A risk management method and device based on knowledge graph

Abstract

The present application provides a risk management method and device based on a knowledge graph, the method comprising: obtaining a risk attribute value n of a business according to business-related information, where n is a positive integer; determining a management pair node of a risk management knowledge graph to be generated according to the risk attribute value; and determining a management path of the risk management knowledge graph according to the management pair node. The present application can form a risk management path and realize flexible management of risks.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and specifically to a risk management method and device based on a knowledge graph. Background Art

[0002] In the process of financial risk control, a fixed information transmission method is usually used for information transmission, that is, the information flow direction is pre-set, and the information is reviewed step by step according to the position level of the auditor, and the risk is judged, resulting in low work efficiency. For example, in the process of anti-money laundering risk control, the risk level control structure is relatively fixed, which manually reviews risk data and determines whether there is a money laundering risk. That is, auditors can only conduct risk audits according to their position level, and cannot flexibly change the level control model according to the level of risk, that is, they cannot flexibly control the direction of information flow. Furthermore, since the existing technology uses a traditional relational database model for data storage, the relevant auditors cannot easily predict the risk control path, that is, the direction of information flow, and the ability to prevent and control unknown risks is relatively limited. Summary of the invention

[0003] In response to the problems in the prior art, the present application provides a risk management method and device based on a knowledge graph, which can form a risk management path and achieve flexible risk management.

[0004] In order to solve the above technical problems, this application provides the following technical solutions:

[0005] In a first aspect, the present application provides a risk management method based on a knowledge graph, comprising:

[0006] Obtain the risk attribute value n of the business according to the business related information, where n is a positive integer;

[0007] Determine the management and control paired nodes of the risk management and control knowledge graph to be generated according to the risk attribute value;

[0008] Determine the control path of the risk control knowledge graph according to the control paired nodes.

[0009] Further, determining the control paired nodes of the risk control knowledge graph to be generated according to the risk attribute value includes:

[0010] Determining a risk control level according to the risk attribute value;

[0011] A plurality of groups of control paired nodes are determined according to the risk control level.

[0012] Further, when n is 1, the control paired nodes include a group of initial control paired nodes, a group of secondary control paired nodes, and a group of final control paired nodes, and the control path of the risk control knowledge graph is determined according to the control paired nodes, including:

[0013] A first controlled risk node is formed according to the control preliminary review result of the initial risk node of the initial controlled paired node, and the initial risk node and the first controlled risk node constitute the initial controlled paired node;

[0014] The first controlled risk node is inherited to obtain a first risk node to be controlled, and a second controlled risk node is formed according to the control review result of the first risk node to be controlled, and the first risk node to be controlled and the second controlled risk node constitute the re-controlled paired node;

[0015] The second controlled risk node is inherited to obtain the second risk node to be controlled, and the final controlled risk node is formed according to the final review result of the management and control of the second risk node to be controlled. The second risk node to be controlled and the final controlled risk node constitute the final controlled paired node.

[0016] Furthermore, after forming the second controlled risk node according to the control review result of the first risk node to be controlled, the method further includes:

[0017] It is determined whether the intervention attribute value of the second controlled risk node is 1. If it is 1, a final controlled risk node is obtained.

[0018] Further, when n is 2, the control paired nodes include two groups of initial control paired nodes, two groups of secondary control paired nodes and one group of final control paired nodes, and the step of determining the risk control knowledge graph control path according to the control paired nodes includes:

[0019] According to the control preliminary review result of the initial risk node of the first group of initially controlled paired nodes, a first controlled risk node is formed, wherein the initial risk node and the first controlled risk node constitute the first group of initially controlled paired nodes;

[0020] The first controlled risk node is inherited to obtain a first risk node to be controlled, and a second controlled risk node is formed according to the control review result of the first risk node to be controlled, wherein the first risk node to be controlled and the second controlled risk node constitute a first group of re-controlled paired nodes;

[0021] The second controlled risk node is inherited to obtain a second risk node to be controlled, and a third controlled risk node is formed according to the preliminary review result of the control of the second risk node to be controlled. The second risk node to be controlled and the third controlled risk node constitute a second group of preliminary controlled paired nodes;

[0022] The third controlled risk node is inherited to obtain a third risk node to be controlled, and a fourth controlled risk node is formed according to the control review result of the third risk node to be controlled, and the third risk node to be controlled and the fourth controlled risk node constitute a second group of re-controlled paired nodes;

[0023] The fourth controlled risk node is inherited to obtain a fourth risk node to be controlled, and a final controlled risk node is formed according to the final review result of the management and control of the fourth risk node to be controlled. The fourth risk node to be controlled and the final controlled risk node constitute the final controlled paired node.

[0024] Furthermore, the risk management method further includes:

[0025] It is determined whether the intervention attribute value of the second controlled risk node or the fourth controlled risk node is 1. If it is 1, a final controlled risk node is obtained.

[0026] Further, when n is 3, the control paired nodes include three groups of initial control paired nodes, three groups of secondary control paired nodes and one group of final control paired nodes, and the step of determining the risk control knowledge graph control path according to the control paired nodes includes:

[0027] According to the control preliminary review result of the initial risk node of the first group of initially controlled paired nodes, a first controlled risk node is formed, wherein the initial risk node and the first controlled risk node constitute the first group of initially controlled paired nodes;

[0028] The first controlled risk node is inherited to obtain a first risk node to be controlled, and a second controlled risk node is formed according to the control review result of the first risk node to be controlled, wherein the first risk node to be controlled and the second controlled risk node constitute a first group of re-controlled paired nodes;

[0029] The second controlled risk node is inherited to obtain a second risk node to be controlled, and a third controlled risk node is formed according to the preliminary review result of the control of the second risk node to be controlled. The second risk node to be controlled and the third controlled risk node constitute a second group of preliminary controlled paired nodes;

[0030] The third controlled risk node is inherited to obtain a third risk node to be controlled, and a fourth controlled risk node is formed according to the control review result of the third risk node to be controlled, and the third risk node to be controlled and the fourth controlled risk node constitute a second group of re-controlled paired nodes;

[0031] The fourth controlled risk node is inherited to obtain a fourth risk node to be controlled, and a fifth controlled risk node is formed according to the preliminary review result of the control of the fourth risk node to be controlled. The fourth risk node to be controlled and the fifth controlled risk node constitute a third group of preliminary controlled paired nodes;

[0032] The fifth controlled risk node is inherited to obtain a fifth risk node to be controlled, and a sixth controlled risk node is formed according to the control review result of the fifth risk node to be controlled, and the fifth risk node to be controlled and the sixth controlled risk node constitute a third group of re-controlled paired nodes;

[0033] The sixth controlled risk node is inherited to obtain the sixth risk node to be controlled, and a final controlled risk node is formed according to the final review result of the control of the sixth risk node to be controlled. The sixth risk node to be controlled and the final controlled risk node constitute a final controlled paired node.

[0034] Furthermore, the risk management method further includes:

[0035] It is determined whether the intervention attribute value of the second controlled risk node, the fourth controlled risk node or the sixth controlled risk node is 1. If it is 1, a final controlled risk node is obtained.

[0036] Furthermore, the risk management method further includes:

[0037] When each controlled risk node is re-controlled, the original state is obtained;

[0038] When each risk node to be controlled or the original state is abandoned, an intermediate state is obtained;

[0039] When the original state or the intermediate state is released, the initial risk node, the second risk node to be controlled or the fourth risk node to be controlled corresponding to each original state or each intermediate state is returned to.

[0040] In a second aspect, the present application provides a risk management and control device based on a knowledge graph, comprising:

[0041] An acquisition unit, used to acquire a risk attribute value n of the business according to the business related information, where n is a positive integer;

[0042] A generating unit, configured to determine a pair of control nodes of a risk control knowledge graph to be generated according to the risk attribute value;

[0043] A determination unit is used to determine the control path of the risk control knowledge graph according to the control paired nodes.

[0044] Furthermore, the generating unit comprises:

[0045] A level determination module, used to determine the risk control level according to the risk attribute value;

[0046] The node determination module is used to determine multiple groups of control paired nodes according to the risk control level.

[0047] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the risk management method based on the knowledge graph when executing the program.

[0048] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the risk management method based on the knowledge graph.

[0049] In response to the problems in the prior art, the present application provides a risk management method and device based on a knowledge graph, which can obtain the risk attribute value of a business according to business-related information, and then generate the management and control paired nodes of the risk management knowledge graph, and finally determine the management and control path of the risk management knowledge graph, forming a risk hierarchy model for intuitive analysis and flexible control of risk factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is one of the flow charts of the risk management method based on the knowledge graph in the embodiment of this application;

[0051] Figure 2 A flowchart for determining the management and control paired nodes of the risk management and control knowledge graph to be generated in an embodiment of the present application;

[0052] Figure 3 One of the flow charts for determining the control path of the risk control knowledge graph in the embodiment of the present application;

[0053] Figure 4 The second flowchart of determining the control path of the risk control knowledge graph in the embodiment of the present application;

[0054] Figure 5 The third flowchart of determining the control path of the risk control knowledge graph in the embodiment of the present application;

[0055] Figure 6 This is the second flow chart of the risk management method based on the knowledge graph in the embodiment of this application;

[0056] Figure 7 This is a structural diagram of a risk management and control device based on a knowledge graph in an embodiment of the present application;

[0057] Figure 8 A structural diagram of a generating unit in an embodiment of the present application;

[0058] Fig. 9 A schematic diagram of the control path of the risk control knowledge graph in one embodiment of the present application;

[0059] Fig.10A schematic diagram of a control path of a risk control knowledge graph in another embodiment of the present application;

[0060] Fig.11 This is a schematic diagram of a control path of a risk control knowledge graph in another embodiment of the present application;

[0061] Fig.12 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] See also Figure 1 In order to form a risk management path and realize flexible risk management, this application provides a risk management method based on knowledge graph, including:

[0064] S101: Obtain a risk attribute value n of the business according to relevant business information, where n is a positive integer;

[0065] It is understandable that the embodiments of the present application can be applied to but not limited to anti-money laundering risk management scenarios in the banking field. The core of the risk management method based on the knowledge graph provided in this application is to establish a dynamic risk management knowledge graph that can solve risk management, and the risk attribute value of the business can be obtained based on the business-related information in the specific business scenario. These businesses include but are not limited to remittance business, purchase of wealth management products, purchase of funds, purchase of insurance, etc. The above risk attribute value can be n, where n is a positive integer. In the embodiments of the present application, n can be 1, 2 or 3, corresponding to low risk, medium risk or high risk, respectively.

[0066] In one embodiment, the business-related information may include: the remitter's personal information, the remittance amount, and the remittance channel. First, the remitter's personal information is judged. If the remitter is included in the international sanctions list, the risk attribute value of the business is set to 3, that is, high risk, and there is no need to judge the remittance amount and remittance channel in the business-related information; otherwise, the remittance amount in the business-related information is continued to be judged. The embodiment of the present application divides the remittance amount into three levels of RMB 100,000, RMB 1 million, and RMB 10 million, which correspond to 1, 2, and 3 in the risk attribute value respectively; finally, the remittance channel in the business-related information is judged. The embodiment of the present application divides the remittance channel into two categories: domestic channels and overseas channels. If the remittance is through an overseas channel, 1 is added to the risk attribute value determined according to the remittance amount. If the risk attribute value determined by the remittance amount is already 3, there is no need to add 1 to the risk attribute value determined according to the remittance amount, but the risk attribute value of the business can be directly determined as 3.

[0067] In another embodiment, the business-related information may include: the trader's personal information, transaction channels, transaction characteristics, industry characteristics (applicable to public transactions) and occupational characteristics (applicable to private transactions). Among them, the trader's personal information may include: name, nationality, ID number or passport number, etc.; transaction channels may include: financial products, stocks, funds, insurance or transfers, etc.; transaction characteristics may include: single card or multiple cards, single or multiple transactions, transaction amount, transaction frequency, etc.; industry characteristics (applicable to public transactions) may include: low-risk industries, medium-risk industries and high-risk industries; occupational characteristics (applicable to private transactions) may include: low-risk occupations, medium-risk occupations and high-risk occupations. After the risk attribute values ​​of the trader's personal information, transaction channels, transaction characteristics, industry characteristics (applicable to public transactions) and occupational characteristics (applicable to private transactions) are determined respectively, the final risk attribute value of the business can be calculated using the weighted summation method according to the weights corresponding to the trader's personal information, transaction channels, transaction characteristics, industry characteristics (applicable to public transactions) and occupational characteristics (applicable to private transactions). In one embodiment, the weights of the trader's personal information, transaction channels, transaction characteristics and industry characteristics (applicable to corporate transactions) can be set to 30%, 20%, 40% and 10% respectively; in another embodiment, the weights of the trader's personal information, transaction channels, transaction characteristics and occupational characteristics (applicable to private transactions) can be set to 20%, 20%, 40% and 20% respectively.

[0068] S102: Determine the control paired nodes of the risk control knowledge graph to be generated according to the risk attribute value;

[0069] Understandably, see Fig. 9In the risk management knowledge graph, the management and control paired nodes of the risk management knowledge graph to be generated can be determined according to the risk attribute values, such as (N1, N2), (N3, N4), etc.

[0070] Suppose the risk entry node is S, and determine the risk control level of the risk control knowledge graph to be generated according to the risk attribute value corresponding to the risk entry node S. In one embodiment, suppose the risk attribute value x is positively correlated with the risk control level. When x takes the value of n, the number of paired nodes is (2*n+1). Among them, there are n pairs of initial control paired nodes, n pairs of complex control paired nodes and 1 pair of final control paired nodes. The number of risk control levels of the risk control knowledge graph is (2*n+1).

[0071] S103: Determine the control path of the risk control knowledge graph based on the control paired nodes.

[0072] Understandably, see Fig. 9 , the nodes involved in the risk control knowledge graph include: risk entry node S, initial risk node N1, controlled risk nodes, such as N2, N4, etc., risk nodes to be controlled, such as N1, N3, N5, etc., and final controlled risk node F. In addition, the risk control knowledge graph also involves: original state and intermediate state. The so-called original state refers to the node obtained from the controlled risk node after re-control; the so-called intermediate state refers to the node obtained from the risk node to be controlled after abandoning control.

[0073] When determining the control path of the risk control knowledge graph based on the control paired nodes, first, in the risk control knowledge graph, a path from the risk entry node S to the initial risk node N1 can be generated according to the risk attribute value. Then, the control paired nodes are generated according to the risk control level determined in S102. Each level corresponds to a control paired node, and the relationship between the two nodes between the levels is inheritance, and inheritance can refer to the replication of node characteristics. Finally, the final control risk node F is generated, and the final control risk node F is the node where the risk is finally controlled, and the intervention attribute value of the final control risk node F is 1. In addition, when the intervention attribute value of the controlled risk node of the even-numbered level is 1, the final control risk node F will inherit this node without continuing to go through subsequent risk control levels. According to the above method, all paths from the risk entry node S to the final control risk node F can be determined. These paths are a set of compliant risk control paths. Please see the following description for specific embodiments.

[0074] From the above description, it can be seen that the risk management method based on knowledge graph provided in this application can obtain the risk attribute value of the business according to the business-related information, and then generate the management and control paired nodes of the risk management knowledge graph, and finally determine the management and control path of the risk management knowledge graph, and construct a risk hierarchy model for intuitive analysis and flexible control of risk factors.

[0075] See also Figure 2 , according to the risk attribute value, determine the control pair nodes of the risk control knowledge graph to be generated, including:

[0076] S201: Determine the risk control level according to the risk attribute value;

[0077] S202: Determine multiple groups of control paired nodes according to the risk control level.

[0078] See also Figure 3 and Fig. 9 , when n is 1, the control pair nodes include a group of initial control pair nodes, a group of secondary control pair nodes and a group of final control pair nodes. The control path of the risk control knowledge graph is determined according to the control pair nodes, including:

[0079] S301: A controlled risk node N2 is formed according to the initial risk node N1 of the initial control paired node (N1, N2). The initial risk node N1 and the controlled risk node N2 constitute the initial control paired node (N1, N2).

[0080] It can be understood that the so-called initial control can refer to the program set in the client to determine whether the risk corresponding to the business is within the controllable range, give the initial control result, and reach the controlled risk node N2. In one embodiment, the initial control result can be obtained based on the traders, transaction channels and transaction amounts involved in the business. In another embodiment, the initial control result can be obtained based on the personal information, transaction channels, transaction characteristics, industry characteristics (applicable to public transactions) and occupational characteristics (applicable to private transactions) of the traders involved in the business. If the controlled risk node N2 needs to be re-controlled, the controlled risk node N2 will return to the original state N1', and after release, return to the initial risk node N1. The initial control result can be given by the initial control personnel using the client.

[0081] S302: Inherit the controlled risk node N2 to obtain the uncontrolled risk node N3, and form the controlled risk node N4 according to the management and control review result of the uncontrolled risk node N3. The uncontrolled risk node N3 and the controlled risk node N4 form a re-controlled pair of nodes (N3, N4).

[0082] It can be understood that the so-called re-control can refer to the program set in the client to determine whether the risk corresponding to the business is within the controllable range, give the re-control result, and reach the controlled risk node N4. If the controlled risk node N3 needs to be abandoned, the controlled risk node N3 returns to the intermediate state N2'. If the controlled risk node N4 needs to be re-controlled, the controlled risk node N4 will return to the original state N3', after abandoning control, return to the intermediate state N2', and then return to the initial risk node N1 after release. The original state N3' can also be re-controlled and returned to the controlled risk node N4. In one embodiment, the re-control result can be obtained based on the traders, transaction channels and transaction amounts involved in the business. In another embodiment, the re-control result can be obtained based on the personal information, transaction channels, transaction characteristics, industry characteristics (applicable to public transactions) and occupational characteristics (applicable to private transactions) of the traders involved in the business. The re-control result can be given by the re-control personnel using the client.

[0083] S303: Inherit the controlled risk node N4 to obtain the risk node to be controlled N5, and form the final controlled risk node F according to the final review result of the control of the risk node to be controlled N5. The risk node to be controlled N5 and the final controlled risk node F constitute the final controlled paired node (N5, F).

[0084] It can be understood that when the final risk control node F is reached, the final risk control of the business is completed. The so-called final control may refer to the judgment by the program set in the client whether the risk corresponding to the business is within the controllable range. In one embodiment, the final control result can be obtained based on the traders, transaction channels and transaction amounts involved in the business. In another embodiment, the final control result can be obtained based on the personal information, transaction channels, transaction characteristics, industry characteristics (applicable to public transactions) and occupational characteristics (applicable to private transactions) of the traders involved in the business. The final control result can be given by the final control personnel using the client.

[0085] In one embodiment, after the controlled risk node N4 is formed according to the control review result of the risk node to be controlled N3, it also includes: judging whether the intervention attribute value of the controlled risk node N4 is 1, and if it is 1, forming the final controlled risk node F.

[0086] It is understandable that if the program set in the client determines that the risk has been controlled at this point, there is no need to continue to go through subsequent control levels, and the risk control can be ended directly, that is, the final control risk node F is formed.

[0087] From the above description, it can be seen that the risk management method based on the knowledge graph provided in this application can determine the management path of the risk management knowledge graph according to the management paired nodes.

[0088] See also Figure 4 and Fig.10When n is 2, the control paired nodes include two groups of initial control paired nodes, two groups of secondary control paired nodes and one group of final control paired nodes. The risk control knowledge graph control path is determined according to the control paired nodes, including:

[0089] S401: According to the initial control review result of the initial risk node N1 of the initial control paired node (N1, N2), the controlled risk node N2 is formed, and the initial risk node N1 and the controlled risk node N2 constitute the initial control paired node (N1, N2). The specific method is shown in S301, which will not be repeated here.

[0090] S402: Inherit the controlled risk node N2 to obtain the uncontrolled risk node N3, and form the controlled risk node N4 according to the control review result of the uncontrolled risk node N3. The uncontrolled risk node N3 and the controlled risk node N4 form a re-controlled pair of nodes (N3, N4). The specific method is shown in S302, which will not be repeated here.

[0091] S403: Inherit the controlled risk node N4 to obtain the uncontrolled risk node N5, and form the controlled risk node N6 according to the preliminary review result of the control of the uncontrolled risk node N5. The uncontrolled risk node N5 and the controlled risk node N6 form another initial control pair node (N5, N6). The specific method is shown in S301, which will not be repeated here.

[0092] S404: Inherit the controlled risk node N6 to obtain the uncontrolled risk node N7, and form the controlled risk node N8 according to the control review result of the uncontrolled risk node N7. The uncontrolled risk node N7 and the controlled risk node N8 form another re-controlled pair node (N7, N8). The specific method is shown in S302, which will not be repeated here.

[0093] S405: Inherit the controlled risk node N8 to obtain the risk node to be controlled N9, and form the final controlled risk node F according to the final control result of the risk node to be controlled N9. The risk node to be controlled N9 and the final controlled risk node F form a final controlled paired node (N9, F). The specific method is shown in S303, which will not be repeated here.

[0094] In one embodiment, it is determined whether the intervention attribute value of the controlled risk node N4 or the controlled risk node N8 is 1. If it is 1, a final controlled risk node F is formed.

[0095] It is understandable that if the program set in the client determines that the risk has been controlled at this point, there is no need to continue to go through subsequent control levels, and the risk control can be ended directly, that is, the final control risk node F is formed.

[0096] From the above description, it can be seen that the risk management method based on the knowledge graph provided in this application can determine the management path of the risk management knowledge graph according to the management paired nodes.

[0097] See also Figure 5 and Fig.11 When n is 3, the control paired nodes include three groups of initial control paired nodes, three groups of secondary control paired nodes and one group of final control paired nodes. The risk control knowledge graph control path is determined according to the control paired nodes, including:

[0098] S501: According to the initial control review result of the initial risk node N1 of the initial control paired node (N1, N2), the controlled risk node N2 is formed, and the initial risk node N1 and the controlled risk node N2 constitute the initial control paired node (N1, N2). The specific method is shown in S301, which will not be repeated here.

[0099] S502: Inherit the controlled risk node N2 to obtain the uncontrolled risk node N3, and form the controlled risk node N4 according to the control review result of the uncontrolled risk node N3. The uncontrolled risk node N3 and the controlled risk node N4 form a re-controlled pair of nodes (N3, N4). The specific method is shown in S302, which will not be repeated here.

[0100] S503: Inherit the controlled risk node N4 to obtain the uncontrolled risk node N5, and form the controlled risk node N6 according to the preliminary review result of the control of the uncontrolled risk node N5. The uncontrolled risk node N5 and the controlled risk node N6 form another initial control pair node (N5, N6). The specific method is shown in S301, which will not be repeated here.

[0101] S504: Inherit the controlled risk node N6 to obtain the uncontrolled risk node N7, and form the controlled risk node N8 according to the control review result of the uncontrolled risk node N7. The uncontrolled risk node N7 and the controlled risk node N8 form another re-controlled pair node (N7, N8). The specific method is shown in S302, which will not be repeated here.

[0102] S505: Inherit the controlled risk node N8 to obtain the uncontrolled risk node N9, and form the controlled risk node N10 according to the preliminary review result of the control of the uncontrolled risk node N9. The uncontrolled risk node N9 and the controlled risk node N10 form another preliminary controlled paired node (N9, N10). The specific method is shown in S301, which will not be repeated here.

[0103] S506: Inherit the controlled risk node N10 to obtain the uncontrolled risk node N11, and form the controlled risk node N12 according to the control review result of the uncontrolled risk node N11. The uncontrolled risk node N11 and the controlled risk node N12 form another re-controlled pair node (N11, N12). The specific method is shown in S302, which will not be repeated here.

[0104] S507: Inherit the controlled risk node N12 to obtain the risk node to be controlled N13, and form the final controlled risk node F according to the final control result of the risk node to be controlled N13. The risk node to be controlled N13 and the final controlled risk node F form another final controlled paired node (N13, F). The specific method is shown in S303, which will not be repeated here.

[0105] In one embodiment, it is determined whether the intervention attribute value of the controlled risk node N4, the fourth controlled risk node N8 or the controlled risk node N12 is 1. If it is 1, a final controlled risk node is formed.

[0106] It is understandable that if the program set in the client determines that the risk has been controlled at this point, there is no need to continue to go through subsequent control levels, and the risk control can be ended directly, that is, the final control risk node F is formed.

[0107] From the above description, it can be seen that the risk management method based on the knowledge graph provided in this application can determine the management path of the risk management knowledge graph according to the management paired nodes.

[0108] See also Figure 6 , Fig. 9 , Fig.10 and Fig.11 The risk management method based on knowledge graph provided in this application also includes:

[0109] S601: When the controlled risk nodes N2, N4, N6, N8, N10 and N12 are re-controlled, the original states N1', N3', N5', N7', N9' and N11' corresponding to the controlled risk nodes N2, N4, N6, N8, N10 and N12 are formed.

[0110] S602: When each of the risk nodes to be controlled N3, N5, N7, N9, N11 and N13 or the original states N3', N7' and N11' is abandoned, intermediate states N2', N6' and N10' are formed; among which, the risk nodes to be controlled N3, N5 and the original state N3' correspond to returning to the intermediate state N2'; the risk nodes to be controlled N7, N9 and the original state N7' correspond to returning to the intermediate state N6'; the risk nodes to be controlled N11, N13 and the original state N11' correspond to returning to the intermediate state N10'.

[0111] S603: When the original states N3', N7' and N11' or the intermediate states N2', N6' and N10' are released, return to the initial risk node, the risk node to be controlled or the risk node to be controlled corresponding to each original state N3', N5' and N11' or each intermediate state N2', N6' and N10'.

[0112] From the above description, it can be seen that the risk management method based on knowledge graph provided in this application can obtain the risk attribute value of the business according to the business-related information, and then generate the management and control paired nodes of the risk management knowledge graph, and finally determine the management and control path of the risk management knowledge graph, and construct a risk hierarchy model for intuitive analysis and flexible control of risk factors.

[0113] Based on the same inventive concept, the embodiments of the present application also provide a risk management and control device based on a knowledge graph, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of solving the problem by the risk management and control device based on the knowledge graph is similar to the risk management and control method based on the knowledge graph, the implementation of the risk management and control device based on the knowledge graph can refer to the implementation of the method based on software performance benchmark determination, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0114] See also Figure 7 In order to form a risk management path and realize flexible risk management, the present application provides a risk management device based on a knowledge graph, including: an acquisition unit 701, a generation unit 702 and a determination unit 703.

[0115] An acquisition unit 701 is used to acquire a risk attribute value n of a business according to business related information, where n is a positive integer;

[0116] A generating unit 702 is used to determine a control pair node of a risk control knowledge graph to be generated according to the risk attribute value;

[0117] The determination unit 703 is used to determine the control path of the risk control knowledge graph according to the control paired nodes.

[0118] See also Figure 8 The generation unit 702 includes: a level determination module 801 and a node determination module 802.

[0119] A level determination module 801 is used to determine the risk control level according to the risk attribute value;

[0120] The node determination module 802 is used to determine multiple groups of control paired nodes according to the risk control level.

[0121] From the hardware level, in order to form a risk management path and realize flexible risk management, the present application provides an embodiment of an electronic device that includes all or part of the content of the risk management method based on a knowledge graph, and the electronic device specifically includes the following content:

[0122] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between the risk management and control device based on knowledge graph and related equipment such as core business system, user terminal and related database; the logic controller can be a desktop computer, tablet computer and mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the logic controller can be implemented with reference to the embodiment of the risk management and control method based on knowledge graph and the embodiment of the risk management and control device based on knowledge graph in the embodiment, and the contents thereof are incorporated herein, and the repeated parts are not repeated.

[0123] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0124] In practical applications, part of the risk management method based on the knowledge graph can be executed on the electronic device side as described above, or all operations can be completed in the client device. The specific selection can be based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.

[0125] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0126] Fig.12 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig.12 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig.12 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0127] In one embodiment, the risk management method function based on the knowledge graph can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:

[0128] S101: Obtain a risk attribute value n of the business according to relevant business information, where n is a positive integer;

[0129] S102: Determine a pair of control nodes of a risk control knowledge graph to be generated according to the risk attribute value;

[0130] S103: Determine the control path of the risk control knowledge graph according to the control paired nodes.

[0131] The present application provides a risk management method and device based on a knowledge graph, which can obtain the risk attribute value of a business according to business-related information, and then generate management and control paired nodes of the risk management knowledge graph, and finally determine the management and control path of the risk management knowledge graph, forming a risk hierarchy model for intuitive analysis and flexible control of risk factors.

[0132] In another embodiment, the risk management device based on the knowledge graph can be configured separately from the central processing unit 9100. For example, the risk management device based on the knowledge graph can be configured as a chip connected to the central processing unit 9100, and the functions of the risk management method based on the knowledge graph can be implemented through the control of the central processing unit.

[0133] like Fig.12 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig.12 In addition, the electronic device 9600 may also include Fig.12 For components not shown, reference may be made to the prior art.

[0134] like Fig.12 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0135] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0136] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0137] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0138] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0139] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0140] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0141] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the risk management method based on the knowledge graph in the above embodiments, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, all the steps of the risk management method based on the knowledge graph in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0142] S101: Obtain a risk attribute value n of the business according to relevant business information, where n is a positive integer;

[0143] S102: Determine a pair of control nodes of a risk control knowledge graph to be generated according to the risk attribute value;

[0144] S103: Determine the control path of the risk control knowledge graph according to the control paired nodes.

[0145] The present application provides a risk management method and device based on a knowledge graph, which can obtain the risk attribute value of a business according to business-related information, and then generate management and control paired nodes of the risk management knowledge graph, and finally determine the management and control path of the risk management knowledge graph, forming a risk hierarchy model for intuitive analysis and flexible control of risk factors.

[0146] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0148] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0150] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A risk management method based on knowledge graph, characterized in that: include: Obtaining a risk attribute value n of the business according to the business-related information, where n is a positive integer; wherein the business-related information includes the remitter's personal information, remittance amount and remittance channel, the trader's personal information, transaction channel, transaction characteristics, industry characteristics and occupational characteristics; the risk attribute value is calculated by using a weighted summation method according to the weights corresponding to each data item in the business-related information; Determine the control pair nodes of the risk control knowledge graph to be generated according to the risk attribute value; wherein the number of pairs of control pairs of nodes is (2×n+1); Determining a control path of the risk control knowledge graph according to the control paired nodes; Among them, control includes initial control, re-control and final control; The initial control refers to the program set in the client to determine whether the risk corresponding to the business is within the controllable range and give the initial control result; The re-control refers to the program set in the client to determine whether the risk corresponding to the business is within the controllable range and give the re-control result; The final control refers to the program set in the client to determine whether the risk corresponding to the business is within the controllable range; When n is 1, the control paired nodes include a group of initial control paired nodes, a group of secondary control paired nodes, and a group of final control paired nodes, and the control path of the risk control knowledge graph is determined according to the control paired nodes, including: A first controlled risk node is formed according to the control preliminary review result of the initial risk node of the initial controlled paired node, and the initial risk node and the first controlled risk node constitute the initial controlled paired node; The first controlled risk node is inherited to obtain a first risk node to be controlled, and a second controlled risk node is formed according to the control review result of the first risk node to be controlled, and the first risk node to be controlled and the second controlled risk node constitute the re-controlled paired node; The second controlled risk node is inherited to obtain the second risk node to be controlled, and the final controlled risk node is formed according to the final review result of the management and control of the second risk node to be controlled. The second risk node to be controlled and the final controlled risk node constitute the final controlled paired node.

2. The risk management method according to claim 1, characterized in that: Determining the control paired nodes of the risk control knowledge graph to be generated according to the risk attribute value includes: Determining a risk control level according to the risk attribute value; A plurality of groups of control paired nodes are determined according to the risk control level.

3. The risk management method according to claim 1, characterized in that: After forming the second controlled risk node according to the control review result of the first risk node to be controlled, the method further includes: It is determined whether the intervention attribute value of the second controlled risk node is 1. If it is 1, a final controlled risk node is obtained.

4. The risk management method according to claim 1, characterized in that: When n is 2, the control paired nodes include two groups of initial control paired nodes, two groups of secondary control paired nodes and one group of final control paired nodes, and the determining of the risk control knowledge graph control path according to the control paired nodes includes: According to the control preliminary review result of the initial risk node of the first group of initially controlled paired nodes, a first controlled risk node is formed, wherein the initial risk node and the first controlled risk node constitute the first group of initially controlled paired nodes; The first controlled risk node is inherited to obtain a first risk node to be controlled, and a second controlled risk node is formed according to the control review result of the first risk node to be controlled, and the second risk node to be controlled and the second controlled risk node constitute a first group of re-controlled paired nodes; The second controlled risk node is inherited to obtain a second risk node to be controlled, and a third controlled risk node is formed according to the preliminary review result of the control of the second risk node to be controlled. The first risk node to be controlled and the third controlled risk node constitute a second group of preliminary controlled paired nodes; The third controlled risk node is inherited to obtain a third risk node to be controlled, and a fourth controlled risk node is formed according to the control review result of the third risk node to be controlled, and the third risk node to be controlled and the fourth controlled risk node constitute a second group of re-controlled paired nodes; The fourth controlled risk node is inherited to obtain a fourth risk node to be controlled, and a final controlled risk node is formed according to the final review result of the management and control of the fourth risk node to be controlled. The fourth risk node to be controlled and the final controlled risk node constitute a final controlled paired node.

5. The risk management method according to claim 4, characterized in that: Also includes: It is determined whether the intervention attribute value of the second controlled risk node or the fourth controlled risk node is 1. If it is 1, a final controlled risk node is obtained.

6. The risk management method according to claim 1, characterized in that: When n is 3, the control paired nodes include three groups of initial control paired nodes, three groups of secondary control paired nodes and one group of final control paired nodes, and the determining of the risk control knowledge graph control path according to the control paired nodes includes: According to the preliminary review results of the control of the initial risk node of the first group of initially controlled paired nodes, a first controlled risk node is formed, wherein the initial risk node and the first controlled risk node constitute the first group of initially controlled paired nodes; The first controlled risk node is inherited to obtain a first risk node to be controlled, and a second controlled risk node is formed according to the control review result of the first risk node to be controlled, wherein the first risk node to be controlled and the second controlled risk node constitute a first group of re-controlled paired nodes; The second controlled risk node is inherited to obtain a second risk node to be controlled, and a third controlled risk node is formed according to the preliminary review result of the control of the second risk node to be controlled. The second risk node to be controlled and the third controlled risk node constitute a second group of preliminary controlled paired nodes; The third controlled risk node is inherited to obtain a third risk node to be controlled, and a fourth controlled risk node is formed according to the control review result of the third risk node to be controlled, and the third risk node to be controlled and the fourth controlled risk node constitute a second group of re-controlled paired nodes; The fourth controlled risk node is inherited to obtain a fourth risk node to be controlled, and a fifth controlled risk node is formed according to the preliminary review result of the control of the fourth risk node to be controlled. The fourth risk node to be controlled and the fifth controlled risk node constitute a third group of preliminary controlled paired nodes; The fifth controlled risk node is inherited to obtain a fifth risk node to be controlled, and a sixth controlled risk node is formed according to the control review result of the fifth risk node to be controlled, and the fifth risk node to be controlled and the sixth controlled risk node constitute a third group of re-controlled paired nodes; The sixth controlled risk node is inherited to obtain the sixth risk node to be controlled, and a final controlled risk node is formed according to the final review result of the control of the sixth risk node to be controlled. The sixth risk node to be controlled and the final controlled risk node constitute a final controlled paired node.

7. The risk management method according to claim 6, characterized in that: Also includes: It is determined whether the intervention attribute value of the second controlled risk node, the fourth controlled risk node or the sixth controlled risk node is 1. If it is 1, a final controlled risk node is obtained.

8. The risk management method according to any one of claims 1 to 7, characterized in that: Also includes: When each controlled risk node is re-controlled, the original state is obtained; When each risk node to be controlled or the original state is abandoned, an intermediate state is obtained; When the original state or the intermediate state is released, the initial risk node, the second risk node to be controlled or the fourth risk node to be controlled corresponding to each original state or each intermediate state is returned to.

9. A risk management and control device based on knowledge graph, characterized in that: include: An acquisition unit is used to acquire a risk attribute value n of the business according to the business related information, where n is a positive integer; wherein the business related information includes the personal information of the remitter, the remittance amount and the remittance channel, the personal information of the trader, the transaction channel, the transaction characteristics, the industry characteristics and the occupation characteristics; the risk attribute value is calculated by a weighted summation method according to the weight corresponding to each data item in the business related information; A generating unit, used for determining the control pair nodes of the risk control knowledge graph to be generated according to the risk attribute value; wherein the number of pairs of control pair nodes is (2×n+1); A determination unit, configured to determine a control path of the risk control knowledge graph according to the control paired nodes; Among them, control includes initial control, re-control and final control; The initial control refers to the program set in the client to determine whether the risk corresponding to the business is within the controllable range and give the initial control result; The re-control refers to the program set in the client to determine whether the risk corresponding to the business is within the controllable range and give the re-control result; The final control refers to the program set in the client to determine whether the risk corresponding to the business is within the controllable range; When n is 1, the control paired nodes include a group of initial control paired nodes, a group of secondary control paired nodes, and a group of final control paired nodes, and the control path of the risk control knowledge graph is determined according to the control paired nodes, including: A first controlled risk node is formed according to the control preliminary review result of the initial risk node of the initial controlled paired node, and the initial risk node and the first controlled risk node constitute the initial controlled paired node; The first controlled risk node is inherited to obtain a first risk node to be controlled, and a second controlled risk node is formed according to the control review result of the first risk node to be controlled, and the first risk node to be controlled and the second controlled risk node constitute the re-controlled paired node; The second controlled risk node is inherited to obtain the second risk node to be controlled, and the final controlled risk node is formed according to the final review result of the management and control of the second risk node to be controlled. The second risk node to be controlled and the final controlled risk node constitute the final controlled paired node.

10. The risk management and control device according to claim 9, characterized in that: The generating unit comprises: A level determination module, used to determine the risk control level according to the risk attribute value; The node determination module is used to determine multiple groups of control paired nodes according to the risk control level.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the risk management method based on the knowledge graph described in any one of claims 1 to 8 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the risk management method based on the knowledge graph described in any one of claims 1 to 8 are implemented.

Images