Customer group information processing method and device, electronic equipment and computer program product

Abstract

The invention discloses a customer group information processing method and device, electronic equipment and a computer program product. Relates to the field of financial science and technology, and the method comprises the steps: obtaining customer group information, building an information network diagram according to the user information of M financial users in the customer group information, and obtaining an initial information network diagram, the initial information network diagram comprises M nodes, and each node indicates the user information of one financial user; determining a degree sequence of the initial information network diagram, and performing sub-diagram division on the initial information network diagram according to the degree sequence to obtain a divided information network diagram; and adjusting the divided information network diagram according to the node degree value of each node in the divided information network diagram to obtain a target information network diagram. According to the method and the device, the technical problems that the processing efficiency is low and the generated information network graph cannot keep the circulation characteristic of the customer group information when the privacy protection processing is performed on the information network graph obtained by constructing the customer group information in the related technology are solved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and more specifically, to a method, apparatus, electronic device, and computer program product for processing customer information. Background Technology

[0002] With economic development, communication between financial institutions has become increasingly frequent, and emerging financial products and services have increased the diversity of cooperation among them. However, within this cooperation framework, how to process and share customer data has become a major challenge for the industry.

[0003] Currently, financial institutions need to take data anonymization measures when sharing customer information, such as using differential privacy technologies to avoid exposing personal identification details when providing customer statistics or behavioral characteristic analysis. While these methods can guarantee user privacy to a certain extent, they focus on ensuring the security of individual data and fail to effectively retain information reflecting the mobility of customer networks. This can easily lead to the loss of key connectivity information in the original data, thereby reducing the value of the data.

[0004] Furthermore, social network models are constructed when sharing customer information. In these models, connections and interactions between individuals create liquidity, which not only reflects the effective dissemination of information within the network but also characterizes the assessment of the value of potential partners. However, because the aforementioned privacy protection technologies primarily focus on anonymizing surface-level data and fail to fully consider the liquidity value within graph attributes, financial institutions face a dilemma in balancing data privacy and liquidity value when sharing information.

[0005] There are currently no effective solutions to the technical problems of low processing efficiency and inability of the generated information network graph to retain the flow characteristics of customer information when performing privacy protection processing on the information network graph constructed from customer information in related technologies. Summary of the Invention

[0006] The main objective of this application is to provide a method, apparatus, electronic device, and computer program product for processing customer information, in order to solve the technical problems in the related art where the processing efficiency is low and the generated information network diagram cannot retain the flow characteristics of customer information when performing privacy protection processing on the information network diagram constructed from customer information.

[0007] To achieve the above objectives, according to one aspect of this application, a method for processing customer group information is provided. The method includes: acquiring customer group information stored by a financial institution; constructing an information network graph based on the user information of M financial users in the customer group information to obtain an initial information network graph, wherein the initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between nodes corresponding to two financial users with a social relationship, where M is a positive integer; determining the degree sequence of the initial information network graph; subdividing the initial information network graph according to the degree sequence to obtain a subdivided information network graph, wherein the subdivided information network graph includes N sub-information network graphs, where N is less than M, and N is a positive integer; adjusting the subdivided information network graph according to the node degree value of each node in the subdivided information network graph to obtain a target information network graph, wherein the node degree value of each node refers to the number of edges directly connected to each node in the subdivided information network graph.

[0008] Optionally, determining the degree sequence of the initial information network graph includes: for a node in the initial information network graph, obtaining the number of edges directly connected to the node to obtain the node degree value; for each node in the initial information network graph, calculating the similarity between the node degree values ​​of the node and M-1 nodes respectively to obtain a set of similarity data, wherein the set of similarity data includes M-1 similarity data; performing similarity clustering on the M nodes to obtain Y node sets, and determining the degree value of each node set to obtain Y set degree values, wherein Y is a positive integer; arranging the Y set degree values ​​in descending order to obtain the degree sequence.

[0009] Optionally, the initial information network graph is subdivided according to the degree sequence to obtain the subdivided information network graph, including: obtaining M nodes associated with the degree sequence, taking each node as a subgraph to obtain M initial subgraphs; obtaining the node degree values ​​of the M nodes in the initial information network graph according to the degree sequence, calculating the module degree value of the initial information network graph according to the M node degree values ​​to obtain the initial module degree value; for any two initial subgraphs in the M initial subgraphs, calculating the module degree value of the initial information network graph after combining the two initial subgraphs to obtain R candidate module degree values, where R is a positive integer; dividing the M initial subgraphs according to the R candidate module degree values ​​to obtain N network subgraphs, and the N sub-information network graphs associated with the N network subgraphs constitute the subdivided information network graph.

[0010] Optionally, dividing the M initial subgraphs according to the R candidate modularity values ​​to obtain N network subgraphs includes: calculating the difference between the R candidate modularity values ​​and the initial modularity values ​​to obtain R incremental values; merging the two initial subgraphs corresponding to the incremental values ​​with the largest values ​​to obtain a merged subgraph; obtaining the information network graph after obtaining the merged subgraph to obtain a first information network graph; calculating the modularity value of the first information network graph to obtain an updated modularity value; obtaining the number of subgraphs after division; if the number of subgraphs is less than a preset number, dividing the merged subgraph and the M-1 initial subgraphs according to the updated modularity value until the number of subgraphs is equal to the preset number; and determining the merged subgraph as N network subgraphs.

[0011] Optionally, adjusting the partitioned information network graph based on the node degree value of each node in the partitioned information network graph to obtain the target information network graph includes: for a sub-information network graph in the partitioned information network graph, obtaining G nodes in the sub-information network graph and obtaining the node degree value associated with each node to obtain G node degree values, where G is a positive integer; for the i-th node and the j-th node among the G nodes, determining the modification type of the i-th node and the j-th node based on the G node degree values, where i and j are positive integers; modifying the i-th node and the j-th node according to the modification type, and modifying the node degree value of the i-th node and the node degree value of the j-th node to obtain the modified sub-information network graph; merging the N modified sub-information network graphs to obtain the target information network graph.

[0012] Optionally, determining the modification type of the i-th node and the j-th node based on the G node degree values ​​includes: obtaining the node degree value of the i-th node from the G node degree values ​​to obtain the i-th node degree value; obtaining the node degree value of the j-th node from the G node degree values ​​to obtain the j-th node degree value; calculating the circulation index value between the i-th node and the j-th node using the i-th node degree value and the j-th node degree value; obtaining the index mapping rule; and filtering the modification type from the index mapping rule based on the circulation index value, wherein the index mapping rule includes multiple candidate modification types and the numerical range of the circulation index value corresponding to each candidate modification type.

[0013] Optionally, modifying the i-th node and the j-th node according to the modification type includes: if the i-th node and the j-th node are connected, deleting the edge between the i-th node and the j-th node; if the i-th node and the j-th node are not connected, adding an edge between the i-th node and the j-th node; obtaining the k-th node from the G nodes, deleting the edge between the i-th node and the k-th node and adding an edge between the j-th node and the k-th node if the i-th node and the k-th node are connected, where k is a positive integer; obtaining the z-th node from the G nodes, deleting the edge between the i-th node and the k-th node and the edge between the j-th node and the z-th node if the i-th node and the k-th node are connected and the j-th node and the z-th node are connected, and adding an edge between the k-th node and the z-th node, where z is a positive integer; if the modification type indicates a new node, obtaining the new node and adding an edge between the i-th node and the new node.

[0014] To achieve the above objectives, according to another aspect of this application, a customer group information processing apparatus is provided. The apparatus includes: an acquisition unit, configured to acquire customer group information stored by a financial institution, and construct an information network graph based on the user information of M financial users in the customer group information to obtain an initial information network graph, wherein the initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between nodes corresponding to two financial users with a social relationship, where M is a positive integer; a determination unit, configured to determine the degree sequence of the initial information network graph, and perform subgraph partitioning of the initial information network graph according to the degree sequence to obtain a partitioned information network graph, wherein the partitioned information network graph includes N partitioned sub-information network graphs, where N is less than M, and N is a positive integer; and an adjustment unit, configured to adjust the partitioned information network graph according to the node degree value of each node in the partitioned information network graph to obtain a target information network graph, wherein the node degree value of each node refers to the number of edges directly connected to each node in the partitioned information network graph.

[0015] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform any of the above-mentioned customer information processing methods.

[0016] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory storing an executable program, and the processor for running the program, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any of the above-described methods for processing customer information.

[0017] According to another aspect of the present invention, a computer program product is also provided, the computer program product including a computer program, wherein when the computer program is executed by a processor, it implements any of the above-described methods for processing customer information.

[0018] In this embodiment, a customer group information processing method is adopted. Customer group information stored by financial institutions is obtained, and an information network graph is constructed based on the user information of M financial users in the customer group information to obtain an initial information network graph. The initial information network graph includes M nodes, each node indicating the user information of a financial user. Each edge in the initial information network graph refers to the edge between nodes corresponding to two financial users with a social relationship, where M is a positive integer. The degree sequence of the initial information network graph is determined, and the initial information network graph is subdivided according to the degree sequence to obtain a subdivided information network graph. The subdivided information network graph includes N sub-information network graphs, where N is less than M and N is a positive integer. The subdivided information network graph is adjusted according to the node degree value of each node in the subdivided information network graph to obtain... The target information network graph, where the degree value of each node refers to the number of edges directly connected to each node in the partitioned information network graph, solves the technical problems of low processing efficiency and inability to retain the flow characteristics of customer information when performing privacy protection processing on information network graphs constructed from customer information in related technologies. By determining the degree sequence of the initial information network graph, the initial information network graph constructed from customer information is subgraphed according to the degree sequence to obtain the partitioned information network graph. Then, the partitioned information network graph is adjusted using the node degree values ​​to obtain the target information network graph. This achieves the technical effect of improving the processing efficiency of privacy protection processing of information network graphs without destroying the basic structure of the social network and retaining the flow characteristics of customer information corresponding to the information network graph. Attached Figure Description

[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 It is a hardware structure block diagram of a computer terminal (or mobile device) used to implement a method for processing customer information;

[0021] Figure 2 This is a flowchart of a customer information processing method provided in the embodiments of this application;

[0022] Figure 3 This is a schematic diagram of an optional customer information processing method provided according to an embodiment of this application;

[0023] Figure 4 This is a schematic diagram of a customer information processing apparatus provided according to an embodiment of this application;

[0024] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties. For example, this system has interfaces with relevant users or organizations to provide users with corresponding operation data for them to choose to agree to or refuse automated decision-making results. Before obtaining relevant information, a request for obtaining the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained after receiving consent from the aforementioned user or organization; if the user chooses to refuse, the expert decision-making process is initiated. Users can view the purpose of data use in real time through authorization decoding and have the right to withdraw authorization or delete data at any time. After the authorization is withdrawn, the system will terminate the relevant data processing within 24 hours.

[0028] It should be noted that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize use or refuse use.

[0029] Example 1

[0030] According to an embodiment of this application, a method embodiment for processing customer group information is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) used to implement a method for processing customer information, such as... Figure 1 As shown, computer terminal 10 (or mobile device) may include one or more ( Figure 1 The processor 102 (which may include, but is not limited to, a microprocessor MCU (Microcontroller Unit) or a programmable gate array (FPGA)) is shown as 102a, 102b, ..., 102n. It also includes a memory 104 for storing data and a transmission device 106 for communication functions. In addition, it may include: a display, an input / output interface, a Universal Serial Bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a keyboard, a cursor control device, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0032] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0033] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the customer information processing method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned customer information processing method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0034] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network interface controller (NIC) and a network interface, which can be connected to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a radio frequency (RF) module, used for wireless communication with the Internet.

[0035] The display can be, for example, a touchscreen liquid crystal display (LCD), which allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0036] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for processing customer group information is shown. Figure 2 This is a flowchart of a customer information processing method provided in an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0037] Step S201: Obtain customer group information stored by financial institutions, and construct an information network graph based on the user information of M financial users in the customer group information to obtain an initial information network graph. The initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between the nodes corresponding to two financial users who have a social relationship. M is a positive integer.

[0038] It should be noted that customer information includes basic information about financial users, transaction records, and social relationships among them. To protect the privacy of the acquired customer information while selectively retaining liquidity-related value, the financial users in the customer information can be treated as nodes. Each node represents an independent individual in the information network graph, carrying user information such as identity and account activity. An edge is connected between nodes corresponding to two financial users with social relationships, forming an edge in the initial information network graph. This maps the customer information onto a graph structure, forming the initial information network graph. By transforming abstract customer information into a graphical representation, the information network graph makes data liquidity a visible and controllable attribute. This allows financial institutions to selectively retain this crucial liquidity value while protecting user privacy. Social relationships can be multi-dimensional, including shared projects and business cooperation history. Each edge signifies some form of interaction or connection between the parties.

[0039] Step S202: Determine the degree sequence of the initial information network graph, and divide the initial information network graph into subgraphs according to the degree sequence to obtain the divided information network graph. The divided information network graph includes N sub-information network graphs, where N is less than M and N is a positive integer.

[0040] It should be noted that the degree sequence refers to the set of all nodes in the initial information network with their degrees arranged. The degree sequence records the number of connections of each node corresponding to each financial user, that is, the number of edges directly adjacent to each node. A high degree indicates that the node has more connections in the graph.

[0041] Specifically, after obtaining the initial information network graph constructed based on customer group information, the degree sequence of this initial information network graph can be determined first. Based on this sequence, subgraph partitioning is performed, decomposing the original initial information network graph into multiple sub-information network graphs. Each sub-graph corresponds to a relatively independent financial user community. Subgraph partitioning refers to decomposing the original information network graph into several independent subgraphs, which are part of the partitioned information network graph. It should be noted that subgraph partitioning can be performed by identifying the community structure in the network, that is, grouping nodes with similar degrees or close connections into the same subgraph. This minimizes the connections between subgraphs and maximizes the connection density within a subgraph, thereby protecting the liquidity characteristics of nodes from easy identification while maintaining the liquidity within the subgraph.

[0042] Step S203: Adjust the partitioned information network graph according to the node degree value of each node in the partitioned information network graph to obtain the target information network graph. The node degree value of each node refers to the number of edges directly connected to each node in the partitioned information network graph.

[0043] Specifically, after obtaining the partitioned information network graph, the degree value of each node in the graph can be determined. The degree value reflects the node's social activity within the network, i.e., how many other nodes it has direct social relationships or information exchange channels with. Then, these degree values ​​are used to readjust the information network graph. For example, the degree can be changed by adding edges (adding edges between two non-directly connected nodes), deleting edges (deleting edges between two directly connected nodes), or replacing edges (adjusting the degree by swapping connections between nodes). New isolated or connected nodes can also be added to the network, thus finding the optimal balance between protecting privacy and maintaining flow.

[0044] Through the above adjustments, the target information network diagram was finally obtained. This network diagram retains the key circulation value of the initial information network diagram, while implementing refined data anonymization to achieve secure data flow.

[0045] The customer information processing method provided in this application involves acquiring customer information stored by financial institutions, constructing an information network graph based on the user information of M financial users in the customer information, and obtaining an initial information network graph. The initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between nodes corresponding to two financial users with a social relationship. M is a positive integer. The method then determines the degree sequence of the initial information network graph and partitions it into subgraphs based on the degree sequence, resulting in a sub-information network graph. The sub-information network graph includes N sub-information network graphs, where N is less than M and N is a positive integer. Finally, the method adjusts the sub-information network graph based on the node degree value of each node in the sub-information network graph to obtain the target... The information network graph, where the degree value of each node refers to the number of edges directly connected to each node in the partitioned information network graph, solves the technical problems of low processing efficiency and inability to retain the flow characteristics of customer information when performing privacy protection processing on information network graphs constructed from customer information in related technologies. By determining the degree sequence of the initial information network graph, the initial information network graph constructed from customer information is subdivided according to the degree sequence to obtain the partitioned information network graph. Then, the partitioned information network graph is adjusted using the node degree values ​​to obtain the target information network graph. Thus, the technical effect of improving the processing efficiency of privacy protection processing of information network graphs is achieved without destroying the basic structure of the social network and retaining the flow characteristics of customer information corresponding to the information network graph is achieved.

[0046] Optionally, in the customer group information processing method provided in this application embodiment, determining the degree sequence of the initial information network graph includes: for a node in the initial information network graph, obtaining the number of edges directly connected to the node to obtain the node degree value; for each node in the initial information network graph, calculating the similarity between the node and the node degree values ​​of M-1 nodes to obtain a set of similarity data, wherein the set of similarity data includes M-1 similarity data; performing similarity clustering on the M nodes to obtain Y node sets, and determining the degree value of each node set to obtain Y set degree values, wherein Y is a positive integer; arranging the Y set degree values ​​in descending order to obtain the degree sequence.

[0047] Specifically, when calculating the degree sequence of the initial information network graph, the number of edges directly connected to each node in the initial information network graph can be obtained first. This data is used as the node degree value of each node. The node degree value intuitively reflects the breadth of the node's connections in the network, that is, the node's social activity. For financial user nodes, the higher the degree value, the more important the role that node plays in information flow.

[0048] Furthermore, for each node in the initial information network graph, its node degree value is compared with that of the other nodes in the network. Using specific similarity calculation formulas (such as Euclidean distance, Pearson correlation coefficient, etc.), a set of results containing multiple similarity data is obtained, thereby identifying nodes with similar connection patterns in the network and providing a data foundation for further community segmentation and optimization. Then, based on the calculated similarity data, the nodes are clustered to form multiple node sets. For each formed node set, the set degree value, representing the average degree or total degree of all nodes in the set, is further calculated. The obtained set degree values ​​are then sorted in descending order to generate a degree sequence.

[0049] This embodiment constructs a degree sequence by clustering nodes based on similarity, which not only reduces the adverse impact on circulation during the data anonymization process, but also enhances the privacy attributes of the data.

[0050] Optionally, in the customer group information processing method provided in this application embodiment, the process of dividing the initial information network graph into subgraphs based on the degree sequence to obtain the divided information network graph includes: obtaining M nodes associated with the degree sequence, taking each node as a subgraph to obtain M initial subgraphs; obtaining the node degree values ​​of the M nodes in the initial information network graph based on the degree sequence, calculating the module degree value of the initial information network graph based on the M node degree values ​​to obtain the initial module degree value; for any two initial subgraphs in the M initial subgraphs, calculating the module degree value of the initial information network graph after combining the two initial subgraphs to obtain R candidate module degree values, where R is a positive integer; dividing the M initial subgraphs based on the R candidate module degree values ​​to obtain N network subgraphs, and the N sub-information network graphs associated with the N network subgraphs constitute the divided information network graph.

[0051] Specifically, after obtaining the degree sequence of the initial information network graph, each node associated with the degree sequence can first be treated as a subgraph (i.e., assigned to a community), resulting in multiple initial subgraphs. Then, based on the current network structure and community division, the modularity value of the initial information network graph is calculated according to the node degree value of each node, yielding the initial modularity value. The modularity value serves as a quantitative indicator for evaluating the quality of the community structure in the graph. By comparing intra-community connections with expected random connections, it can measure the tightness of the communities.

[0052] Furthermore, any two subgraphs are selected from all the initial subgraphs and combined, and the modularity value of the combined network is calculated to obtain candidate modularity values. That is, for each pair of possible merged communities, the modularity of the merged network is calculated, thereby exploring the impact of different subgraph combinations on flowability, identifying which combinations can most effectively enhance the connectivity of nodes within a community, and reducing ineffective cross-community flow. Finally, the initial subgraphs are further divided based on the candidate modularity values ​​to obtain multiple network subgraphs, and the sub-information network graphs associated with these optimized network subgraphs together constitute the divided information network graph.

[0053] This embodiment divides the initial information network graph using degree sequence steps to obtain the divided information network graph. This not only effectively reduces the risk of attackers locating individuals through social network analysis, but also allows financial institutions to share data while maintaining the continuity and efficiency of the network structure.

[0054] Optionally, in the customer group information processing method provided in this application embodiment, dividing M initial subgraphs according to R candidate modularity values ​​to obtain N network subgraphs includes: calculating the difference between the R candidate modularity values ​​and the initial modularity values ​​to obtain R incremental values; merging the two initial subgraphs corresponding to the incremental values ​​with the largest values ​​to obtain a merged subgraph; obtaining the information network graph after obtaining the merged subgraph to obtain a first information network graph; calculating the modularity value of the first information network graph to obtain an updated modularity value; obtaining the number of subgraphs after division; if the number of subgraphs is less than a preset number, dividing the merged subgraph and M-1 initial subgraphs according to the updated modularity value until the number of subgraphs is equal to the preset number; and determining the merged subgraphs as N network subgraphs.

[0055] Specifically, when dividing the initial subgraph, the modularity values ​​before and after merging can be compared. That is, the difference between the candidate modularity value and the initial modularity value can be calculated to obtain the incremental value of the modularity after merging compared to the modularity before merging. The incremental value is used to quantify the contribution of each merged subgraph scheme to improving the flow of the information network graph, thereby selecting the merging scheme that can best improve the quality of the community structure. If the incremental value is positive, it indicates that the community division after merging has optimized the modularity; if the incremental value is negative, it means that the merging has damaged the quality of the community structure.

[0056] Furthermore, among all possible community merges, the merge with the largest increase in modularity is selected for practical operation. This involves merging the two initial subgraphs corresponding to the largest increment, resulting in a merged subgraph. This process is repeated, calculating the modularity value of the first information network graph formed by the merged subgraphs. Based on this updated modularity value, the merged subgraph and the initial subgraphs are continuously partitioned until the network is finally merged into one or a predetermined number of subgraphs, thus obtaining the network subgraph. The final determined subgraphs then form the partitioned information network graph. It should be noted that a greedy algorithm can be used when partitioning the initial subgraphs, selecting the community combination with the largest increase in modularity for merging in each iteration. This process can use a priority queue (such as a max-heap) to efficiently manage the selection of community combinations, significantly reducing algorithm complexity. The max-heap data structure can accelerate the calculation of the increase in modularity. After each community merge, only the increase in modularity of the affected node pairs needs to be updated, without recalculating the increase in modularity of the entire network. In other words, the max-heap can quickly find and extract the community combination with the largest increase in modularity.

[0057] This embodiment obtains a network subgraph by dividing the initial subgraph, which can gradually optimize the community structure of the network, allowing social network data to maintain its mining value within the scope of compliance, thereby improving the technical level of privacy protection and maintaining the flow and community attributes of the data.

[0058] Optionally, in the customer group information processing method provided in this application embodiment, adjusting the divided information network graph according to the node degree value of each node in the divided information network graph to obtain the target information network graph includes: for a sub-information network graph in the divided information network graph, obtaining G nodes in the sub-information network graph and obtaining the node degree value associated with each node to obtain G node degree values, where G is a positive integer; for the i-th node and the j-th node among the G nodes, determining the modification type of the i-th node and the j-th node according to the G node degree values, where i and j are positive integers; modifying the i-th node and the j-th node according to the modification type, and modifying the node degree value of the i-th node and the node degree value of the j-th node to obtain the modified sub-information network graph; merging the N modified sub-information network graphs to obtain the target information network graph.

[0059] After obtaining the partitioned information network graph, adjustments can be made using graph modification. It's important to note that when modifying the graph, to minimize structural disruption, the community partitioning results become the boundary of the operation. For example, modifications within the same community (the same sub-information network graph) are prioritized to maintain community characteristics and reduce the impact on the overall network structure. Regarding inter-community edges (adjacent sub-information network graphs): if cross-community modifications are needed, communities with fewer inter-community edges or closer proximity (i.e., adjacent sub-information network graphs) are selected to minimize the risk of disrupting the community structure. The degree of nodes is adjusted to meet anonymization requirements. The distance between communities can be defined as the number of edges between them; the more edges between two communities, the closer they are.

[0060] Specifically, for a sub-information network graph within the partitioned information network graph, the degree value of each node in the graph is first obtained. Then, for two nodes (the i-th node and the j-th node) in the sub-information network graph, the modification type can be determined based on their degree values. Modification types can include edge addition, edge deletion, edge swapping, and node addition. The selection of modification types aims to maximize the flow of nodes within each community while minimizing the flow between communities to protect privacy. After obtaining the modification type, corresponding edge addition, edge deletion, edge swapping, or node addition operations can be performed on the i-th and j-th nodes according to the determined modification type, while simultaneously adjusting the degree values ​​of these two nodes to achieve the dual goals of optimizing flow and enhancing anonymity. After each sub-information network graph is modified, they are merged into a whole to form the modified sub-information network graph. Subsequently, these modified sub-information network graphs are merged to generate the target information network graph.

[0061] This embodiment utilizes the node degree value to determine the type of modification to the node, and then performs corresponding operations based on the modification type. This maintains the continuity and flow of the entire social network, while achieving appropriate data isolation between different communities. It also enables data anonymization within compliance limits, avoids the decline in information flow efficiency caused by over-processing, and maintains the flow and data mining value of the social network by preserving necessary connections between nodes, thereby achieving the goal of balancing the flow value information with privacy protection.

[0062] Optionally, in the customer group information processing method provided in this application embodiment, determining the modification type of the i-th node and the j-th node based on G node degree values ​​includes: obtaining the node degree value of the i-th node from the G node degree values ​​to obtain the i-th node degree value; obtaining the node degree value of the j-th node from the G node degree values ​​to obtain the j-th node degree value; calculating the circulation index value between the i-th node and the j-th node using the i-th node degree value and the j-th node degree value; obtaining the index mapping rule; and filtering the modification type from the index mapping rule based on the circulation index value, wherein the index mapping rule includes multiple candidate modification types and the numerical range of the circulation index value corresponding to each candidate modification type.

[0063] Specifically, to preserve the overall fluidity of the social network graph, the maximum eigenvalue of the network adjacency matrix needs to be protected. Therefore, when determining the modification type, we can first obtain the degree values ​​of the i-th and j-th nodes, then obtain the index mapping rule, compare the calculated fluidity index value with the value range in the rule, and select the modification type most suitable for the current fluidity index value. This ensures that each modification operation can accurately adjust the fluidity while avoiding unnecessary damage to privacy protection. It should be noted that the fluidity index value between the i-th and j-th nodes can be calculated using the following formula: ,in, Represents a node The node degree value; d (y j ) Represents a node v j The node degree value; This represents the maximum degree value of a node in a sub-information network graph. Represents a node and nodes The set of all first-order neighbor nodes. It should be noted that if node and nodes It is also in that set, so we include it here; This represents the set of second-order neighbor nodes of two nodes. It should be noted that if a node appears in the set... The nodes in also appeared The same applies to it; d(n 1 ) and d(n 2 ) Representing sets respectively Neutralization set The node degree value of a node. This metric measures the influence of an edge on the maximum eigenvalue of the entire network. The larger the value, the stronger the node's influence. and nodes The greater the impact of the edge between two nodes on the maximum eigenvalue of the entire social network, the more it will affect the network's flowability. In this case, it is necessary to carefully consider deleting (if it exists) or adding (if it does not exist) the edge between the two nodes.

[0064] This embodiment introduces circulation indicator values ​​and indicator mapping rules to provide financial institutions with a more refined control mechanism when sharing data on social networks, thereby improving the efficiency of data protection.

[0065] Optionally, in the customer group information processing method provided in this application embodiment, modifying the i-th node and the j-th node according to the modification type includes: if the i-th node and the j-th node are connected, deleting the edge between the i-th node and the j-th node; if the i-th node and the j-th node are not connected, adding an edge between the i-th node and the j-th node; obtaining the k-th node from the G nodes, deleting the edge between the i-th node and the k-th node and adding an edge between the j-th node and the k-th node if the i-th node and the k-th node are connected, where k is a positive integer; obtaining the z-th node from the G nodes, deleting the edge between the i-th node and the k-th node and the edge between the j-th node and the z-th node if the i-th node and the k-th node are connected and the j-th node and the z-th node are connected, and adding an edge between the k-th node and the z-th node, where z is a positive integer; if the modification type indicates a new type, obtaining the new node and adding an edge between the i-th node and the new node.

[0066] After determining the modification type for the i-th and j-th nodes, the corresponding operation can be performed according to the type. The modification type can be: edge addition (for two nodes in the graph that are not directly connected, connect the two nodes to the edge set, and increment the node degree by one), edge deletion (for two nodes in the graph that are directly connected, delete the connection between the two nodes, and decrement the node degree by one), edge swap (nodes A and B are connected but not C; B needs to reduce its connection while C needs to increase its connection; delete the connection between A and B and add the connection between A and C), and node addition (add a node that did not exist before and connect it to an existing node).

[0067] Specifically, when (That is, the i-th node). (That is, the j-th node) needs to have its degree reduced, and the two nodes are neighbors (that is, when the i-th node and the j-th node are connected). In this case, edge deletion is called, and the node is directly reduced. Delete it. When , All nodes need to have their degree values ​​added, and they are not neighbors (i.e., the i-th node and the j-th node are not connected). In this case, the edge addition function is called to directly connect the two nodes and add an edge. .

[0068] Furthermore, when , Both require reducing the node degree value, but they are not connected. In this case, edge swapping is called, and each is selected... , A neighbor (That is, the kth node) and (That is, the z-th node), satisfies Delete edge and At the same time, increase the number of sides ,so , The node degree value is reduced by one, while their neighbors... , The node degree value remains unchanged. The node degree value needs to be reduced. A node degree value needs to be added. Regardless of whether the two nodes are connected, the following operation is required: Select a neighbor. Delete edge At the same time, increase the number of sides ,so The node degree value is reduced by one, while The node degree value is incremented by one.

[0069] Furthermore, in addition to this, if the node If a node needs to increase its degree, but there are no nodes in the network that can do so, the node can be incremented by calling the node increment method. Connect to the newly added node to increase the degree. When a node... If a node needs to be reduced but there are no other nodes in the graph that require reduction, then select two neighbors of that node. , In this case, the two neighboring nodes are not neighbors. The node can then be deleted. With these two neighboring nodes , Add an edge between two neighboring nodes. This enables nodes to decrease their own degree.

[0070] This embodiment protects user privacy while preserving liquidity characteristics by modifying the edges and nodes between two nodes. It achieves precise protection of the liquidity value information of the information network graph, reduces the identifiability of individuals in the graph structure, and improves the efficiency of financial institutions in handling big data privacy issues.

[0071] This application also provides a method for processing customer group information. Figure 3 This is a schematic diagram of an optional customer information processing method provided according to an embodiment of this application, such as... Figure 3 As shown, the method includes:

[0072] To protect the data privacy of the acquired customer information and retain the liquidity value information in the data, we can first treat the financial users in the customer information as nodes. Each node represents an independent individual in the information network graph. We can connect the nodes corresponding to two financial users who have social relationships with an edge and use this edge as an edge in the initial information network graph. In this way, the customer information is mapped onto a graph structure to form the initial information network graph.

[0073] Furthermore, the initial information network graph is adjusted using a network anonymization module. Specifically, after obtaining the initial information network graph constructed based on customer information, the node degree sequence can first be anonymized based on the idea of ​​univariate micro-aggregation, that is, the degree sequence of the initial information network graph is determined. Then, based on this sequence, subgraph partitioning (that is, community partitioning and node classification) is performed, decomposing the original initial information network graph into multiple sub-information network graphs. Each subgraph corresponds to a relatively independent financial user community. Subgraph partitioning refers to decomposing the original information network graph into several independent subgraphs, which are part of the partitioned information network graph. After obtaining the partitioned information network graph, the degree value of each node in the partitioned information network graph can be determined. Then, the information network graph can be readjusted (that is, graph modification based on graph properties) using these node degree values. For example, the node degree can be changed by adding edges (adding an edge between two non-directly connected nodes), deleting edges (deleting an edge between two directly connected nodes), or replacing edges (adjusting the node degree by exchanging the connections between nodes). New isolated nodes or connected nodes can also be added, thereby finding the best balance between protecting privacy and maintaining flow.

[0074] Through the above adjustments, the target information network diagram was finally obtained. This network diagram retains the key circulation value of the initial information network diagram, while implementing refined data anonymization to achieve secure data flow.

[0075] This embodiment determines the degree sequence of the initial information network graph, divides the initial information network graph constructed from customer information into subgraphs based on the degree sequence, obtains the divided information network graph, and then adjusts the divided information network graph using the node degree values ​​to obtain the target information network graph. This achieves the technical effect of improving the processing efficiency of privacy protection processing of information network graphs while not destroying the basic structure of the social network and preserving the flow characteristics of customer information corresponding to the information network graph.

[0076] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0077] Example 2

[0078] This application also provides a customer information processing apparatus. It should be noted that this customer information processing apparatus can be used to execute the customer information processing method provided in this application. The following describes the customer information processing apparatus provided in this application.

[0079] According to an embodiment of this application, an apparatus for implementing the above-described customer information processing method is also provided. Figure 4 This is a schematic diagram of a customer information processing device provided according to an embodiment of this application, such as... Figure 4 As shown, the device includes: an acquisition unit 40, a determination unit 41, and an adjustment unit 42.

[0080] The acquisition unit 40 is used to acquire customer information stored by financial institutions, and construct an information network graph based on the user information of M financial users in the customer information to obtain an initial information network graph. The initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between the nodes corresponding to two financial users who have a social relationship. M is a positive integer.

[0081] The determining unit 41 is used to determine the degree sequence of the initial information network graph, and to divide the initial information network graph into subgraphs according to the degree sequence to obtain the divided information network graph. The divided information network graph includes N sub-information network graphs, where N is less than M and N is a positive integer.

[0082] The adjustment unit 42 is used to adjust the partitioned information network graph according to the node degree value of each node in the partitioned information network graph to obtain the target information network graph. The node degree value of each node refers to the number of edges directly connected to each node in the partitioned information network graph.

[0083] The customer information processing apparatus provided in this application embodiment includes an acquisition unit 40 for acquiring customer information stored by financial institutions, constructing an information network graph based on the user information of M financial users in the customer information to obtain an initial information network graph. The initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between nodes corresponding to two financial users with a social relationship. M is a positive integer. A determination unit 41 is used to determine the degree sequence of the initial information network graph, and perform subgraph partitioning on the initial information network graph based on the degree sequence to obtain a partitioned information network graph. The partitioned information network graph includes N partitioned sub-information network graphs, where N is less than M and N is a positive integer. An adjustment unit 42 is used to adjust the partitioned information network graph based on the node degree value of each node in the partitioned information network graph. The information network graph is adjusted to obtain the target information network graph. The degree value of each node refers to the number of edges directly connected to each node in the partitioned information network graph. This addresses the technical problems of low processing efficiency and the inability to retain the flow characteristics of customer information when performing privacy protection processing on information network graphs constructed from customer information in related technologies. By determining the degree sequence of the initial information network graph, the initial information network graph constructed from customer information is subdivided according to the degree sequence to obtain the partitioned information network graph. Then, the node degree values ​​are used to adjust the partitioned information network graph to obtain the target information network graph. This achieves the technical effect of improving the processing efficiency of privacy protection processing of information network graphs without destroying the basic structure of the social network and retaining the flow characteristics of customer information corresponding to the information network graph.

[0084] Optionally, in the customer group information processing device provided in this application embodiment, the determining unit 41 includes: a first acquisition module, used to acquire the number of edges directly connected to a node in an initial information network graph, and obtain a node degree value; a first calculation module, used to calculate the similarity between the node and M-1 nodes in the initial information network graph, and obtain a set of similarity data, wherein the set of similarity data includes M-1 similarity data; a clustering module, used to perform similarity clustering on the M nodes, obtain Y node sets, and determine the degree value of each node set, and obtain Y set degree values, wherein Y is a positive integer; and an arrangement module, used to arrange the Y set degree values ​​in descending order to obtain a degree sequence.

[0085] Optionally, in the customer group information processing device provided in this application embodiment, the determining unit 41 includes: a second acquisition module, used to acquire M nodes associated with the degree sequence, and take each node as a subgraph to obtain M initial subgraphs; a third acquisition module, used to acquire the node degree values ​​of the M nodes in the initial information network graph according to the degree sequence, and calculate the module degree value of the initial information network graph according to the M node degree values ​​to obtain the initial module degree value; a second calculation module, used to calculate the module degree value of the initial information network graph after combining any two initial subgraphs in the M initial subgraphs to obtain R candidate module degree values, where R is a positive integer; and a partitioning module, used to partition the M initial subgraphs according to the R candidate module degree values ​​to obtain N network subgraphs, and the partitioned information network graph is composed of N sub-information network graphs associated with the N network subgraphs.

[0086] Optionally, in the customer group information processing device provided in the embodiments of this application, the determining unit 41 includes: a third calculation module, used to calculate the difference between R candidate module degree values ​​and the initial module degree value respectively to obtain R incremental values, and merge the two initial subgraphs corresponding to the incremental value with the largest value to obtain a merged subgraph; a fourth acquisition module, used to acquire the information network graph after obtaining the merged subgraph to obtain a first information network graph, calculate the module degree value of the first information network graph to obtain an updated module degree value; and a fifth acquisition module, used to acquire the number of subgraphs after division, and if the number of subgraphs is less than a preset number, divide the merged subgraph and M-1 initial subgraphs according to the updated module degree value until the number of subgraphs is equal to the preset number, and determine the merged subgraph as N network subgraphs.

[0087] Optionally, in the customer group information processing device provided in this application embodiment, the adjustment unit 42 includes: a sixth acquisition module, used to acquire G nodes in a sub-information network graph of a divided information network graph, and acquire the node degree value associated with each node to obtain G node degree values, where G is a positive integer; a determination module, used to determine the modification type of the i-th node and the j-th node based on the G node degree values, where i and j are positive integers; a modification module, used to modify the i-th node and the j-th node according to the modification type, and modify the node degree value of the i-th node and the node degree value of the j-th node to obtain a modified sub-information network graph; and a merging module, used to merge N modified sub-information network graphs to obtain a target information network graph.

[0088] Optionally, in the customer group information processing device provided in this application embodiment, the adjustment unit 42 includes: a seventh acquisition module, used to acquire the node degree value of the i-th node from G node degree values ​​to obtain the i-th node degree value, and acquire the node degree value of the j-th node from G node degree values ​​to obtain the j-th node degree value; a fourth calculation module, used to calculate the circulation index value between the i-th node and the j-th node using the i-th node degree value and the j-th node degree value; and an eighth acquisition module, used to acquire index mapping rules, and filter the modification type from the index mapping rules according to the circulation index value, wherein the index mapping rules include multiple candidate modification types and the numerical range of the circulation index value corresponding to each candidate modification type.

[0089] Optionally, in the customer group information processing apparatus provided in this application embodiment, the adjustment unit 42 includes: a deletion module, used to delete the edge between the i-th node and the j-th node when the i-th node and the j-th node are connected; an addition module, used to add the edge between the i-th node and the j-th node when the i-th node and the j-th node are not connected; and a ninth acquisition module, used to acquire the k-th node among the G nodes, and when the i-th node and the k-th node are connected, delete the edge between the i-th node and the k-th node and add the j-th node. The edge between the node and the k-th node, where k is a positive integer; the tenth acquisition module is used to acquire the z-th node among the G nodes. If the i-th node is connected to the k-th node and the j-th node is connected to the z-th node, delete the edge between the i-th node and the k-th node, delete the edge between the j-th node and the z-th node, and add the edge between the k-th node and the z-th node, where z is a positive integer; the eleventh acquisition module is used to acquire the newly added node when the modification type indicates the addition of a new type, and add the edge between the i-th node and the newly added node.

[0090] It should be noted that the acquisition unit 40, determination unit 41, and adjustment unit 42 mentioned above correspond to steps S201 to S203 in Embodiment 1. The instances and application scenarios implemented by the above units and corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and can run in the computer terminal 10 provided in Embodiment 1.

[0091] Example 3

[0092] Embodiments of this application may provide a computer terminal, which may be any computer terminal device in a group of computer terminals. Optionally, in this embodiment, the aforementioned computer terminal may also be replaced with a mobile terminal or an electronic device, etc.

[0093] Optionally, in this embodiment, the computer terminal may be located in at least one of a plurality of network devices in a computer network.

[0094] In this embodiment, the computer terminal described above can execute the program code for the following steps in the customer information processing method: acquiring customer information stored by a financial institution; constructing an information network graph based on the user information of M financial users in the customer information to obtain an initial information network graph, wherein the initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between nodes corresponding to two financial users with a social relationship, where M is a positive integer; determining the degree sequence of the initial information network graph; dividing the initial information network graph into subgraphs based on the degree sequence to obtain a sub-information network graph, wherein the sub-information network graph includes N sub-information network graphs, where N is less than M, and N is a positive integer; adjusting the sub-information network graph based on the node degree value of each node in the sub-information network graph to obtain a target information network graph, wherein the node degree value of each node refers to the number of edges directly connected to each node in the sub-information network graph.

[0095] Optionally, the computer terminal described above can execute the following steps in the customer group information processing method: For a node in the initial information network graph, obtain the number of edges directly connected to the node to obtain the node degree value; For each node in the initial information network graph, calculate the similarity between the node degree value and the node degree values ​​of M-1 nodes to obtain a set of similarity data, wherein the set of similarity data includes M-1 similarity data; Perform similarity clustering on the M nodes to obtain Y node sets, and determine the degree value of each node set to obtain Y set degree values, wherein Y is a positive integer; Sort the Y set degree values ​​in descending order to obtain a degree sequence.

[0096] Optionally, the computer terminal described above can execute the following steps in the customer group information processing method: obtaining M nodes associated with the degree sequence, treating each node as a subgraph to obtain M initial subgraphs; obtaining the node degree values ​​of the M nodes in the initial information network graph according to the degree sequence, calculating the modularity value of the initial information network graph based on the M node degree values ​​to obtain the initial modularity value; for any two initial subgraphs in the M initial subgraphs, calculating the modularity value of the initial information network graph after combining the two initial subgraphs to obtain R candidate modularity values, where R is a positive integer; dividing the M initial subgraphs according to the R candidate modularity values ​​to obtain N network subgraphs, and forming the divided information network graph from the N subgraphs associated with the N network subgraphs.

[0097] Optionally, the computer terminal described above can execute the following steps in the customer group information processing method: calculate the difference between the R candidate modularity values ​​and the initial modularity value to obtain R incremental values; merge the two initial subgraphs corresponding to the incremental value with the largest value to obtain a merged subgraph; obtain the information network graph after obtaining the merged subgraph to obtain a first information network graph; calculate the modularity value of the first information network graph to obtain an updated modularity value; obtain the number of subgraphs after partitioning; if the number of subgraphs is less than a preset number, partition the merged subgraph and M-1 initial subgraphs according to the updated modularity value until the number of subgraphs is equal to the preset number; and determine the merged subgraph as N network subgraphs.

[0098] Optionally, the aforementioned computer terminal can execute the following steps in the customer information processing method: For a sub-information network graph in the divided information network graph, obtain G nodes in the sub-information network graph and obtain the node degree value associated with each node to obtain G node degree values, where G is a positive integer; For the i-th node and the j-th node among the G nodes, determine the modification type of the i-th node and the j-th node according to the G node degree values, where i and j are positive integers; Modify the i-th node and the j-th node according to the modification type, and modify the node degree value of the i-th node and the node degree value of the j-th node to obtain the modified sub-information network graph; Merge the N modified sub-information network graphs to obtain the target information network graph.

[0099] Optionally, the computer terminal described above can execute the following steps in the customer group information processing method: obtaining the node degree value of the i-th node from G node degree values, obtaining the node degree value of the j-th node from G node degree values, obtaining the node degree value of the j-th node; calculating the circulation index value between the i-th node and the j-th node using the i-th node degree value and the j-th node degree value; obtaining the index mapping rule, and filtering the modification type from the index mapping rule according to the circulation index value, wherein the index mapping rule includes multiple candidate modification types and the numerical range of the circulation index value corresponding to each candidate modification type.

[0100] Optionally, the computer terminal described above can execute the following steps in the customer group information processing method: If the i-th node and the j-th node are connected, delete the edge between the i-th node and the j-th node; if the i-th node and the j-th node are not connected, add an edge between the i-th node and the j-th node; obtain the k-th node from the G nodes, and if the i-th node and the k-th node are connected, delete the edge between the i-th node and the k-th node, and add an edge between the j-th node and the k-th node, where k is a positive integer; obtain the z-th node from the G nodes, and if the i-th node and the k-th node are connected, and the j-th node and the z-th node are connected, delete the edge between the i-th node and the k-th node, delete the edge between the j-th node and the z-th node, and add an edge between the k-th node and the z-th node, where z is a positive integer; if the modification type indicates the addition of a new type, obtain the new node and add an edge between the i-th node and the new node.

[0101] Optionally, Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (Only one is shown) processor 502, memory 504, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0102] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the customer information processing method and apparatus in this application embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned customer information processing method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0103] The processor can invoke the information and application program stored in the memory through the transmission device to execute the steps described above in the customer information processing method.

[0104] Those skilled in the art will understand that Figure 5 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 5 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 5 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 5 The different configurations shown.

[0105] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0106] Example 4

[0107] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the customer information processing method provided in Embodiment 1.

[0108] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0109] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: obtaining customer group information stored by the financial institution; constructing an information network graph based on the user information of M financial users in the customer group information to obtain an initial information network graph, wherein the initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between nodes corresponding to two financial users with social relationships, where M is a positive integer; determining the degree sequence of the initial information network graph; dividing the initial information network graph into subgraphs based on the degree sequence to obtain a subdivided information network graph, wherein the subdivided information network graph includes N sub-information network graphs, where N is less than M, and N is a positive integer; adjusting the subdivided information network graph based on the node degree value of each node in the subdivided information network graph to obtain a target information network graph, wherein the node degree value of each node refers to the number of edges directly connected to each node in the subdivided information network graph.

[0110] This application also provides a computer program product, which, when executed on a data processing device, is suitable for performing steps of a method for processing customer information.

[0111] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0112] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of this application 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0117] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for processing customer group information, characterized in that, include: Obtain customer group information stored by financial institutions, and construct an information network graph based on the user information of M financial users in the customer group information to obtain an initial information network graph. The initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between the nodes corresponding to two financial users who have a social relationship. M is a positive integer. Determine the degree sequence of the initial information network graph, and divide the initial information network graph into subgraphs according to the degree sequence to obtain a divided information network graph, wherein the divided information network graph includes N divided sub-information network graphs, where N is less than M and N is a positive integer; The partitioned information network graph is adjusted based on the degree value of each node in the partitioned information network graph to obtain the target information network graph. The degree value of each node refers to the number of edges directly connected to each node in the partitioned information network graph.

2. The method according to claim 1, characterized in that, Determining the degree sequence of the initial information network graph includes: For a node in the initial information network graph, the number of edges directly connected to the node is obtained to get the node degree value; For each node in the initial information network graph, the similarity between the node and the node degree values ​​of M-1 nodes is calculated to obtain a set of similarity data, wherein the set of similarity data includes M-1 similarity data. Similarity clustering is performed on the M nodes to obtain Y node sets, and the degree value of each node set is determined to obtain Y set degree values, where Y is a positive integer; The degree values ​​of the Y sets are sorted in descending order to obtain the degree sequence.

3. The method according to claim 1, characterized in that, The initial information network graph is subdivided according to the degree sequence to obtain a sub-information network graph including: Obtain the M nodes associated with the degree sequence, and treat each node as a subgraph to obtain M initial subgraphs; The node degree values ​​of the M nodes in the initial information network graph are obtained according to the degree sequence, and the module degree value of the initial information network graph is calculated according to the M node degree values ​​to obtain the initial module degree value. For any two initial subgraphs among the M initial subgraphs, calculate the modularity value of the initial information network graph after combining the two initial subgraphs to obtain R candidate modularity values, where R is a positive integer; The M initial subgraphs are divided according to the R candidate modularity values ​​to obtain N network subgraphs, and the N sub-information network graphs associated with the N network subgraphs constitute the divided information network graph.

4. The method according to claim 3, characterized in that, Based on the R candidate module degree values, the M initial subgraphs are divided to obtain N network subgraphs, including: Calculate the difference between the R candidate modularity values ​​and the initial modularity value to obtain R incremental values. Then merge the two initial subgraphs corresponding to the incremental values ​​with the largest values ​​to obtain a merged subgraph. Obtain the information network graph after merging the subgraphs to obtain the first information network graph, calculate the module degree value of the first information network graph, and obtain the updated module degree value; Obtain the number of subgraphs after partitioning. If the number of subgraphs is less than a preset number, partition the merged subgraph and M-1 initial subgraphs according to the updated modularity value until the number of subgraphs is equal to the preset number. Then, determine the merged subgraphs as the N network subgraphs.

5. The method according to claim 1, characterized in that, The information network graph is adjusted based on the degree value of each node in the partitioned information network graph to obtain the target information network graph, which includes: For a sub-information network graph in the divided information network graph, obtain G nodes in the sub-information network graph and obtain the node degree value associated with each node to obtain G node degree values, where G is a positive integer; For the i-th node and the j-th node among the G nodes, the modification type of the i-th node and the j-th node is determined according to the degree values ​​of the G nodes, where i and j are positive integers; The i-th node and the j-th node are modified according to the modification type, and the node degree values ​​of the i-th node and the j-th node are modified to obtain the modified sub-information network graph. The target information network graph is obtained by merging the N modified sub-information network graphs.

6. The method according to claim 5, characterized in that, The modification types of the i-th node and the j-th node are determined based on the G node degree values, including: Obtain the node degree value of the i-th node from the G node degree values ​​to obtain the node degree value of the i-th node; obtain the node degree value of the j-th node from the G node degree values ​​to obtain the node degree value of the j-th node. The flow index value between the i-th node and the j-th node is calculated using the degree value of the i-th node and the degree value of the j-th node; Obtain the indicator mapping rules, and filter the modification type from the indicator mapping rules according to the circulation indicator value. The indicator mapping rules include multiple candidate modification types and the numerical range of the circulation indicator value corresponding to each candidate modification type.

7. The method according to claim 5, characterized in that, Modifying the i-th node and the j-th node according to the modification type includes: If the i-th node and the j-th node are connected, delete the edge between the i-th node and the j-th node; If the i-th node and the j-th node are not connected, add an edge between the i-th node and the j-th node; Obtain the k-th node from the G nodes. If the i-th node and the k-th node are connected, delete the edge between the i-th node and the k-th node, and add an edge between the j-th node and the k-th node, where k is a positive integer. Obtain the z-th node among the G nodes. If the i-th node is connected to the k-th node and the j-th node is connected to the z-th node, delete the edge between the i-th node and the k-th node, delete the edge between the j-th node and the z-th node, and add the edge between the k-th node and the z-th node, where z is a positive integer. If the modification type indicates the addition of a new type, obtain the new node and add an edge between the i-th node and the new node.

8. A customer group information processing device, characterized in that, include: The acquisition unit is used to acquire customer group information stored by financial institutions, and construct an information network graph based on the user information of M financial users in the customer group information to obtain an initial information network graph. The initial information network graph includes M nodes, each node indicating the user information of a financial user, and each edge in the initial information network graph refers to the edge between the nodes corresponding to two financial users who have a social relationship. M is a positive integer. A determining unit is configured to determine the degree sequence of the initial information network graph, and to perform subgraph partitioning on the initial information network graph according to the degree sequence to obtain a partitioned information network graph, wherein the partitioned information network graph includes N partitioned sub-information network graphs, where N is less than M and N is a positive integer; The adjustment unit is used to adjust the partitioned information network graph according to the node degree value of each node in the partitioned information network graph to obtain the target information network graph, wherein the node degree value of each node refers to the number of edges directly connected to each node in the partitioned information network graph.

9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the customer information processing method according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the customer information processing method according to any one of claims 1 to 7.

Images