Bank user data processing method, device and equipment based on meta-universe scene

Abstract

The invention discloses a bank user data processing method, device and equipment based on a meta-universe scene, and relates to the technical field of data processing, and the bank user data processing method based on the meta-universe scene comprises the steps: obtaining bank user data of a user in the meta-universe scene; constructing a relationship circle network of the users based on the bank user data; performing network structure processing on the relation circle network through a structure analysis method to obtain an account social network of the user; and obtaining user attribute data, and constructing a user portrait of the user based on the user attribute data and the account social network. The relation circle network of the user is constructed, and the account social network of the user is processed on the relation circle network through the structural analysis method, so that the analysis of the transaction data of each relation circle of the user is realized, the accuracy of user portrait construction is improved, the user portrait of the user is constructed through the user attribute data and the account social network, and the user experience is improved. And accurate marketing activity recommendation is provided for the user.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and equipment for processing bank user data based on a metaverse scenario. Background Art

[0002] With the rapid development of digital technology, the Metaverse, as an emerging virtual world platform, is gradually changing the way people socialize, entertain, work and conduct financial transactions. In the Metaverse, users can use their virtual identities to conduct various financial activities, such as fund transfers, investments, and purchases of virtual goods. These activities generate a large amount of data, which is of great significance for understanding user behavior, optimizing financial services, and improving user experience.

[0003] However, when existing solutions process financial data in the metaverse, the innovation and development of banking business are restricted due to factors such as inaccurate user portrait construction and lack of visualization of financial relationships. Summary of the invention

[0004] The main purpose of this application is to provide a method, device and equipment for processing bank user data based on the metaverse scenario, aiming to solve the technical problem of inaccurate user portrait construction.

[0005] To achieve the above objectives, the present application proposes a method for processing bank user data based on a metaverse scenario, and the method for processing bank user data based on a metaverse scenario includes: Obtain the user's bank user data in the Metaverse scenario; Building a relationship circle network of the user based on the bank user data; Performing network structure processing on the relationship circle network by a structural analysis method to obtain the account social network of the user; User attribute data is obtained, and a user profile of the user is constructed based on the user attribute data and the account social network.

[0006] In some implementations, the step of constructing the user's relationship circle network based on the bank user data includes: Determining a data interaction type based on the bank user data; Acquire the data interaction type of the bank user data, construct a mapping relationship for the bank user data, and obtain a local network mapping; The relationship circle network of the user is constructed according to the local network mapping in the same data interaction type.

[0007] In some implementations, the structural analysis method includes a community discovery algorithm and a network node influence algorithm, and the step of performing network structure processing on the relationship circle network by the structural analysis method to obtain the user's account social network includes: Identifying the network structure in each of the relationship circle networks based on a community discovery algorithm to obtain the behavioral characteristics of the user; Constructing an overall relationship network diagram of the user according to the behavioral characteristics; Calculate the influence ratio of each relationship node in the overall relationship network diagram based on the network node influence algorithm; The network structure of the overall relationship network diagram is optimized based on the influence ratio to obtain the account social network of the user.

[0008] In some implementations, the step of performing network structure optimization on the overall relationship network diagram based on the influence ratio to obtain the user's account social network includes: Sorting the relationship nodes in the overall relationship network diagram based on the influence proportions to obtain the sorted relationship nodes; The influence levels of the sorted relationship nodes are divided according to the preset division weights to obtain high-influence nodes, medium-influence nodes, low-influence nodes and no-influence nodes; When the influence ratio of the non-influenced node is lower than a preset cleaning threshold, performing node cleaning on the non-influenced node; A network is reconstructed based on the high-influence nodes, the medium-influence nodes, the low-influence nodes, and the non-influence nodes after node cleaning to obtain the account social network of the user.

[0009] In some implementations, the step of acquiring the data interaction type of the bank user data and constructing a mapping relationship for the bank user data to obtain a local network mapping includes: Taking the user as the first relationship node in the network; generating a second relationship node corresponding to the first relationship node based on the bank user data; determining a node mapping relationship between the first relationship node and the second relationship node based on a data interaction type of the bank user data; Constructing a network relationship diagram based on the node mapping relationships; The network relationship graph is subjected to dimensionality reduction processing based on an adversarial autoencoder network to obtain a local network mapping.

[0010] In some implementations, the step of obtaining user attribute data and constructing a user profile of the user based on the user attribute data and the account social network includes: Acquire user attribute data, and perform labeling processing based on the user attribute data to obtain user data labels; Embedding the user data label into a first relationship node corresponding to the user in the account social network to obtain a labeled relationship node; A user portrait of the user is generated according to the account social network and the labeled relationship nodes.

[0011] In addition, to achieve the above purpose, the present application also proposes a bank user data processing device based on the metaverse scenario, and the bank user data processing device based on the metaverse scenario includes: The data acquisition module is used to obtain the bank user data of the user in the Metaverse scenario; A network construction module, used to construct a relationship circle network of the user based on the bank user data; A network processing module, used to perform network structure processing on the relationship circle network by a structural analysis method to obtain the account social network of the user; The portrait generation module is used to obtain user attribute data and build a user portrait of the user based on the user attribute data and the account social network.

[0012] In addition, to achieve the above-mentioned objectives, the present application also proposes a bank user data processing device based on a metaverse scenario, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the bank user data processing method based on the metaverse scenario as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the bank user data processing method based on the metaverse scenario as described above are implemented.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the bank user data processing method based on the metaverse scenario as described above.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: This application obtains the user's bank user data in the metaverse scenario; constructs the user's relationship circle network based on the bank user data; processes the relationship circle network through structural analysis to obtain the user's account social network; obtains the user's attribute data, and constructs the user's user profile based on the user attribute data and the account social network. Since the user's account social network is obtained by constructing the user's relationship circle network and processing the relationship circle network through structural analysis, the transaction data in each relationship circle of the user is analyzed, the accuracy of user profile construction is improved, and the user's user profile is constructed through user attribute data and account social network, which is convenient for providing users with accurate marketing activity recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A flowchart diagram of the first embodiment of the bank user data processing method based on the Metaverse scenario of this application; Figure 2 A flowchart diagram of the second embodiment of the bank user data processing method based on the metaverse scenario of this application; Figure 3 A schematic diagram of the network structure of an adversarial autoencoding network in one implementation of an embodiment of the present application; Figure 4 A flowchart diagram of the third embodiment of the bank user data processing method based on the metaverse scenario of this application; Figure 5 This is a schematic diagram of the module structure of a bank user data processing device based on a metaverse scenario in an embodiment of the present application; Figure 6 This is a structural diagram of a bank user data processing device based on a metaverse scenario in an embodiment of the present application.

[0019] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0021] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0022] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a server, a computer, etc., or an electronic device, a virtual device, etc. that can realize the above functions. The following takes a bank user data processing device (hereinafter referred to as a processing device) based on a metaverse scenario as an example to illustrate this embodiment and the following embodiments.

[0023] Based on this, the embodiment of the present application provides a bank user data processing method based on the metaverse scenario, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the bank user data processing method based on the Metaverse scenario of the present application.

[0024] In this embodiment, the bank user data processing method based on the metaverse scenario includes steps S10 to S40: Step S10, obtaining the user's bank user data in the Metaverse scenario.

[0025] It can be understood that the Metaverse is a virtual space that can map the real world and is independent of the real world. Through technologies in multiple fields such as communications, finance, hardware, software, computer vision, and optics, the constructed Metaverse virtual scene can be accessed and used anytime and anywhere without being restricted by time and space.

[0026] It should be noted that the above-mentioned bank user data is also the data related to the user's bank transactions and bank services in the Metaverse scenario. Based on the different transaction types or service types, the bank user data can be divided into different data interaction types, which may specifically include transfer data, consumption data, red envelope data, relatives and friends related data, contact data, etc. The embodiments of the present application do not limit this.

[0027] It is understandable that processing bank user data through the Metaverse scenario can improve data processing efficiency and user experience. At the same time, in the Metaverse scenario, banks can use technologies such as smart contracts to conduct more stringent security management and compliance reviews of bank user data, thereby improving the privacy and security of bank user data and preventing data leakage and abuse. In addition, in the Metaverse scenario, banks can build virtual financial service scenarios to provide users with more convenient and comprehensive financial services. This virtual-real service model helps banks break the limitations of traditional physical space and achieve comprehensive coverage of financial services.

[0028] Step S20: constructing a relationship circle network of the user based on the bank user data.

[0029] It should be noted that based on the bank user data, different relationship circles of the user can be determined, thereby realizing the construction of the user's relationship circle network. Specifically, the above relationship circle network can include: transfer relationship circle network, consumption relationship circle network, relative and friend association relationship circle network, contact network, etc., which is not limited in the embodiment of the present application.

[0030] It needs to be explained that by building a relationship circle network, we can have a deeper understanding of users' social and consumption habits, so as to provide users with more personalized and more accurate services. At the same time, through the relationship circle network, banks can identify potential risk points, such as abnormal capital flow, etc., and through timely warning and intervention, it can help reduce risk losses. By networking bank user data into relationship circles, it not only helps to improve user experience and risk management level, but also provides banks with accurate marketing and cooperation opportunities.

[0031] In a specific implementation, the processing device can construct a user's relationship circle network based on bank user data. By analyzing the relationship circle network, it can better build a user portrait for the user and provide the user with more personalized and accurate services.

[0032] Step S30, performing network structure processing on the relationship circle network by a structural analysis method to obtain the account social network of the user; Step S40, obtaining user attribute data, and constructing a user profile of the user based on the user attribute data and the account social network.

[0033] It should be noted that structural analysis can be a systematic analysis method that uses graph theory and mathematical models to study the relationship between users, users and the network they are in, and networks and networks. Structural analysis can be used to analyze the relationship structure or attributes in social networks. In relationship circle networks and account social networks, a node can be regarded as a user and an organization (such as a merchant, commercial district, etc.). By focusing on the user's relationship circle network, the user's account social network can be determined, and the user's social behavior and characteristics can be understood, and the user's corresponding account social network can be established.

[0034] It should be explained that the user's account social network can be an alternative social network built based on the user's bank user data in financial scenarios. Through this account social network, it is easy to understand the user's transaction behavior, as well as the connection and association between users and users, and between users and merchants in economic activities. In the user's account social network, a node can represent a user or a merchant, and an edge can represent a transaction relationship between users or between users and merchants, such as a transfer relationship. Through the account social network, it can provide accurate and powerful support for the user's precision marketing and user profile.

[0035] It should be noted that the above user attribute data may include bank user data and user personal information data. The above personal information data may include personal information such as interest preferences and user age filled in by the user himself. When obtaining the user attribute data, a data authorization request may be initiated to the user terminal first. When the user terminal passes the data authorization request, the user attribute data may be sent to the processing device or an intermediate device connected to the processing device.

[0036] It is understandable that when the user's account social network and user attribute data are determined, a user profile of the user in the financial field can be constructed based on the user attribute data and the account social network.

[0037] In a specific implementation, the processing device can process the network structure of the relationship circle network based on the community discovery algorithm to obtain the user's account social network. The user's user portrait is constructed based on the account-related network and user attribute data, so that the user's financial transaction relationship, financial transaction method, financial transaction preference, etc. in the financial field can be clearly expressed, so that the bank can accurately recommend marketing activities for the user, which is helpful to build the user's virtual private bank. Users can use virtual reality devices such as VR glasses to view their personal data, user portraits, etc. in a private environment, and obtain marketing activities such as financial advice provided by the bank system.

[0038] The embodiment of the present application obtains the user's bank user data in the metaverse scenario; constructs the user's relationship circle network based on the bank user data; processes the relationship circle network through the structural analysis method to obtain the user's account social network; obtains the user's attribute data, and constructs the user's user profile based on the user attribute data and the account social network. Since the user's account social network is obtained by constructing the user's relationship circle network and processing the relationship circle network through the structural analysis method, the transaction data in each relationship circle of the user is analyzed, the accuracy of the user profile construction is improved, and the user profile of the user is constructed through the user attribute data and the account social network, which is convenient for providing users with accurate marketing activity recommendations.

[0039] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , Figure 2 A flowchart of Embodiment 2 of the method for processing bank user data based on the Metaverse scenario of the present application is provided. In the embodiment of the present application, the step of constructing the user's relationship circle network based on the bank user data includes: Step S21, determining a data interaction type based on the bank user data; Step S22, obtaining the data interaction type of the bank user data, constructing a mapping relationship for the bank user data, and obtaining a local network mapping; Step S23: constructing the relationship circle network of the user according to the local network mapping in the same data interaction type.

[0040] It should be noted that the data types of bank user data in the embodiment of the present application may include transfer data, consumption data, red envelope data, friends and relatives association data, etc., and the embodiment of the present application does not limit this. Based on bank user data of different data interaction types, the behavior types of users in different behaviors can be determined. For example, transfer data can correspond to user behavior with the behavior type of transfer, and consumption data can correspond to user behavior with the behavior type of consumption, etc.

[0041] It should be explained that when determining the data interaction type of the user, a mapping relationship can be constructed based on the data interaction type and the bank user data, thereby determining the local network mapping of the relationship circle network. Specifically, the step of obtaining the data interaction type of the bank user data and constructing a mapping relationship for the bank user data to obtain the local network mapping includes: taking the user as the first relationship node in the network; generating a second relationship node corresponding to the first relationship node based on the bank user data; determining the node mapping relationship between the first relationship node and the second relationship node based on the data interaction type of the bank user data; constructing a network relationship graph based on each of the node mapping relationships; and performing dimensionality reduction processing on the network relationship graph based on an adversarial autoencoder network to obtain a local network mapping.

[0042] It is understandable that a user's network relationship graph can be constructed based on the bank interaction data, and the network relationship graph may include several nodes. Among them, the user can be regarded as the first relationship node in the network relationship graph, and other users, merchants, merchant groups, etc. that interact with the user can be regarded as the second relationship node in the network relationship graph. The edge between the two relationship nodes can be regarded as the user behavior or relationship corresponding to the bank user data. Specifically, based on the bank user data, user behavior (such as transfer, consumption, etc.) or user relationship (such as common transfer relationship, uncommon transfer relationship, etc.) can be determined.

[0043] It should be noted that based on the first relationship node and the second relationship node, a node mapping relationship between nodes can be constructed. Different node mapping relationships can be constructed based on different bank user data, and the network relationship graph corresponding to the user can be determined based on these node mapping relationships.

[0044] In some implementations of the embodiments of the present application, in order to realize the conversion of a network relationship graph into a local network mapping, the embodiments of the present application propose an adversarial autoencoder network, through which the dimensionality reduction processing of the network relationship graph can be realized.

[0045] It should be noted that the above-mentioned adversarial autoencoder network is a coding network constructed based on the idea of ​​generative adversarial network. Figure 3 As shown, Figure 3 The network structure diagram of the adversarial autoencoding network in one implementation of the embodiment of the present application is shown in FIG. The adversarial autoencoding network includes an autoencoding module and an adversarial module.

[0046] It should be noted that Figure 3 As shown, the input data can be the above network relationship diagram, or it can be training data for training the adversarial autoencoder network. The input training data can include positive samples and negative samples to improve the learning efficiency of the network.

[0047] It is understandable that the self-encoding module includes an encoder and a decoder. By encoding the input data through the encoder, the implicit code of the network node in the low-dimensional implicit space can be obtained. Specifically, in order to improve the nonlinear information processing capability of the network, the encoder of the embodiment of the present application may include a nonlinear activation layer, which may include a nonlinear activation function ReLU, thereby realizing the mapping of the original network relationship graph to the low-dimensional implicit space to obtain the implicit code z . The decoder encodes the hidden z The original input is reconstructed to obtain reconstructed output data, which may be a local network map corresponding to the network relationship diagram.

[0048] It should be noted that the embodiment of the present application introduces adversarial training into the training process of the auto-encoding module. Specifically, the adversarial training process may include: applying a preset prior distribution to the implicit representation distribution obtained by the auto-encoding module, so that the distribution learned by the auto-encoding module is close to the preset distribution, restricting the implicit codes of similar network nodes to come from the same distribution, and obtaining the aggregated posterior distribution. This process is equivalent to adding an adversarial constraint term to the auto-encoding module using adversarial training. In order to achieve this process, the embodiment of the present application adds a discriminator on the basis of the auto-encoding module, and uses the encoder of the auto-encoding module as a generator, so that the aforementioned adversarial training process can be realized by the zero-sum game of the generator and the discriminator. By introducing adversarial training, similar inputs can be closer in the cause space, thereby avoiding the manifold fragmentation problem of the auto-encoding module, so that the module can learn the low-dimensional implicit representation of the network well, that is, obtain the local network mapping after dimensionality reduction processing.

[0049] It can be understood that when a low-dimensional local network mapping is obtained after dimensionality reduction processing, the user's low-dimensional relationship circle network can be constructed based on the local network mapping. By performing network structure processing on these relationship circle networks, the user's account social network can be obtained. Specifically, the structural analysis method includes a community discovery algorithm and a network node influence algorithm. The step of performing network structure processing on the relationship circle network by the structural analysis method to obtain the user's account social network includes: identifying the network structure in each of the relationship circle networks based on the community discovery algorithm to obtain the user's behavioral characteristics; constructing the user's overall relationship network diagram based on the behavioral characteristics; calculating the influence ratio of each relationship node in the overall relationship network diagram based on the network node influence algorithm; optimizing the network structure of the overall relationship network diagram based on the influence ratio to obtain the user's account social network.

[0050] It should be understood that the community discovery algorithm is a structural analysis method used to identify user relationships in a relationship circle network. The community discovery algorithm can divide the nodes in the network into different communities, so that the nodes within the community have a high internal connectivity, while the connectivity between communities is low, thereby making the connections between the nodes in each community closer. The community discovery algorithm helps to understand the structure and dynamics of the network, and thus facilitates the analysis of each relationship circle network.

[0051] Specifically, the community discovery algorithm used in the embodiments of the present application may include the SLPA algorithm, the Fast-Unfolding algorithm, the Girvan-Newman algorithm, etc., and the embodiments of the present application are not limited to this.

[0052] It should be noted that through the community discovery algorithm, the user's community identity in different relationship circle networks can be determined. Combined with consumption information such as consumption habits, consumption preferences, and social activity determined based on the user's bank user data, the user's behavioral characteristics can be obtained. The behavioral characteristics may include consumption frequency, consumption amount, consumption identity, etc. Based on the relationship circle network and the user's behavioral characteristics, each relationship circle network can be fused to obtain the user's overall relationship network diagram. Specifically, each relationship circle network can be regarded as a network structure centered on the node corresponding to the user. By taking the user node as the central node of the overall relationship network diagram, the node mapping relationship in the relationship circle network and the user's behavioral characteristics are integrated into the new network to obtain the overall relationship network diagram.

[0053] It is understandable that the network node influence algorithm can be a structural analysis method for evaluating the influence of nodes in the network on other nodes. In the embodiment of the present application, the network node influence algorithm used may include the HITS algorithm, the Closeness centrality algorithm, etc., which is not limited in the embodiment of the present application.

[0054] It should be noted that the network node influence algorithm can be used to evaluate the influence of users in the overall relationship network diagram. By combining the overall relationship network diagrams of each user, the global overall relationship network diagram can be obtained, and then the core nodes in the global overall relationship network diagram can be determined to achieve precise marketing activity recommendations for each user.

[0055] In some implementations of the embodiments of the present application, based on the influence of each node in the user's overall relationship network diagram, the importance of other second relationship nodes to the first relationship node corresponding to the user can also be determined, that is, the influence ratio of each relationship node in the overall relationship network diagram to the first relationship node can be determined.

[0056] It is understandable that when the influence ratio between the relationship nodes is determined, the network structure of the overall relationship network diagram can be optimized based on the influence ratio to obtain the user's account social network. Specifically, the step of optimizing the network structure of the overall relationship network diagram based on the influence ratio to obtain the user's account social network includes: sorting the relationship nodes in the overall relationship network diagram based on the influence ratio to obtain the sorted relationship nodes; dividing the sorted relationship nodes into influence levels according to preset division weights to obtain high-influence nodes, medium-influence nodes, low-influence nodes and no-influence nodes; when the influence ratio of the no-influence node is lower than the preset cleaning threshold, the no-influence node is cleaned; reconstructing the network based on the high-influence nodes, medium-influence nodes, low-influence nodes and the no-influence nodes after node cleaning to obtain the user's account social network.

[0057] It should be noted that the specific values ​​of the above-mentioned preset division weights can be selected based on the needs during use, and the embodiments of the present application are not limited to this.

[0058] In some implementations of the embodiments of the present application, for the division of influence levels, the preset division weight corresponding to the high-influence node can be 20%, the preset division weight corresponding to the medium-influence node can be 30%, the preset division weight corresponding to the low-influence node can be 30%, and the preset division weight corresponding to the no-influence node can be 20%. That is, for the sorted relationship nodes, the relationship nodes with influence ratio ranking in the top 20% can be divided into high-influence nodes, the relationship nodes with influence ratio ranking in the range of 20% to 50% can be divided into medium-influence nodes, the relationship nodes with influence ratio ranking in the range of 50% to 80% can be divided into low-influence nodes, and the relationship nodes with influence ratio ranking in the bottom 20% can be divided into no-influence nodes.

[0059] In some implementations of the embodiments of the present application, a preset cleaning threshold may be set, and the value of the preset cleaning threshold may be set based on the needs of the actual application. When the influence ratio of the non-influenced node is lower than the preset cleaning threshold, the non-influenced node may be cleaned out of the overall relationship network diagram of the user, but the non-influenced node is not processed in the global overall relationship network diagram.

[0060] It should be understood that the overall relationship network diagram of the user can be reconstructed based on the high-influence nodes, medium-influence nodes, low-influence nodes, and the nodes without influence after node cleaning, thereby obtaining the user's account social network.

[0061] The embodiment of the present application determines the data interaction type based on the bank user data; obtains the data interaction type of the bank user data to construct a mapping relationship for the bank user data to obtain a local network mapping; and constructs the user's relationship circle network according to the local network mapping in the same data interaction type. This achieves accurate understanding of customer needs, enhances the risk management capability of data, and realizes global network construction based on a social network that can be based on multiple users, thereby conducting precision marketing and potential user discovery.

[0062] Based on the first embodiment and / or the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those of the above-mentioned first embodiment and / or the second embodiment can refer to the above introduction, and will not be repeated later. Figure 4 , Figure 4 A flowchart of Embodiment 3 of the method for processing bank user data based on the Metaverse scenario of this application is provided. In this embodiment of the application, the step of obtaining user attribute data and constructing a user portrait of the user based on the user attribute data and the account social network includes: Step S41, obtaining user attribute data, and performing labeling processing based on the user attribute data to obtain a user data label; Step S42, embedding the user data label into the first relationship node corresponding to the user in the account social network to obtain a labeled relationship node; Step S43: generating a user portrait of the user according to the account social network and the labeled relationship nodes.

[0063] It should be noted that the above user attribute data may include bank user data and user personal information data. The above personal information data may include personal information such as interest preferences and user age filled in by the user himself. By collecting the user's attribute data, they can be processed and converted into user data tags. By embedding these user data tags into the first relationship node corresponding to the user in the account social network or the global overall relationship network, the labeled relationship node can be obtained.

[0064] It is understandable that the user's user profile can be obtained by visualizing the user's account social network and the user's labeled relationship nodes. The user profile can be used to characterize the user's consumption habits, consumption frequency, consumption preferences, consumption areas and other information. The user can view the user profile, account social network and other personal data in a private environment through virtual reality devices such as VR glasses, and obtain suggestions provided by the banking system.

[0065] The embodiment of the present application obtains user data labels by labeling based on user attribute data; embeds the user data label into the first relationship node corresponding to the user in the account social network to obtain a labeled relationship node; and generates a user portrait of the user based on the account social network and the labeled relationship node. Since the user's financial behavior and preferences are deeply understood through bank user data, and a relationship circle network is constructed to determine the financial relationship and relationship strength between the user and other individuals or merchants, the relationship circle network is processed by structural analysis, so that the generated user portrait can be more accurate. By generating user data labels based on user attribute data, the user portrait is enriched, making the generated user portrait more comprehensive.

[0066] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the bank user data processing method based on the metaverse scenario of the present application. More forms of simple transformations based on this technical concept are all within the scope of protection of the present application.

[0067] This application also provides a bank user data processing device based on the metaverse scenario, please refer to Figure 5 , the bank user data processing device based on the metaverse scenario includes: A data acquisition module 10 is used to acquire the bank user data of the user in the Metaverse scenario; A network construction module 20, configured to construct a relationship circle network of the user based on the bank user data; A network processing module 30 is used to perform network structure processing on the relationship circle network by a structural analysis method to obtain the account social network of the user; The portrait generation module 40 is used to obtain user attribute data and build a user portrait of the user based on the user attribute data and the account social network.

[0068] The bank user data processing device based on the Metaverse scenario provided by the present application adopts the bank user data processing method based on the Metaverse scenario in the above embodiment, which can solve the technical problem of inaccurate user portrait construction. Compared with the prior art, the beneficial effects of the bank user data processing device based on the Metaverse scenario provided by the present application are the same as the beneficial effects of the bank user data processing method based on the Metaverse scenario provided by the above embodiment, and the other technical features of the bank user data processing device based on the Metaverse scenario are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0069] The present application provides a bank user data processing device based on a metaverse scenario, and the bank user data processing device based on a metaverse scenario includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the bank user data processing method based on the metaverse scenario in the above-mentioned embodiment one.

[0070] Reference below Figure 6 , which shows a schematic diagram of the structure of a bank user data processing device based on a metaverse scenario suitable for implementing an embodiment of the present application. The bank user data processing device based on a metaverse scenario in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The bank user data processing device based on the metaverse scenario shown is merely an example and should not bring any limitations to the functions and scope of use of the embodiments of the present application.

[0071] like Figure 6As shown, the bank user data processing device based on the metaverse scenario may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the bank user data processing device based on the metaverse scenario are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the bank user data processing device based on the metaverse scenario to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a bank user data processing device based on the metaverse scenario with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0072] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0073] The bank user data processing device based on the Metaverse scenario provided by the present application adopts the bank user data processing method based on the Metaverse scenario in the above embodiment, which can solve the technical problem of inaccurate user portrait construction. Compared with the prior art, the beneficial effects of the bank user data processing device based on the Metaverse scenario provided by the present application are the same as the beneficial effects of the bank user data processing method based on the Metaverse scenario provided by the above embodiment, and the other technical features of the bank user data processing device based on the Metaverse scenario are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0074] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0075] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0076] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the bank user data processing method based on the metaverse scenario in the above-mentioned embodiment.

[0077] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0078] The above-mentioned computer-readable storage medium may be included in a bank user data processing device based on a metaverse scenario; or it may exist independently without being assembled into a bank user data processing device based on a metaverse scenario.

[0079] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the bank user data processing device based on the Metaverse scenario, the bank user data processing device based on the Metaverse scenario: Obtain the user's bank user data in the Metaverse scenario; Building a relationship circle network of the user based on the bank user data; Performing network structure processing on the relationship circle network by a structural analysis method to obtain the account social network of the user; User attribute data is obtained, and a user profile of the user is constructed based on the user attribute data and the account social network.

[0080] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0081] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0082] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0083] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for processing bank user data based on the metaverse scenario, and can solve the technical problem of inaccurate user portrait construction. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the method for processing bank user data based on the metaverse scenario provided in the above-mentioned embodiment, and will not be elaborated here.

[0084] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned bank user data processing method based on the metaverse scenario.

[0085] The computer program product provided by this application can solve the technical problem of inaccurate user portrait construction. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the bank user data processing method based on the metaverse scenario provided by the above embodiment, which will not be repeated here.

[0086] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for processing bank user data based on a metaverse scenario, characterized in that: The method comprises: Obtain the user's bank user data in the Metaverse scenario; Building a relationship circle network of the user based on the bank user data; Performing network structure processing on the relationship circle network by a structural analysis method to obtain the account social network of the user; User attribute data is obtained, and a user profile of the user is constructed based on the user attribute data and the account social network.

2. The method for processing bank user data based on the metaverse scenario as claimed in claim 1, characterized in that: The step of constructing the user's relationship circle network based on the bank user data includes: Determining a data interaction type based on the bank user data; Acquire the data interaction type of the bank user data, construct a mapping relationship for the bank user data, and obtain a local network mapping; The relationship circle network of the user is constructed according to the local network mapping in the same data interaction type.

3. The method for processing bank user data based on the metaverse scenario as claimed in claim 2, characterized in that: The structural analysis method includes a community discovery algorithm and a network node influence algorithm. The step of performing network structure processing on the relationship circle network by the structural analysis method to obtain the user's account social network includes: Identifying the network structure in each of the relationship circle networks based on a community discovery algorithm to obtain the behavioral characteristics of the user; Constructing an overall relationship network diagram of the user according to the behavioral characteristics; Calculate the influence ratio of each relationship node in the overall relationship network diagram based on the network node influence algorithm; The network structure of the overall relationship network diagram is optimized based on the influence ratio to obtain the account social network of the user.

4. The method for processing bank user data based on the metaverse scenario as claimed in claim 3, characterized in that: The step of optimizing the network structure of the overall relationship network diagram based on the influence ratio to obtain the user's account social network includes: Sorting the relationship nodes in the overall relationship network diagram based on the influence proportions to obtain the sorted relationship nodes; The influence levels of the sorted relationship nodes are divided according to the preset division weights to obtain high-influence nodes, medium-influence nodes, low-influence nodes and no-influence nodes; When the influence ratio of the non-influenced node is lower than a preset cleaning threshold, performing node cleaning on the non-influenced node; A network is reconstructed based on the high-influence nodes, the medium-influence nodes, the low-influence nodes, and the non-influence nodes after node cleaning to obtain the account social network of the user.

5. The method for processing bank user data based on the metaverse scenario as claimed in claim 2, characterized in that: The step of acquiring the data interaction type of the bank user data, constructing a mapping relationship for the bank user data, and obtaining a local network mapping includes: Taking the user as the first relationship node in the network; generating a second relationship node corresponding to the first relationship node based on the bank user data; determining a node mapping relationship between the first relationship node and the second relationship node based on a data interaction type of the bank user data; Constructing a network relationship diagram based on the node mapping relationships; The network relationship graph is subjected to dimensionality reduction processing based on an adversarial autoencoder network to obtain a local network mapping.

6. The method for processing bank user data based on the metaverse scenario as claimed in claim 1, characterized in that: The step of obtaining user attribute data and constructing a user profile of the user based on the user attribute data and the account social network includes: Acquire user attribute data, and perform labeling processing based on the user attribute data to obtain user data labels; Embedding the user data label into a first relationship node corresponding to the user in the account social network to obtain a labeled relationship node; A user portrait of the user is generated according to the account social network and the labeled relationship nodes.

7. A bank user data processing device based on the metaverse scenario, characterized in that: The bank user data processing device based on the metaverse scenario includes: The data acquisition module is used to obtain the bank user data of the user in the Metaverse scenario; A network construction module, used to construct a relationship circle network of the user based on the bank user data; A network processing module, used to perform network structure processing on the relationship circle network by a structural analysis method to obtain the account social network of the user; The portrait generation module is used to obtain user attribute data and build a user portrait of the user based on the user attribute data and the account social network.

8. A bank user data processing device based on the Metaverse scenario, characterized in that: The device includes: a memory, a processor, and a bank user data processing program based on a metaverse scenario stored in the memory and executable on the processor, wherein the bank user data processing program based on a metaverse scenario is configured to implement the steps of a bank user data processing method based on a metaverse scenario as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a bank user data processing program based on the Metaverse scenario, and when the bank user data processing program based on the Metaverse scenario is executed by the processor, the steps of the bank user data processing method based on the Metaverse scenario as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, which, when executed by a processor, implements the steps of the bank user data processing method based on the metaverse scenario as described in any one of claims 1 to 6.

Images