Risk Monitoring and Handling Method, Device, Electronic Device, and Storage Medium

Abstract

The present application discloses a risk monitoring and processing method, apparatus, electronic device, and storage medium. The method includes first obtaining network risk information to be monitored; extracting a directly associated entity and a risk event from the network risk information, and determining an importance index and an emotion index of the risk event for the directly associated entity; obtaining the entity relationship of the directly associated entity, and establishing at least one conduction path between the directly associated entity and the indirectly associated entity according to the entity relationship; performing emotion conduction based on the at least one established conduction path, and determining the importance index and the emotion index of the indirectly associated entity regarding the network risk information. In the present invention, risk analysis and determination are performed by extracting the directly associated entity and the risk event from the network risk information and determining the importance index and the emotion index of the directly associated entity, and according to the established conduction path, the risk information is effectively guided to the indirectly associated entity, improving the accuracy of risk information processing.

Description

Technical Field

[0001] The present invention relates to the field of information processing, and particularly to a risk monitoring and processing method, apparatus, electronic device, and storage medium. Background Art

[0002] With the rapid development of new technologies such as mobile Internet and Internet of Things, mankind has entered the data era. The information storm brought by the data era is changing our way of life, work, and thinking, and also has a profound impact on network risk management.

[0003] Network risk is carried by the network and centered around events. It is the expression, dissemination, interaction, and subsequent influence of the emotions, attitudes, opinions, and views of the majority of Internet users. Internet users can quickly obtain various types of social information from the network through various channels, and publish their subjective opinions on the Internet and communicate with others. While closely monitoring risks, being able to deeply explore the value of risk big data is conducive to obtaining feedback from society, the market, and users, and thus obtaining business opportunities.

[0004] If relying on manual monitoring of network risk information from millions of data every day, the efficiency of network risk monitoring and processing will be greatly reduced. When manually screening network risk information during risk monitoring and processing, it is easy to miss some information, reducing the accuracy of network risk monitoring and processing. Summary of the Invention

[0005] Based on this, the embodiments of the present application provide a risk monitoring and processing method, apparatus, electronic device, and storage medium, which can improve the accuracy of network risk monitoring and processing.

[0006] In a first aspect, a risk monitoring and processing method is provided. The method includes:

[0007] Obtain network risk information to be monitored;

[0008] Extract a directly associated entity and a risk event from the network risk information through keyword recognition, and receive risk indication information sent by a user to determine an importance index and an emotion index of the risk event for the directly associated entity;

[0009] Obtain the entity relationship of the directly associated entity, and establish at least one conduction path between the directly associated entity and an indirectly associated entity according to the entity relationship; wherein, an emotion conduction coefficient is further included in the conduction path;

[0010] Perform emotion conduction based on the at least one established conduction path to determine the importance index and emotion index of the indirectly associated entity regarding the network risk information.

[0011] Optionally, receiving the risk indication information sent by the user to determine the importance index and sentiment index of the risk event for the directly associated entity, including:

[0012] Determining the importance index of the risk event for the directly associated entity according to the first formula, and the first formula specifically includes:

[0013] PI(X0|e j )=P(e j )·R(X0,e j )

[0014] Among them, PI(X0|e j ) represents the importance of the risk event e j to the directly associated entity X0, P(e j ) represents the importance of the risk event e j , and R(X0,e j ) represents the degree of association between the risk event e j and the directly associated entity X0.

[0015] Optionally, performing sentiment conduction based on the established at least one conduction path to determine the importance index of the indirectly associated entity regarding the network risk information, including:

[0016] Determining the importance index of the risk event for the indirectly associated entity according to the second formula, and the second formula specifically includes:

[0017] PE(X i |e j )=PI(X0|e j )·R(X i ,X0)

[0018] Among them, PE(X i |e) represents the importance of the risk event e j to the indirectly associated entity X i , PI(X0|e j ) represents the importance of the risk event e j to the directly associated entity X0, and R(X i ,X0) represents the degree of association between the indirectly associated entity X i and the directly associated entity X0.

[0019] Optionally, the degree of association between the indirectly associated entity and the directly associated entity specifically includes:

[0020]

[0021] Among them, R(X i ,X0) represents the degree of association between the indirectly associated entity X iDegree of association with the directly associated entity X0, RP j (X i , X0) represents the indirectly associated entity X i and the directly associated entity X0 on the reachable path P j where the indirectly associated entity X i Degree of association with the directly associated entity X0, n represents the number of reachable paths.

[0022] Optionally, on the reachable path P j where the indirectly associated entity X i Degree of association with the directly associated entity X0 specifically includes:

[0023]

[0024] Among them, RS kj (X j0 , X j1 ) represents on the reachable path P j at the j-th step, the degree of association of the path between adjacent entities X j0 , X j1 , f represents a piecewise function, represents a path parameter, D k represents the depth of the path, C takes values in (0, 1), m represents the length of the reachable path, and j represents the current path.

[0025] Optionally, establish at least one conduction path between the directly associated entity and the indirectly associated entity according to the entity relationship, including:

[0026] Determine the degree of association between the indirectly associated entity X i and the directly associated entity X0 according to the third formula, and the third formula specifically includes:

[0027]

[0028] Among them, R(X i , X0) represents the degree of association between the indirectly associated entity X i and the directly associated entity X0, X j is the path adjacent point of X i , R(X j , X0) represents the degree of association between the indirectly associated entity X j and the directly associated entity X0, RS(X i , X j ) represents the path association degree, m represents the length of the reachable path, and j represents the current path.

[0029] Optionally, perform emotion conduction based on the established at least one conduction path to determine the emotion index of the indirectly associated entity regarding the network risk information, including:

[0030] Determine the sentiment index degree of the indirectly associated entity regarding the network risk information according to the fourth formula, and the specific fourth formula includes:

[0031] SE(X i |e j ) = SI(X0|e j )·SP(P j )

[0032] st.arg(P j , X i ), max{PI(X0|e j )·R(X i , X0)}

[0033] Among them, SE(X i |e j ) represents the sentiment index of the risk event e j on the indirectly associated entity X i , SI(X s |e j ) represents the sentiment index of the risk event e j on the directly associated entity X0, SP(P j ) represents the sentiment conduction coefficient of the path P j , PI(X0|e j ) represents the importance of the risk event e j to the directly associated entity X0, and R(X i , X0) represents the association degree between the indirectly associated entity X i and the directly associated entity X0.

[0034] Second, a risk monitoring and processing device is provided, and the device includes:

[0035] An acquisition module, configured to acquire network risk information to be monitored;

[0036] An extraction module, configured to extract a directly associated entity and a risk event from the network risk information through keyword recognition, and receive risk indication information sent by a user to determine the importance index and sentiment index of the risk event for the directly associated entity;

[0037] A building module, configured to acquire the entity relationship of the directly associated entity, and establish at least one conduction path between the directly associated entity and the indirectly associated entity according to the entity relationship; wherein, the conduction path further includes a sentiment conduction coefficient;

[0038] A determination module, configured to determine an importance index and an emotion index of the indirectly associated entity with respect to the network risk information based on at least one established conduction path for emotion conduction.

[0039] In a third aspect, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the risk monitoring and processing method according to any one of the first aspects described above is implemented.

[0040] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the risk monitoring and processing method according to any one of the first aspects described above is implemented.

[0041] In the technical solution provided by the embodiments of the present application, first, network risk information to be monitored is obtained; a directly associated entity and a risk event are extracted from the network risk information, and an importance index and an emotion index of the risk event with respect to the directly associated entity are determined; an entity relationship of the directly associated entity is obtained, and at least one conduction path between the directly associated entity and the indirectly associated entity is established according to the entity relationship; wherein, an emotion conduction coefficient is further included in the conduction path; emotion conduction is performed based on the at least one established conduction path, and an importance index and an emotion index of the indirectly associated entity with respect to the network risk information are determined. In the present invention, risk analysis and determination are performed by extracting a directly associated entity and a risk event from network risk information and determining an importance index and an emotion index of the directly associated entity. According to the established conduction path, the risk information is effectively guided to the indirectly associated entity, improving the accuracy of risk information processing. Description of the Drawings

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, other implementation drawings can be obtained by extending according to the provided drawings without creative efforts.

[0043] Figure 1 It is a flowchart of the steps of a risk monitoring and processing method provided by an embodiment of the present application;

[0044] Figure 2 It is a schematic diagram of self-risk and surrounding risks provided by an embodiment of the present application;

[0045] Figure 3 It is a schematic diagram when there are multiple related risks between the directly associated entity and the indirectly associated entity in an embodiment of the present application;

[0046] Figure 4Schematic diagram of a case when this application is in a single - path, full - conduction embodiment;

[0047] Figure 5 Schematic diagram of a case when this application is in a single - path, non - full - conduction embodiment;

[0048] Figure 6 Schematic diagram of a case when this application is in a multi - path conduction embodiment;

[0049] Figure 7 Schematic diagram of a case when this application is in a non - homogeneous entity association embodiment;

[0050] Figure 8 Block diagram of a risk monitoring and processing device provided by an embodiment of this application;

[0051] Figure 9 Schematic diagram of an electronic device provided by an embodiment of this application. Detailed implementation manners

[0052] In order to make the objectives, technical solutions and advantages of this application clearer and more understandable, the following further details this application in combination with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0053] In the description of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more. Terms such as "first", "second", "third", "fourth", etc. in the specification and claims of the present invention and the above - mentioned drawings are intended to distinguish the objects being referred to. For a solution with a time - sequence process, this way of term expression does not necessarily need to be understood as describing a specific order or sequence. For a solution of a device structure, this way of term expression also does not distinguish the importance level, positional relationship, etc.

[0054] In addition, the terms "include", "have" and any of their variations are intended to cover non - exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units that are clearly listed, but may also include other steps or units that are inherent to these processes, methods, products or devices although not clearly listed, or steps or units added by further optimized solutions based on the concept of the present invention.

[0055] For the convenience of understanding this embodiment, first, a risk monitoring and processing method disclosed in the embodiments of this application is introduced in detail. Please refer to Figure 1 , which shows a flowchart of a risk monitoring and processing method provided by an embodiment of this application. The method may include the following steps:

[0056] Step 101, obtain network risk information to be monitored.

[0057] Set up monitoring on the corresponding platform to obtain the time of risk information acquisition, and obtain the risk information updated by the monitored platform in real time or within a preset time period. Specifically, the risk information obtained by extracting the following information from announcements, regulations, etc. includes: risk type, title, release date, risk link. Among them, the risk type can include announcement information, administrative penalty information, etc.; the title can include the 2019 annual report of Company A, etc.

[0058] Step 102: Extract the directly associated entity and risk event from the network risk information through keyword recognition, and receive the risk indication information sent by the user to determine the importance index and sentiment index of the risk event for the directly associated entity.

[0059] Specifically, according to the relationship between the risk and the associated entity, the risk can be divided into: its own risk, surrounding risk, such as Figure 2 , in the figure:

[0060] (1) Its own risk. The associated entity X0 is directly associated with the risk event e. Therefore, the risk event e is the own risk of the associated entity X0, and X0 is the directly associated entity.

[0061] (2) Surrounding risk. The associated entity X i is indirectly associated with the risk event e (there may be Pi - related risks in the middle). Therefore, the risk event e is the surrounding risk of the associated entity X i , and X i is the indirectly associated entity.

[0062] Among them, the associated entities include enterprises, industries, regions, concepts, etc.

[0063] Risk contains two types of attributes: importance, sentiment.

[0064] (1) Importance. The degree of influence of the risk event e on the associated entity, which can be characterized by an importance index.

[0065] (2) Sentiment. The sentiment of the risk event e towards the associated entity, which can be characterized by a sentiment index.

[0066] Such as Figure 3 shows a schematic diagram between the directly associated entity X0 and the indirectly associated entity X i when there are multiple related risks. Among them, the RSi path can be characterized as the target path of the directly associated entity and the indirectly associated entity at the specified risk time.

[0067] In this application, the importance of a risk event is determined based on factors such as the type and attributes of the risk; the degree of association of a risk event with a directly associated entity is not determined manually, but by an association degree algorithm, which is determined by the TI / IDF algorithm in the embodiments of this application; the sentiment of a risk event towards a directly associated entity is determined by the risk sentiment, and the determination of the risk sentiment is through a classification algorithm (such as: Bayes network). Specifically:

[0068] For example, in the annual report of Company A in 2019 as the risk information, it can be determined that the directly associated entity is Company A, and at the same time, the importance index and sentiment index of this information for Company A are determined manually. Among them, the importance index and sentiment index can include:

[0069] Table 1 Definition of Importance Index

[0070]

[0071] Table 2 Definition of Sentiment Index

[0072]

[0073] Step 103: Obtain the entity relationship of the directly associated entity, and establish at least one conduction path between the directly associated entity and the indirectly associated entity according to the entity relationship.

[0074] Among them, the conduction path also includes an emotion conduction coefficient.

[0075] In the embodiments of this application, in the self-risk, there is a direct association between the associated entity and the risk event. The definitions and algorithms of its importance and sentiment are as follows:

[0076] Determine the importance index of the risk event for the directly associated entity according to the first formula, and the first formula specifically includes:

[0077] PI(X0|e j )=P(e j )·R(X0,e j ) (1)

[0078] Among them, PI(X0|e j ) represents the importance of the risk event e j to the directly associated entity X0, P(e j ) represents the importance of the risk event e j , and R(X0,e j ) represents the degree of association of the risk event e j with the directly associated entity X0.

[0079] And according to SI(X0|e j ) represents the risk event e jSentiment towards the directly associated entity X0.

[0080] In peripheral risk, the associated entity is indirectly associated with the risk event. The definition and algorithm of its importance and sentiment are as follows.

[0081] The importance index of the risk event to the indirectly associated entity is determined according to the second formula, wherein the second formula specifically includes:

[0082] PE(X i |e j )=PI(X0|e j )·R(X i ,X0) (2)

[0083] Among them, PE(X i |e) represents risk event e j For indirectly related entity X i The importance of PI(X0|e j ) represents risk event e j The importance of the directly related entity X0, R(X i , X0) represents the indirect related entity X i The degree of association with the directly related entity X0.

[0084] In an optional embodiment of the present application, the degree of association between the indirectly associated entity and the directly associated entity specifically includes:

[0085]

[0086] Among them, R(X i , X0) represents the indirect related entity X i The degree of association with the directly related entity X0, RP j (X i , X0) represents the indirect related entity X i With the directly related entity X0 on the reachable path P j Indirectly related entity X i The association degree with the directly related entity X0, n represents the number of reachable paths.

[0087] In an optional embodiment of the present application, on the reachable path P j Indirectly related entity X i The degree of association with the directly related entity X0 specifically includes:

[0088]

[0089] Among them, RS kj (X j0 , X j1 ) represents a reachable path P jIn step j, for the adjacent entities X on the j-th path j0 , X j1 , the correlation degree of the path between them, f represents a piecewise function, represents the path parameter, D k represents the depth of the path, C takes values in (0, 1), m represents the length of the reachable path, and j represents the current path.

[0090] Among them, the relationship type of the path correlation degree can be equity or management. Since the contribution of the equity ratio to the correlation degree is non - continuous and non - linear, a piecewise function is introduced in the correlation degree algorithm to amplify and reduce the contribution of the equity ratio above and below 50% respectively.

[0091] When the path depth exceeds 1, the definition of the piecewise function f is as follows.

[0092]

[0093] When the path depth is 1, the two companies are directly related. We stipulate that the importance of the acquirer (shareholding > 5%) is general (0.6), and the definition of the piecewise function f is as follows.

[0094] f = ((x - 0.05) / 0.95)*0.4 + 0.6

[0095] Here, the piecewise function f maps the space [0.05, 1] to [0.6, 1], and f can be regarded as a combination of three linear functions f1, f2, f3.

[0096] f = f3(f2(f1(x)))

[0097] f1 maps the space [0.05, 1] to [0, 1].

[0098] f2 maps the space [0, 1] to [0, 0.4].

[0099] f3 maps the space [0, 0.4] to [0.6, 1].

[0100] Because there is also an inverse - proportional - like relationship between the path length from the starting node to the target node and the correlation degree. The shorter the path, the stronger the correlation degree, and vice versa. Therefore, a function similar to the half - life function is introduced in the correlation degree algorithm, taking the path length as the influencing factor of the correlation degree, In, D k represents the depth of the path, C takes values in (0, 1), the larger the value of C, the slower the attenuation. In the embodiments of this application, through experiments, when C = 0.85, it fits the actual application, so C = 0.85 is adopted.

[0101] Entity X i The correlation degree R(X i, X0), is transformed as follows according to the third formula. Specifically:

[0102] Determine the indirectly associated entity X according to the third formula i The degree of association with the directly associated entity X0, and the third formula specifically includes:

[0103]

[0104] Among them, R(X i , X0) represents the degree of association between the indirectly associated entity X i and the directly associated entity X0, X j is the path adjacent point of X i , R(X j , X0) represents the degree of association between the indirectly associated entity X j and the directly associated entity X0, RS(X i , X j ) represents the step - path association degree, m represents the length of the reachable path, and j represents the current path.

[0105] Therefore, the calculation of R(X i , X0) is essentially a process of dynamic programming and can be implemented by recursion. In this embodiment, the method of queue and level traversal can be used to implement it. To improve the execution efficiency of the algorithm, "pruning" can be performed during the level traversal.

[0106] Suppose the importance index of the self - risk of the starting directly associated entity X0 is 5 (very important). If during the traversal, the path association degree RP k of the traversed path P k (X i , X0) ≤ 0.4, then, through this reachable path P k , the importance index of the peripheral risk of the indirectly associated entity X i is less than or equal to 2 (unimportant or extremely unimportant). Therefore, when the path association degree RP k ≤ 0.4, "pruning" can be performed.

[0107] Step 104, conduct emotion conduction based on the established at least one conduction path, and determine the importance index and emotion index of the indirectly associated entity regarding the network risk information.

[0108] Conduct emotion conduction based on the established at least one conduction path, and determine the emotion index of the indirectly associated entity regarding the network risk information, including:

[0109] Determine the emotion index degree of the indirectly associated entity regarding the network risk information according to the fourth formula, and the fourth formula specifically includes:

[0110] SE(Xi |e j ) = SI(X0|e j )·SP(P j )

[0111] st.arg(P j ,X i ),max{PI(X0|e j )·R(X i ,X0)}

[0112] Wherein, SE(X i |e j ) represents the sentiment index of the risk event e j towards the indirectly associated entity X i ; SI(X s |e j ) represents the sentiment index of the risk event e j towards the directly associated entity X0; SP(P j ) represents the sentiment conduction coefficient of the path P j ; PI(X0|e j ) represents the importance of the risk event e j towards the directly associated entity X0; R(X i ,X0) represents the association degree between the indirectly associated entity X i and the directly associated entity X0.

[0113] In an alternative embodiment of the present application, path propagation includes (1) single - path, full - conduction cases; (2) single - path, non - full - conduction cases; (3) multi - path conduction cases; (4) non - homogeneous entity associations.

[0114] Specifically, in 1. Single - path, full - conduction cases, as Figure 4 shown:

[0115] Case illustration:

[0116] Company A holds 100.00% equity of Company B.

[0117] (1) Importance:

[0118] PI(Company A|e1) = 3 (average)

[0119] R(Company A, Company B) = (1 / 2 + 0.5)*1 = 1.

[0120] PE(Company B|e1) = 3*1 = 3 (average)

[0121] (2) Sentiment:

[0122] SI(Company A|e1) = 0 (neutral);

[0123] SE(B Company|e1) = 0 * 1 = 0 (Neutral)

[0124] 2. In single - path, non - full - conduction cases, such as Figure 5 :

[0125] Case illustration:

[0126] Company A holds 9.70% equity in Company B.

[0127] (1) Importance:

[0128] PI(Company A|e2) = 4 (Important)

[0129] R(A, B) = 0.097 / 2 = 0.0485.

[0130] PE(B|e2) = 4 * 0.0485 = ceil(0.194) = 1 (Extremely unimportant)

[0131] (2) Sentiment:

[0132] SI(A|e2) = - 1 (Negative)

[0133] SP(P j ) = 1

[0134] SE(B|e2) = - 1 * 1 = - 1 (Negative)

[0135] 3. In multi - path conduction cases, such as Figure 6 shown below:

[0136] Case illustration:

[0137] Company A controls Company F through multiple paths.

[0138] (1) Importance:

[0139] PI(Company A|e2) = 4 (Important)

[0140] R(Company A, Company F) = max{RP j (A, Company F)}

[0141] Since there are 3 paths for Company A to reach Company F, the path with the highest correlation needs to be selected from these 3 reachable paths. The correlation calculations for the 3 reachable paths are as follows.

[0142] The correlation calculation for Path 1 is as follows:

[0143] RP1(Company A, Company F) = (1 / 2 + 0.5) * (0.0224 / 2) * (1 / 2 + 0.5) * (0.9823 / 2 + 0.5) * 0.85 ^ (4 - 1) = 0.0069

[0144] RP2(A Company, F Company) = (0.3560 / 2) * (1 / 2 + 0.5) * (0.9823 / 2 + 0.5) * 0.85 ^ (3 - 1) = 0.1286

[0145] RP3(A Company, F Company) = (1 / 2 + 0.5) * (0.0224 / 2) * (1 / 2 + 0.5) * (0.9823 / 2 + 0.5) * 0.85 ^ (4 - 1) = 0.0069

[0146] To sum up:

[0147] R(A Company, F Company) = 0.1286

[0148] PI(A Company|e2) = 4 (Important)

[0149] PE(A|e2) = max{ceil(0.1286 * 4)} = 1 (Extremely unimportant)

[0150] (2) Emotion:

[0151] SI(A Company|e2) = -1 (Negative)

[0152] To sum up:

[0153] SE(F Company|e2) = -1 * 1 = -1 (Negative)

[0154] 4. In the case of non - homogeneous entity association, as Figure 7 shown:

[0155] To avoid "computing explosion and information explosion" caused by the conduction of system - type risks (industry - type risks, concept - type risks, regional - type risks), the conduction of risks only occurs between entities of the same type. Specifically, it means that risks only conduct between enterprises and enterprises, industries and industries, regions and regions, and concepts and concepts.

[0156] When a user views the risks of an enterprise, the industry and regional risks related to the enterprise are associated through the industry and regional attributes of the enterprise, rather than being conducted from the industry and region to the enterprise.

[0157] Case illustration:

[0158] Industry - type risks are associated with enterprise entities through industry entities.

[0159] (1) Importance:

[0160] PI(Network payment security system|Industry: Contributes to building a payment security defense line) = 4 (Important)

[0161] R(Corporation C, Network Payment Security System) = 1

[0162] PE(Corporation C | Industry: Contributes to Building the Payment Security Defense Line)

[0163] = max{PI(Network Payment Security System | Industry: Contributes to Building the Payment Security Defense Line) * R(Corporation C, Network Payment Security System)}

[0164] = max{4 * 1} = 4 (Important)

[0165] (2) Emotion:

[0166] SI(Xs | ej) = 1 (Positive)

[0167] SP(Pj) = 1

[0168] SE(Corporation C | Industry: Contributes to Building the Payment Security Defense Line) = 1 * 1 = 1 (Positive)

[0169] Please refer to Figure 8 , which shows a block diagram of a risk monitoring and processing device 200 provided by an embodiment of the present application. As Figure 8 shown, the device 200 may include: an acquisition module 201, an extraction module 202, a establishment module 203, and a determination module 204.

[0170] The acquisition module 201 is configured to acquire network risk information to be monitored;

[0171] The extraction module 202 is configured to extract a directly associated entity and a risk event from the network risk information through keyword recognition, and receive risk indication information sent by a user to determine an importance index and an emotion index of the risk event for the directly associated entity;

[0172] The establishment module 203 is configured to acquire an entity relationship of the directly associated entity, and establish at least one conduction path between the directly associated entity and an indirectly associated entity according to the entity relationship; wherein, the conduction path further includes an emotion conduction coefficient;

[0173] The determination module 204 is configured to perform emotion conduction based on the at least one established conduction path, and determine an importance index and an emotion index of the indirectly associated entity regarding the network risk information.

[0174] For the specific limitations of the risk monitoring and processing device, reference can be made to the limitations of the risk monitoring and processing method in the above text, which will not be elaborated here. Each module in the above risk monitoring and processing device can be implemented in whole or in part by software, hardware, and their combinations. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0175] In one embodiment, an electronic device is provided. The electronic device may be a computer, and its internal structural diagram may be as Figure 9 shown. The electronic device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the device is used to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for risk monitoring and processing data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a risk monitoring and processing method.

[0176] Those skilled in the art can understand that the structure shown in Figure 9 is only a block diagram of a part of the structure related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0177] In an embodiment of this application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the above risk monitoring and processing method.

[0178] The computer-readable storage medium provided in this embodiment has the same implementation principle and technical effects as the above method embodiment, which will not be elaborated here.

[0179] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in M forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Symchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0180] The technical features of the above embodiments can be combined arbitrarily (as long as there is no contradiction in the combination of these technical features). For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described; these embodiments that are not explicitly written out should also be considered to be within the scope described in this specification.

[0181] In the foregoing, the present application has been described in a relatively specific and detailed manner through general descriptions and specific embodiments. It should be understood that based on the technical concept of the present application, several conventional adjustments or further innovations can be made to these specific embodiments; but as long as they do not depart from the technical concept of the present application, the technical solutions obtained by these conventional adjustments or further innovations also fall within the protection scope of the claims of the present application.

Claims

1. A risk monitoring and processing method, characterized in that, The method includes: Obtaining network risk information to be monitored; Extracting a directly associated entity and a risk event from the network risk information through keyword recognition, and receiving risk indication information sent by a user to determine an importance index and an emotion index of the risk event for the directly associated entity; Obtaining the entity relationship of the directly associated entity, and establishing at least one conduction path between the directly associated entity and an indirectly associated entity according to the entity relationship; wherein, an emotion conduction coefficient is further included in the conduction path; Performing emotion conduction based on the at least one established conduction path to determine the importance index and the emotion index of the indirectly associated entity regarding the network risk information; Performing emotion conduction based on the at least one established conduction path to determine the emotion index of the indirectly associated entity regarding the network risk information, including: Determining the emotion index degree of the indirectly associated entity regarding the network risk information according to a fourth formula, and the fourth formula specifically includes: ， Among them, represents the sentiment index of the risk event for indirectly associated entities ; represents the sentiment index of the risk event for directly associated entities ; represents the sentiment conduction coefficient of the path ; represents the importance of the risk event for directly associated entities ; represents the association degree between the indirectly associated entity and the directly associated entity .

2. The method according to claim 1, characterized in that, Receiving risk indication information sent by a user to determine the importance index and the emotion index of the risk event for the directly associated entity, including: Determining the importance index of the risk event for the directly associated entity according to a first formula, and the first formula specifically includes: ， Among them, represents a risk event for the directly associated entity importance, represents the importance of the risk event importance, represents the risk event for the directly associated entity degree of association.

3. The method according to claim 1, characterized in that, Performing emotion conduction based on the at least one established conduction path to determine the importance index of the indirectly associated entity regarding the network risk information, including: Determining the importance index of the risk event for the indirectly associated entity according to a second formula, and the second formula specifically includes: ， Among them, represents the importance of a risk event to an indirectly related entity ; represents the importance of a risk event to a directly related entity ; represents the degree of association between an indirectly related entity and a directly related entity .

4. The method according to claim 3, characterized in that, The association degree between the indirectly associated entity and the directly associated entity specifically includes: ， Among them, represents the indirect associated entity and the direct associated entity of the association degree, represents the indirect associated entity and the direct associated entity on the reachable path the indirect associated entity and the direct associated entity of the association degree, represents the number of reachable paths.

5. The method according to claim 4, characterized in that, On the reachable path Indirectly associated entities The degree of association with directly associated entities Specifically includes: ， Among them, represents the reachable path In on the step path, the correlation degree of the step path between adjacent entities represents a piecewise function represents the path parameter represents the depth of the path The value of represents the length of the reachable path represents the current path 6. The method according to claim 1, characterized in that, Establishing at least one conduction path between the directly associated entity and the indirectly associated entity according to the entity relationship, including: Determine the indirectly associated entity according to the third formula and the directly associated entity The degree of association, and the specific content of the third formula includes: ， Among them, represents an indirectly associated entity with the directly associated entity degree of association is the path adjacent node represents an indirectly associated entity with the directly associated entity degree of association represents the step path degree of association represents the length of the reachable path represents the current path 7. A risk monitoring and processing device, characterized in that, The device includes: An obtaining module, configured to obtain network risk information to be monitored; An extraction module, configured to extract a directly associated entity and a risk event from the network risk information through keyword recognition, and receive risk indication information sent by a user to determine an importance index and an emotion index of the risk event for the directly associated entity; A establishing module, configured to obtain the entity relationship of the directly associated entity, and establish at least one conduction path between the directly associated entity and an indirectly associated entity according to the entity relationship; wherein, an emotion conduction coefficient is further included in the conduction path; A determining module, configured to perform emotion conduction based on the at least one established conduction path to determine the importance index and the emotion index of the indirectly associated entity regarding the network risk information; Performing emotion conduction based on the at least one established conduction path to determine the emotion index of the indirectly associated entity regarding the network risk information, including: Determining the emotion index degree of the indirectly associated entity regarding the network risk information according to a fourth formula, and the fourth formula specifically includes: ， Among them, represents the risk event for the indirectly associated entity emotional index, represents the risk event for the directly associated entity emotional index, represents the path emotional conduction coefficient, represents the risk event for the directly associated entity importance, represents the indirectly associated entity and the directly associated entity association degree.

8. An electronic device, characterized in that, Including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, the risk monitoring processing method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that, A computer program is stored thereon, and when the computer program is executed by a processor, the risk monitoring processing method according to any one of claims 1 to 6 is implemented.

Images