CN111724250A - Risk propagation determination method and device, computer system and readable storage medium - Google Patents
Risk propagation determination method and device, computer system and readable storage medium Download PDFInfo
- Publication number
- CN111724250A CN111724250A CN202010611452.9A CN202010611452A CN111724250A CN 111724250 A CN111724250 A CN 111724250A CN 202010611452 A CN202010611452 A CN 202010611452A CN 111724250 A CN111724250 A CN 111724250A
- Authority
- CN
- China
- Prior art keywords
- risk
- target
- propagation
- network
- individual data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device, a computer system and a readable storage medium for determining dynamic risk propagation, which relate to the technical field of information security and comprise the following steps: establishing a risk network and acquiring a target moment, and preprocessing the risk network to acquire a target network; acquiring a preset attenuation coefficient, and calculating risk factors corresponding to each propagation relation in a target network at the target moment based on the creation moment and the preset attenuation coefficient; determining risk data of each individual data of the state to be determined in the target network at the target moment according to the risk factors; and carrying out risk state marking on each state individual data to be determined in the target network based on the risk data to obtain a target result, thereby solving the problem that the accuracy of a risk evaluation result made by an entity with unknown risk is low in the prior art because the time and the structural change of a risk network structure are not considered by the prior static network.
Description
Technical Field
The present invention relates to the field of information security technologies, and in particular, to a method and an apparatus for determining risk propagation, a computer system, and a readable storage medium.
Background
With the rapid development of the internet, the incidence rate of fraud and credit risks of the internet is increased, in order to prevent fraud and wind control, a risk propagation technology can be used for fraud identification and risk propagation prediction, and risk propagation is a graph calculation method applied to a graph or a relational network for risk propagation, and the main purpose of the method is to propagate risk performance from entities which are present to entities which are not present so as to perform risk assessment and judgment prediction on the entities which are not present in risk performance.
The current common risk propagation method is based on a static graph or a relationship network, that is, risk factors on each propagation relationship in the risk propagation network are fixed values, that is, the propagated risks are consistent at any time, but in the actual use process, each risk propagation changes along with the lapse of time, that is, the propagated risks are dynamically changed, so that the current static network does not consider the structural changes of time and a risk network structure, and the accuracy of a risk evaluation result made on an entity with unknown risk is low.
Disclosure of Invention
The invention aims to provide a method, a device, a computer system and a readable storage medium for determining risk propagation, which are used for solving the problem that the accuracy of a risk evaluation result made by an entity with unknown risk is low in the prior art because the existing static network does not consider the time and the structural change of a risk network structure.
To achieve the above object, the present invention provides a dynamic risk propagation determining method, including: establishing a risk network and acquiring a target moment, and preprocessing the risk network to acquire a target network;
the risk network comprises a plurality of individual data and a propagation relation corresponding to each individual data, wherein the propagation relation is a directed relation with creation time and an initial risk factor;
acquiring a preset attenuation coefficient, and calculating risk factors corresponding to each propagation relation in a target network at the target moment based on the creation moment and the preset attenuation coefficient;
determining risk data of each individual data of the state to be determined in the target network at the target moment according to the risk factors;
and marking the risk state of each individual data in the state to be determined in the target network based on the risk data to obtain a target result.
Further, obtaining risk factors corresponding to each propagation relation in the target network at the target time based on the creation time and a preset attenuation coefficient, wherein any one of the propagation relations comprises the following steps:
acquiring an initial risk factor and a creation time on the propagation relation;
acquiring the attenuation of the risk factor from the target moment to the creation moment based on a preset attenuation coefficient;
and obtaining a risk factor corresponding to the propagation relation at the target moment based on the initial risk factor and the attenuation amount.
Further, the determining of the risk data of each to-be-determined state individual data in the target network at the target time according to the risk factor includes the following for any to-be-determined state individual data:
acquiring all risk propagation relations associated with the individual data of the state to be determined based on the target network;
calculating the propagated risk corresponding to each risk propagation relation associated with the individual data of the state to be determined in real time based on the risk factors;
and screening the risk data to obtain a maximum value, namely the risk data corresponding to the target time of the individual data of the state to be determined.
Further comprising uploading the target result to a blockchain.
Further, the preprocessing the risk network to obtain a target network includes:
acquiring individual data in the risk network and a propagation relation corresponding to each individual data based on the risk network;
marking each individual data based on the current risk state of each individual data, and acquiring an initial network based on the marked individual data and the corresponding propagation relation of each individual data;
acquiring a target moment and setting a time window based on the target moment;
segmenting the initial network based on the time window to obtain a target network;
the method also comprises uploading the target result to a block chain after the target result is obtained.
Further, the marking of the individual data based on the current risk status of the individual data includes:
judging whether the individual data risk states are in a preset period one by one;
if so, marking the individual data based on the current risk state;
if the judgment result is negative, marking the individual data as the individual data of the state to be determined;
and merging all the individual data marked as the state to be determined to obtain an individual data set of the state to be determined.
Further, segmenting the initial network based on the time window to obtain a target network, including the following steps:
acquiring each propagation relation and time data corresponding to each propagation relation in an initial network;
and removing the propagation relation of the time data not in the time window to obtain the target network.
Further, before obtaining the target network, the following is also included:
after removing the propagation relation of the time data which is not in the time window, removing the individual data which is not associated with the propagation relation again.
To achieve the above object, the present invention further provides a dynamic risk propagation determining apparatus, including:
the system comprises a preprocessing module, a target network and a risk analysis module, wherein the preprocessing module is used for establishing a risk network, acquiring a target moment, and preprocessing the risk network to acquire the target network;
the risk network comprises a plurality of individual data and a propagation relation corresponding to each individual data, wherein the propagation relation is a directed relation with creation time and an initial risk factor;
the acquisition module is used for acquiring a preset attenuation coefficient and calculating risk factors corresponding to target moments corresponding to all propagation relations in the target network based on the creation moment and the preset attenuation coefficient;
the calculation module is used for determining the risk data of each to-be-determined state individual data in the target network at the target moment according to the risk factors;
and the processing module is used for carrying out risk state marking on each to-be-determined state individual data in the target network based on the risk data to obtain a target result.
To achieve the above object, the present invention further provides a computer system, which includes a plurality of computer devices, each computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processors of the plurality of computer devices jointly implement the steps of the above dynamic risk propagation determination method when executing the computer program.
To achieve the above object, the present invention further provides a computer-readable storage medium comprising a plurality of storage media, each storage medium having stored thereon a computer program, the computer programs stored in the storage media, when executed by a processor, collectively implementing the steps of the above dynamic risk propagation determination method.
According to the dynamic risk propagation determining method, the dynamic risk propagation determining device, the computer system and the readable storage medium, after the risk network is established and the target network is obtained through processing, the risk factors on each real-time propagation relation corresponding to the target time on the target network are obtained based on the rule that the propagation relation is gradually weakened along with time and based on the time change and the attenuation coefficient, so that the calculation of real-time dynamic risk propagation is achieved, and the problem that the accuracy of risk evaluation results made on individual data with unknown risks is low due to the fact that the static network does not consider the time and the structural change of the risk network structure in the prior art is solved.
Drawings
Fig. 1 is a flowchart of a first embodiment of a dynamic risk propagation determination method according to the present invention;
fig. 2 is a detailed flowchart of preprocessing the risk network to obtain a target network in the first embodiment of the dynamic risk propagation determining method of the present invention;
fig. 3 is a specific flowchart of acquiring an individual data set in a state to be determined based on the current risk state of each individual data according to the first embodiment of the dynamic risk propagation determination method of the present invention;
fig. 4 is a specific flowchart of segmenting the initial network based on the time window to obtain a target network in the first embodiment of the dynamic risk propagation determining method of the present invention;
fig. 5 is a dynamic risk state diagram showing a process of preprocessing a risk network to obtain a target network according to a specific embodiment of the dynamic risk propagation determination method according to the present invention;
fig. 6 is a specific flowchart of obtaining a risk factor corresponding to a propagation relationship at any target in the first embodiment of the dynamic risk propagation determining method according to the present invention;
fig. 7 is a specific flowchart of acquiring the propagated risk corresponding to any one of the individual data target moments in the state to be determined according to the first embodiment of the dynamic risk propagation determination method of the present invention;
FIG. 8 is a schematic diagram of program modules of a second embodiment of a dynamic risk propagation determination device according to the present invention;
fig. 9 is a schematic diagram of a hardware structure of a computer device in the third embodiment of the computer system according to the present invention.
Reference numerals:
61. preprocessing module 611, acquisition unit 612 and judgment unit
613. Execution unit 614, segmentation unit 62, acquisition module
63. Calculation module 64 and processing module
7. Computer device 71, memory 72, processor
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a dynamic risk propagation determining method, a dynamic risk propagation determining device, a computer system and a readable storage medium, relates to the technical field of information security, adopts data analysis of big data, and provides a dynamic risk propagation determining method based on a preprocessing module, an acquisition module, a calculation module and a processing module. The invention establishes a risk network through a preprocessing module and processes to obtain a target network, wherein the risk network comprises a plurality of individual data and a propagation relation corresponding to each individual data, the propagation relation is a directed relation with establishment time and an initial risk factor, then the establishment time and an attenuation coefficient are obtained, the risk data to be propagated on each individual data of the target network is calculated by combining the target network, finally, the processing module is used for marking each individual data based on the risk data to obtain a final target result, the risk that the individual data in a state to be determined on the target network are propagated at the target time is calculated in real time based on time change and the attenuation coefficient, the risk prediction and marking of all the individual data in the target network are realized through the mode, and the problem that the existing static network does not consider the structural change of time and risk network structure in the prior art is solved, the problem that the accuracy of a risk evaluation result of an individual with unknown risk is low is solved, dynamic risk prediction is achieved, and the accuracy of the risk evaluation result is improved.
Example one
Referring to fig. 1, a dynamic risk propagation determining method of the present embodiment includes the following steps:
s100: establishing a risk network and acquiring a target moment, and preprocessing the risk network to acquire a target network;
the risk network comprises a plurality of individual data and a propagation relation corresponding to each individual data, wherein the propagation relation is a directed relation with creation time and an initial risk factor;
in the embodiment provided by the application, before the risk network is established, the information related to each individual can be obtained from the cloud, the risk network is established based on the information of each individual, namely, the risk influence relationship between each individual and other individuals is determined.
In the above embodiment, the risk network is preprocessed to obtain the target network, referring to fig. 2, including the following steps:
s110: acquiring individual data in the risk network and a propagation relation corresponding to each individual data based on the risk network;
s120: marking each individual data based on the current risk state of each individual data, and acquiring an initial network based on the marked individual data and the corresponding propagation relation of each individual data;
by way of example and not limitation, in the present solution, the current risk state may be a risk value, and the risk network includes individuals with determined risk values and undetermined risk values, or may be any tangible data identifying risk levels.
Specifically, each individual data is labeled based on the current risk status of each individual data, referring to fig. 3, which includes the following:
s121: judging whether the individual data risk states are in a preset period one by one;
in the above embodiment, the preset period may be defined as a presentation period, the presentation period is a preset period of time, the setting manner of the presentation period time length in the present embodiment is not limited, and the presentation period may be a fixed period, for example: three months, six months and one year; or the term may be derived according to some rule, for example, if a borrowing online network service provides 1-day repayment every month, the presentation period may be set to 1-day end from the beginning of the observation period to the third month; it is also possible that the time calculated from the previous traffic data of the user, i.e. the presentation period is different for different users. The presentation period may start from at least one of when the user registers for an account, the user uses the online network service for the first time, the user uses the online network service each time, and the user is granted the online network service usage right.
S122: if so, marking the individual data based on the current risk state;
in the present scheme, the mark may be a risk value, or may be avatar or abstract data that identifies a risk level at will, and the mark may be kept consistent with a target result process obtained in the present scheme.
S123: if not, marking the individual data as the individual data of the state to be determined.
It should be noted that, in the actual wind control process, as time goes by, the risk states of some individuals may be slowly expressed, and those individuals who do not reach the expression period need to perform risk propagation to previously distinguish and predict the individuals, so in the process of establishing the risk network, the individuals who exhibit the risk states take the actual risk states as the current risk states, the individuals who do not exhibit the risk states are marked as individual data of states to be determined, and the risk states of the individuals who exhibit the risk states are predicted by the risk propagation of the individuals who exhibit the actual risk states to the individuals who do not exhibit the risk states.
S130: acquiring a target moment and setting a time window based on the target moment;
it should be particularly noted that the time window is set mainly for screening the risk propagation relationship showing the risk factor in the time window, that is, the risk relationship is in accordance with the risk propagation calculation, and the risk propagation beyond the time window is negligible due to the long time. It should be noted that the time window is not a necessary process, but in practical applications, the operation efficiency can be greatly increased because the risk factor outside the time window is not zero, but is a very small positive number, but in practical calculations, the risk factor is usually ignored, and the time window is used to ignore the influence of such a decimal on the overall risk propagation.
Specifically, the principle of setting the time window is as follows: taking the target time as a boundary point of the time window, specifically, for example, if the target time is 13:00 and the length of the time window is set to 1H, the time window is set to 12: 00-13:00, the specific duration of the time window can be set according to the actual service scene.
S140: and segmenting the initial network based on the time window to obtain a target network.
Specifically, referring to fig. 4, segmenting the initial network based on the time window to obtain the target network includes the following steps:
s141: acquiring each propagation relation and time data corresponding to each propagation relation in an initial network;
s142: and removing the propagation relation of the time data not in the time window to obtain the target network.
Specifically, since the propagation relationship around a part of the individual data may be completely shifted out after shifting out the propagation relationship that is not within the time window, the individual data becomes an isolated individual data point, that is, there is no risk of propagating to the individual data, and the isolated individual data may be removed.
Thus, the following are also included before the target network is obtained:
after removing the propagation relation of the time data which is not in the time window, removing the individual data which is not associated with the propagation relation again.
In the above embodiment, all propagation relationships exceeding the time window are deleted, and after the propagation relationships are deleted, isolated individual data are deleted, individual data of propagation relationships that are not considered at the current time can be eliminated, so that the data volume can be reduced, and the calculation complexity can be reduced.
By way of example and not limitation, the above described time window arrangement and role is shown in the embodiment shown in fig. 5:
presetting a risk network as a graph, wherein the risk network is from 12:35 to 13: the trend between 00 is shown in fig. 5, where graph (a) is a risk state graph with t being 12: 35; graph (b) is a risk state graph with t 12: 45; graph (c) is a risk state graph with t 13: 00; graphs (a) - (B) - (c) show that as time changes, part of risk propagation relationship disappears, a to H respectively represent one individual data in the risk network, a dark vertex represents an individual data already showing a risk state, a light vertex represents an individual data not showing a risk state, and a straight line between any two adjacent individual data represents the risk propagation relationship between the corresponding two individual data, where t and w represent a risk factor w at time t, and specifically, for example, the risk factor between the individual data a and B at time t 11:50 is 0.3; the time corresponding to the risk factor can be used for subsequently screening out the risk propagation relation conforming to the time window, and if the length of the time window is 1H, then:
12: 35-12: 45 (FIGS. (a) - (b)): the relationship between vertices A and F, D and H exceeds the time window (i.e., within 11:35 to 11: 45), and thus is between 12:45 and vertex F is removed in isolation, only vertex D now represents a risk.
12: 45-13: 00 (panels (b) - (c)): the relationship between vertices A and B, G and H exceeds the time window (i.e., within 11:45 to 12: 00), and thus is between 12:45 and vertex H is removed in isolation, with vertex G presenting a risk.
Through the existence of the time window, when t is 12:45, the propagation relation between individuals A and F, D and H is eliminated, and the individual F is eliminated; and when t is 12:45, the propagation relations between the individuals A and B, G and H are eliminated, and the individual H is eliminated at the same time, so that the finally obtained t is 12:45, and the risk graph obtained by comparing t with the original 12:35 has less individual data and less propagation relations, the data size is reduced, and the calculation complexity is reduced.
In the real-time mode, the initial risk network is processed before the real-time dynamic risk factors are acquired, and the propagation relation and the isolated individuals exceeding the time window are eliminated by adopting a mode of setting the time window, so that the data volume is further reduced, the calculation complexity is reduced, the subsequent acquisition speed of the propagation risk is facilitated, and the working efficiency is improved.
S200: and acquiring a preset attenuation coefficient, and calculating risk factors corresponding to each propagation relation in the target network at the target moment based on the creation moment and the preset attenuation coefficient.
Specifically, referring to fig. 6, in the process of calculating risk factors corresponding to each propagation relationship in the target network at the target time based on the creation time and the preset attenuation coefficient, for any one of the propagation relationships, the method includes the following steps:
s210: acquiring an initial risk factor and a creation time on the propagation relation;
s220: acquiring the attenuation of the risk factor from the target moment to the creation moment based on a preset attenuation coefficient;
s230: and obtaining a risk factor corresponding to the propagation relation at the target moment based on the initial risk factor and the attenuation amount.
In the above embodiment, the following formula is used to describe the risk factor, and the risk factor is calculated for each propagation relationship as follows:
wherein, tj0For the creation time of the propagation relation α is the attenuation coefficient, ωjtFor the risk factor, ω, of the propagation relation j at the instant tj0Is the initial risk factor of the propagation relation j.
It should be noted that, in the following description,
the attenuation amount in S220 is described above.
In the above embodiment, considering that the risk factors in the propagation relationship show a trend of continuously attenuating with the passage of time, for example, the individual a has a certain influence on the individual B at a certain time, but the influence of a on B becomes weaker with the passage of time, that is, the risk influence of a on B shows a trend of attenuating with the passage of time, so that the risk factor corresponding to each propagation relationship at the target time is obtained through the above formula based on the attenuation parameter and the initial risk factor.
By the method, the risk factor at the target moment can be calculated to adapt to the dynamic change condition of the risk factor under the actual condition, so that the risk state at the target moment can be conveniently and accurately predicted subsequently, and the accuracy of the subsequent prediction result is improved.
S300: determining risk data of each individual data of the state to be determined in the target network at the target moment according to the risk factors;
specifically, referring to fig. 7, the above-mentioned determining risk data includes, for any individual data of the state to be determined, the following steps:
s310: acquiring all risk propagation relations associated with the individual data of the state to be determined based on the target network;
specifically, all risk propagation relationships are risk propagation relationships between the individual data of the state to be determined and all associated individual data showing risks.
S320: calculating risk data corresponding to each risk propagation relation associated with the individual data of the state to be determined in real time based on the risk factors;
in the scheme, each individual data is associated with at least one risk propagation relation, and calculating the risk data corresponding to each risk propagation relation is favorable for improving the accuracy of the subsequent risk propagation result dispersion.
S330: and screening the risk data to obtain a maximum value, namely the risk data of the individual data of the state to be determined at the target moment.
The following calculation is specifically described:
for each state to be determined individual data ncThe risk of being propagated corresponding to the target time is:
wherein K is the individual data volume n corresponding to the state to be determinedcThe number of the associated individuals with the existing performance status; omegajtFor the individual data body of the state to be determined and the individual of the existing performance state associated with the data bodyA dynamic risk factor at time t in between; rsctIs an individual ncRisk status at target time t; rsktFor the Kth and the state to be determined individual data volume ncThe risk state of the associated individual with the existing performance state at the target time t;
ωjt×rsktthe risk propagated corresponding to the kth risk propagation relation associated with the individual data of the state to be determined in S320.
Taking the specific risk network in S100 as an example (see fig. 5), assuming that the risk propagation result of the individual E by the surrounding nodes when t is calculated to be 13:00 (graph (c)), where the risk coefficient of D is 10, the risk coefficient of G is 100, the risk coefficients of other nodes that do not change gray are all 0, the attenuation coefficient is 0.05, and the propagation risk value of the current vertex with the maximum value is taken as the propagation result of the current vertex, then:
the risk of E being propagated from nodes A, D, G at 13:00, respectively, is:
risk_from_A＝0.25×0×e^(-0.05(13:00-12:07))
risk_from_D＝0.35×10×e^(-0.05(13:00-12:35))
risk_from_G＝0.05×100×e^(-0.05(13:00-12:17))
the risk result that the final node E is propagated is: risk _ from _ D.
S400: and marking the risk state of each individual data in the state to be determined in the target network based on the risk data to obtain a target result.
In a preferred embodiment, after obtaining the target result, the method further includes uploading the target result to a Blockchain, in the implementation process, the risk state diagram corresponding to the time may also be obtained from the Blockchain, uploading the target result to the Blockchain may ensure the security and the fair transparency to the user, and other devices may download the target result from the Blockchain to verify and determine whether the target result is tampered, where the Blockchain in this example is a novel application mode of computer technologies such as distributed data storage, peer-to-peer transmission, a consensus mechanism, an encryption algorithm, etc., the Blockchain (Blockchain) is essentially a decentralized database, and is a string of data blocks generated by using a cryptographic method in association, each data block includes information of a batch of network transactions for verifying the validity (anti-counterfeiting) of the information and generating a next block, the blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
In the above solution, based on steps S3 and S4, the risk of being propagated corresponding to the target time of the individual data in the state to be determined can be calculated (i.e. obtaining risk data from the propagation relationship), the individual data in the state to be determined are labeled based on the obtained risk data, the labeled individual data and the individual data showing the current risk state are integrated to be recorded as the target result, i.e. the risk states of all the individual data are labeled.
According to the scheme, based on the rule that the propagation relation is gradually weakened along with time, risk factors on each propagation relation corresponding to the target time on the target network are obtained in real time based on the time change and the attenuation coefficient, then the risk propagated on the individual data of the state to be determined is obtained through the corresponding risk factors, risk prediction and marking are carried out on the individual data of the non-represented state through the mode, the method is suitable for dynamic change of the risk factors under the actual scene, accuracy of prediction of the risk state result of the individual data of the non-represented state is improved, and therefore the risk prediction effect of enterprises, loans and the like is improved when the method is applied to the actual scene.
Example two:
referring to fig. 6, a dynamic risk propagation determining apparatus of the present embodiment includes:
the preprocessing module 61 is configured to establish a risk network, acquire a target time, and preprocess the risk network to acquire a target network;
the risk network comprises a plurality of individual data and a propagation relation corresponding to each individual data, wherein the propagation relation is a directed relation with creation time and an initial risk factor;
preferably, the preprocessing module 61 further includes:
the acquisition unit 611 is configured to acquire, based on the risk network, individual data in the risk network and a propagation relationship corresponding to each individual data;
a determining unit 612, configured to mark each individual data based on the current risk state of each individual data, and obtain an initial network based on the marked individual data and a propagation relationship corresponding to each individual data;
an execution unit 613, configured to obtain a target time and set a time window based on the target time;
a dividing unit 614, configured to divide the initial network based on the time window, and obtain a target network.
An obtaining module 62, configured to obtain a preset attenuation coefficient, and calculate risk factors corresponding to each propagation relationship in the target network at the target time based on the creation time and the preset attenuation coefficient;
a calculating module 63, configured to determine, according to the risk factor, risk data of each to-be-determined state individual data in the target network at the target time;
and the processing module 64 is configured to perform risk state marking on each to-be-determined state individual data in the target network based on the risk data, and obtain a target result.
The technical scheme relates to the technical field of information security, and is characterized in that a risk network is established firstly by adopting a preprocessing module based on data analysis of big data, acquiring current risks of each individual data in the risk network to carry out preliminary marking and to-be-determined state individual data, processing by adopting a segmentation unit to obtain a target network, acquiring an attenuation coefficient by an acquisition module and determining a risk factor at the target moment, calculating a propagated risk (namely risk data) corresponding to the target moment based on the risk factor, and finally carrying out risk propagation on each individual data by a processing module (namely transferring the risk data from a propagation relation to the individual data) to obtain a target result. And then the risk propagated on the individual with the target moment in the expression state is obtained to improve the accuracy of the risk prediction result in the subsequent application to the actual scene.
In the scheme, when the risk network is segmented by utilizing the segmentation unit, the propagation relation and the isolated individuals exceeding the time window are removed in a mode of setting the time window, so that the data volume is further reduced, the calculation complexity is reduced, and the working efficiency is improved.
Example three:
in order to achieve the above object, the present invention further provides a computer system, which includes a plurality of computer devices 7, and the components of the dynamic risk propagation determining apparatus according to the second embodiment may be distributed in different computer devices, where the computer devices may be smartphones, tablet computers, notebook computers, desktop computers, rack-mounted servers, blade servers, tower servers, or rack-mounted servers (including independent servers, or a server cluster formed by a plurality of servers) which execute programs, and the like. The computer device of the embodiment at least includes but is not limited to: a memory 71, a processor 72, communicatively coupled to each other via a system bus, as shown in FIG. 7. It should be noted that fig. 7 only shows a computer device with components, but it should be understood that not all of the shown components are required to be implemented, and more or fewer components may be implemented instead.
In this embodiment, the memory 71 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 71 may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory 71 may be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device. Of course, the memory 71 may also include both internal and external storage devices of the computer device. In this embodiment, the memory 71 is generally used to store an operating system and various application software installed on the computer device, such as the program code of the dynamic risk propagation determination method in the first embodiment. Further, the memory 51 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 72 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 72 generally serves to control the overall operation of the computer apparatus. In this embodiment, the processor 72 is configured to run the program code stored in the memory 71 or process data, for example, run the dynamic risk propagation determining device, so as to implement the dynamic risk propagation determining method according to the first embodiment.
Example four
To achieve the above objects, the present invention also provides a computer-readable storage system including a plurality of storage media, such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor 62, implements corresponding functions. The computer readable storage medium of this embodiment is used for storing a dynamic risk propagation determination device, and when executed by the processor 62, implements the dynamic risk propagation determination method of the first embodiment.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A dynamic risk propagation determination method, comprising:
establishing a risk network and acquiring a target moment, and preprocessing the risk network to acquire a target network;
the risk network comprises a plurality of individual data and a propagation relation corresponding to each individual data, wherein the propagation relation is a directed relation with creation time and an initial risk factor;
acquiring a preset attenuation coefficient, and calculating risk factors corresponding to each propagation relation in a target network at the target moment based on the creation moment and the preset attenuation coefficient;
determining risk data of each individual data of the state to be determined in the target network at the target moment according to the risk factors;
and marking the risk state of each individual data in the state to be determined in the target network based on the risk data to obtain a target result.
2. The dynamic risk propagation determination method according to claim 1, wherein the risk factors corresponding to the respective propagation relationships in the target network at the target time are calculated based on the creation time and a preset attenuation coefficient, and for any one of the propagation relationships, the method includes the following steps:
acquiring an initial risk factor and a creation time on the propagation relation;
acquiring the attenuation of the risk factor from the target moment to the creation moment based on a preset attenuation coefficient;
and obtaining a risk factor corresponding to the propagation relation at the target moment based on the initial risk factor and the attenuation amount.
3. The dynamic risk propagation determination method according to claim 1, wherein the determining risk data of each to-be-determined state individual data in the target network at the target time according to the risk factor includes, for any of the to-be-determined state individual data, the following:
acquiring all risk propagation relations associated with the individual data of the state to be determined based on the target network;
calculating risk data corresponding to each risk propagation relation associated with the individual data of the state to be determined in real time based on the risk factors;
screening the risk data to obtain a maximum value, namely the risk data of the individual data at a target moment;
further comprising uploading the target result to a blockchain.
4. The dynamic risk propagation determination method of claim 1, wherein the preprocessing the risk network to obtain a target network comprises:
acquiring individual data in the risk network and a propagation relation corresponding to each individual data based on the risk network;
marking each individual data based on the current risk state of each individual data, and acquiring an initial network based on the marked individual data and the corresponding propagation relation of each individual data;
acquiring a target moment and setting a time window based on the target moment;
and segmenting the initial network based on the time window to obtain a target network.
5. The dynamic risk propagation determination method of claim 4, wherein the marking of individual data based on their current risk status comprises:
judging whether each individual data is in a preset period one by one;
if so, marking the individual data based on the current risk state;
and if not, marking the individual data as the individual data of the state to be determined.
6. The dynamic risk propagation determination method of claim 4, wherein segmenting the initial network based on the time window to obtain a target network comprises:
acquiring each propagation relation and time data corresponding to each propagation relation in an initial network;
and removing the propagation relation of the time data not in the time window to obtain the target network.
7. The dynamic risk propagation determination method of claim 6, further comprising, before obtaining the target network, the following:
after removing the propagation relation of the time data which is not in the time window, removing the individual data which is not associated with the propagation relation again.
8. A dynamic risk propagation determination device, comprising:
the system comprises a preprocessing module, a target network and a risk analysis module, wherein the preprocessing module is used for establishing a risk network, acquiring a target moment, and preprocessing the risk network to acquire the target network;
the risk network comprises a plurality of individual data and a propagation relation corresponding to each individual data, wherein the propagation relation is a directed relation with creation time and an initial risk factor;
the acquisition module is used for acquiring a preset attenuation coefficient and calculating risk factors corresponding to target moments corresponding to all propagation relations in the target network based on the creation moment and the preset attenuation coefficient;
the calculation module is used for determining the risk data of each to-be-determined state individual data in the target network at the target moment according to the risk factors;
and the processing module is used for carrying out risk state marking on each individual data of the state to be determined in the target network based on the risk data to obtain a target result.
9. A computer system comprising a plurality of computer devices, each computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processors of the plurality of computer devices when executing the computer program collectively implement the steps of the dynamic risk propagation determination method of any of claims 1 to 7.
10. A computer-readable storage medium comprising a plurality of storage media, each storage medium having a computer program stored thereon, wherein the computer programs stored by the plurality of storage media, when executed by a processor, collectively implement the steps of the dynamic risk propagation determination method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010611452.9A CN111724250A (en) | 2020-06-29 | 2020-06-29 | Risk propagation determination method and device, computer system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010611452.9A CN111724250A (en) | 2020-06-29 | 2020-06-29 | Risk propagation determination method and device, computer system and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111724250A true CN111724250A (en) | 2020-09-29 |
Family
ID=72571999
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010611452.9A Pending CN111724250A (en) | 2020-06-29 | 2020-06-29 | Risk propagation determination method and device, computer system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111724250A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105556552A (en) * | 2013-03-13 | 2016-05-04 | 加迪安分析有限公司 | Fraud detection and analysis |
| CN106411904A (en) * | 2016-10-10 | 2017-02-15 | 华侨大学 | Network risk control method based on microstate prediction |
| CN107239882A (en) * | 2017-05-10 | 2017-10-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN109559192A (en) * | 2018-10-25 | 2019-04-02 | 深圳壹账通智能科技有限公司 | Risk checking method, device, equipment and storage medium based on association map |
| CN109583620A (en) * | 2018-10-11 | 2019-04-05 | 平安科技（深圳）有限公司 | Enterprise's potential risk method for early warning, device, computer equipment and storage medium |
| US20190188616A1 (en) * | 2015-10-23 | 2019-06-20 | Kpmg Llp | Risk simulation and assessment tool |
| CN110349289A (en) * | 2019-06-21 | 2019-10-18 | 东软集团股份有限公司 | Failure prediction method, device, storage medium and electronic equipment |
| CN110852584A (en) * | 2019-10-30 | 2020-02-28 | 北京航空航天大学 | Risk identification method based on complex network analysis |
-
2020
- 2020-06-29 CN CN202010611452.9A patent/CN111724250A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105556552A (en) * | 2013-03-13 | 2016-05-04 | 加迪安分析有限公司 | Fraud detection and analysis |
| US20190188616A1 (en) * | 2015-10-23 | 2019-06-20 | Kpmg Llp | Risk simulation and assessment tool |
| CN106411904A (en) * | 2016-10-10 | 2017-02-15 | 华侨大学 | Network risk control method based on microstate prediction |
| CN107239882A (en) * | 2017-05-10 | 2017-10-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, device, computer equipment and storage medium |
| CN109583620A (en) * | 2018-10-11 | 2019-04-05 | 平安科技（深圳）有限公司 | Enterprise's potential risk method for early warning, device, computer equipment and storage medium |
| CN109559192A (en) * | 2018-10-25 | 2019-04-02 | 深圳壹账通智能科技有限公司 | Risk checking method, device, equipment and storage medium based on association map |
| CN110349289A (en) * | 2019-06-21 | 2019-10-18 | 东软集团股份有限公司 | Failure prediction method, device, storage medium and electronic equipment |
| CN110852584A (en) * | 2019-10-30 | 2020-02-28 | 北京航空航天大学 | Risk identification method based on complex network analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112184012B (en) | Enterprise risk early warning method, device, equipment and readable storage medium | |
| CN112150014A (en) | Enterprise risk early warning method, device, equipment and readable storage medium | |
| US20170364825A1 (en) | Adaptive augmented decision engine | |
| CN107729560A (en) | User's portrait building method, device and computing device based on big data | |
| CN112580952A (en) | User behavior risk prediction method and device, electronic equipment and storage medium | |
| CN112785157B (en) | Risk identification system updating method and device and risk identification method and device | |
| CN111681091A (en) | Financial risk prediction method and device based on time domain information and storage medium | |
| CN111401700A (en) | Data analysis method, device, computer system and readable storage medium | |
| CN109447791B (en) | Block chain-based fund transaction method and device | |
| CN111860865B (en) | Model construction and analysis method, device, electronic equipment and medium | |
| CN110889725B (en) | Online advertisement CTR estimation method, device, equipment and storage medium | |
| CN112668575B (en) | Key information extraction method and device, electronic equipment and storage medium | |
| CN110197316B (en) | Method and device for processing operation data, computer readable medium and electronic equipment | |
| CN116432040B (en) | Model training method, device and medium based on federal learning and electronic equipment | |
| WO2019095569A1 (en) | Financial analysis method based on financial and economic event on microblog, application server, and computer readable storage medium | |
| CN111724250A (en) | Risk propagation determination method and device, computer system and readable storage medium | |
| CN113177851B (en) | Method and device for storing certificate of online insurance transaction, electronic equipment and storage medium | |
| CN114565470A (en) | Financial product recommendation method based on artificial intelligence and related equipment thereof | |
| CN114298321A (en) | Joint modeling method and device, electronic equipment and storage medium | |
| CN113656586A (en) | Emotion classification method and device, electronic equipment and readable storage medium | |
| CN112132693A (en) | Transaction verification method, transaction verification device, computer equipment and computer-readable storage medium | |
| CN113742564A (en) | Target resource pushing method and device | |
| CN113657910B (en) | Real name authentication method, device, electronic equipment and readable storage medium | |
| Pfeiffer et al. | Discussion of “A formal causal interpretation of the case‐crossover design” by Zach Shahn, Miguel A. Hernan, and James M. Robins | |
| CN114565030B (en) | Feature screening method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |