A method and device for identifying false binding of electricity customers based on link prediction

Abstract

The present invention discloses a method, device, system and computer-readable storage medium for identifying false binding of electricity customers based on link prediction. The method comprises: obtaining an electricity customer map; calculating the degree value of each node in the electricity customer map; for each node, determining the neighboring nodes corresponding to the node; for each neighboring node, calculating the intimacy between the node and the neighboring nodes based on the degree value of the node and the degree value of the neighboring node corresponding to the node; identifying the neighboring nodes that are falsely bound to the node based on the intimacy corresponding to each neighboring node; the present invention can realize the identification of false binding during use, which is conducive to the accurate delivery of promotional information.

Description

Technical Field

[0001] The present invention relates to the field of knowledge graph technology, and in particular to a method, device, system and computer-readable storage medium for identifying false binding of electricity customers based on link prediction. Background Art

[0002] With the rapid development of technologies like graph computing and natural language processing, knowledge graph technology has become increasingly mature and widely adopted across various State Grid information technology projects. While using knowledge graph technology to model relationships with electricity users in the marketing system, it was discovered that some user information was not updated in a timely manner, account number binding was haphazard, and accounts with unrelated account numbers were bound. Currently, there is a lack of research on the correlation between electricity users and account numbers. This makes it impossible to effectively identify invalid contact information and the binding relationship between electricity users and account numbers, thus hindering the accurate delivery of promotional information.

[0003] In view of this, how to identify false binding among electricity customers becomes a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a method, device, system and computer-readable storage medium for identifying false binding of electricity customers based on link prediction, which can realize the identification of false binding during use, and is conducive to the accurate delivery of promotional information.

[0005] To solve the above technical problems, an embodiment of the present invention provides a method for identifying false binding of electricity customers based on link prediction, comprising:

[0006] Obtain a map of electricity customers;

[0007] Calculating the degree value of each node in the electricity customer graph;

[0008] For each node, determine neighboring nodes corresponding to the node;

[0009] For each of the neighbor nodes, calculate the intimacy between the node and the neighbor node according to the degree value of the node and the degree value of the neighbor node corresponding to the node;

[0010] According to the intimacy corresponding to each of the neighbor nodes, neighbor nodes with which the node is falsely bound are identified.

[0011] Optionally, the process of calculating the intimacy between the node and the neighboring nodes according to the degree value of the node and the degree values ​​of the neighboring nodes corresponding to the node includes:

[0012] Determine, from each node, each secondary neighbor node corresponding to the neighbor node;

[0013] Calculating a priority connection index between the node and the neighboring nodes according to the degree value of the node and the degree value of each of the secondary neighboring nodes;

[0014] Calculating a first-order path index between the node and the neighboring node;

[0015] The intimacy between the node and the neighboring nodes is calculated according to the priority connection index and the first-order path index.

[0016] Optionally, the process of calculating the priority connection index between the node and the neighboring nodes according to the degree value of the node and the degree value of each of the secondary neighboring nodes includes:

[0017] The priority connection index between the node and the neighboring nodes is calculated based on the degree value of the node, the degree value of each of the secondary neighboring nodes, and a first calculation relationship, wherein:

[0018] The first calculation relationship is:

[0019] Among them, MPA(i,x) represents the priority connection index between node i and neighbor node x, N(x) is the set of all secondary neighbor nodes of neighbor node x, k i represents the degree value of node i, k n Indicates the degree value of the nth neighbor node.

[0020] Optionally, the process of calculating the first-order path index between the node and the neighboring node includes:

[0021] Calculating the weight of each type of relationship based on the service data between the node and the neighboring nodes;

[0022] The first-order path index between the node and the neighboring node is calculated according to the second calculation relationship, wherein the second calculation relationship is:

[0023] Among them, L(i,x) is the first-order path index between node i and neighbor node x, E(i,x) represents the relationship set between node i and neighbor node x, e represents the current relationship, α e Indicates the weight of the current relationship, l e Indicates whether the current relationship exists.

[0024] Optionally, the relationship categories include appliance contact, payment, work order, householder, and invoice.

[0025] Optionally, the process of identifying neighboring nodes with which the node is falsely bound according to the intimacy corresponding to each neighboring node includes:

[0026] Sort the intimacy corresponding to each of the neighbor nodes by size;

[0027] A preset number of neighbor nodes with the largest intimacy are regarded as real relationship nodes, and the other neighbor nodes are regarded as false relationship nodes.

[0028] The embodiment of the present invention further provides a device for identifying false binding of electricity customers based on link prediction, comprising:

[0029] An acquisition module is used to obtain a map of electricity customers;

[0030] A first calculation module is used to calculate the degree value of each node in the electricity customer graph;

[0031] A determination module, configured to determine, for each node, neighbor nodes corresponding to the node;

[0032] A second calculation module is configured to calculate, for each of the neighboring nodes, the intimacy between the node and the neighboring node according to the degree value of the node and the degree value of the neighboring node corresponding to the node;

[0033] The identification module is used to identify neighboring nodes that have false binding with the node based on the intimacy corresponding to each of the neighboring nodes.

[0034] Optionally, the second calculation module includes:

[0035] a determining unit, configured to determine, from each node, each secondary neighboring node corresponding to the neighboring node;

[0036] A first calculation unit is configured to calculate a priority connection index between the node and the neighboring nodes according to the degree value of the node and the degree value of each of the secondary neighboring nodes;

[0037] A second calculation unit is used to calculate the first-order path index between the node and the neighboring node;

[0038] The third calculation unit is used to calculate the intimacy between the node and the neighboring node according to the priority connection index and the first-order path index.

[0039] The embodiment of the present invention further provides a system for identifying false binding of electricity customers based on link prediction, comprising:

[0040] memory for storing computer programs;

[0041] A processor is configured to implement the steps of the method for identifying false binding of electricity customers based on link prediction as described above when executing the computer program.

[0042] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for identifying false binding of electricity customers based on link prediction as described above are implemented.

[0043] An embodiment of the present invention provides a method, device, system and computer-readable storage medium for identifying false binding of electricity customers based on link prediction. The method includes: obtaining an electricity customer map; calculating the degree value of each node in the electricity customer map; for each node, determining the neighbor nodes corresponding to the node; for each neighbor node, calculating the intimacy between the node and the neighbor nodes based on the degree value of the node and the degree value of the neighbor node corresponding to the node; and identifying the neighbor nodes that are falsely bound to the node based on the intimacy corresponding to each neighbor node.

[0044] It can be seen that the embodiment of the present invention obtains the electricity customer map and calculates the degree value of each node in the electricity customer map, determines the neighbor nodes of each node, and for each neighbor node of each node, calculates the intimacy between the node and the neighbor node according to the degree value of the node and the degree value of the neighbor node, thereby obtaining the intimacy corresponding to the node and each neighbor node, and identifying the neighbor node that has a false binding with the node according to each intimacy; the embodiment of the present invention can realize the identification of false binding during use, which is conducive to the accurate delivery of promotional information. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the prior art and the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A flow chart of a method for identifying false binding of electricity customers based on link prediction provided by an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of an electricity customer map provided by an embodiment of the invention;

[0048] Figure 3 A schematic diagram of another electricity customer map provided by an embodiment of the invention;

[0049] Figure 4A schematic structural diagram of a device for identifying false binding of electricity customers based on link prediction provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The embodiments of the present invention provide a method, device, system and computer-readable storage medium for identifying false binding of electricity customers based on link prediction, which can identify false binding during use and facilitate accurate delivery of promotional information.

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 making creative efforts shall fall within the scope of protection of the present invention.

[0052] Please refer to Figure 1 , Figure 1 A flowchart of a method for identifying false binding of electricity customers based on link prediction is provided in an embodiment of the present invention. The method includes:

[0053] S110: Obtaining a map of electricity users;

[0054] It should be noted that, in the embodiment of the present invention, the user's basic account information and user behavior information can be obtained, and then an electricity customer map can be constructed based on the user's basic account information and user behavior information.

[0055] Specifically, payment data, invoice data, work orders, number of work orders, household owner authentication and electrical contact data, as well as the association data between the electricity customer's account number and mobile phone contacts can be obtained. The payment data can be used to analyze the payment association relationship between the user and the account number, the invoice data can be used to analyze whether the user has processed invoice data for the account number, the number of work orders can be used to analyze whether the user has processed work order data for the account number, and the household owner authentication and electrical contact data can be used to analyze whether the user is the household owner authentication or electrical contact.

[0056] Specifically, when building an electricity customer graph, the graph database can store information such as entities, entity relationships, and entity attributes. The graph mainly includes two types of entities and five types of relationships. The two types of entities are household numbers and contact mobile phone numbers, and the five types of relationships are household owners, work orders, electrical contacts, invoices, and payments. In the graph, there is a relationship between mobile phone numbers and household numbers, that is, there may be an edge. There is no relationship between mobile phone numbers or between household numbers. For example Figure 2The topology shown in the figure shows a relationship where w, x, y, and z are different contact phone numbers, and i and j are different electricity user numbers. Specifically, user number i is associated with four contact phone numbers w, x, y, and z, and user number j is associated with one contact phone number z. There are three edges between user number i and contact phone number x: user owner, work order, and invoice.

[0057] S120: Calculate the degree value of each node in the electricity customer graph;

[0058] Specifically, in the embodiment of the present invention, after the electricity customer map is constructed, each node is determined and the degree value of each node is calculated. For example, Figure 2 The degree value of node w in is 1, the degree value of node x is 3, the degree value of node y is 1, the degree value of node z is 3, the degree value of node i is 6, and the degree value of node j is 2.

[0059] S130: For each node, determine neighboring nodes corresponding to the node;

[0060] It should be noted that, in the embodiment of the present invention, for each node, the neighbor nodes corresponding to the node are determined, for example Figure 2 The neighbor nodes of node i in are node x, node w, node y and node z, the neighbor node of node x is node i, the neighbor node of node w is node i, the neighbor nodes of node z are node i and node j, the neighbor node of node y is node i, and the neighbor node of node j is node z.

[0061] S140: For each neighbor node, calculate the intimacy between the node and the neighbor node based on the node's degree and the degree of the neighbor node corresponding to the node;

[0062] Specifically, after determining the neighbor nodes corresponding to each node, for any node, the intimacy between the node and the neighbor node can be further calculated based on the degree value of the node and the degree value of its neighbor nodes, thereby obtaining multiple intimacy corresponding to the node, each intimacy corresponding to a neighbor node.

[0063] S150: Identify neighboring nodes that have false binding with the node based on the intimacy corresponding to each neighboring node.

[0064] It should be noted that for each node, based on the intimacy corresponding to the node, it is possible to further identify which of the neighboring nodes corresponding to the node are false bindings and which are real bindings. Specifically, the intimacy corresponding to the node can be sorted by size, and then a preset number of neighboring nodes with the greatest intimacy can be regarded as real relationship nodes, and the other neighboring nodes can be regarded as false relationship nodes. In other words, the binding between the two neighboring nodes with the greatest intimacy and the node can be regarded as a real binding, and the binding between the neighboring nodes with other intimacy and the node can be regarded as a false binding.

[0065] Furthermore, the process of calculating the intimacy between the node and its neighbor nodes based on the degree value of the node and the degree values ​​of the neighbor nodes corresponding to the node in S140 may specifically include:

[0066] Determine each secondary neighbor node corresponding to the neighbor node from each node;

[0067] According to the degree value of the node and the degree value of each secondary neighbor node, the priority connection index between the node and the neighbor node is calculated;

[0068] Calculate the first-order path index between the node and its neighbor nodes;

[0069] The intimacy between a node and its neighbor nodes is calculated based on the priority connection index and the first-order path index.

[0070] It should be noted that the method provided in the embodiment of the present invention can be used to calculate the intimacy between any node and any of its neighboring nodes. Specifically, for a node and a corresponding neighboring node, the secondary neighboring nodes corresponding to the neighboring node can be determined from the electricity customer map, that is, the neighboring nodes of the neighboring node are found. In the embodiment of the present invention, the neighboring nodes of the neighboring node are used as secondary neighboring nodes. After determining the secondary neighboring nodes corresponding to the neighboring node, the priority connection index between the node and the neighboring node can be further calculated based on the degree value of the node and the degree value of each secondary neighboring node. Since the intimacy between nodes is also related to the link path between the nodes, the intimacy transmitted by different categories of edges is also different. Therefore, in the embodiment of the present invention, the first-order path index between the node and the neighboring node is also calculated, and then the intimacy between the node and the neighboring node is further calculated based on the priority connection index and the first-order path index between the node and the neighboring node.

[0071] Specifically, the process of calculating the priority connection index between the node and its neighbor nodes based on the degree value of the node and the degree values ​​of each secondary neighbor node may include:

[0072] The priority connection index between the node and its neighbor nodes is calculated based on the degree value of the node and the degree values ​​of each secondary neighbor node and the first calculation relationship, where:

[0073] The first calculation relationship is:

[0074] Among them, MPA(i,x) represents the priority connection index between node i and neighbor node x, N(x) is the set of all secondary neighbor nodes of neighbor node x, k i represents the degree value of node i, k n Indicates the degree value of the nth neighbor node.

[0075] That is, to calculate the priority connection index between node i and neighbor node x, we can first determine the secondary neighbor nodes of neighbor node x, the set of these secondary neighbor nodes is N(x), and then the priority connection index between the node and the neighbor node can be calculated according to the above calculation relationship. The priority connection index calculated by the method proposed in the embodiment of the present invention is more accurate, which is conducive to improving the accuracy of intimacy.

[0076] Specifically, the process of calculating the first-order path index between a node and its neighboring nodes includes:

[0077] Calculate the weight of each type of relationship based on the business data between the node and its neighboring nodes;

[0078] The first-order path index between the node and the neighboring node is calculated according to the second calculation relationship, wherein the second calculation relationship is:

[0079] Among them, L(i,x) is the first-order path index between node i and neighbor node x, and E(i,x) represents the relationship set between node i and neighbor node x, for example, including e 电气联系人 、e 缴费 、e 工单 、e 户主 、e 发票 , e represents the current relationship, α e Indicates the weight of the current relationship, l e Indicates whether the current relationship exists, l e The value of is 0 or 1.

[0080] It should be noted that in embodiments of the present invention, a weighted approach can be used to calculate first-order path metrics. Specifically, business data between a node and its neighboring nodes can be obtained, and the weight of each relationship type can be calculated based on this business data. Relationship categories include appliance contacts, bill payments, work orders, household owners, and invoices. If data for a certain relationship type does not exist, the weight of that relationship is 0. After calculating the weight of each relationship type, the first-order path metric between the node and its neighboring nodes can be further calculated based on the second calculation relationship described above.

[0081] For example Figure 3 As shown in the electricity customer graph, assume that the edge between node i and node x is electrical contact, payment, invoice, the relationship between the two edges between node j and node x is electrical contact, invoice, and the edge between node k and node x is electrical contact. Assume that the weights obtained by the business data are α 电气联系人 =0.1,α 缴费 =0.25,α 工单 =0.2,α 户主 =0.2,α 发票 = 0.25. The intimacy between node x and its three neighbors can be obtained:

[0082]

[0083]

[0084]

[0085] Therefore, it can be concluded that the intimacy value between node i and node x is the largest, which is consistent with the intuitive observation results. It can be considered that there is a real binding between node i, node j and node x, and a false binding between node k and node x. When sending promotion information subsequently, it can be sent to node i and node j so that the promotion information can be delivered accurately.

[0086] It can be seen that the embodiment of the present invention obtains the electricity customer map and calculates the degree value of each node in the electricity customer map, determines the neighbor nodes of each node, and for each neighbor node of each node, calculates the intimacy between the node and the neighbor node according to the degree value of the node and the degree value of the neighbor node, thereby obtaining the intimacy corresponding to the node and each neighbor node, and identifying the neighbor node that has a false binding with the node according to each intimacy; the embodiment of the present invention can realize the identification of false binding during use, which is conducive to the accurate delivery of promotional information.

[0087] On the basis of the above embodiment, the embodiment of the present invention further provides a false binding identification device for electricity customers based on link prediction. Figure 4 , the device comprises:

[0088] An acquisition module 21 is used to acquire a map of electricity users;

[0089] The first calculation module 22 is used to calculate the degree value of each node in the electricity customer graph;

[0090] A determination module 23 is configured to determine, for each node, neighbor nodes corresponding to the node;

[0091] The second calculation module 24 is used to calculate the intimacy between each neighbor node based on the degree value of the node and the degree value of the neighbor node corresponding to the node;

[0092] The identification module 25 is configured to identify neighboring nodes that are falsely bound to the node based on the intimacy corresponding to each neighboring node.

[0093] Optionally, the second calculation module 24 includes:

[0094] A determination unit, configured to determine, from each node, each secondary neighbor node corresponding to the neighbor node;

[0095] A first calculation unit is used to calculate a priority connection index between the node and its neighbor nodes according to the degree value of the node and the degree values ​​of each secondary neighbor node;

[0096] The second calculation unit is used to calculate the first-order path index between the node and the neighboring nodes;

[0097] The third calculation unit is used to calculate the intimacy between the node and the neighboring nodes according to the priority connection index and the first-order path index.

[0098] It should be noted that the link prediction-based electricity customer false binding identification device provided in the embodiment of the present invention has the same beneficial effects as the electricity customer false binding method provided in the above embodiment, and for the specific introduction of the electricity customer false binding method designed in the embodiment of the present invention, please refer to the above embodiment, and the present invention will not go into details here.

[0099] Based on the above embodiment, an embodiment of the present invention further provides a false binding identification system for electricity customers based on link prediction, the system comprising:

[0100] memory for storing computer programs;

[0101] The processor is configured to implement the steps of the above-mentioned method for identifying false binding of electricity customers based on link prediction when executing a computer program.

[0102] For example, the processor in the embodiment of the present invention can be specifically used to obtain an electricity customer map; calculate the degree value of each node in the electricity customer map; for each node, determine the neighbor nodes corresponding to the node; for each neighbor node, calculate the intimacy between the node and the neighbor node based on the degree value of the node and the degree value of the neighbor node corresponding to the node; and identify the neighbor node that has a false binding with the node based on the intimacy corresponding to each neighbor node.

[0103] Based on the above embodiment, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for identifying false binding of electricity customers based on link prediction are implemented.

[0104] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., which can store program codes.

[0105] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0106] It should also be noted that, in this specification, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0107] Professionals may further 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 above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0108] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0109] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying false binding of electricity customers based on link prediction, characterized in that: include: Obtain a map of electricity customers; Calculating the degree value of each node in the electricity customer graph; For each node, determine neighboring nodes corresponding to the node; For each of the neighbor nodes, calculate the intimacy between the node and the neighbor node according to the degree value of the node and the degree value of the neighbor node corresponding to the node; According to the intimacy corresponding to each of the neighboring nodes, the neighboring nodes with which the node is falsely bound are identified; wherein: The process of calculating the intimacy between the node and the neighboring nodes according to the degree value of the node and the degree values ​​of the neighboring nodes corresponding to the node includes: Determine, from each node, each secondary neighbor node corresponding to the neighbor node; Calculating a priority connection index between the node and the neighboring nodes according to the degree value of the node and the degree value of each of the secondary neighboring nodes; Calculating a first-order path index between the node and the neighboring node; The intimacy between the node and the neighboring nodes is calculated according to the priority connection index and the first-order path index.

2. The method for identifying false binding of electricity customers based on link prediction according to claim 1 is characterized in that: The process of calculating the priority connection index between the node and the neighboring nodes according to the degree value of the node and the degree value of each of the secondary neighboring nodes includes: The priority connection index between the node and the neighboring nodes is calculated based on the degree value of the node, the degree value of each of the secondary neighboring nodes, and a first calculation relationship, wherein: The first calculation relationship is: Among them, MPA(i,x) represents the priority connection index between node i and neighbor node x, N(x) is the set of all secondary neighbor nodes of neighbor node x, k i represents the degree value of node i, k n Indicates the degree value of the nth neighbor node.

3. The method for identifying false binding of electricity customers based on link prediction according to claim 1 is characterized in that: The process of calculating the first-order path index between the node and the neighboring node includes: Calculating the weight of each type of relationship based on the service data between the node and the neighboring nodes; The first-order path index between the node and the neighboring node is calculated according to the second calculation relationship, wherein the second calculation relationship is: Among them, L(i,x) is the first-order path index between node i and neighbor node x, E(i,x) represents the relationship set between node i and neighbor node x, e represents the current relationship, α e Indicates the weight of the current relationship, l e Indicates whether the current relationship exists.

4. The method for identifying false binding of electricity customers based on link prediction according to claim 3 is characterized in that: The relationship categories include appliance contact, payment, work order, household owner, and invoice.

5. The method for identifying false binding of electricity customers based on link prediction according to claim 1, characterized in that: The process of identifying neighboring nodes with which the node is falsely bound according to the intimacy corresponding to each of the neighboring nodes includes: Sort the intimacy corresponding to each of the neighbor nodes by size; A preset number of neighbor nodes with the largest intimacy are regarded as real relationship nodes, and the other neighbor nodes are regarded as false relationship nodes.

6. A device for identifying false binding of electricity customers based on link prediction, characterized in that: include: An acquisition module is used to obtain a map of electricity customers; A first calculation module is used to calculate the degree value of each node in the electricity customer graph; A determination module, configured to determine, for each node, neighbor nodes corresponding to the node; A second calculation module is configured to calculate, for each of the neighboring nodes, the intimacy between the node and the neighboring node according to the degree value of the node and the degree value of the neighboring node corresponding to the node; An identification module is used to identify neighboring nodes that have false bindings with the node based on the intimacy corresponding to each of the neighboring nodes; wherein: The second calculation module includes: a determining unit, configured to determine, from each node, each secondary neighboring node corresponding to the neighboring node; A first calculation unit is configured to calculate a priority connection index between the node and the neighboring nodes according to the degree value of the node and the degree value of each of the secondary neighboring nodes; A second calculation unit is used to calculate the first-order path index between the node and the neighboring node; The third calculation unit is used to calculate the intimacy between the node and the neighboring node according to the priority connection index and the first-order path index.

7. A false binding identification system for electricity customers based on link prediction, characterized in that: include: Memory for storing computer programs; A processor is configured to implement the steps of the method for identifying false binding of electricity customers based on link prediction as described in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for identifying false binding of electricity customers based on link prediction as claimed in any one of claims 1 to 5.

Images