Service node recommendation method, system, device and storage medium

Abstract

The present invention provides a service node recommendation method, system, device and storage medium, wherein the method comprises: in response to the user input, extracting the node relationship data of the service class in the database, and constructing a node relationship network according to the node relationship data, in which the service demander node and the service provider node are connected together by connecting edges, clustering each node in the node relationship network using the node attribute data of each node in the node relationship network, obtaining the neighborhood node information of each node in the node relationship network in the node community, and calculating the Euclidean distance between each node and the neighborhood node according to the neighborhood node information, assigning the node a capability value according to the Euclidean distance, and outputting the node recommendation information according to the capability value of each node in the node relationship network. The present invention can accurately recommend nodes by capability value, accurately respond to user needs, and improve user service experience.

Description

Background Art

[0002] In the context of business services, node is an important concept. From the perspective of function, nodes are divided into business demander nodes and business provider nodes. Business provider nodes can provide business services to business demander nodes.

[0003] By using computer technology processing methods, nodes can be classified according to the node attributes of business nodes, so as to provide accurate node matching for business demanders.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] In view of the problems in the prior art, the purpose of the present invention is to provide a service node recommendation method, system, device and storage medium, which overcomes the difficulties of the prior art, can accurately respond to user needs and improve user service experience.

[0006] An embodiment of the present invention provides a service node recommendation method, the method comprising:

[0007] Receive user input;

[0008] In response to user input, user demand information carrying a business class is obtained, and node relationship data of the business class is extracted from a database, and a node relationship network is constructed according to the node relationship data, in which nodes of a business demander and nodes of a business provider are connected together through connection edges;

[0009] Clustering each node in the node relationship network using node attribute data of each node in the node relationship network to obtain at least one node community;

[0010] Obtain the neighboring node information of each node in the node community in the node relationship network and calculate the Euclidean distance between each node and the neighboring node based on the neighboring node information, and assign the node capability value based on the Euclidean distance;

[0011] Output node recommendation information based on the capability value of each node in the node relationship network.

[0012] Optionally, before clustering each node in the node relationship network using the node attribute data of each node in the node relationship network, the service node recommendation method further includes:

[0013] Each node in the node relationship network is vectorized according to the node attribute data to obtain a network representation vector;

[0014] Clustering each node in the node relationship network using the node attribute data of each node in the node relationship network includes:

[0015] The nodes in the node relationship network are clustered using the network representation vector of each node in the node relationship network.

[0016] Optionally, before vectorizing each node in the node relationship network according to the node attribute data, the service node recommendation method includes:

[0017] Each node in the node relationship network is represented by a network adjacency matrix, each value in the network adjacency matrix represents the number of business services provided to the adjacent node, and the number of business services is counted into the node attribute data;

[0018] Each node in the node relationship network is vectorized according to the node attribute data, including:

[0019] The network adjacency matrix of each node in the node relationship network is compressed into a vector space to obtain a network representation vector.

[0020] Optionally, obtaining neighboring node information in the node community where each node in the node relationship network is located and calculating the Euclidean distance between each node and the neighboring node according to the neighboring node information includes:

[0021] For each node i in the node relationship network, obtain the node community CK(i) where node i is located, and obtain all node neighborhoods S(i) in the neighborhood whose shortest path distance to node i is not greater than the target distance in the clustering result, and obtain the target neighborhood SC(i) = CK(i) ∩ S(i), SC(i) describes the node neighborhood information;

[0022] Calculate the Euclidean distance between node i and its neighbor node j in the target neighborhood SC(i), j∈SC(i), xi is the network representation vector of node i.

[0023] Optionally, the nodes are assigned capability values ​​according to the Euclidean distance, including:

[0024] The sum of the influence of node i in the target neighborhood is calculated to represent the ratio of the number of nodes in the node community to the number of nodes in the entire network, and the calculation result is the capability value.

[0025] Optionally, constructing a node relationship network according to the node relationship data includes:

[0026] A node relationship network based on an undirected weighted complex network is constructed according to the node relationship data.

[0027] Optionally, clustering each node in the node relationship network using node attribute data of each node in the node relationship network includes:

[0028] According to the set number of node communities, each node in the node relationship network is clustered using the node attribute data of each node in the node relationship network, and the node communities are sorted according to the number of nodes in each node community.

[0029] The embodiment of the present invention further provides a service node recommendation system, which is used to implement the service node recommendation method, including:

[0030] A receiving module receives user input;

[0031] A response module, in response to user input, obtains user demand information carrying a business class, extracts node relationship data of the business class in a database, and constructs a node relationship network based on the node relationship data, in which nodes of a business demander and nodes of a business provider are connected together through connection edges;

[0032] A clustering module, clustering each node in the node relationship network using node attribute data of each node in the node relationship network to obtain at least one node community;

[0033] The capability value assignment module obtains the neighborhood node information in the node community where each node in the node relationship network is located, calculates the Euclidean distance between each node and the neighborhood node based on the neighborhood node information, and assigns the capability value to the node based on the Euclidean distance;

[0034] The node recommendation module outputs node recommendation information based on the capability value of each node in the node relationship network.

[0035] An embodiment of the present invention further provides a service node recommendation device, comprising:

[0036] processor;

[0037] a memory in which executable instructions for the processor are stored;

[0038] The processor is configured to execute the steps of the above-mentioned service node recommendation method by executing executable instructions.

[0039] An embodiment of the present invention further provides a computer-readable storage medium for storing a program, which implements the steps of the above-mentioned service node recommendation method when executed.

[0040] The purpose of the present invention is to provide a service node recommendation method, system, device and storage medium, which can divide each node in the node relationship network into different node communities through clustering, and each community contains multiple similar nodes. The neighborhood node information of each node in the node community indicates the influence depth range of the node, and the Euclidean distance between each node and the neighborhood node represents the influence on the neighborhood node. In this case, by quantifying the influence of each node on other nodes in the node relationship network using capability values, rather than simply classifying nodes by business class, it is possible to accurately recommend nodes through capability values, accurately respond to user needs, and improve user business experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Other features, objectives and advantages of the present invention will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following accompanying drawings.

[0042] Figure 1 is a flow chart of one embodiment of the service node recommendation method of the present invention;

[0043] Figure 2 is a flow chart of a second embodiment of the service node recommendation method of the present invention;

[0044] Figure 3 It is a module diagram of one embodiment of the service node recommendation system of the present invention;

[0045] Figure 4 It is a module diagram of the second embodiment of the service node recommendation system of the present invention;

[0046] Figure 5 It is a module diagram of the third embodiment of the service node recommendation system of the present invention;

[0047] Figure 6 It is a schematic diagram of the operation of the service node recommendation system of the present invention. DETAILED DESCRIPTION

[0048] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to make the present invention comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art.

[0049] The accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware forwarding modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0050] In addition, the processes shown in the accompanying drawings are only exemplary and do not necessarily include all the steps. For example, some steps can be decomposed, some steps can be combined or partially combined, and the actual execution order may change according to the actual situation. The words "first", "second" and similar words used in the specific description do not indicate any order, quantity or importance, but are only used to distinguish different components. It should be noted that the embodiments of the present invention and the features in different embodiments can be combined with each other without conflict.

[0051] The inventors have encountered in practice that, although nodes of corresponding business classes can be matched and provided to users by virtue of node attributes, nodes that meet the business class matching conditions may not necessarily provide matching business services, and sometimes the business services provided by these nodes are of low quality.

[0052] Therefore, how to respond to user needs and make node recommendations more accurately is a technical problem to be solved by the embodiments of the present invention.

[0053] Figure 1 This is a flowchart of a node recommendation method provided by an embodiment of the present invention. The execution subject of this method is a node recommendation system, which is not a computer device and can run a node recommendation program. Figure 1 ,The node recommendation method includes the following steps:

[0054] Step 110: receiving user input;

[0055] Step 120: in response to user input, user demand information carrying a service class is obtained, and node relationship data of the service class is extracted from a database, and a node relationship network is constructed according to the node relationship data, in which service demander nodes and service provider nodes are connected together through connection edges;

[0056] Step 130: clustering each node in the node relationship network using the node attribute data of each node in the node relationship network to obtain at least one node community;

[0057] Step 140: Obtaining the neighboring node information in the node community where each node in the node relationship network is located, calculating the Euclidean distance between each node and the neighboring node according to the neighboring node information, and assigning the capability value to the node according to the Euclidean distance;

[0058] Step 150: Output node recommendation information according to the capability value of each node in the node relationship network.

[0059] In the embodiment of the present invention, the service demander node and the service provider node do not refer to a specific node, but refer to the business transaction relationship between the two nodes, and the node relationship data refers to a collection of a large amount of data of such business transaction relationship.

[0060] Each node may be a service demander node or a service provider node, or may be both a service demander node and a service provider node.

[0061] Clustering is to divide a data set into different classes or clusters according to a specific standard (such as distance), so that the similarity of data objects in the same cluster is as large as possible, and the difference of data objects in different clusters is as large as possible.

[0062] Using the embodiment of the present invention, each node in the node relationship network is divided into different node communities through clustering, and each community contains multiple similar nodes. The neighboring node information of each node in the node community indicates the influence depth range of the node, and the Euclidean distance between each node and the neighboring node represents the influence on the neighboring node.

[0063] In this case, by quantifying the influence of each node on other nodes in the node relationship network using capability values, rather than simply classifying the nodes by business type, it is possible to accurately recommend nodes based on capability values, accurately respond to user needs, and improve user business experience.

[0064] In an optional embodiment, a user interaction interface may be provided to receive user input, which may be in the form of text input, control triggering or clicking, etc., which is not specifically limited here.

[0065] In this case, the user can input specific business requirement information such as the required business class through the user interaction interface.

[0066] In an optional embodiment, outputting the service node recommendation information may specifically include displaying the recommended node information for the user to confirm or select.

[0067] In an optional embodiment, before clustering each node in the node relationship network using the node attribute data of each node in the node relationship network to obtain at least one node community, the service node recommendation method may further include:

[0068] Each node in the node relationship network is vectorized according to the node attribute data to obtain a network representation vector;

[0069] Clustering each node in the node relationship network using the node attribute data of each node in the node relationship network includes:

[0070] The nodes in the node relationship network are clustered using the network representation vector of each node in the node relationship network.

[0071] By using this embodiment, the computer device can abstract the node attribute data into a vectorized representation, thereby achieving a clustering operation with higher feasibility.

[0072] In an optional embodiment, before vectorizing each node in the node relationship network according to the node attribute data, the service node recommendation method may include:

[0073] Each node in the node relationship network is represented by a network adjacency matrix, each value in the network adjacency matrix represents the number of business services provided to the adjacent node, and the number of business services is counted into the node attribute data;

[0074] Each node in the node relationship network is vectorized according to the node attribute data, including:

[0075] The network adjacency matrix of each node in the node relationship network is compressed into a vector space to obtain a network representation vector.

[0076] In an optional embodiment, constructing a node relationship network according to the node relationship data includes:

[0077] A node relationship network based on an undirected weighted complex network is constructed according to the node relationship data.

[0078] In an undirected weighted complex network, there is no directional information between nodes.

[0079] In an optional embodiment, clustering each node in the node relationship network using node attribute data of each node in the node relationship network includes:

[0080] According to the set number of node communities, each node in the node relationship network is clustered using the node attribute data of each node in the node relationship network, and the node communities are sorted according to the number of nodes in each node community.

[0081] In an optional embodiment, obtaining neighboring node information in a node community where each node in the node relationship network is located and calculating the Euclidean distance between each node and the neighboring node according to the neighboring node information includes:

[0082] For each node i in the node relationship network, obtain the node community CK(i) where node i is located, and obtain all node neighborhoods S(i) in the neighborhood whose shortest path distance to node i is not greater than the target distance in the clustering result, and obtain the target neighborhood SC(i) = CK(i) ∩ S(i), SC(i) describes the node neighborhood information;

[0083] Calculate the Euclidean distance d between node i and its neighbor node j in the target neighborhood SC(i) ij =(xi-xj) 2 , j∈SC(i), xi is the network representation vector of node i.

[0084] In an optional embodiment, assigning capability values ​​to nodes according to Euclidean distances includes:

[0085] Calculate the sum of the influence of node i in the target neighborhood It represents the ratio of the number of nodes in the node community to the number of nodes in the entire network. The calculation result is the capacity value.

[0086] Figure 2 A flowchart of an application scenario of the service node recommendation method provided in an embodiment of the present invention. The service node recommendation method may include the following steps:

[0087] Step 210, through the public industrial ecology information and enterprise cooperation case information, the industrial ecology cooperation relationship network model is constructed. It is an undirected weighted complex network, represented by G(V,E), where the node V is the enterprise node, the connecting edge E is the bidding information, and the adjacency matrix is ​​recorded as w(n×n)=(w ij ), then w ij is the number of cooperative projects between enterprise vi and enterprise vj, otherwise w ij = 0. The industrial business ecological cooperation relationship network model corresponds to the node relationship network mentioned above.

[0088] Step 220, compress the network adjacency matrix w(n×n) into a low-dimensional space of N*r through Node2Vec network representation learning. One enterprise node corresponds to one vector, where the vector of any node i is represented as xi=(xi1,xi2,xi3...xir), i=1,2,3....N, and r is an adjustable parameter.

[0089] Step 230, use K-means clustering to divide the N node vectors xir into K node communities, and sort them according to the number of nodes in the node community, denoted as C = (C1, C2, C3...CK), where K is an adjustable parameter, and the number of community nodes CN1>CN2>...>CN k .

[0090] Step 240, randomly select node i in the node relationship network G, obtain the node community CK(i) where node i is located, and obtain all node neighborhoods S(i) in the neighborhood whose shortest path distance to node i is not greater than 2, and the enterprise influence domain SC(i) = CK(i) ∩ S(i); calculate the Euclidean distance d between node i and node j in its influence domain SC(i) ij =(xi-xj) 2 , j∈SC(i),xi is the network representation learning vector.

[0091] Step 250: Calculate the total influence of any node i in its influence domain It represents the ratio of the number of nodes in the community to the total number of nodes in the entire network. The calculation result is the influence of the enterprise in the industrial ecology, which corresponds to the capability value mentioned above.

[0092] The embodiment of the present invention constructs an industrial ecological cooperation relationship network based on the enterprise cooperation information in the industrial ecology, reduces the complexity of the model through network characterization and clustering algorithm, and evaluates the influence of enterprises in a large-scale industrial ecological cooperation network with fast speed and high accuracy, which helps enterprises to develop new industrial ecological cooperation needs.

[0093] The embodiment of the present invention utilizes network representation learning to obtain a low-dimensional vector representation of enterprise cooperation characteristics, and on this basis uses a clustering algorithm and combines the neighborhood characteristics of network nodes to construct an enterprise influence domain and influence calculation formula, which focuses more on the scope of enterprise influence in the industrial ecology and can improve the scientificity and accuracy of the influence of enterprise ecological cooperation.

[0094] Figure 3 FIG. 1 is a schematic diagram of a module of an embodiment of the service node recommendation system of the present invention. Figure 3 As shown, the service node recommendation system of the present invention includes but is not limited to:

[0095] A receiving module 310 receives user input;

[0096] The response module 320 obtains user demand information carrying a service class in response to user input, extracts node relationship data of the service class in a database, and constructs a node relationship network according to the node relationship data, in which service demander nodes and service provider nodes are connected together through connection edges;

[0097] A clustering module 330, clustering each node in the node relationship network using node attribute data of each node in the node relationship network to obtain at least one node community;

[0098] A capability value assignment module 340 obtains the neighboring node information in the node community where each node in the node relationship network is located, calculates the Euclidean distance between each node and the neighboring node according to the neighboring node information, and assigns the capability value to the node according to the Euclidean distance;

[0099] The node recommendation module 350 outputs node recommendation information according to the capability value of each node in the node relationship network.

[0100] The implementation principle of the above modules can be found in the relevant introduction of the business node recommendation method, which will not be repeated here.

[0101] The service node recommendation system of the present invention divides each node in the node relationship network into different node communities by clustering, and each community contains multiple similar nodes. The neighborhood node information of each node in the node community indicates the influence depth range of the node, and the Euclidean distance between each node and the neighborhood node represents the influence on the neighborhood node. In this case, by quantifying the influence of each node on other nodes in the node relationship network using capability values, rather than simply classifying nodes by business class, it is possible to accurately recommend nodes by capability values, accurately respond to user needs, and improve user service experience.

[0102] Optionally, the response module 320 is specifically configured to:

[0103] A node relationship network based on an undirected weighted complex network is constructed according to the node relationship data.

[0104] Optionally, the clustering module 330 is specifically used for:

[0105] According to the set number of node communities, each node in the node relationship network is clustered using the node attribute data of each node in the node relationship network, and the node communities are sorted according to the number of nodes in each node community.

[0106] Optionally, with Figure 3 compared to, Figure 4 The service node recommendation system shown also includes:

[0107] A vector representation module 410, before clustering the nodes in the node relationship network using the node attribute data of each node in the node relationship network, vectorizes each node in the node relationship network according to the node attribute data to obtain a network representation vector;

[0108] The clustering module 420 is specifically used for:

[0109] The nodes in the node relationship network are clustered using the network representation vector of each node in the node relationship network.

[0110] Optionally, with Figure 4compared to, Figure 5 The service node recommendation system shown also includes:

[0111] A network adjacency matrix characterization module 510, before vectorizing each node in the node relationship network according to the node attribute data, characterizes each node in the node relationship network using a network adjacency matrix, each value in the network adjacency matrix characterizes the number of business services to the adjacent node, and the number of business services is counted into the node attribute data;

[0112] The vector representation module 520 is specifically used for:

[0113] The network adjacency matrix of each node in the node relationship network is compressed into a vector space to obtain a network representation vector.

[0114] Optionally, the capability value assignment module 530 is specifically used for:

[0115] For each node i in the node relationship network, obtain the node community CK(i) where node i is located, and obtain all node neighborhoods S(i) in the neighborhood whose shortest path distance to node i is not greater than the target distance in the clustering result, and obtain the target neighborhood SC(i) = CK(i) ∩ S(i), SC(i) describes the node neighborhood information;

[0116] Calculate the Euclidean distance d between node i and its neighbor node j in the target neighborhood SC(i) ij =(xi-xj) 2 , j∈SC(i), xi is the network representation vector of node i.

[0117] Optionally, the capability value assignment module 530 is further configured to:

[0118] Calculate the sum of the influence of node i in the target neighborhood It represents the ratio of the number of nodes in the node community to the number of nodes in the entire network. The calculation result is the capacity value.

[0119] The embodiment of the present invention further provides a service node recommendation device, comprising a processor and a memory, wherein executable instructions of the processor are stored, wherein the processor is configured to execute the steps of the service node recommendation method by executing the executable instructions.

[0120] As shown above, the service node recommendation device of this embodiment can divide each node in the node relationship network into different node communities through clustering, and each community contains multiple similar nodes. The neighboring node information of each node in the node community indicates the influence depth range of the node, and the Euclidean distance between each node and the neighboring node represents the influence on the neighboring node.

[0121] In this case, by quantifying the influence of each node on other nodes in the node relationship network using capability values, rather than simply classifying the nodes by business type, it is possible to accurately recommend nodes based on capability values, accurately respond to user needs, and improve user business experience.

[0122] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0123] Figure 6 This is a schematic diagram of the structure of the service node recommendation device of the present invention. Figure 6 The electronic device 600 according to this embodiment of the present invention is described. Figure 6 The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0124] like Figure 6 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0125] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps of various exemplary embodiments of the present invention described in the service node recommendation method section of the present specification. For example, the processing unit 610 can execute the following steps: Figure 1 or the steps shown in 2.

[0126] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 621 and / or a cache memory unit 622 , and may further include a read-only memory unit (ROM) 623 .

[0127] The storage unit 620 may also include a program / utility 624 having a set (at least one) of program modules 625, such program modules 625 including but not limited to: a processing system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0128] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0129] The electronic device 600 may also communicate with one or more external devices 670 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 600, and / or any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 650.

[0130] Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0131] The embodiment of the present invention also provides a computer-readable storage medium for storing a program, and the steps of the service node recommendation method are implemented when the program is executed. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary embodiments of the present invention described in the above service node recommendation method section of this specification.

[0132] The program product for implementing the above method according to an embodiment of the present invention may adopt a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0133] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0134] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0135] Program code for performing the processes of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0136] In summary, the purpose of the present invention is to provide a service node recommendation method, system, device and storage medium, which can divide the nodes in the node relationship network into different node communities through clustering, and each community contains multiple similar nodes. The neighborhood node information of each node in the node community indicates the influence depth range of the node, and the Euclidean distance between each node and the neighboring node represents the influence on the neighboring node. In this case, by quantifying the influence of each node on other nodes in the node relationship network using capability values, rather than simply classifying nodes by business class, it is possible to accurately recommend nodes through capability values, accurately respond to user needs, and improve user business experience.

[0137] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.

Claims

1. A service node recommendation method, characterized in that: include: Receive user input; In response to the user input, user demand information carrying a service class is obtained, and node relationship data of the service class is extracted from a database, and a node relationship network is constructed according to the node relationship data, in which service demander nodes and service provider nodes are connected together through connection edges; Clustering each node in the node relationship network using node attribute data of each node in the node relationship network to obtain at least one node community; Obtaining neighbor node information of each node in the node relationship network in the node community, calculating the Euclidean distance between each node and the neighbor node according to the neighbor node information, and assigning capability values ​​to the nodes according to the Euclidean distance; Output node recommendation information according to the capability value of each node in the node relationship network; Obtaining neighbor node information of each node in the node relationship network in the node community and calculating the Euclidean distance between each node and the neighbor node according to the neighbor node information, and assigning a capability value to the node according to the Euclidean distance, including: For each node i in the node relationship network, obtain the node community CK(i) where the node i is located, and obtain all node neighborhoods S(i) in the neighborhood whose shortest path distance to the node i is not greater than the target distance in the clustering result, and obtain the target neighborhood SC(i)=CK(i)∩S(i), wherein SC(i) describes the node neighborhood information; Calculate the Euclidean distance d between the node i and its neighboring node j in the target neighborhood SC(i) ij =(xi-xj) 2 , j∈SC(i), xi is the network representation vector of the node i; Calculate the sum of the influence of the node i in the target neighborhood It represents the ratio of the number of nodes in the node community to the number of nodes in the entire network, and the calculation result is the capability value.

2. The service node recommendation method according to claim 1, characterized in that: Before clustering the nodes in the node relationship network using the node attribute data of the nodes in the node relationship network, the service node recommendation method further includes: Vectorizing each node in the node relationship network according to the node attribute data to obtain a network representation vector; Clustering each node in the node relationship network using the node attribute data of each node in the node relationship network includes: The nodes in the node relationship network are clustered using the network representation vector of each node in the node relationship network.

3. The service node recommendation method according to claim 2, characterized in that: Before vectorizing each node in the node relationship network according to node attribute data, the service node recommendation method includes: Characterizing each node in the node relationship network using a network adjacency matrix, wherein each value in the network adjacency matrix represents the number of business services provided to an adjacent node, and counting the number of business services into the node attribute data; The vectorizing each node in the node relationship network according to the node attribute data includes: The network adjacency matrix of each node in the node relationship network is compressed into a vector space to obtain the network representation vector.

4. The service node recommendation method according to claim 1, characterized in that: The step of constructing a node relationship network according to the node relationship data includes: A node relationship network based on an undirected weighted complex network is constructed according to the node relationship data.

5. The service node recommendation method according to claim 1, characterized in that: The clustering of each node in the node relationship network using the node attribute data of each node in the node relationship network includes: According to the set number of node communities, each node in the node relationship network is clustered using the node attribute data of each node in the node relationship network, and the node communities are sorted according to the number of nodes in each node community.

6. A service node recommendation system, characterized in that: include: A receiving module receives user input; a response module, in response to the user input, obtaining user demand information carrying a service class, extracting node relationship data of the service class in a database, and constructing a node relationship network according to the node relationship data, in which service demander nodes and service provider nodes are connected together through connection edges; A clustering module, clustering each node in the node relationship network using the node attribute data of each node in the node relationship network to obtain at least one node community; A capability value assignment module, which obtains the neighborhood node information of each node in the node community in the node relationship network, calculates the Euclidean distance between each node and the neighborhood node according to the neighborhood node information, and assigns capability values ​​to the nodes according to the Euclidean distance; A node recommendation module, which outputs node recommendation information according to the capability value of each node in the node relationship network; Obtaining neighbor node information of each node in the node relationship network in the node community and calculating the Euclidean distance between each node and the neighbor node according to the neighbor node information, and assigning a capability value to the node according to the Euclidean distance, including: For each node i in the node relationship network, obtain the node community CK(i) where the node i is located, and obtain all node neighborhoods S(i) in the neighborhood whose shortest path distance to the node i is not greater than the target distance in the clustering result, and obtain the target neighborhood SC(i)=CK(i)∩S(i), wherein SC(i) describes the node neighborhood information; Calculate the Euclidean distance d between the node i and its neighboring node j in the target neighborhood SC(i) ij =(xi-xj) 2 , j∈SC(i), xi is the network representation vector of the node i; Calculate the sum of the influence of the node i in the target neighborhood It represents the ratio of the number of nodes in the node community to the number of nodes in the entire network, and the calculation result is the capability value.

7. A service node recommendation device, characterized in that: include: processor; a memory storing executable instructions of the processor; The processor is configured to execute the steps of the service node recommendation method according to any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the service node recommendation method according to any one of claims 1 to 5 are implemented.

Images