where r x Represents the xth character;

[0127] When R threshold =min(|numR-rn|), the role matrix R obtained by comparing the threshold at this moment M The node role identification matrix obtained for the final network.

[0128] The above steps are used to obtain the preliminary role allocation of nodes in the entire network.

[0129] like Figure 2 As shown in the final network diagram of the framework, each node v in the split multi-role network i Has its own character attributes r(v i ). Finally, merge the role attributes of all split nodes in the multi-role network, that is merge get The set(·) function removes duplicate roles from the set. After completing these steps, we get the multi-role labels R(v1), R(v2), ..., R(v n ).

[0130] S4. The role representation of the enterprise node is integrated with the neighborhood feature information of the enterprise node to obtain the multi-role embedding representation of the enterprise node, such as Figure 5 As shown; specifically including:

[0131] S41, splicing the global role representation and the local role representation of the enterprise node to obtain a complete role representation that integrates global and local role information;

[0132] S42, using the characteristic function to calculate all node features and evaluation points to obtain the neighborhood feature information of the enterprise node, and performing feature fusion on the probability distribution matrix obtained by quantum walking to obtain the feature representation of the enterprise node;

[0133] S43: Fusing the complete role representation and the feature representation of the enterprise node to obtain a multi-role embedded representation of the enterprise node.

[0134] In real networks, different distributions of enterprise node neighborhood features may have different effects on enterprise nodes. Therefore, considering the complexity of node neighborhood feature distribution, the present invention does not fuse feature information in a simple linear aggregation manner, but uses a graph-based feature function to describe the neighborhood feature distribution of enterprise nodes, and uses quantum walk results as the connection strength to weight the feature function to obtain feature information that highlights the node structure.

[0135] S4. The role representation of the enterprise node is integrated with the neighborhood feature information of the enterprise node to obtain the multi-role embedding representation of the enterprise node. The specific formula is:

[0136] S41, concatenating the global role representation and the local role representation of the enterprise node to obtain a complete role representation that integrates global and local role information; specifically: z′=concat{z local , z glocal};

[0137] S42, using the characteristic function to calculate all node features and evaluation points, to obtain the neighborhood feature information of the enterprise node, and to perform feature fusion on the probability distribution matrix obtained by quantum walking, to obtain the feature representation of the enterprise node, specifically:

[0138]

[0139] Among them, x w is the feature vector of the target node w; M kg (v,w) represents the probability value of enterprise node v wandering to enterprise node w in the probability matrix; parameter θ represents the evaluation point value, set θ∈[-6,6];

[0140] Probability distribution matrix in quantum walk It is used to represent the strength of association between enterprise nodes in the characteristic function. The larger the distribution probability value, the greater the strength of association between enterprise nodes. The present invention uses the characteristic function of quantum walk weighting The enterprise node role information is integrated with the enterprise node neighborhood feature information to obtain a better and richer node feature representation. feature .

[0141] S43, fusing the complete role representation and the feature representation of the enterprise node to obtain a multi-role embedded representation of the enterprise node, specifically: Z = concat{z′, z feature}.

[0142] That is, the role and structure information are finally fused together to obtain the final multi-role embedding representation.

[0143] The present invention proposes a multi-role network representation method for enterprise network nodes that realizes self-network splitting and quantum walking, and realizes multi-role identification and embedded representation of enterprise nodes in the network. Specifically, first, the enterprise nodes are divided into self-networks by traversing the entire network, and then the enterprise nodes are split to generate multi-role nodes according to the different sub-networks divided from each node, and then the role structure and other information of the network are obtained by using the superposition of quantum walking. The role attribute information of the enterprise nodes in the network is identified according to the similarity of the walk sequences of different enterprise nodes. Then, the model uses a weighted feature function to fuse the neighborhood information of the nodes to obtain more comprehensive role features. Finally, the model designs a variational autoencoder to reduce information noise, and forms a multi-role embedded representation of the enterprise network that has realized multi-role identification. The method proposed by the present invention realizes multi-role identification of enterprise nodes in the network, and improves the accuracy of the multi-role embedded representation of enterprise nodes in the network, so as to further help effectively manage the supply chain, optimize business cooperation and improve enterprise competitiveness.

[0144] Figure 6 A multi-role embedding representation system based on ego network splitting is provided in an embodiment of the present invention. Figure 6 As shown, the multi-role embedding representation system based on self-network splitting includes a multi-role network construction module, a node walk sequence acquisition module, a role identification generation module and a multi-role embedding representation construction module;

[0145] The multi-role network construction module splits and reconstructs the enterprise network data set to construct a multi-role network;

[0146] The node walk sequence acquisition module captures the enterprise node walk sequence through quantum walk based on the multi-role network;

[0147] The role identification generation module compares the wandering sequence and generates a role identification;

[0148] The multi-role embedding representation construction module integrates the role representation of the enterprise node with the neighborhood feature information of the enterprise node to obtain the multi-role embedding representation of the enterprise node.

[0149] The above-mentioned multi-role embedding representation system based on ego-network splitting can be implemented in the form of a computer program, which can be run on a computer device.

[0150] The computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0151] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute a multi-role embedding representation method based on ego network splitting.

[0152] The processor is used to provide computing and control capabilities to support the operation of the entire computer equipment.

[0153] The internal memory provides an environment for the operation of a computer program in a non-volatile storage medium. When the computer program is executed by a processor, the processor can execute a multi-role embedding representation method based on self-network splitting.

[0154] The network interface is used to communicate with other devices over the network. Those skilled in the art will appreciate that the above-mentioned computer device structure is only a partial structure related to the present application solution, and does not constitute a limitation on the computer device to which the present application solution is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0155] The processor is used to run a computer program stored in the memory, which implements the multi-role embedding representation method based on self-network splitting described in Example 1.

[0156] It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0157] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0158] The present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes a multi-role embedding representation method based on ego network splitting as described in Embodiment 1.

[0159] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, or any other computer-readable storage medium that can store program codes.

[0160] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0161] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0162] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0163] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0164] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A multi-role embedding representation method based on ego network splitting, characterized in that: Includes steps: S1, split and reconstruct the enterprise network dataset to build a multi-role network; Specifically include: S11. Based on the enterprise network data set, perform self-network splitting; wherein, in the enterprise network data set, nodes represent different enterprises, and edges represent the relationship between enterprise nodes; S12. Reconstructing the network based on the split nodes to form a multi-role network; wherein, in the multi-role network, nodes represent different enterprises, edges represent the relationship between enterprise nodes, node characteristics include enterprise scale and business type, and node roles include supplier, distributor, and customer; S2. Based on the multi-role network, capturing the enterprise node wandering sequence through quantum wandering; specifically including: S21. During the global walk, a probability distribution matrix is ​​obtained under the current walk evolution times; based on the probability distribution matrix, a global role representation of the enterprise node and a global quantum walk sequence are generated; S22. Based on the biased quantum walk, generate a local role representation and a local quantum walk sequence of the enterprise node; S3. Compare the walk sequences and generate role identifiers; specifically, it includes: S31, splicing the global quantum walk sequence and the local quantum walk sequence to obtain a complete walk sequence of the enterprise node; S32, determining a similarity function of the complete walk sequences of two enterprise nodes; S33, based on the similarity function, performing sequence alignment on all nodes in the entire network to construct a similarity matrix; S34, obtaining a node role identification matrix of the enterprise network according to the similarity matrix; S4. The role representation of the enterprise node is integrated with the neighborhood feature information of the enterprise node to obtain a multi-role embedded representation of the enterprise node; specifically, the steps include: S41, splicing the global role representation and the local role representation of the enterprise node to obtain a complete role representation that integrates global and local role information; S42, using the characteristic function to calculate all node features and evaluation points to obtain the neighborhood feature information of the enterprise node, and performing feature fusion on the probability distribution matrix obtained by quantum walking to obtain the feature representation of the enterprise node; S43: Fusing the complete role representation and the feature representation of the enterprise node to obtain a multi-role embedded representation of the enterprise node.

2. The method according to claim 1, characterized in that Step S11: splitting the self-network based on the enterprise network data set, specifically: The enterprise network dataset is G = (V, E), where nodes represent different enterprises and edges represent the relationship between enterprise nodes. Traverse all nodes in the graph and perform the following steps for each node: The neighbor nodes of node v are defined as Disconnect the edges between the target node ν and all surrounding one-hop neighbor nodes. The edge set at this moment is Compute the connected subgraph in the disconnected network Among them C i Represents node v i By disconnecting the subgraph set from the surrounding neighbors, Represents node v i The sth subgraph in the generated set i sub-graphs, s i is the number of connected subgraphs; Each of the subnetworks can represent a specific role characteristic of the central node; The central node splits into s i nodes, each node is assigned to its own subnet; that is, for each connected subgraph Create a new node Make the new node set make Finally, we get a set of nodes During the node splitting process, the number of roles in the network is obtained 3. The method according to claim 1, characterized in that Step S12: Reconstruct the network based on the split nodes to form a multi-role network, specifically including: External reconstruction: split each node Connect the node V on the original graph G to the target node v. i , traverse all its edges (v i，u )∈E; for the connected subgraph set C after disconnecting the edges i , if u exists in the subgraph In the j ; Update the new edge set in For node v i In the corresponding subgraph The new nodes generated under this condition; therefore, the network after external reconstruction is G′=(V′, E″); Internal reconstruction: Perform the following operations on the externally reconstructed network G′: traverse all nodes v in the original network G i , find its split node set V′ i ,in For the set V′ i All nodes in the , are connected to each other, building new edges where 1≤j≤k≤s i ; Update edge set Form a multi-role network.

4. The method according to claim 1, characterized in that: Step S21: During the global walk, a probability distribution matrix is ​​obtained under the current walk evolution times; based on the probability distribution matrix, a global role representation of the enterprise node and a global quantum walk sequence are generated, specifically: in, d (v) represents the node degree of enterprise node ν, A represents the adjacency matrix of the graph, SumO is the row summation function, k g represents the number of global quantum walk evolutions; Indicates that enterprise node v is in the kth g The evolution sequence representation obtained under the quantum walk evolution times; It represents the evolution sequence representation of enterprise node v under the k-1th quantum walk evolution number; Indicates that enterprise node w is in the kth g -The evolution sequence representation obtained under 1 quantum walk evolution times; Indicated by The kth row of concatenation g The evolution sequence matrix obtained under the number of quantum walk evolutions; M0(v, ·) represents the initialization vector obtained by calculating the degree of different nodes v; M0 represents the initialization matrix spliced ​​by row according to M0(v, ·); zglobal is the global role representation of the enterprise node, which is expressed as the sum of the probability matrix under the global walk; z global The i-th row represents the enterprise node v i The global walk sequence of nodes obtained by summing the probability matrix is ​​then horizontally arranged to obtain the final global quantum walk sequence: q = {q(v1), q(v2), ..., q(v n )}.

5. The method according to claim 1, characterized in that Step S22, based on the biased quantum walk, generates the local role representation and local quantum walk sequence of the enterprise node, specifically: obtain global role information through quantum walk, bias the quantum walk to emphasize the local structure of the enterprise node, and use the bias probability p ratio The initial probability of each enterprise node is biased, and the local role representation z of the node is obtained by calculating the role proximity local , Where M′0(v,·) represents the bias probability p ratio The initialization sequence is obtained by calculating the degrees of different nodes v below; M′0 represents the initialization matrix spliced ​​row by row according to M′0(v, ·); local It is expressed as the sum of the probability matrix under local walk, k l represents the number of local quantum walk evolutions; M′1 represents the probability matrix obtained under one evolution of the local quantum walk; represents the local quantum walk k l The probability matrix obtained under the second evolution; z local The i-th row represents the enterprise node v i The local walk sequence of the node obtained by summing the probability matrix is ​​z local The walk sequence of each node in the latitudinal arrangement is spliced ​​in rows to obtain the final local quantum walk sequence: q′={q′(v1), q′(v2), ..., q′(v n )}.

6. The method according to claim 1, characterized in that Step S3, comparing the walking sequence and generating a role identification; specifically including: S31, concatenate the global quantum walk sequence and the local quantum walk sequence to obtain a complete walk sequence of the enterprise node, specifically: Q = concat (q, q'), where Q (v i ) represents node v i The walking sequence of S32. Determine the similarity function of the complete walk sequences of the two enterprise nodes, specifically: S33, based on the similarity function, sequence alignment is performed on all nodes in the entire network to construct a similarity matrix; wherein the similarity matrix is ​​identified as M R ; S34, obtaining a node role identification matrix of the enterprise network according to the similarity matrix; specifically comprising: Set the initial threshold R threshold =0.5, if R similarity (v i , v j )≥R threshol d ， Then v i , v j Marked as the same character; According to the similarity matrix M R Mark all nodes to get the role matrix R at this time M ; Set the parameter Δ = 0.05, and calculate the statistical R M The number of roles in rn, if rn≤numR, then let R threshold =R threshold +Δ, if rn≥numR, then let R threshold =R threshold -Δ; calculate the value of |numR-rn| under each parameter; repeat the steps to determine R similarity (v i , v j ) and the new threshold R threshold If R similarity (v i , v j )≥R threshold , then b i , v j Mark as the same role and update the role matrix R at this time M At this time R M for: where r x Represents the xth character; When R threshold =min(|mumR-rn|), the role matrix R obtained by comparing the threshold at this moment M The node role identification matrix obtained for the final network.

7. The method according to claim 1, characterized in that S4. The role representation of the enterprise node is integrated with the neighborhood feature information of the enterprise node to obtain the multi-role embedding representation of the enterprise node. The specific formula is: S41, concatenating the global role representation and the local role representation of the enterprise node to obtain a complete role representation that integrates global and local role information; specifically: z′=concat{z local , z global }; S42, using the characteristic function to calculate all node features and evaluation points, to obtain the neighborhood feature information of the enterprise node, and to perform feature fusion on the probability distribution matrix obtained by quantum walking, to obtain the feature representation of the enterprise node, specifically: Among them, x w is the feature vector of the target node w; M kg (v, w) represents the probability value of enterprise node v wandering to enterprise node w in the probability matrix; parameter θ represents the evaluation point value, set θ∈[-6, 6]; S43, fusing the complete role representation and the feature representation of the enterprise node to obtain a multi-role embedded representation of the enterprise node, specifically: Z = concat {z', z feature }.

8. A multi-role embedding representation system based on ego-network splitting, characterized in that: The multi-role embedding representation system executes the multi-role embedding representation method based on ego network splitting as claimed in claim 1, comprising: a multi-role network construction module, a node walk sequence acquisition module, a role identification generation module and a multi-role embedding representation construction module; The multi-role network construction module splits and reconstructs the enterprise network data set to construct a multi-role network; The node walk sequence acquisition module captures the enterprise node walk sequence through quantum walk based on the multi-role network; The role identification generation module compares the wandering sequence and generates a role identification; The multi-role embedding representation construction module integrates the role representation of the enterprise node with the neighborhood feature information of the enterprise node to obtain the multi-role embedding representation of the enterprise node.

9. A computer device, characterized in that: The device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images