User screening method, device, electronic device and storage medium

Abstract

The present invention discloses a user screening method, device, electronic device and storage medium. Based on the historical user data authorized to be obtained within a set time, a user transaction network model is constructed by univariate analysis and graph calculation methods, and the nodes in the user transaction network model include a first user and a second user; for each second node, the recommendation index value corresponding to the second node is determined based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node; and the second user who meets the preset conditions is screened as the target user according to the recommendation index value. By constructing a user transaction network model, the connection relationship between the first user and the second user can be obtained. By determining the recommendation index value of each second node, the target user who meets the preset conditions can be screened as a new user that can be expanded, avoiding the low accuracy and efficiency of the manual method, and improving the accuracy and efficiency of new user expansion.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular to a user screening method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of the financial industry, many financial institutions such as banks will expand new users through various channels to increase their own user holdings in order to develop their business.

[0003] At present, the traditional method of expanding new users is to adopt manual methods, specifically, to recommend financial products or services to potential user groups based on the personal experience or connections of business personnel in order to expand them into new users, where potential user groups can refer to groups that have a certain possibility of becoming new users of financial institutions. However, the use of this manual method to expand new users will lead to inaccurate positioning of potential user groups due to the uneven capabilities of business personnel themselves, such as insufficient personal experience or connections of business personnel, which will further affect the efficiency of new user expansion.

[0004] Therefore, how to improve the efficiency of new user development is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present invention provides a user screening method, device, electronic equipment and storage medium to improve the efficiency of screening users.

[0006] According to one aspect of the present invention, a user screening method is provided, comprising:

[0007] Based on the historical user data authorized and obtained within a set time, a user transaction network model is constructed by univariate analysis and graph calculation methods, wherein the nodes in the user transaction network model include a first user and a second user, the types of business processing institutions to which the first user and the second user belong are different, the second user is the user with whom the first user transacts when processing business at the business processing institution, the node corresponding to the first user is a first node, and the node corresponding to the second user is a second node;

[0008] For each second node, determining a recommendation index value corresponding to the second node based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node;

[0009] A second user who meets a preset condition is selected as a target user according to the recommendation index value, wherein the preset condition is that the recommendation index value is greater than a preset threshold.

[0010] According to another aspect of the present invention, there is provided a user screening device, comprising:

[0011] A construction module, used to construct a user transaction network model through univariate analysis and graph calculation methods based on historical user data authorized to be obtained within a set time, wherein the nodes in the user transaction network model include a first user and a second user, the types of business processing institutions to which the first user and the second user belong are different, the second user is a user with whom the first user transacts when conducting business at the business processing institution, the node corresponding to the first user is a first node, and the node corresponding to the second user is a second node;

[0012] A determination module, configured to determine, for each second node, a recommendation index value corresponding to the second node based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node;

[0013] A screening module is used to screen second users who meet preset conditions as target users according to the recommendation index value, wherein the preset condition is that the recommendation index value is greater than a preset threshold.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the user screening method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user screening method described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention is to first construct a user transaction network model based on the historical user data authorized within a set time through univariate analysis and graph calculation methods. The nodes in the user transaction network model include a first user and a second user. The types of business handling institutions to which the first user and the second user belong are different. The second user is the user traded by the first user when handling business in the business handling institution. The node corresponding to the first user is the first node, and the node corresponding to the second user is the second node; then for each second node, the recommended index value corresponding to the second node is determined based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node; finally, the second user who meets the preset conditions is selected as the target user according to the recommended index value, wherein the preset condition is that the recommended index value is greater than the preset threshold. The method can obtain the connection relationship between the first user and the second user by constructing the user transaction network model, and then by determining the recommended index value of the second node corresponding to each second user, the target user who meets the preset conditions can be selected based on the recommended index value as a new user that can be expanded, thereby avoiding the low accuracy and efficiency of the manual method, and effectively improving the accuracy and efficiency of new user expansion.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A flowchart of a user screening method is provided for the first embodiment of the present invention;

[0023] Figure 2 A flowchart of a user screening method provided in Embodiment 2 of the present invention;

[0024] Figure 3 A schematic diagram of the structure of a user screening device provided in Embodiment 3 of the present invention;

[0025] Figure 4 A schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1 A flowchart of a user screening method is provided for the first embodiment of the present invention. This embodiment is applicable to the case of screening users. The method can be executed by a user screening device. The user screening device can be implemented in the form of hardware and / or software. The user screening device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0030] S110. Based on the historical user data authorized within a set time, a user transaction network model is constructed through univariate analysis and graph calculation methods, wherein the nodes in the user transaction network model include a first user and a second user, the node corresponding to the first user is a first node, and the node corresponding to the second user is a second node.

[0031] The first user and the second user belong to different types of business processing institutions, and the second user is the user with whom the first user transacts when conducting business at the business processing institution.

[0032] In this embodiment, with the rapid development of the financial industry, many financial institutions such as banks will expand new users through various channels to increase their own user holdings in order to develop their business. Taking banks as an example, in order to expand new users, banks can use the method provided in this embodiment to expand users who do not belong to the bank into new users of the bank. On this basis, historical user data can be understood as business data associated with the users held by the business handling agency that wants to expand new users before the current moment; it should be noted that the historical user data is authorized and stored by the user. Business handling agencies can be understood as agencies that provide users with various business handling functions, such as banks and other institutions. Historical user data may include basic user information, user asset information, user transaction information, and user product holding information of users held by business handling agencies.

[0033] Among them, user basic information may refer to the relevant information required when a user registers as a new user of a certain business processing institution; for example, if the user is an individual, the corresponding user basic information may be the user's name, address, ID card information, etc.; if the user is an enterprise, the corresponding user basic information may be the user's enterprise registration name, registered address, enterprise holding and shareholding information, enterprise actual controller information, etc. User asset information may refer to information related to lending between the user and the business processing institution; for example, user asset information may be user guarantee information, user collateral information, etc. Among them, user guarantee information may refer to the information of the individual or enterprise that guarantees the user, and user collateral information may refer to the movable or immovable asset information pledged by the user. User transaction information may refer to the related information of the user's fund transaction with his or her counterparty through the corresponding business processing institution. For example, user transaction information may be information such as the user's fund inflow or fund outflow. The user's counterparty may be an individual or an enterprise. User product holding information may refer to the information on the user's holding of the business processing institution's public products, wherein the business processing institution's public products can be understood as financial service products related to deposits, loans, etc. launched by the business processing institution.

[0034] It should be noted that in this embodiment, the specific information content included in the historical user data is not limited and can be flexibly set according to actual needs.

[0035] Univariate analysis, also known as "univariate statistical analysis", refers to the description and statistics of the characteristics and laws of the distribution of a single variable at a point in time by collating, processing, organizing and displaying the data of a single variable, and calculating indicators that reflect the central tendency and dispersion of the data. A single variable can be understood as a single variable parameter. For example, a sub-information in the basic information of a user, such as information on corporate holdings and equity participation, can belong to a single variable, so historical user data can include multiple single variables. Graph computing methods can refer to a method of modeling data in the form of a graph to obtain results that were difficult to obtain from a flat perspective in the past. Among them, a graph can be an abstract data structure used to represent the relationship between objects, consisting of nodes and edges: nodes represent objects, and edges represent the relationship between objects.

[0036] Assuming that the business handling institution that wants to expand new users is Bank A, the user transaction network model can be understood as a graph network model that includes existing users of Bank A and their corresponding non-Bank A users, as well as the edges that represent the transaction relationship between the two. Among them, the nodes in the user transaction network model can refer to each object contained in the user transaction network model, that is, existing users of Bank A and their corresponding non-Bank A users. The nodes in the user transaction network model can include the first user and the second user. The types of business handling institutions to which the first user and the second user belong are different. It can be understood that the first user belongs to Bank A, and the second user does not belong to Bank A, such as Bank B; that is, Bank A and Bank B are two different types of business handling institutions. On this basis, the first user can refer to an existing user of Bank A; the second user can refer to the user with whom the first user trades when handling business at this business handling institution (i.e. Bank A), that is, the corresponding non-Bank A user. In the user transaction network model, the node corresponding to the first user can be called the first node, and the node corresponding to the second user can be called the second node.

[0037] Taking the enterprise holding and participating information in the user basic information as an example, if there may be some first users in the enterprise holding and participating information, and the corresponding holding or participating persons do not belong to the same business handling institution as the first user, then these holding or participating persons can be considered as the second users corresponding to the first user. It is understandable that each first user can correspond to one or more second users.

[0038] In this embodiment, based on the historical user data authorized to be obtained within a set time, a user transaction network model can be constructed through univariate analysis and graph calculation methods. Exemplarily, first, data analysis and processing can be performed on each single variable in the historical user data through univariate analysis; then, for each single variable, based on the data processing results obtained by the univariate analysis, a corresponding graph network model can be obtained through a graph calculation method; finally, the graph network models corresponding to all single variables are correspondingly fused to obtain a user transaction network model. For example, univariate analysis and graph calculation are performed on the enterprise holding and shareholding information in the user basic information to obtain a graph network model 1 including the first user A and its corresponding second users A and B, and univariate analysis and graph calculation are performed on the user guarantee information in the user asset information to obtain a graph network model 2 of the first user A and its corresponding second users A, C and D. On this basis, the fusion of graph network model 1 and graph network model 2 can be understood as the integration of the second user corresponding to the first user A, that is, the fused user transaction network model includes the first user A and its corresponding second users A, B, C and D.

[0039] S120. For each second node, determine a recommendation index value corresponding to the second node based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node.

[0040] In this embodiment, the nodes in the user transaction network model may include a first node and a second node. The degree corresponding to each first node or second node may refer to the number of edges connected to the node in the user transaction network model. The transaction scale information corresponding to the second node may be understood as information characterizing the transaction volume between the second node and the corresponding first node, wherein the transaction volume may be understood as the size of the transaction amount. The transaction frequency information corresponding to the second node may be understood as information characterizing the number of transactions between the second node and the corresponding first node. The recommendation index value may refer to a value characterizing the degree to which the second node can be recommended as a user to be expanded. The higher the recommendation index value, the more suitable the corresponding second node is as a user to be expanded. The user to be expanded may be understood as a user waiting to be expanded to become a new user of the business processing agency to which the first node belongs.

[0041] Exemplarily, the recommendation index value corresponding to each second node can be determined by three index values, namely, the association index value, the transaction scale index value, and the transaction frequency index value. Among them, the association index value can refer to the index information determined based on the degree corresponding to the second node, which is used to characterize the direct influence of the second node on the corresponding first node. The corresponding association index value can be determined based on the size of the degree corresponding to the second node, wherein the larger the degree corresponding to the second node, the greater the direct influence of the second node on the corresponding first node, and the larger the corresponding association index value.

[0042] The transaction scale index value may refer to index information determined based on transaction scale information and used to characterize the indirect influence of the second node on the corresponding first node. Based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction scale information corresponding to the second node, the transaction scale index value corresponding to the second node may be determined; wherein the larger the transaction scale index value, the greater the indirect influence of the corresponding second node on the corresponding first node.

[0043] The transaction frequency index value may refer to index information determined based on the transaction frequency information and used to characterize the indirect influence of the second node on the corresponding first node. Based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction frequency information corresponding to the second node, the transaction frequency index value corresponding to the second node may be determined; wherein the larger the transaction frequency index value, the greater the indirect influence of the corresponding second node on the corresponding first node.

[0044] It is understandable that a second node may correspond to a correlation index value, a transaction scale index value and a transaction frequency index value. On this basis, the recommended index value corresponding to the second node can be determined according to these three index values. This embodiment limits the way of determining the corresponding recommended index value according to the correlation index value, the transaction scale index value and the transaction frequency index value. For example, the average of the correlation index value, the transaction scale index value and the transaction frequency index value of the second node can be used as the corresponding recommended index value; or the weighted average of the correlation index value, the transaction scale index value and the transaction frequency index value of the second node can be used as the corresponding recommended index value; or the difference between the correlation index value of the second node and the minimum value of each correlation index value and the difference between the maximum value of each correlation index value and the minimum value of each correlation index value can be used as the ratio 1. Similarly, the ratio 2 obtained based on the transaction scale index value and the ratio 3 obtained based on the transaction frequency index value can be obtained. On this basis, the average or weighted average of the ratio 1, the ratio 2 and the ratio 3 can be used as the corresponding recommended index value.

[0045] In this embodiment, for each second node, based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node, the corresponding three index values ​​can be determined, namely the association index value, the transaction scale index value and the transaction frequency index value; on this basis, the corresponding recommended index value can be determined by which index value it is, and one second node can correspond to one recommended index value.

[0046] S130. Filter a second user who meets a preset condition as a target user according to the recommendation index value, wherein the preset condition is that the recommendation index value is greater than a preset threshold.

[0047] In this embodiment, the preset condition may refer to a pre-set condition for screening target users. For example, the preset condition may be that the recommendation index value is greater than a preset threshold. The preset threshold may refer to a pre-set threshold, and the specific value of the preset threshold may be flexibly set according to actual needs. The target user may be understood as a user selected from all second users as a user to be expanded.

[0048] According to the recommendation index value of each second node, a second user meeting a preset condition, that is, a second user whose recommendation index value is greater than a preset threshold, is taken as a target user.

[0049] This embodiment 1 provides a user screening method, firstly, based on the historical user data authorized to be obtained within a set time, a user transaction network model is constructed by univariate analysis and graph calculation method, the nodes in the user transaction network model include a first user and a second user, the types of business handling institutions to which the first user and the second user belong are different, the second user is the user traded by the first user when handling business in the business handling institution, the node corresponding to the first user is the first node, and the node corresponding to the second user is the second node; then, for each second node, the recommended index value corresponding to the second node is determined based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node; finally, the second user who meets the preset conditions is selected as the target user according to the recommended index value, wherein the preset condition is that the recommended index value is greater than the preset threshold. The method can obtain the connection relationship between the first user and the second user by constructing the user transaction network model, and then by determining the recommended index value of the second node corresponding to each second user, the target user who meets the preset conditions can be selected based on the recommended index value as a new user that can be expanded, thereby avoiding the situation of low accuracy and efficiency of manual methods, and effectively improving the accuracy and efficiency of new user expansion.

[0050] Embodiment 2

[0051] Figure 2 This is a flowchart of a user screening method provided in the second embodiment of the present invention. The second embodiment is refined on the basis of the above embodiments. In this embodiment, the process of building a user transaction network model, determining the recommendation index value corresponding to the second node, and determining and issuing a target user list is described in detail. It should be noted that the technical details not described in detail in this embodiment can be referred to any of the above embodiments. Figure 2 As shown, the method includes:

[0052] S210: Based on each univariate information in the historical user data, a corresponding sub-network model is constructed through univariate analysis and graph calculation methods, wherein one univariate information corresponds to one sub-network model.

[0053] In this embodiment, the historical user data may include basic user information, user asset information, user transaction information, and user product holding information corresponding to the first user. Among them, the basic user information, user asset information, user transaction information, or user product holding information may include multiple single variable information. Based on each single variable information in the historical user data, a corresponding sub-network model can be constructed through single variable analysis and graph calculation methods. The sub-network model can be understood as a network model that includes the first user and the second user, and the connection relationship between the two, determined based on a single variable information. Among them, a single variable information can correspond to a sub-network model

[0054] Optionally, historical user data includes user basic information, user asset information, user transaction information and user product holding information corresponding to the first user; the user basic information includes at least one first sub-information as univariate information, the first sub-information represents the user basic information; the user asset information includes at least one second sub-information as univariate information, the second sub-information represents the user asset information; the user transaction information includes at least one third sub-information as univariate information, the third sub-information represents the user transaction information; the user product holding information includes at least one fourth sub-information as univariate information, the fourth sub-information represents the user product holding information.

[0055] Among them, the user basic information may include at least one first sub-information as univariate information, and the first sub-information can be used to characterize the user basic information. For example, the first sub-information can be the user's corporate registration name, registered address, or corporate holding and shareholding information in the above embodiment.

[0056] The user asset information may include at least one second sub-information as univariate information. The second sub-information may be used to characterize the user asset information. For example, the second sub-information may be the user guarantee information, user collateral information, etc. in the above-mentioned embodiment.

[0057] The user transaction information class may include at least one third sub-information as univariate information. The third sub-information may be used to characterize the user transaction information. For example, the third sub-information may be information such as the user's capital inflow or capital outflow in the above-mentioned embodiment.

[0058] The user product holding information may include at least one fourth sub-information as univariate information, and the fourth sub-information may be used to characterize the user product holding information. For example, the fourth sub-information may be information such as the user's holding of public products of the business handling agency in the above embodiment.

[0059] S220: The sub-network models are integrated to generate a user transaction network model. The nodes in the user transaction network model include a first user and a second user. The node corresponding to the first user is a first node, and the node corresponding to the second user is a second node.

[0060] In this embodiment, the connection relationship between the first user and the second user included in each sub-network model is integrated to generate a user transaction network model. Among them, the nodes in the user transaction network model may include the first user and the second user, the node corresponding to the first user is the first node, and the node corresponding to the second user is the second node. The types of business processing institutions to which the first user and the second user belong are different, and the second user can be understood as the user with whom the first user trades when conducting business in this business processing institution.

[0061] S230. For each second node, determine a correlation index value corresponding to the second node based on the degree corresponding to the second node.

[0062] In this embodiment, for each second node in the user transaction network model, the correlation index value corresponding to the second node may be determined based on the degree corresponding to the second node.

[0063] For example, the calculation formula of the correlation index value can be:

[0064] D0(i)=ln(degree(i)+1);

[0065] Wherein, D0(i) may represent the association index value of the second node i; degree(i) may represent the degree corresponding to the second node i.

[0066] S240: Determine a transaction scale index value corresponding to the second node based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction scale information corresponding to the second node.

[0067] In this embodiment, the transaction scale index value corresponding to the second node may be determined based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction scale information corresponding to the second node.

[0068] For example, the calculation formula of the transaction size index value can be:

[0069] D1(i)=ln(1+∑ j (AMT(i,j)×degree(j)));

[0070] Where D1(i) can represent the transaction scale index value of the second node i; AMT(i,j) can represent the transaction scale information corresponding to the second node i, that is, the total transaction volume between the second node i and the corresponding first node j; degree(j) can represent the degree corresponding to the first node j. j∈all first nodes; i∈all second nodes.

[0071] S250: Determine a transaction frequency index value corresponding to the second node based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction frequency information corresponding to the second node.

[0072] In this embodiment, the transaction frequency index value corresponding to the second node may be determined based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction frequency information corresponding to the second node.

[0073] For example, the calculation formula for the transaction frequency index value can be:

[0074] D2(i)=ln(1+∑ j (NUM(i,j)×degree(j)));

[0075] Among them, D2(i) can represent the transaction frequency index value corresponding to the second node i; NUM(i,j) can represent the transaction frequency information corresponding to the second node i, that is, the total number of transactions between the second node i and the corresponding first node j.

[0076] S260: Determine a recommendation index value corresponding to the second node based on the association index value, the transaction scale index value, and the transaction frequency index value.

[0077] In this embodiment, the recommended index value corresponding to the second node can be determined based on the association index value, the transaction scale index value and the transaction frequency index value. Wherein, one second node can correspond to one association index value, one transaction scale index value and one transaction frequency index value.

[0078] Optionally, determining the recommended index value corresponding to the second node based on the association index value, the transaction scale index value and the transaction frequency index value includes: for each second node, taking the ratio of the difference between the association index value corresponding to the second node and the first minimum value to the difference between the first maximum value and the first minimum value as the first sub-value; taking the ratio between the difference between the transaction scale index value corresponding to the second node and the second minimum value to the difference between the second maximum value and the second minimum value as the second sub-value; taking the ratio between the difference between the transaction frequency index value corresponding to the second node and the third minimum value to the difference between the third maximum value and the third minimum value as the third sub-value; taking the average value of the first sub-value, the second sub-value and the third sub-value as the recommended index value corresponding to the second node;

[0079] Among them, the first minimum value and the first maximum value can be the minimum value and the maximum value of each correlation index value; the second minimum value and the second maximum value can be the minimum value and the maximum value of each transaction scale index value; the third minimum value and the third maximum value can be the minimum value and the maximum value of each transaction frequency index value.

[0080] The calculation formula for determining the recommendation index value corresponding to the second node based on the association index value, the transaction scale index value, and the transaction frequency index value may be:

[0081]

[0082] Here, R(i) may represent the recommendation index value corresponding to the second node i.

[0083] S270: Filter a second user who meets a preset condition as a target user according to the recommendation index value, wherein the preset condition is that the recommendation index value is greater than a preset threshold.

[0084] In this embodiment, second users meeting a preset condition may be screened out from all second users according to the recommendation index value as target users, wherein the preset condition may be that the recommendation index value is greater than a preset threshold value.

[0085] S280. Match a corresponding target business processing organization according to the area code information of the first user of the target user corresponding transaction.

[0086] In this embodiment, the region code information may refer to information representing the region to which the first user belongs, such as the region information may be information of provinces and cities such as Tianjin and Beijing. According to the region code information of the first user to which the target user corresponds to the transaction, a business processing organization of the same type as the business processing organization corresponding to the first user in the region represented by the region code information may be matched as the target business processing organization.

[0087] S290: Send the user list consisting of the target users to the target business processing organization for processing.

[0088] In this embodiment, the user list consisting of target users can be understood as organizing the target users belonging to the same target business processing organization into a user list based on all the screened target users, and sending the user list to the corresponding target business processing organization, so that the target business processing organization can carry out corresponding new user expansion according to the user list.

[0089] This second embodiment provides a user screening method, which specifically describes the process of constructing a user transaction network model, determining the recommended index value corresponding to the second node, and determining and sending the target user list. This method can determine the connection relationship between the first user and the second user by constructing a user transaction network model, and then determine the corresponding recommended index value based on the three indexes of each second node determined. It can screen out target users that meet the preset conditions based on the recommended index value as new users that can be expanded, thereby avoiding the low accuracy and efficiency of manual methods; on this basis, it can also effectively improve the accuracy and efficiency of new user expansion by classifying the target user list and sending it to the corresponding target business processing agency.

[0090] Embodiment 3

[0091] Figure 3 This is a schematic diagram of the structure of a user screening device provided by Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a construction module 310, a determination module 320 and a screening module 330;

[0092] Among them, the construction module 310 is used to construct a user transaction network model through univariate analysis and graph calculation methods based on the historical user data authorized to be obtained within a set time, wherein the nodes in the user transaction network model include a first user and a second user, the types of business processing institutions to which the first user and the second user belong are different, the second user is the user with whom the first user transacts when conducting business at the business processing institution, the node corresponding to the first user is the first node, and the node corresponding to the second user is the second node;

[0093] A determination module 320, configured to determine, for each second node, a recommendation index value corresponding to the second node based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node;

[0094] The screening module 330 is used to screen second users who meet a preset condition as target users according to the recommendation index value, wherein the preset condition is that the recommendation index value is greater than a preset threshold.

[0095] The third embodiment provides a user screening device, firstly, through the construction module 310, based on the historical user data authorized and obtained within a set time, a user transaction network model is constructed by univariate analysis and graph calculation method, the nodes in the user transaction network model include a first user and a second user, the first user and the second user belong to different types of business processing institutions, the second user is the user traded by the first user when conducting business in the current business processing institution, the node corresponding to the first user is the first node, and the node corresponding to the second user is the second node; then, through the determination module 320, for each second node, based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node, the recommendation index value corresponding to the second node is determined; finally, through the screening module 330, according to the recommendation index value, the second user who meets the preset conditions is screened as the target user, wherein the preset condition is that the recommendation index value is greater than the preset threshold. The device can obtain the connection relationship between the first user and the second user by constructing a user transaction network model, and then by determining the recommendation index value of the second node corresponding to each second user, it can screen out target users that meet preset conditions based on the recommendation index value as new users that can be expanded, thereby avoiding the low accuracy and efficiency of manual methods and effectively improving the accuracy and efficiency of new user expansion.

[0096] Optionally, the historical user data includes basic user information, user asset information, user transaction information, and user product holding information corresponding to the first user;

[0097] The user basic information includes at least one first sub-information as univariate information, and the first sub-information represents the user basic information;

[0098] The user asset information includes at least one second sub-information as univariate information, wherein the second sub-information represents the user asset information;

[0099] The user transaction information includes at least one third sub-information as univariate information, and the third sub-information represents the user transaction information;

[0100] The user product holding information includes at least one fourth sub-information as univariate information, and the fourth sub-information represents the user product holding information.

[0101] Optionally, building module 310 includes:

[0102] A construction unit, configured to construct a corresponding sub-network model based on each univariate information in the historical user data by univariate analysis and graph calculation method, wherein one univariate information corresponds to one sub-network model;

[0103] A fusion unit is used to fuse the sub-network models to generate the user transaction network model.

[0104] Optionally, the determination module 320 includes:

[0105] A first determining unit, configured to determine, for each second node, a relevance index value corresponding to the second node based on the degree corresponding to the second node;

[0106] A second determining unit, configured to determine a transaction scale index value corresponding to the second node based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction scale information corresponding to the second node;

[0107] A third determining unit, configured to determine a transaction frequency index value corresponding to the second node based on the degree corresponding to the first node having a transaction corresponding to the second node and the transaction frequency information corresponding to the second node;

[0108] a fourth determining unit, configured to determine a recommendation index value corresponding to the second node based on the association index value, the transaction scale index value, and the transaction frequency index value;

[0109] Among them, one second node corresponds to one association index value, one transaction scale index value and one transaction frequency index value.

[0110] Optionally, the fourth determining unit is specifically configured to:

[0111] For each second node, taking the ratio of the difference between the association index value corresponding to the second node and the first minimum value and the difference between the first maximum value and the first minimum value as the first sub-value;

[0112] The ratio between the difference between the transaction scale index value corresponding to the second node and the second minimum value and the difference between the second maximum value and the second minimum value is used as the second sub-value;

[0113] The ratio between the difference between the transaction frequency index value corresponding to the second node and the third minimum value and the difference between the third maximum value and the third minimum value is used as the third sub-value;

[0114] taking an average value of the first sub-value, the second sub-value and the third sub-value as a recommendation index value corresponding to the second node;

[0115] Among them, the first minimum value and the first maximum value are the minimum value and the maximum value of each of the association index values; the second minimum value and the second maximum value are the minimum value and the maximum value of each of the transaction scale index values; the third minimum value and the third maximum value are the minimum value and the maximum value of each of the transaction frequency index values.

[0116] Optionally, the device further comprises:

[0117] A matching module, for matching a corresponding target business processing institution according to the area code information of the first user to whom the target user corresponds for the transaction, after selecting the second user who meets the preset conditions as the target user according to the recommendation index value;

[0118] The sending module is used to send the user list consisting of the target users to the target business processing organization for processing.

[0119] The user screening device provided in the embodiment of the present invention can execute the user screening method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0120] Embodiment 4

[0121] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0122] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0123] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0124] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a user screening method.

[0125] In some embodiments, the user screening method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method XXX described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the user screening method in any other suitable manner (e.g., by means of firmware).

[0126] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0127] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0128] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0129] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0130] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0131] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0132] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0133] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A user screening method, characterized in that: The method comprises: Based on the historical user data authorized and obtained within a set time, a user transaction network model is constructed by univariate analysis and graph calculation methods, wherein the nodes in the user transaction network model include a first user and a second user, the types of business processing institutions to which the first user and the second user belong are different, the second user is the user with whom the first user transacts when processing business at the business processing institution, the node corresponding to the first user is a first node, and the node corresponding to the second user is a second node; For each second node, determining a recommendation index value corresponding to the second node based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node; According to the recommendation index value, a second user meeting a preset condition is selected as a target user, wherein the preset condition is that the recommendation index value is greater than a preset threshold; The user transaction network model is constructed by using univariate analysis and graph calculation methods, including: Processing each single variable in the historical user data through the univariate analysis to obtain a data processing result; Based on the data processing result, a corresponding graph network model is obtained by using the graph calculation method; The graph network models corresponding to all the single variables are integrated accordingly to obtain the user transaction network model; The step of determining, for each second node, a recommendation index value corresponding to the second node based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node comprises: For each second node, determining a relevance index value corresponding to the second node based on the degree corresponding to the second node; Determine a transaction scale index value corresponding to the second node based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction scale information corresponding to the second node; Determine a transaction frequency index value corresponding to the second node based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction frequency information corresponding to the second node; Determining a recommendation index value corresponding to the second node based on the association index value, the transaction scale index value, and the transaction frequency index value; Among them, one second node corresponds to one association index value, one transaction scale index value and one transaction frequency index value.

2. The method according to claim 1, characterized in that The historical user data includes basic user information, user asset information, user transaction information, and user product holding information corresponding to the first user; The user basic information includes at least one first sub-information as univariate information, and the first sub-information represents the user basic information; The user asset information includes at least one second sub-information as univariate information, wherein the second sub-information represents the user asset information; The user transaction information includes at least one third sub-information as univariate information, and the third sub-information represents the user transaction information; The user product holding information includes at least one fourth sub-information as univariate information, and the fourth sub-information represents the user product holding information.

3. The method according to claim 1, characterized in that Determining a recommendation index value corresponding to the second node based on the association index value, the transaction scale index value, and the transaction frequency index value includes: For each second node, taking the ratio of the difference between the association index value corresponding to the second node and the first minimum value and the difference between the first maximum value and the first minimum value as the first sub-value; The ratio between the difference between the transaction scale index value corresponding to the second node and the second minimum value and the difference between the second maximum value and the second minimum value is used as the second sub-value; The ratio between the difference between the transaction frequency index value corresponding to the second node and the third minimum value and the difference between the third maximum value and the third minimum value is used as the third sub-value; taking an average value of the first sub-value, the second sub-value and the third sub-value as a recommendation index value corresponding to the second node; Among them, the first minimum value and the first maximum value are the minimum value and the maximum value of each of the association index values; the second minimum value and the second maximum value are the minimum value and the maximum value of each of the transaction scale index values; the third minimum value and the third maximum value are the minimum value and the maximum value of each of the transaction frequency index values.

4. The method according to claim 1, characterized in that: After selecting a second user who meets the preset condition as a target user according to the recommendation index value, the method further includes: Matching a corresponding target business processing organization according to the area code information of the first user of the target user corresponding to the transaction; The user list consisting of the target users is sent to the target business processing organization for processing.

5. A user screening device, characterized in that: include: A construction module, used to construct a user transaction network model through univariate analysis and graph calculation methods based on historical user data authorized to be obtained within a set time, wherein the nodes in the user transaction network model include a first user and a second user, the types of business processing institutions to which the first user and the second user belong are different, the second user is a user with whom the first user transacts when conducting business at the business processing institution, the node corresponding to the first user is a first node, and the node corresponding to the second user is a second node; A determination module, configured to determine, for each second node, a recommendation index value corresponding to the second node based on the degree corresponding to the node in the user transaction network model and the transaction scale information and transaction frequency information corresponding to the second node; A screening module, configured to screen a second user who meets a preset condition as a target user according to the recommendation index value, wherein the preset condition is that the recommendation index value is greater than a preset threshold; The construction module is further used to process each single variable in the historical user data through the single variable analysis to obtain a data processing result; based on the data processing result, obtain a corresponding graph network model through the graph calculation method; and fuse the graph network models corresponding to all the single variables to obtain the user transaction network model; The determining module comprises: A first determining unit, configured to determine, for each second node, a relevance index value corresponding to the second node based on the degree corresponding to the second node; A second determining unit, configured to determine a transaction scale index value corresponding to the second node based on the degree corresponding to the first node of the transaction corresponding to the second node and the transaction scale information corresponding to the second node; A third determining unit, configured to determine a transaction frequency index value corresponding to the second node based on the degree corresponding to the first node having a transaction corresponding to the second node and the transaction frequency information corresponding to the second node; a fourth determining unit, configured to determine a recommendation index value corresponding to the second node based on the association index value, the transaction scale index value, and the transaction frequency index value; Among them, one second node corresponds to one association index value, one transaction scale index value and one transaction frequency index value.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the user screening method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user screening method according to any one of claims 1 to 4 when executed.

Images