New user risk assessment method, device, electronic device and medium

Abstract

The present disclosure provides a new user risk assessment method, including: obtaining information of a new user, the information of the new user including information of a second account and N second associated entities; obtaining a relationship network diagram, in which S first accounts and M first associated entities are nodes, and each first account is connected to the first associated entity used and a corresponding first associated weight is set; the second account is connected to the relationship network diagram as a node; the first risk value of the first account connected to the second associated entity is obtained; based on the first risk value and the first associated weight between the first account and the first associated entity, the second risk value of the second account is calculated to perform risk control on the new user according to the second risk value. The present disclosure also provides a new user assessment device, an electronic device and a storage medium.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and more specifically, to a new user risk assessment method, a new user risk assessment device, an electronic device, and a storage medium. Background Art

[0002] In the fields of e-commerce, finance, or food delivery, user risk assessment is the most important means of controlling user risk behavior. In the traditional risk control field, the user risk assessment method usually collects multiple behavioral data of known users, mines and analyzes them, and then uses machine learning algorithms to score the risks of known users in order to control the risks of known users.

[0003] In the process of implementing the concept of the present disclosure, the inventors found that there are at least the following problems in the prior art:

[0004] Due to the small amount of behavioral data on new users, the existing user risk assessment methods do not have sufficient data support and are therefore unable to conduct risk assessment on new users. Summary of the invention

[0005] In view of this, the embodiments of the present disclosure provide a new user risk assessment method, device, electronic device and storage medium that can perform risk control on new users in combination with a known user relationship network diagram.

[0006] One aspect of an embodiment of the present disclosure provides a new user risk assessment method, comprising: obtaining information of a new user, the information of the new user including information of a second account and N second associated entities, wherein each second associated entity is information of an entity used by the new user to log in to the second account; obtaining a relationship network diagram, wherein S first accounts and M first associated entities are nodes in the relationship network diagram, and according to the situation that a known user uses the first associated entity when logging in to each first account, each first account is correspondingly connected to the used first associated entity and a corresponding first associated weight is set; when N second associated entities and M first associated entities have an intersection, the second account is connected to the relationship network diagram as a node, wherein the second account is connected to the second associated entity, wherein N, S and M are integers greater than or equal to 1; obtaining a first risk value of the first account connected to the second associated entity; and calculating a second risk value of the second account based on the first risk value and the first association weight between the first account and the first associated entity, so as to perform risk control on the new user according to the second risk value.

[0007] According to an embodiment of the present disclosure, the method further includes constructing the association network diagram. The construction of the association network diagram includes: obtaining information of the S first accounts and the M first associated entities used by the S first accounts to log in; using the S first accounts and the M first associated entities as nodes, respectively, to connect each first account with the first associated entity used by it; and calculating the first association weight of each first account with each first associated entity used by it based on the number of times the first account uses each first associated entity.

[0008] According to an embodiment of the present disclosure, when S is greater than or equal to 2, connecting each first account with the first associated entity it has used includes: connecting each first account with the first associated entity it has used to construct a local relationship network diagram; when at least two of the first accounts have used the same first associated entity, merging at least two of the local relationship network diagrams, including: at least two of the first accounts are simultaneously connected to the same first associated entity.

[0009] According to an embodiment of the present disclosure, the calculation of the first association weight between the first account and each of the first associated entities used by the first account includes: obtaining the first entity type to which each of the first associated entities belongs; obtaining the first number of times the first account uses each of the first associated entities; counting the second number of times the first account uses each of the first entity types, wherein the second number is the total number of times the first account uses all of the first associated entities in each of the first entity types; and calculating the first association weight between the first account and each of the first associated entities used based on the first number and the second number.

[0010] According to an embodiment of the present disclosure, calculating the second risk value of the second account includes: calculating the second association weight between the second account and each of the second associated entities; obtaining the third risk value of each of the second associated entities; and calculating the second risk value based on the third risk value and the second association weight.

[0011] According to an embodiment of the present disclosure, the calculation of the second association weight between the second account and each of the second associated entities includes: obtaining the second entity type to which each of the second associated entities belongs; obtaining the third number of times the second account uses each of the second associated entities; counting the fourth number of times the second account uses each of the second entity types, wherein the fourth number is the total number of times the second account uses all of the second associated entities in each of the second entity types; and calculating the second association weight between the second account and each of the second associated entities based on the third number and the fourth number.

[0012] According to an embodiment of the present disclosure, obtaining the third risk value of each second associated entity includes: obtaining a first influence value of each first account connected to the second associated entity on the second associated entity, wherein the first influence value is the product of the first risk value and the corresponding first association weight; accumulating and summing all the first influence values ​​to obtain a first cumulative sum; and calculating the third risk value of the second associated entity based on the number of the first accounts connected to the second associated entity and the first cumulative sum.

[0013] According to an embodiment of the present disclosure, calculating the second risk value based on the third risk value and the second association weight includes: calculating the second impact value of each second associated entity on the new user, wherein the second impact value is the product of the third risk value and the corresponding second association weight; accumulating and summing all the second impact values ​​to obtain a second cumulative sum; and obtaining the second risk value based on the number of the second associated entities and the second cumulative sum.

[0014] Another aspect of the disclosed embodiment provides a new user risk assessment device, which includes an information acquisition module, a network acquisition module, a user access module, a risk acquisition module, and a risk calculation module. The information acquisition module is used to acquire information of a new user, the information of the new user includes information of a second account and N second associated entities, wherein each second associated entity is information of an entity used by the new user to log in to the first account; the network acquisition module is used to acquire a relationship network diagram, wherein S first accounts and M first associated entities are nodes in the relationship network diagram, and each first account is connected to the used first associated entity and a corresponding first associated weight is set according to the situation that a known user logs in to each first account and uses the first associated entity; the user access module is used to connect the second account as a node to the relationship network diagram when there is an intersection between N second associated entities and M first associated entities, wherein the second account is connected to the second associated entity, wherein N, S and M are integers greater than or equal to 1; the risk acquisition module is used to acquire a first risk value of the first account connected to the second associated entity; the risk calculation module is used to calculate a second risk value of the second account based on the first risk value and the first associated weight between the first account and the first associated entity, so as to perform risk control on the new user according to the second risk value.

[0015] Another aspect of the present disclosure provides an electronic device. The electronic device includes a memory and one or more processors. The memory stores one or more instructions. When the one or more instructions are executed by the one or more processors, the one or more processors implement the above method.

[0016] Another aspect of an embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method described above when executed.

[0017] Another aspect of an embodiment of the present disclosure provides a computer program, wherein the computer program includes computer executable instructions, and the instructions are used to implement the method described above when executed.

[0018] Another aspect of the embodiments of the present disclosure provides a computer program product, including a computer program / instruction, which implements the method described above when executed by a processor.

[0019] One or more of the above-mentioned embodiments have the following advantages or beneficial effects: it can at least partially solve the problem of being unable to perform risk control on new users, by connecting the second account logged in by the new user to the relationship network diagram constructed based on the behavioral data of known users, and then calculating the second risk value of the second account, thereby achieving the technical effect of risk control on new users. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0021] Figure 1 An exemplary system architecture to which a new user risk assessment method can be applied according to an embodiment of the present disclosure is schematically shown;

[0022] Figure 2 The following is a schematic diagram showing a process flow of a new user risk assessment method according to an embodiment of the present disclosure;

[0023] Figure 3 Schematically shows a relationship network diagram according to an embodiment of the present disclosure;

[0024] Figure 4 The schematic diagram schematically shows a process diagram of constructing an association network diagram according to an embodiment of the present disclosure;

[0025] Figure 5 The following schematically shows a flow chart of constructing an association network diagram according to another embodiment of the present disclosure;

[0026] Figure 6The following schematically shows a flow chart of calculating the first association weight according to an embodiment of the present disclosure;

[0027] Figure 7 A schematic diagram of a process of calculating a second risk value of a second account according to an embodiment of the present disclosure is schematically shown;

[0028] Figure 8 The flowchart of calculating the second association weight according to the embodiment of the present disclosure is schematically shown;

[0029] Fig. 9 The schematic diagram shows a process of obtaining a third risk value according to an embodiment of the present disclosure;

[0030] Fig.10 A schematic diagram of a process for calculating a second risk value according to an embodiment of the present disclosure is schematically shown;

[0031] Fig.11 A block diagram of a new user risk assessment device according to an embodiment of the present disclosure is schematically shown;

[0032] Fig.12 The overall architecture diagram of the new user risk assessment device according to an embodiment of the present disclosure is schematically shown;

[0033] Fig.13 A schematic diagram schematically shows a process diagram of risk transfer in a user relationship network diagram according to an embodiment of the present disclosure; and

[0034] Fig.14 A block diagram of a computer system suitable for implementing a new user risk assessment method and system according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0035] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0036] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0037] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0038] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0039] In the fields of e-commerce shopping, food delivery, or financial loans, risk control is usually performed on users based on their risk values. For example, e-commerce shopping platforms will determine the user's discount based on the user's risk value, food delivery platforms will also determine the user's purchase price based on the user's risk value, and financial loan platforms will refer to the user's risk value to evaluate the user's loan amount. In the prior art, risk values ​​are usually obtained by analyzing various existing behaviors of users. However, for new users, there is a lack of sufficient behavioral data for analysis, which makes it impossible to determine effective risk control for new users.

[0040] The following takes an e-commerce shopping platform as an example to explain in detail the new user risk assessment method provided by the embodiment of the present disclosure.

[0041] E-commerce platforms integrate various behavioral data of users on the platform, such as the personal information filled in by known users when registering accounts, and the information generated by behaviors such as placing orders, collecting coupons, making payments, and after-sales service when logging in to accounts. Through the above behavioral data, we can analyze the dependence between users (such as buying and selling) and upstream and downstream relationships (A buys from B), family and collective relationships, and friendships. For example, we can use the objective associations between users to build a relationship network between users, and then propagate the risks of known users to new users in the form of energy propagation to control the risks of new users.

[0042] The embodiment of the present disclosure provides a new user risk assessment method, device, electronic device, and medium. The risk assessment method includes: obtaining information of a new user, the information of the new user includes information of a second account and N second associated entities, wherein each second associated entity is information of an entity used by the new user to log in to the second account; obtaining a relationship network diagram, wherein S first accounts and M first associated entities are nodes in the relationship network diagram, and each first account is connected to the used first associated entity and a corresponding first associated weight is set according to the situation that a known user logs in to each first account and uses the first associated entity; when N second associated entities and M first associated entities have an intersection, the second account is connected to the relationship network diagram as a node, wherein the second account is connected to the second associated entity, wherein N, S and M are integers greater than or equal to 1; obtaining a first risk value of the first account connected to the second associated entity; based on the first risk value and the first associated weight between the first account and the first associated entity, calculating the second risk value of the second account, so as to perform risk control on the new user according to the second risk value.

[0043] By using the new user risk assessment method of the embodiment of the present disclosure, a user relationship network diagram can be constructed, and the second account can be connected to the user relationship network diagram, and the second risk value of the second account can be calculated using the first risk value and the first association weight. In this way, the risk of known users is transmitted to new users in the form of energy transmission, thereby improving the risk perception ability of new users, and further improving the system risk control ability of the e-commerce platform.

[0044] Figure 1 The exemplary system architecture 100 to which the new user risk assessment method according to an embodiment of the present disclosure can be applied is schematically shown. It should be noted that: Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0045] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0046] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0047] For example, a user can use terminal devices 101, 102, and 103 to register or log in three accounts respectively, or register or log in multiple accounts on each terminal device 101, 102, and 103. After logging in to the account on the e-commerce platform, the user performs shopping, after-sales service, or trial operations. Among them, the terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0048] The server 105 may be a server that provides various services, such as a background management server that provides support for the e-commerce platform browsed by the user using the terminal devices 101, 102, and 103 (for example only). The background management server may analyze and process the received data such as the user request, and feedback the processing results (such as the web page, information, or data obtained or generated according to the user request, etc.) to the terminal device. In addition, the background management server may also store the data such as the mobile phone number, device identification, delivery address, IP address, etc. used by the user to register an account or log in to the account for purchase or after-sales behavior, so that after receiving the risk assessment request, the stored behavior data can be analyzed and processed, and the risk assessment results can be fed back.

[0049] It should be noted that the new user risk assessment method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the new user risk assessment device provided in the embodiment of the present disclosure can generally be set in the server 105. The new user risk assessment method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the new user risk assessment device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0050] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0051] Figure 2The flowchart of the new user risk assessment method according to the embodiment of the present disclosure is schematically shown.

[0052] like Figure 2 As shown, the new user risk assessment method according to the embodiment of the present disclosure includes operations S210 to S250.

[0053] In operation S210, information of the new user is obtained, where the information of the new user includes information of a second account and N second associated entities, wherein each second associated entity is information of an entity used by the new user to log in to the second account.

[0054] According to an embodiment of the present disclosure, for example, the information of a new user is [Account ID: 0001; Mobile phone number 1: 0011; Device 1: AAAA; IP address 1: 124.xx.xx.xx.00; Delivery address 1: xx community], where the second account ID is 0001, and the second associated entity includes the mobile phone number, device, IP address, and delivery address, i.e., the information of the four entities used in the process of the new user registering or logging in to account 0001. It should be noted that the above information of the new user is only an example, and the present disclosure does not limit the content and type of the information obtained.

[0055] Then, in operation S220, a relationship network diagram is obtained, wherein the relationship network diagram has S first accounts and M first associated entities as nodes respectively, and based on the known situation of a user logging into each first account and using the first associated entity, each first account is connected to the used first associated entity and a corresponding first associated weight is set.

[0056] According to an embodiment of the present disclosure, for example, the information of the known user 1 is [Account ID: 0002; Mobile phone number 1: 0011; Device 2: AAAB; IP address 1: 124.xx.xx.xx.00; Delivery address 1: xx community], and the information of the known user 2 is [Account ID: 0003; Mobile phone number 2: 0012; Device 3: AAAC; IP address 2: 124.xx.xx.xx.11; Delivery address 1: xx community], wherein the two first accounts are account 0002 and account 0003, respectively, and the first associated entity is the entity information such as the mobile phone number, device, IP address and delivery address used by the known user to log in to the account ID.

[0057] In operation S230, when there is an intersection between the N second associated entities and the M first associated entities, the second account is connected to the relationship network diagram as a node, wherein the second account is connected to the second associated entity, wherein N, S and M are integers greater than or equal to 1 respectively.

[0058] Figure 3 The figure schematically shows a relationship network diagram according to an embodiment of the present disclosure.

[0059] like Figure 3 As shown, in the relationship network diagram 310 , account IDs and associated entities are used as nodes, and each account ID is connected to a used associated entity.

[0060] According to an embodiment of the present disclosure, for example, when the associated entity information used by account 0001 intersects with the associated entity information used by accounts 0002 and 0003, specifically, for example, both account 0001 and account 0002 use mobile phone number 1, IP address 1, and delivery address 1, and account 0001 and account 0003 use the same delivery address 1. Then, account 0001 is connected as a node to the relationship network diagram 310, and account 0001 is connected to the associated entities (mobile phone number 1, IP address 1, and delivery address 1) used in the relationship network diagram 310.

[0061] It should be noted that the node content, quantity and connection relationship between nodes in the relationship network diagram 310 are only examples. For example, when the second account 0004 of another new user logs in as a node and generates a connection relationship with device 1, the relationship network diagram 310 may include nodes representing account 0001, device 1 and mobile phone number 4.

[0062] In operation S240, a first risk value of a first account connected to a second associated entity is obtained.

[0063] According to the embodiments of the present disclosure, take the known user 1 and its information [Account ID: 0002; Mobile phone number 1: 0011; Device 2: AAAB; IP address 1: 124.xx.xx.xx.00; Delivery address 1: xx community] as an example. For example, in the after-sales scenario, the known user 1 logs in to account 0002 to perform corresponding after-sales behaviors. It uses mobile phone number 1, device 2, IP address 1 and delivery address 1 when placing an order to perform behaviors such as returns, complaints, and compensation. By analyzing the above behavioral data, potential risk behavior characteristics are mined, and then the behavioral risks of the known user 1 in the after-sales scenario are evaluated.

[0064] According to an embodiment of the present disclosure, the risk assessment of the known user 1 may be completed before or after the relationship network diagram 310 is constructed, or the risk assessment may be completed simultaneously with the process of constructing the relationship network diagram 310. For example, a scoring card algorithm (e.g., feature weighted fusion, Bayesian information fusion algorithm, etc.) or a machine learning algorithm (e.g., support vector machine algorithm, logistic regression algorithm, and decision tree algorithm, etc.) may be used to score the risk of the known user 1 to obtain the risk value of the known user 1 in the after-sales scenario.

[0065] It should be noted that the embodiments of the present disclosure may score known users for individual pre-sales, transaction, marketing or after-sales scenarios, or may score known users by comprehensively considering the behaviors of known users in various scenarios.

[0066] In operation S250, a second risk value of the second account is calculated based on the first risk value and a first association weight between the first account and the first association entity, so as to perform risk control on the new user according to the second risk value.

[0067] In the prior art, for example, there are some users in the black industry chain who engage in "fleecing" on e-commerce platforms. Usually, these users frequently register new accounts (the e-commerce system will identify them as new users), and then purchase items on the e-commerce platform at preferential prices for new users. Using the new user risk assessment method of the disclosed embodiment, the risk value of the new account can be obtained in combination with the relationship network diagram, so as to conduct risk assessment on new users identified by the e-commerce system, and then a suitable risk control mode can be adopted to avoid losses to the e-commerce platform.

[0068] Figure 4 The flowchart of constructing an association network diagram according to an embodiment of the present disclosure is schematically shown.

[0069] like Figure 4 As shown, before operation S220, the new user risk assessment method may further include constructing a correlation network diagram, wherein constructing the correlation network diagram may include operations S410 to S420.

[0070] In operation S410, information of S first accounts and M first associated entities used to log in the S first accounts is obtained.

[0071] According to the embodiments of the present disclosure, referring to Figure 1 and Figure 3 , for example, device 2 is one of the embodiments of terminal device 102. Taking account 0002 logged in by known user 1 as an example, after known user 1 logged in to account 0002, he purchased a book. In the process of purchasing the book, first, when known user 1 logged in to account 0002 to access the e-commerce platform, server 105 will obtain the IP address information of known user 1 when accessing through network 104. At the same time, known user 1, for example, logged in to account 0002 through a shopping application installed on device 2, and made subsequent purchases, then server 105 will obtain the identifier AAAB of device 2. Then, entity information such as the mobile phone number, delivery address, consignee, and payment account used by known user 1 when placing an order will also be obtained and stored by server 105.

[0072] In operation S420, the S first accounts and the M first associated entities are respectively used as nodes, and each first account is connected with the first associated entity that it has used.

[0073] The following combination Figure 5 , describing in detail the process of connecting each first account with the first associated entity used by it in operation S420.

[0074] Figure 5 A schematic diagram of a process for constructing an association network diagram according to another embodiment of the present disclosure is schematically shown.

[0075] like Figure 5 As shown, when S is greater than or equal to 2, connecting each first account with the used first associated entity in operation S420 may also include operations S510 to S520.

[0076] In operation S510, each first account is connected with the used first associated entity to construct a local relationship network graph.

[0077] Then, in operation S520, when at least two first accounts have used the same first associated entity, at least two local relationship network graphs are merged, which includes: at least two first accounts are connected to the same first associated entity at the same time.

[0078] According to the embodiments of the present disclosure, referring to Figure 3 , for example, two first accounts are obtained, namely account 0002 and account 0003. First, take account 0002 as the central node, and take the associated entities mobile phone number 1, device 2, IP address 1 and delivery address 1 used by account 0002 as neighbor nodes, connect the central node with the neighbor nodes to form a local relationship network diagram centered on account 0002. At the same time, construct the local relationship network diagram of account 0003 in a similar way to the steps of constructing the local relationship network diagram of account 0002. Then, since both account 0002 and account 0003 use the same delivery address 1, the node representing delivery address 1 is an overlapping node. At this time, make account 0002 and account 0003 connected to delivery address 1 at the same time to merge the two local relationship network diagrams. Finally, after the local relationship network diagrams are merged, a relationship network diagram containing all accounts and associated entities is obtained.

[0079] It should be noted that there is no order restriction for the above steps. For example, two local relationship network diagrams centered on account 0002 and account 0003 can be constructed at the same time, and then the two local relationship network diagrams can be merged based on overlapping nodes. Alternatively, two central nodes and multiple neighbor nodes (only one delivery address 1) can be determined first, and then the central nodes can be connected to the associated neighbor nodes respectively.

[0080] In operation S430 , based on the number of times each first associated entity is used by the first account, a first association weight between each first account and each first associated entity used by the first account is calculated.

[0081] According to the embodiment of the present disclosure, a heterogeneous graph structure is adopted to construct the relationship network diagram 310. There are various types of nodes and various types of associated relationship types in the relationship network diagram 310. For example, in addition to the account ID, the relationship network diagram 310 also includes associated entities used by the account (such as devices, mobile phone numbers, payment accounts or delivery addresses, etc.), and connects the account ID with different types of associated entities.

[0082] By utilizing the new user risk assessment method of the disclosed embodiment, on the one hand, the relationship between accounts can be intuitively displayed in the form of a relationship network diagram; on the other hand, for situations with a large number of accounts, the complexity of the graph structure can be reduced, thereby effectively improving the efficiency of risk propagation.

[0083] The following combination Figure 6 , describing in detail the process of calculating the first association weight of each first account and each first associated entity used by the first account based on the number of times the first account uses each first associated entity in operation S430.

[0084] Figure 6 The figure schematically shows a flow chart of calculating the first association weight according to an embodiment of the present disclosure.

[0085] like Figure 6 As shown, calculating the first association weight between the first account and each first associated entity used by the first account in operation 430 may also include operations S610 to S640.

[0086] In operation S610, a first entity type to which each first associated entity belongs is obtained.

[0087] In operation S620, a first number of times each first associated entity is used by the first account is obtained.

[0088] In operation S630, a second number of times the first account uses each first entity type is counted, wherein the second number is the total number of times the first account uses all first associated entities in each first entity type.

[0089] In operation S640 , a first association weight between the first account and each first associated entity that has been used is calculated based on the first number and the second number.

[0090] According to the embodiments of the present disclosure, referring again to Figure 3 , taking the calculation of the first association weight W1 between account 0002 and mobile phone number 1 as an example. For example, W1 can be calculated according to formula (1).

[0091] W1=1-e -rn (1)

[0092] Where W1 represents the association weight between account 0002 and mobile number 1. n represents the number of times account 0002 uses mobile number 1. It represents the percentage of times that account 0002 uses mobile number 1, where N represents the total number of times the user uses all entities of the same category as mobile number 1.

[0093] Specifically, for example, during the shopping process of account 0002, mobile number 1 was used 20 times, and mobile number 3 was used 80 times. Moreover, mobile number 1 and mobile number 3 belong to the same communication type, that is, the number of times the communication type was used was 100 times. It can be seen that n is 20, N is 100, and r is 0.2. Substituting the above data into formula (1):

[0094] W1=1-e -0.2*20

[0095] It should be noted that the above classification method and data on the number of times are only examples. The first association weight between the first account and each first associated entity used in the relationship network diagram can be calculated according to formula (1) based on actual conditions.

[0096] Generally, the greater the association weight between the first account and each first associated entity, the greater the mutual influence between the nodes, and vice versa. Using the new user risk assessment method provided by the embodiment of the present disclosure, the first association weight can be dynamically updated according to the change of the number of uses through the weight assessment algorithm (1) of the class index, so that the relationship network diagram can be updated in time, effectively ensuring the accuracy of new user risk control.

[0097] Figure 7 The flowchart of calculating the second risk value of the second account according to the embodiment of the present disclosure is schematically shown.

[0098] like Figure 7 As shown, calculating the second risk value of the second account in operation 250 may further include operations S710 to S730.

[0099] In operation S710 , a second association weight between the second account and each second associated entity is calculated.

[0100] The following combination Figure 8 , describing in detail the specific process of calculating the second association weight in operation 710.

[0101] Figure 8 The flowchart of calculating the second association weight according to the embodiment of the present disclosure is schematically shown.

[0102] like Figure 8As shown, calculating the second association weight between the second account and each second associated entity in operation 710 may further include operations S810 to S840.

[0103] In operation S810, a second entity type to which each second associated entity belongs is obtained.

[0104] In operation S820, a third number of times the second account uses each second associated entity is obtained.

[0105] In operation S830, a fourth number of times the second account uses each second entity type is counted, where the fourth number is a total number of times the second account uses all second associated entities in each second entity type.

[0106] In operation S840, a second association weight between the second account and each second associated entity is calculated based on the third number and the fourth number.

[0107] According to the embodiments of the present disclosure, referring to Figure 3 , taking the calculation of the second association weight between account 0001 and mobile number 1 as an example, W2 can still be calculated according to formula (1). Specifically, for example, account 0001 also uses mobile number 4. Account 0001 uses mobile number 1 once and mobile number 3 four times. Moreover, mobile number 1 and mobile number 4 belong to the same communication type, that is, the number of times the communication type is used is 5 times. It can be seen that n is 1, N is 5, and r is 0.2. Substituting the above data into formula (1):

[0108] W2=1-e -0.2*1

[0109] It should be noted that the transition from a new user to a known user referred to in the embodiments of the present disclosure may be a transition process, and does not only refer to an account that has just been registered, or an account that has only made one purchase.

[0110] By utilizing the new user risk assessment method of the disclosed embodiment, as the number of times a new user logs into the second account and uses each second associated entity gradually changes, the second associated weight is dynamically updated, thereby improving the risk identification coverage capability for all users and increasing the support capability for business risk control.

[0111] In operation S720 , a third risk value of each second associated entity is obtained.

[0112] Fig. 9 The flowchart of obtaining the third risk value according to the embodiment of the present disclosure is schematically shown.

[0113] like Fig. 9 As shown, obtaining the third risk value of each second associated entity in operation S720 may also include operations S910 to S930.

[0114] In operation S910, a first influence value of each first account connected to the second associated entity on the second associated entity is obtained, wherein the first influence value is a product of a first risk value and a corresponding first associated weight.

[0115] In operation S920, all first impact values ​​are accumulated and summed to obtain a first accumulated sum;

[0116] In operation S930, a third risk value of the second associated entity is obtained based on the number of first accounts connected to the second associated entity and the first accumulated sum.

[0117] According to the embodiments of the present disclosure, referring to Figure 3 , taking the third risk value of delivery address 1 as an example. First, according to the process of operations S810 to S840, the association weight W3 between account 0002 and delivery address 1 and the association weight W4 between account 0003 and delivery address 1 can be obtained by formula (1). At the same time, according to operation S240, the first risk value V1 of account 0002 and the first risk value V2 of account 0003 can be obtained. Then, the third risk value of the second associated entity can be calculated according to the following formula:

[0118]

[0119] Among them, γ represents the correction parameter of node degree to risk value, 0<γ≤1; β represents the energy propagation attenuation factor, 0<β≤1; ε i Representative node n i The impact value on node n, for example, the impact value of account 0002 on delivery address 1, where ε i =V i W(n i , n), V i Representative node n i The risk value, W(n i , n) represents node n i The association weight of n, for example, the association weight W3 between account 0001 and delivery address 1; d represents the node degree, for example, the node n directly connected to node n i The number of

[0120] According to the embodiment of the present disclosure, it can be seen from formula (2) that d and β, as well as ε i It plays a key role in energy propagation. For example, in extreme cases, when ε i =1, V = (1-e -γd)β. When d is large enough, v≈β. Intuitively, when all connected nodes of a node have high risk values ​​and their associated weights are large, it is only affected by the energy transfer attenuation factor β. At this time, when β is large, that is, the attenuation is small, the risk value of the user is also high.

[0121] Then, by Figure 3 It can be seen that the node degree d of the delivery address 1 is 2. Substituting the associated weights W3, W4 and the first risk values ​​V1, V2 into formula (2), the risk value V3 of the delivery address 1 can be obtained as follows:

[0122]

[0123] It should be noted that γ, as a correction parameter, is affected by the node degree d. For example, its initial value can be 0.5, and then it can be trained using a deep learning algorithm to obtain the relationship between γ and d. Because for a node that needs to calculate the risk value, the larger its node degree d is, the less it is affected by a certain known user, that is, the degree of connection in the relationship network diagram is associated with the influence of interpersonal relationships in real society.

[0124] In addition, because there is a common information loss problem in information propagation theory. The energy propagation in the relationship network diagram of the disclosed embodiment is similar to this. Even if the association weight between two nodes is 1, the energy propagation between the two nodes will decay, and the degree of decay is determined by the energy propagation decay factor β. Among them, β can also be trained using a deep learning algorithm. For example, β can be a constant, or the value of β can be set accordingly according to the different association weights between the two nodes.

[0125] In operation S730 , a second risk value is calculated based on the third risk value and the second associated weight.

[0126] The following combination Fig.10 , describing in detail the process of calculating the second risk value in operation S730.

[0127] Fig.10 The flowchart of calculating the second risk value according to the embodiment of the present disclosure is schematically shown.

[0128] like Fig.10 As shown, obtaining the third risk value of each second associated entity in operation S630 may also include operations S1010 to S1030.

[0129] In operation S1010, a second influence value of each second associated entity on the new user is calculated, wherein the second influence value is a product of the third risk value and the corresponding second associated weight.

[0130] In operation S1020, all second impact values ​​are accumulated and summed to obtain a second accumulated sum;

[0131] In operation S1030 , a second risk value is obtained based on the number of second associated entities and the second accumulated sum.

[0132] According to the embodiments of the present disclosure, referring to Figure 3 , take the calculation of the second risk value V4 of account 0001 as an example.

[0133] First, according to operations S910 to S930, the risk value V5 of mobile phone number 1, the risk value V6 of IP address 1, and the risk value V7 of delivery address 1 are obtained respectively. At the same time, according to operations S810 to S840, the association weight W2 of account 0001 with mobile phone number 1, the association weight W5 with IP address 1, and the association weight W6 with delivery address 1 are obtained respectively. In addition, by Figure 3 It can be seen that account 0001 is connected to 5 associated entities, among which device 1 and mobile phone number 4 are not nodes belonging to the relationship network diagram 310. At this time, device 1 and mobile phone number 4 can be ignored. Therefore, the node degree d of account 0001 is 3.

[0134] Then, substituting the above data into formula (2) we can get:

[0135]

[0136] The embodiments of the present disclosure do not impose any specific restrictions on the values ​​of γ and β, which can be set by the user in practical applications.

[0137] By using the new user risk assessment method of the embodiment of the present disclosure, based on the idea of ​​risk propagation, the risk value of the first account is transmitted layer by layer to the second account to obtain a second risk value, thereby making full use of the information of known users to realize risk assessment of new users.

[0138] Fig.11 The block diagram of a new user risk assessment device according to an embodiment of the present disclosure is schematically shown.

[0139] like Fig.11 As shown, the new user risk assessment device 1100 includes an information acquisition module 1110, a network acquisition module 1120, a user access module 1130, a risk acquisition module 1140, a risk calculation module 1150 and a network construction module 1160. The new user risk assessment device 1100 can be used to implement reference Figure 2 to Figure 10 Described new user risk assessment methodology.

[0140] Specifically, the information acquisition module 1110 may, for example, perform operation S210 to acquire information of the new user, where the information of the new user includes information of the second account and N second associated entities, wherein each second associated entity is information of an entity used by the new user to log in to the first account.

[0141] The network acquisition module 1120 can, for example, perform operation S220 to obtain a relationship network diagram, wherein the relationship network diagram has S first accounts and M first associated entities as nodes, and based on the known user logging in to each first account and using the first associated entity, each first account is connected to the used first associated entity and a corresponding first associated weight is set.

[0142] The user access module 1130 can, for example, perform operation S230, which is used to connect the second account as a node to the relationship network diagram when there is an intersection between N second associated entities and M first associated entities, wherein the second account is connected to the second associated entity, wherein N, S and M are integers greater than or equal to 1 respectively.

[0143] The risk acquisition module 1140 may, for example, perform operation S240 to acquire a first risk value of a first account connected to the second associated entity.

[0144] The risk calculation module 1150 may, for example, perform operation S250 to calculate a second risk value of the second account based on the first risk value and a first association weight between the first account and the first associated entity, so as to perform risk control on the new user according to the second risk value.

[0145] According to an embodiment of the present disclosure, the new user risk assessment device 1100 may further include a network construction module 1160, which may, for example, perform operations S410 to S430 to construct a relationship network diagram. Furthermore, the network construction module may, for example, further perform operations S510 to S520.

[0146] According to an embodiment of the present disclosure, the new user risk assessment device 1100 may further include a first association weight calculation module. The first association weight calculation module may, for example, perform operations S610 to S640 to calculate a first association weight between the first account and each first associated entity used.

[0147] According to an embodiment of the present disclosure, the new user risk assessment device 1100 may further include a second risk value calculation module. The second risk value calculation module may, for example, perform operations S710 to S730 to calculate a second risk value.

[0148] According to an embodiment of the present disclosure, the new user risk assessment device 1100 may further include a second association weight calculation module, which may, for example, perform operations S810 to S840 to calculate a second association weight between the second account and each used second associated entity.

[0149] According to an embodiment of the present disclosure, the new user risk assessment device 1100 may further include a third risk value calculation module. The third risk value calculation module may, for example, perform operations S910 to S930 to calculate a third risk value.

[0150] According to an embodiment of the present disclosure, the new user risk assessment device 1100 may further include a second risk value calculation submodule. The second risk value calculation submodule may, for example, perform operations S1010 to S1030 to obtain a second risk value.

[0151] Fig.12 The overall architecture diagram of the new user risk assessment device 1100 according to an embodiment of the present disclosure is schematically shown.

[0152] like Fig.12 As shown, the new user risk assessment device 1100 may include operations S1210 to S1240 during the new user risk assessment process.

[0153] In operation S1210, for example, the risk acquisition module 1140 may execute operation S240 to perform a basic risk assessment on the first account and acquire a first risk value of the first account connected to the second associated entity.

[0154] In operation S1220, for example, the network construction module 1160 may be instructed to perform operations S410 to S430 to construct a relationship network diagram.

[0155] In operation S1230, for example, the first association weight calculation module may be firstly instructed to perform operations S610 to S640, and then the third risk value calculation module may be instructed to perform operations S910 to S930. In addition, the second association weight calculation module may be instructed to perform operations S810 to S840.

[0156] In operation S1240, for example, the second risk value calculation module may be instructed to execute operations S710 to S730 to obtain and output the second risk value.

[0157] The following combination Fig.13 , describing in detail one embodiment of risk transfer in operation S1230.

[0158] Fig.13 The schematic diagram shows the process flow of risk transfer in the user relationship network diagram according to the embodiment of the present disclosure. Fig.13 yes Figure 3 One embodiment of the user relationship network diagram 310.

[0159] like Fig.13 As shown, infected account nodes 1310, 1320, and 1330 can be the first account logged in by a known user. Associated entity node 1340 can represent a company address, for example, and associated entity node 1350 can represent a group address, and the group includes the company represented by associated entity node 1340. Therefore, associated entity nodes 1340 and 1350 have an associated relationship, and associated entity nodes 1340 and 1350 are connected. Uninfected account nodes 1360 and 1370 can be the second account logged in by a new user. And, Fig.13 , the association weights w1 to w6 between two connected nodes are shown.

[0160] According to the embodiments of the present disclosure, referring to Fig.13 , when the uninfected account nodes 1360 and 1370 are connected to the associated entity nodes 1340 and 1350 at the same time. Taking the calculation of the risk value of the uninfected account node 1360 as an example, it can be obtained from Fig.13 It can be seen that, first, the risk of the infected account nodes 1310 and 1320 is transmitted to the associated entity node 1340, and at the same time, the risk of the infected account node 1330 is first transmitted to the associated entity node 1350, and then transmitted from the associated entity node 1350 to 1340. The process of transmitting the risk to the associated entity node 1340 is the process of obtaining the risk value of the associated entity node 1340 by performing operations S910 to S930 through the third risk value calculation module. Then, the associated entity node 1340 transmits the risk to the uninfected account node 1360, that is, the second risk value calculation module performs operations S710 to S730, thereby obtaining and outputting the risk value of the uninfected account node 1360. Among them, since the uninfected account node 1370 is connected to the relationship network at the same time, its risk propagation process is not taken into account.

[0161] It should be noted that the association weight w4 between the association entity nodes 1340 and 1350 may be, for example, a static constant. Fig.13 The other associated weights in can be calculated according to the above formula (1).

[0162] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0163] For example, any multiple of the information acquisition module 1110, the network acquisition module 1120, the user access module 1130, the risk acquisition module 1140, the risk calculation module 1150, and the network construction module 1160 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the information acquisition module 1110, the network acquisition module 1120, the user access module 1130, the risk acquisition module 1140, the risk calculation module 1150, and the network construction module 1160 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware or in an appropriate combination of any of them. Alternatively, at least one of the information acquisition module 1110, the network acquisition module 1120, the user access module 1130, the risk acquisition module 1140, the risk calculation module 1150 and the network construction module 1160 can be at least partially implemented as a computer program module, which can perform corresponding functions when executed.

[0164] Fig.14 A block diagram of a computer system suitable for implementing a new user risk assessment method and system according to an embodiment of the present disclosure is schematically shown. Fig.14The computer system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0165] like Fig.14 As shown, the computer system 1400 according to the embodiment of the present disclosure includes a processor 1401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1402 or the program loaded from the storage part 1408 to the random access memory (RAM) 1403. The processor 1401 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 1401 may also include an onboard memory for caching purposes. The processor 1401 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0166] In RAM 1403, various programs and data required for the operation of system 1400 are stored. Processor 1401, ROM 1402, and RAM 1403 are connected to each other via bus 1404. Processor 1401 performs various operations of the method flow according to the embodiment of the present disclosure by executing the programs in ROM 1402 and / or RAM 1403. It should be noted that the program can also be stored in one or more memories other than ROM 1402 and RAM 1403. Processor 1401 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the programs stored in one or more memories.

[0167] According to an embodiment of the present disclosure, the system 1400 may further include an input / output (I / O) interface 1405, which is also connected to the bus 1404. The system 1400 may further include one or more of the following components connected to the I / O interface 1405: an input section 1406 including a keyboard, a mouse, etc.; an output section 1407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1408 including a hard disk, etc.; and a communication section 1409 including a network interface card such as a LAN card, a modem, etc. The communication section 1409 performs communication processing via a network such as the Internet. A drive 1410 is also connected to the I / O interface 1405 as needed. A removable medium 1411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1410 as needed, so that a computer program read therefrom is installed into the storage section 1408 as needed.

[0168] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1409, and / or installed from the removable medium 1411. When the computer program is executed by the processor 1401, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0169] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0170] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: 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), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a 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, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0171] An embodiment of the present disclosure also includes a computer program product, which includes a computer program, which contains program code for executing the method provided by the embodiment of the present disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the new user risk assessment method provided by the embodiment of the present disclosure.

[0172] When the computer program is executed by the processor 1401, the above functions defined in the system / device of the embodiment of the present disclosure are executed. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0173] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 1409, and / or installed from the removable medium 1411. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0174] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0175] The flowchart diagram 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 disclosure. In this regard, each square box in the flowchart diagram or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, 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 or flowchart diagram, and the combination of the square boxes in the block diagram or flowchart diagram, 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.

[0176] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0177] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A new user risk assessment method, comprising: Acquire information of a new user, where the information of the new user includes information of a second account and N second associated entities, wherein each of the second associated entities is information of an entity used by the new user to log in to the second account; Obtaining a relationship network diagram, wherein the relationship network diagram has S first accounts and M first associated entities as nodes, and according to the known use of the first associated entity by a user when logging into each of the first accounts, each of the first accounts is correspondingly connected to the first associated entity used, and a corresponding first associated weight is set; When N of the second associated entities and M of the first associated entities have an intersection, the second account is connected to the relationship network graph as a node, wherein the second account is connected to the second associated entity, wherein N, S and M are integers greater than or equal to 1 respectively; Obtaining a first risk value of the first account connected to the second associated entity, and obtaining a third risk value of each of the second associated entities; calculating a second association weight between the second account and each of the second associated entities, and calculating a second risk value of the second account based on the third risk value and the second association weight, so as to perform risk control on the new user according to the second risk value; The obtaining of the third risk value of each of the second associated entities includes: Obtaining a first influence value of each of the first accounts connected to the second associated entity on the second associated entity, wherein the first influence value is a product of the first risk value and the corresponding first associated weight; Accumulate and sum all the first impact values ​​to obtain a first accumulated sum; Calculate the ratio of the first cumulative sum divided by the number of the first accounts connected to the second associated entity, and obtain the third risk value of the second associated entity based on the product of the ratio and an energy transmission attenuation factor, where the energy transmission attenuation factor is greater than 0 and less than or equal to 1.

2. The method according to claim 1, wherein: The method further includes constructing the association network diagram, which includes: Obtaining information of the S first accounts and the M first associated entities that have been used by the S first accounts to log in; Using the S first accounts and the M first associated entities as nodes, respectively, to connect each of the first accounts with the first associated entity that it has used; and Based on the number of times the first account uses each of the first associated entities, a first association weight between each of the first accounts and each of the first associated entities used by the first account is calculated.

3. According to the new user risk assessment method of claim 2, when S is greater than or equal to 2, connecting each first account with the first associated entity used by it comprises: Connecting each of the first accounts with the first associated entities that have been used to construct a local relationship network graph; When at least two of the first accounts have used the same first associated entity, merging at least two of the local relationship network graphs, including: At least two of the first accounts are simultaneously connected to the same first associated entity.

4. According to the new user risk assessment method of claim 2, the calculating of the first association weight between the first account and each of the first associated entities used by the first account comprises: Obtaining a first entity type to which each of the first associated entities belongs; Obtaining a first number of times the first account uses each of the first associated entities; Counting the second times of using each of the first entity types by the first account, wherein the second times is the total times of using all the first associated entities in each of the first entity types by the first account; The first association weight between the first account and each of the first associated entities used is calculated based on the first number of times and the second number of times.

5. According to the new user risk assessment method of claim 1, the calculating the second association weight between the second account and each of the second associated entities comprises: Obtaining a second entity type to which each of the second associated entities belongs; Obtaining the third number of times the second account uses each of the second associated entities; Counting a fourth number of times the second account uses each second entity type, wherein the fourth number is a total number of times the second account uses all the second associated entities in each second entity type; The second association weight between the second account and each of the second associated entities is calculated based on the third number and the fourth number.

6. The new user risk assessment method according to claim 1, wherein: The calculating the second risk value based on the third risk value and the second association weight comprises: Calculating a second impact value of each second associated entity on the new user, wherein the second impact value is a product of the third risk value and the corresponding second associated weight; Accumulate and sum all the second impact values ​​to obtain a second accumulated sum; The second risk value is obtained based on the number of the second associated entities and the second accumulated sum.

7. A new user risk assessment device, comprising: An information acquisition module, used to acquire information of a new user, wherein the information of the new user includes information of a second account and N second associated entities, wherein each of the second associated entities is information of an entity used by the new user to log in to the second account; a network acquisition module, configured to acquire a relationship network diagram, wherein the relationship network diagram has S first accounts and M first associated entities as nodes, and according to a known situation that a user logs in to each first account and uses the first associated entity, each first account is correspondingly connected to the first associated entity used and a corresponding first associated weight is set; a user access module, configured to access the second account as a node to the relationship network diagram when there is an intersection between N of the second associated entities and M of the first associated entities, wherein the second account is connected to the second associated entity, wherein N, S and M are integers greater than or equal to 1 respectively; a risk acquisition module, configured to acquire a first risk value of the first account connected to the second associated entity, and to acquire a third risk value of each of the second associated entities; a risk calculation module, configured to calculate a second association weight between the second account and each of the second associated entities, and calculate a second risk value of the second account based on the third risk value and the second association weight, so as to perform risk control on the new user according to the second risk value; The obtaining of the third risk value of each of the second associated entities includes: Obtaining a first influence value of each of the first accounts connected to the second associated entity on the second associated entity, wherein the first influence value is a product of the first risk value and the corresponding first associated weight; Accumulate and sum all the first impact values ​​to obtain a first accumulated sum; Calculate the ratio of the first cumulative sum divided by the number of the first accounts connected to the second associated entity, and obtain the third risk value of the second associated entity based on the product of the ratio and an energy transmission attenuation factor, where the energy transmission attenuation factor is greater than 0 and less than or equal to 1.

8. An electronic device comprising: one or more processors; a memory for storing one or more instructions, Wherein, when the one or more instructions are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images