CN110245165B - Risk conduction associated graph optimization method and device and computer equipment - Google Patents
Risk conduction associated graph optimization method and device and computer equipment Download PDFInfo
- Publication number
- CN110245165B CN110245165B CN201910419723.8A CN201910419723A CN110245165B CN 110245165 B CN110245165 B CN 110245165B CN 201910419723 A CN201910419723 A CN 201910419723A CN 110245165 B CN110245165 B CN 110245165B
- Authority
- CN
- China
- Prior art keywords
- risk
- association
- data
- user
- nodes
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of big data, and provides a risk conduction associated map optimization method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring risk nodes in an initial risk conduction association graph and user risk data corresponding to the risk nodes, determining equipment label risk weight parameters of the risk nodes according to equipment label information corresponding to the risk nodes, determining reference weight parameters of association factors according to association factors between directly associated risk nodes and corresponding user risk data, determining risk conduction weight parameters of the association factors under each association level according to association factor combinations between indirectly associated risk nodes and association levels of each association factor in the combinations, combining the reference weight parameters, determining the risk conduction weight parameters of the association factors under each association level, updating the parameters of the initial risk conduction association graph, optimizing the risk conduction association graph, fully mining deep relation among the nodes of the association graph, optimizing the initial risk conduction association graph, and improving risk analysis efficiency.
Description
Technical Field
The application relates to the technical field of big data, in particular to a risk conduction associated map optimization method and device, computer equipment and a storage medium.
Background
The knowledge graph is also called as a scientific knowledge graph, is a series of different graphs for displaying the relation between the knowledge development process and the structure, describes knowledge resources and carriers thereof by using a visualization technology, and excavates, analyzes, constructs, draws and displays knowledge and the mutual relation between the knowledge resources and the carriers. In a general sense, the main goal of a knowledge graph is to describe various entities and concepts existing in the real world, and the associations between them.
The traditional knowledge graph can be constructed through entities and incidence relations among the entities, can be used for risk conduction among the entities, and in some application scenarios, the risk conduction incidence graph can be constructed through establishing incidence relations among nodes based on certain factor information, so that a relation network among the nodes is represented, and risk conduction analysis is carried out.
However, in the knowledge graph constructed in the traditional manner, the diversity of the node data dimensions leads to the complexity of the association relationship of the risk conduction association graph to a certain extent. On one hand, the traditional risk transmission association graph has huge node basic data, which affects the calculation complexity of relationship transmission to a certain extent, and on the other hand, the relationship transmission calculation between the nodes is determined by combing the association relationship between the nodes and calculating in real time, so that the problem that the data analysis efficiency is not high when the risk transmission association graph is used for risk transmission analysis is caused, and the risk transmission association graph is urgently needed to be optimized.
Disclosure of Invention
In view of the above, it is necessary to provide a risk propagation associated map optimization method, apparatus, computer device and storage medium capable of improving the efficiency of associated map analysis in view of the above technical problems.
A risk conductance association map optimization method, the method comprising:
acquiring risk nodes in an initial risk conduction association graph and user risk data corresponding to the risk nodes;
acquiring equipment label information of a risk user corresponding to the risk node, and determining an equipment label risk weight parameter of the risk node according to the equipment label information and the user risk data;
determining association factors among directly associated risk nodes, association factor combinations among indirectly associated risk nodes and association levels of all association factors in the association factor combinations according to the association relationship among the risk nodes, and determining benchmark weight parameters of the association factors according to user risk data corresponding to the risk nodes;
determining risk conduction weight parameters of the association factors under each association level according to the reference weight parameters of the association factors in the association factor combination and the association levels of the association factors;
updating the parameters of the initial risk transmission association map according to the equipment label risk weight parameters, the benchmark weight parameters of the association factors and the risk transmission weight parameters of the association factors at different association levels to obtain an optimized risk transmission association map.
In one embodiment, before the obtaining the risk nodes in the initial risk conduction associated graph and the user risk data corresponding to the risk nodes, the method further includes:
acquiring user data information of each user for constructing an initial risk conduction associated graph, marking each user as an associated graph node, screening risk users carrying user risk data in each user, and marking the associated graph node corresponding to the risk user as a risk node;
extracting a plurality of data dimension information carried in a message according to the acquired data information, and extracting a data value corresponding to each data dimension in the user data information;
searching each feature association graph node containing the same data value, and marking the data dimension corresponding to the data value as an association factor among the feature association graph nodes;
and constructing the initial risk conduction associated graph according to the associated graph nodes and the associated factors, wherein the initial risk conduction associated graph is marked with risk nodes.
In one embodiment, before the extracting, according to the obtained data information, a plurality of pieces of data dimension information carried in a message and extracting a data value corresponding to each of the data dimensions in the user data information, the method further includes:
acquiring sample data of an existing risk user, and carrying out data dimension marking on risk data in the sample data;
counting the co-occurrence frequency of each dimension data in each sample data, and screening out the data dimension of which the co-occurrence frequency meets a set threshold;
and generating the data information extraction message carrying the data dimension information according to the data dimension obtained by screening.
In one embodiment, the obtaining device tag information of a risk user corresponding to the risk node, and determining the device tag risk weight parameter of the risk node according to the device tag information and the user risk data includes:
acquiring equipment label information of a risk node corresponding to a risk user, and extracting risk identifiers carried by equipment labels in the equipment label information, wherein the risk identifiers comprise risks and no risks;
obtaining the influence weight of each risk label on the user risk data according to the combination result corresponding to the risk identification carried by each risk label and the user risk data corresponding to the risk node;
and determining equipment label risk weight parameters of the risk nodes according to risk labels carrying risk identifications in the risk nodes and the influence weights of the risk labels.
In one embodiment, the determining the risk propagation weight parameter of the association factor at each association level according to the benchmark weight parameter of each association factor in the association factor combination and the association level of the association factor comprises:
acquiring a combination weight parameter corresponding to the association factor combination according to the association level of each association factor in the association factor combination and user risk data corresponding to a corresponding risk node in the association factor combination;
and acquiring risk conduction weight parameters of the association factors under each association level according to the combination weight parameters and the reference weight parameters of the association factors in the association factor combination.
In one embodiment, after the updating the parameters of the initial risk transmission association map according to the device tag risk weight parameter, the reference weight parameter of the association factor, and the risk transmission weight parameters of the association factor at different association levels to obtain an optimized risk transmission association map, the method further includes:
when a risk analysis request of a target user is received, acquiring equipment label information of the target user;
acquiring first risk data of a target user according to the equipment label information;
searching the associated risk user of the target user according to the optimized risk conduction associated map;
acquiring the conduction risk probability of the associated risk user to the target user according to the reference weight parameter of the associated factor and the risk conduction weight parameter of the associated factor under different association levels to obtain second risk data;
and obtaining the risk probability of the target user according to the first risk data and the second risk data.
In one embodiment, after obtaining the risk probability of the target user according to the first risk data and the second risk data, the method further includes:
according to the risk probability of each user in the obtained sample data and the default condition of each user, dividing risk levels and determining a service suggestion corresponding to each risk level;
and searching the risk level of the risk probability of the target user according to the risk probability of the target user, and outputting a service suggestion corresponding to the risk level.
A risk conductance association map optimization apparatus, the apparatus comprising:
the risk node acquisition module is used for acquiring risk nodes in the initial risk conduction association graph and user risk data corresponding to the risk nodes;
the equipment label risk weight parameter determination module is used for acquiring equipment label information of a risk user corresponding to the risk node and determining an equipment label risk weight parameter of the risk node according to the equipment label information and the user risk data;
the benchmark weight parameter determination module is used for determining association factors among directly associated risk nodes, association factor combinations among indirectly associated risk nodes and association levels of all association factors in the association factor combinations according to the association relation among the risk nodes, and determining benchmark weight parameters of the association factors according to user risk data corresponding to the risk nodes;
a risk conduction weight parameter determination module, configured to determine a risk conduction weight parameter of each association factor in the association factor combination according to a reference weight parameter of each association factor and an association level of the association factor;
and the initial risk conduction associated map optimizing module is used for updating the parameters of the initial risk conduction associated map according to the equipment tag risk weight parameters, the benchmark weight parameters of the associated factors and the risk conduction weight parameters of the associated factors at different association levels to obtain an optimized risk conduction associated map.
A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor when executing the computer program performs the steps of:
acquiring risk nodes in an initial risk conduction association graph and user risk data corresponding to the risk nodes;
acquiring equipment label information of a risk user corresponding to the risk node, and determining an equipment label risk weight parameter of the risk node according to the equipment label information and the user risk data;
determining association factors among directly associated risk nodes, association factor combinations among indirectly associated risk nodes and association levels of all association factors in the association factor combinations according to the association relationship among the risk nodes, and determining benchmark weight parameters of the association factors according to user risk data corresponding to the risk nodes;
determining risk conduction weight parameters of the association factors under each association level according to the reference weight parameters of the association factors in the association factor combination and the association levels of the association factors;
updating the parameters of the initial risk transmission association map according to the equipment label risk weight parameters, the benchmark weight parameters of the association factors and the risk transmission weight parameters of the association factors at different association levels to obtain an optimized risk transmission association map.
A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of:
acquiring risk nodes in an initial risk conduction association graph and user risk data corresponding to the risk nodes;
acquiring equipment label information of a risk user corresponding to the risk node, and determining an equipment label risk weight parameter of the risk node according to the equipment label information and the user risk data;
determining association factors among directly associated risk nodes, association factor combinations among indirectly associated risk nodes and association levels of all association factors in the association factor combinations according to the association relationship among the risk nodes, and determining benchmark weight parameters of the association factors according to user risk data corresponding to the risk nodes;
determining risk conduction weight parameters of the association factors under each association level according to the reference weight parameters of the association factors in the association factor combination and the association levels of the association factors;
updating the parameters of the initial risk transmission associated map according to the equipment label risk weight parameters, the reference weight parameters of the associated factors and the risk transmission weight parameters of the associated factors under different association levels to obtain an optimized risk transmission associated map.
According to the risk conduction association graph optimization method, the risk conduction association graph optimization device, the computer equipment and the storage medium, on the basis of an initial risk conduction association graph, equipment label information of a risk user corresponding to a risk node is analyzed through association factors among directly associated risk nodes to obtain equipment label risk weight parameters, reference weight parameters of the association factors are determined through the association factors among the directly associated risk nodes, the risk conduction weight parameters of the association factors under the association levels are determined through the association levels of the association factors in association factor combinations among the indirectly associated risk nodes, so that the initial risk conduction association graph is optimized, deep connection among the nodes of the association graph is fully excavated, specific conduction parameters among the risk nodes are determined, the risk conduction can be directly conducted by utilizing the risk conduction association graph optimized through the parameters, the sorting and real-time calculation process of the association relationships among the nodes is simplified, the obtained equipment label risk weight parameters are used as evaluation parameters of node data, the node basic data volume is simplified, the risk conduction analysis is convenient, and the risk analysis efficiency is improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a risk-propagation associated map optimization method;
FIG. 2 is a schematic flow chart diagram of a risk conductance correlation map optimization method in one embodiment;
FIG. 3 is a schematic flow chart diagram illustrating a method for optimizing a risk transmission correlation map according to another embodiment;
FIG. 4 is a schematic flow chart diagram illustrating a method for optimizing a risk conductance correlation map in accordance with yet another embodiment;
FIG. 5 is a schematic flow chart diagram illustrating a method for optimizing a risk transmission correlation map according to yet another embodiment;
FIG. 6 is a block diagram of an apparatus for optimizing a risk conductance correlation map in one embodiment;
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application 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 and not restrictive on the broad application.
The risk conduction correlation map optimization method provided by the application can be applied to an application environment as shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 acquires risk nodes in the initial risk conduction association graph and user risk data corresponding to the risk nodes, acquires equipment label information of risk users corresponding to the risk nodes, determines equipment label risk weight parameters of the risk nodes according to the equipment label information and the user risk data, determines association factors among directly associated risk nodes, association factor combinations among indirectly associated risk nodes and association levels of all the association factors in the association factor combinations according to association relations among the risk nodes, determines reference weight parameters of the association factors according to the reference weight parameters of all the association factors in the association factor combinations and the association levels of the association factors according to the user risk data corresponding to the risk nodes, and determines risk conduction weight parameters of the association factors under all the association levels; updating the parameters of the initial risk conduction associated map according to the equipment tag risk weight parameters, the reference weight parameters of the associated factors and the risk conduction weight parameters of the associated factors at different association levels to obtain an optimized risk conduction associated map, and pushing the optimized risk conduction associated map to the terminal 102. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a risk conduction association map optimization method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
step S300, acquiring risk nodes in the initial risk conduction association graph and user risk data corresponding to the risk nodes.
The initial risk conduction association graph is a knowledge graph which is constructed by taking users as nodes, taking the same data existing among the users as a connection relation and taking data dimensions corresponding to the same data as association factors among the nodes and is used for representing the connection among the users. The user risk data refers to risk behaviors such as default and overdue, and the risk evaluation is performed according to specific default conditions of the user risk data, so that the value of grading the user risk condition can be obtained through analyzing the risk behavior records of each user in the existing risk database. In the embodiment, the more the risk behavior frequency is, the more the episode corresponding to the risk behavior is serious, the larger the user risk data value corresponding to the user is, the user who does not generate the risk behavior does not contain the user risk data, and according to the user risk data, whether each user of the initial risk conduction associated graph is a risk user can be determined, and the risk node labeling of the initial risk conduction associated graph is performed.
Step S400, acquiring equipment label information of a risk user corresponding to the risk node, and determining an equipment label risk weight parameter of the risk node according to the equipment label information and the user risk data.
The risk nodes are nodes containing user risk data, users corresponding to the risk nodes are risk users, risk behaviors generated by the risk users generally have related records in mobile equipment used by the users, for example, browsing records, searching records, bad APP using records, loan APP using records, equipment flashing records, multiple equipment with the same mobile phone number, different mobile phone numbers of different equipment and the like, each data record in the user mobile equipment corresponds to an equipment label, risk identification of each equipment label is determined to be risky or not risky according to matching of data content of the specific data record and a risk database, a plurality of equipment label combinations with the risk identification can be obtained according to numerous risk nodes and user risk data of each risk node, accordingly, influence weight of each equipment label on the user risk data is obtained, and equipment label risk weight parameters of the risk nodes are obtained through accumulative calculation of the influence weight.
Step S500, according to the incidence relation among the risk nodes, determining the incidence factors among the directly related risk nodes, the incidence factor combinations among the indirectly related risk nodes and the incidence levels of all the incidence factors in the incidence factor combinations, and determining the benchmark weight parameters of the incidence factors according to the user risk data corresponding to the risk nodes.
The association relationship refers to a relationship between two nodes, and includes a direct association and an indirect association, for example, the user a, the user B, and the user C are all risk users, when the user a and the user B are at the same home address, they are associated together according to the association factor of the home address, the association relationship between the user a and the user B is a direct association, when the user B and the user C have the same work unit, they are associated together according to the association factor of the work unit, the association relationship between the user B and the user C is also a direct association, and thus, the association relationship between the user a and the user C is an indirect association through the user B. According to the user risk data of the risk users and the association factors among the risk nodes with the direct association relationship, an association relationship formula group of a plurality of association factors and the user risk data is constructed, because the user risk data are known data, the reference weight parameters of the association factors can be obtained through data calculation and data fitting processing of data calculation results, and the reference weight parameters are used for representing the conductivity strength of the association factors among the nodes.
One or more intermediate nodes may exist between the indirectly associated risk nodes, so that a plurality of association factors correspondingly exist, for example, when the user a, the user D and the user E are risk users, and the user B and the user C are normal users, the user a and the user B are directly associated through an association factor of a home address, the user B and the user C are directly associated through an association factor of a work unit, the user B and the user D are directly associated through the same mobile phone number, the user C and the user E are directly associated through the same software account number, according to the direct association relationship, the indirect association between the user a and the user D, the indirect association between the user a and the user E, the indirect association between the user D and the user E, the association factor combinations among the risk users are different, and according to the number of the association factors, the association level of each association factor in the association factor combination can be determined. Wherein the relevance rank of the relevance factor is related to the relevance conduction direction. For example, user a-home address-user B-mobile phone number-user D, and user D-mobile phone number-user B-home address-user a, in the two association factor combinations, the association level corresponding to the association factor of mobile phone number is different, and the association factor of home address is also different.
Step S600, determining risk transmission weight parameters of the association factors under each association level according to the reference weight parameters of the association factors in the association factor combination and the association levels of the association factors.
And constructing an association relation formula group of a plurality of association factor combinations and the user risk data according to the user risk data of each risk user, the reference weight parameters of each association factor and the association factors among the risk nodes with indirect association relation.
And step S700, updating the parameters of the initial risk transmission associated map according to the equipment label risk weight parameters, the reference weight parameters of the associated factors and the risk transmission weight parameters of the associated factors at different association levels to obtain an optimized risk transmission associated map.
On the basis of the original initial risk conduction associated map, optimizing the risk conduction associated map by analyzing the risk weight parameters of all equipment labels, the reference weight parameters of the association factors among the nodes and the risk conduction weight parameters of all the association factors under different association levels, and deducing probability data of risk conduction according to the optimized risk conduction associated map by combining the label, factor weight ratio and difference information of association degrees. In the optimized risk conduction association map, if a certain node can be clearly identified to be a risk node with fraud, the fraud risk probability of other nodes with unknown risk conditions associated with the node can be obtained, the accuracy of the risk probability result is improved, and then whether the node is a fraud person or not can be evaluated based on the risk probability, so that rejection or key investigation is carried out, and labor and time are saved.
According to the risk conduction association map optimization method, on the basis of an initial risk conduction association map, equipment label information of a risk user corresponding to a risk node is analyzed through the existence of association factors among directly associated risk nodes to obtain equipment label risk weight parameters, reference weight parameters of the association factors are determined through the existence of the association factors among the directly associated risk nodes, the risk conduction weight parameters of the association factors under the association levels are determined through the association levels of the association factors in association factor combinations among indirectly associated risk nodes, the initial risk conduction association map is optimized, deep connection among the nodes of the association map is fully mined, specific conduction parameters among the risk nodes are determined, the risk conduction association map optimized through the parameters can be used for conducting risk directly, the combing and real-time calculating process of the association relationship among the nodes is simplified, the equipment label risk weight parameters obtained through analysis are used as evaluation parameters of node data, the node basic data volume is simplified, the risk conduction analysis is facilitated, and the risk analysis efficiency is improved.
In another embodiment, as shown in fig. 3, before acquiring the risk nodes in the initial risk conduction association graph and the user risk data corresponding to the risk nodes, step S300 further includes:
step S120, obtaining user data information of each user for constructing the initial risk conduction associated graph, marking each user as an associated graph node, screening risk users carrying user risk data in each user, and marking the associated graph node corresponding to the risk user as a risk node.
Step S140, extracting a plurality of data dimension information carried in the message according to the acquired data information, and extracting a data value corresponding to each data dimension in the user data information.
Step S160, searching each feature association graph node containing the same data value, and marking the data dimension corresponding to the data value as an association factor between the feature association graph nodes.
Step S180, constructing the initial risk conduction associated map according to the associated map nodes and the associated factors, wherein the initial risk conduction associated map is marked with risk nodes.
The initial risk conduction association graph is used for displaying association relations among users, users containing user data information are marked as association graph nodes, the user data information can be data information of all dimensions of defaulted users including risk data or data information of all dimensions of non-defaulted users in a normal state, the data information extraction message is used for extracting relevant data values of required data dimensions from the user data information according to the data dimension information carried by the data information extraction message, and the data dimension information is obtained by analyzing in advance according to actual requirements and used for representing all data dimensions of strong and weak connections among the users. By setting the data dimension, the initial risk transmission model can be more orderly and more standard. If the same data value exists between the two nodes, the node can be determined as a feature association graph node, risk users carrying user risk data in each user are screened, association graph nodes corresponding to the risk users are marked as risk nodes, an association relation between the two feature association graph nodes is established according to the data value, data dimensions corresponding to the data value are marked as association factors between the feature association graph nodes, and an initial risk conduction association graph marked with the risk nodes is constructed and obtained on the basis of the association graph nodes and the association factors.
In one embodiment, as shown in fig. 3, before the step S140 of extracting a plurality of data dimension information carried in the message according to the acquired data information and extracting a data value corresponding to each data dimension in the user data information, the method further includes:
and S132, acquiring sample data of the existing risk users, and carrying out data dimension marking on the risk data in the sample data.
Step S134, counting the co-occurrence frequency of each dimension data in each sample data, and screening out the data dimension whose co-occurrence frequency meets the set threshold.
And step S136, generating a data information extraction message carrying data dimension information according to the data dimension obtained by screening.
The co-occurrence is the phenomenon that the same fields appear in different data at the same time, the co-occurrence frequency of the same dimension data is that the frequency that the specific fields of the dimension labels appear in different data at the same time is determined according to the dimension labels of the same fields, sample data of a large number of existing risk users is obtained, the sample data is cleaned, interference information is removed, data dimension marking is carried out on the sample data after data cleaning is completed, the co-occurrence frequency of the data with the same dimension among the samples is counted, the data dimension with the co-occurrence frequency meeting a set threshold value is screened out, and a data information extraction message carrying data dimension information is generated according to the screened data dimension to determine the association factor among the nodes of the initial association map. The set threshold of the co-occurrence frequency can be set according to actual requirements.
In another embodiment, as shown in fig. 4, in step S400, obtaining device tag information of a risk user corresponding to a risk node, and determining a device tag risk weight parameter of the risk node according to the device tag information and user risk data includes:
step S420, obtaining equipment label information of the risk user corresponding to the risk node, and extracting risk identifications carried by each equipment label in the equipment label information, wherein the risk identifications comprise risks and no risks.
And step S440, obtaining the influence weight of each risk label on the user risk data according to the combination result corresponding to the risk identification carried by each risk label and the user risk data corresponding to the risk node.
And step S460, determining equipment label risk weight parameters of the risk nodes according to risk labels carrying risk identifiers in the risk nodes and the influence weights of the risk labels.
The equipment label information is a label set formed by a plurality of equipment labels, and the equipment labels specifically comprise equipment fingerprints, starting time, a simulator, a bad APP, a loan APP, a browser record, a search record, an agent IP (Internet protocol), a call record, an address list, weChat data, equipment flashing, an equipment blacklist, a plurality of equipment with the same number of mobile phones, different numbers of mobile phones with the same equipment, equipment common land and the like. And each equipment label searches a corresponding risk database according to the specific data record, and when the matched data record exists, the risk identification of the equipment label is marked as risky, otherwise, the equipment label is marked as no risk. The method comprises the steps of combining risk identifications corresponding to equipment labels in a label set to obtain a risk identification combination result, constructing a relational group of a plurality of risk identification combinations and user risk data according to the risk identification combination result corresponding to each risk node and the user risk data corresponding to each risk node, solving the relational group to obtain a plurality of groups of calculation results, performing data fitting processing according to the corresponding numerical value of each risk label in the calculation results, obtaining the influence weight of each risk label on the user risk data according to the fitting result, and obtaining the equipment label risk weight parameter of the risk node through accumulation calculation according to the risk labels carrying the risk identifications and the influence weights of each risk label in each risk node.
In a further embodiment, as shown in fig. 5, the step S600 of determining the risk transmission weight parameter of the association factor at each association level according to the reference weight parameter of each association factor in the association factor combination and the association level of the association factor includes:
step S620, obtaining a combination weight parameter corresponding to the association factor combination according to the association grade of each association factor in the association factor combination and the user risk data corresponding to the corresponding risk node in the association factor combination.
And step S640, acquiring risk transmission weight parameters of the association factors under each association level according to the combination weight parameters and the reference weight parameters of the association factors in the association factor combination.
The association factor combination refers to a plurality of association factors existing between two risk nodes, and the combination weight parameter corresponding to the association factor combination refers to the overall conductive influence proportion from one risk user to another risk user, for example, a risk user a is indirectly associated with a risk user C through a normal user B, a plurality of association relations exist between the user a and the user B, a plurality of association relations also exist between the user B and the user C, so a plurality of association factor combinations exist between the user a and the user C, but the combination weight parameters corresponding to different association factor combinations are the same. Through the multiple combination weight parameters and the reference weight parameters of each association factor in the association factor combination, the risk conduction weight parameters of the association factors under each association level can be obtained through solving and data fitting processing of the relationship group by constructing the relationship group.
In one embodiment, in step S700, updating parameters of the initial risk transmission association map according to the device tag risk weight parameters, the reference weight parameters of the association factors, and the risk transmission weight parameters of the association factors at different association levels, so as to obtain an optimized risk transmission association map, further including:
and when a risk analysis request of the target user is received, acquiring equipment label information of the target user.
And obtaining first risk data of the target user according to the equipment label information.
And searching the associated risk user of the target user according to the optimized risk conduction associated map.
And acquiring the conduction risk probability of the associated risk user to the target user according to the reference weight parameters of the associated factors and the risk conduction weight parameters of the associated factors at different association levels, and acquiring second risk data.
And obtaining the risk probability of the target user according to the first risk data and the second risk data.
After the risk conduction association graph is optimized, a user can carry out risk analysis on a target user, the first risk data of the target user can be obtained through proportion accumulation calculation of each equipment label according to the risk identification and the equipment label risk weight parameter of each equipment label in the equipment label information by obtaining equipment label information of the user, the association risk users of the target user can be searched according to the user information of the user and the optimized risk conduction association graph, the association risk users including directly associated risk users and indirectly associated risk users can be obtained, the conduction risk probability of the association risk users on the target user can be obtained through risk conduction according to the reference weight parameter of the association factor, the risk conduction weight parameters of the association factor under different association levels and the user risk data of the association risk users with the target user, the second risk data can be obtained, and the risk probability of the target user can be obtained through obtaining the weighting parameters of the first risk data and the second risk data. The weighting parameters of the first risk data and the second risk data can be obtained by analyzing the equipment tag risk weighting parameters of the risk nodes, the risk conduction results of the risk nodes and the user risk data of the risk nodes.
In one embodiment, after obtaining the risk probability of the target user according to the first risk data and the second risk data in step S860, the method further includes:
and dividing risk grades according to the risk probability of each user in the obtained sample data and the default condition of each user, and determining service suggestions corresponding to each risk grade.
And searching the risk level of the risk probability of the target user according to the risk probability of the target user, and outputting a service suggestion corresponding to the risk level.
In one embodiment, if a node of the risk node conducting graph can clearly identify that the node is a credit node with fraud, the risk node conducting graph can calculate the fraud risk probability of other nodes associated with the node through risk conduction, and a fraud probability threshold value can be defined according to the graph drilling effect. For example, risk probability (corresponding percentile data) [0, 40): low risk; [40, 80): risk of fraud; [80, + ] suspected fraud. And searching the risk level of the risk probability of the target user, outputting a service suggestion corresponding to the risk level, wherein the risk node conduction graph can be identified according to different colors, so that a case dispatcher can directly give a basis for refusing or subsequent key investigation.
It should be understood that although the various steps in the flow charts of fig. 2-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 6, there is provided a risk conductance correlation map optimization apparatus, including:
a risk node obtaining module 300, configured to obtain a risk node in the initial risk conduction associated graph and user risk data corresponding to the risk node;
the device tag risk weight parameter determination module 400 is configured to obtain device tag information of a risk user corresponding to a risk node, and determine a device tag risk weight parameter of the risk node according to the device tag information and user risk data;
the benchmark weight parameter determination module 500 is configured to determine association factors between directly associated risk nodes, association factor combinations between indirectly associated risk nodes, and association levels of each association factor in the association factor combinations according to association relations between the risk nodes, and determine benchmark weight parameters of the association factors according to user risk data corresponding to the risk nodes;
a risk transmission weight parameter determination module 600, configured to determine a risk transmission weight parameter of the association factor at each association level according to the reference weight parameter of each association factor in the association factor combination and the association level of the association factor;
and the initial risk conduction associated map optimizing module 700 is configured to update parameters of the initial risk conduction associated map according to the equipment tag risk weight parameters, the reference weight parameters of the associated factors, and the risk conduction weight parameters of the associated factors at different association levels, so as to obtain an optimized risk conduction associated map.
In another embodiment, the risk conduction associated graph optimizing apparatus further includes an initial risk conduction associated graph building module, configured to obtain user data information of each user for building the initial risk conduction associated graph, label each user as an associated graph node, screen a risk user carrying user risk data in each user, label an associated graph node corresponding to the risk user as a risk node, extract multiple data dimension information carried in the message according to the obtained data information, extract a data value corresponding to each data dimension in the user data information, find each feature associated graph node containing the same data value, label a data dimension corresponding to the data value as an association factor between the feature associated graph nodes, build the initial risk conduction associated graph according to the associated graph nodes and the association factors, and label the initial risk conduction associated graph with the risk node.
In another embodiment, the initial risk conduction correlation map building module is further configured to obtain sample data of an existing risk user, perform data dimension labeling on risk data in the sample data, count co-occurrence frequencies of all dimension data in all sample data, screen out data dimensions of which the co-occurrence frequencies meet a set threshold, and generate a data information extraction message carrying data dimension information according to the screened data dimensions.
In another embodiment, the device tag risk weight parameter determining module 400 is further configured to obtain device tag information of a risk user corresponding to a risk node, extract risk identifiers carried by device tags in the device tag information, where the risk identifiers include risk and risk free, obtain an influence weight of each risk tag on user risk data according to a combination result corresponding to the risk identifier carried by each risk tag and the user risk data corresponding to the risk node, and determine a device tag risk weight parameter of the risk node according to the risk tag carrying the risk identifier in the risk node and the influence weight of each risk tag.
In a further embodiment, the risk conductance weight parameter determining module 600 is further configured to obtain a combination weight parameter corresponding to the association factor combination according to the association level of each association factor in the association factor combination and user risk data corresponding to a risk node corresponding to the association factor combination, and obtain a risk conductance weight parameter of the association factor at each association level according to the combination weight parameter and a reference weight parameter of each association factor in the association factor combination.
In another embodiment, the risk conduction associated map optimizing device further includes a target user risk analysis module, configured to, when a risk analysis request of a target user is received, obtain device tag information of the target user, obtain first risk data of the target user according to the device tag information, find an associated risk user of the target user according to the optimized risk conduction associated map, obtain a conduction risk probability of the associated risk user to the target user according to a reference weight parameter of the association factor and risk conduction weight parameters of the association factor at different association levels, obtain second risk data, and obtain a risk probability of the target user according to the first risk data and the second risk data.
In one embodiment, the risk conduction associated map optimization device further includes a risk analysis result output module, configured to divide risk levels according to risk probabilities of users in the acquired sample data and default conditions of the users, determine service suggestions corresponding to the risk levels, find a risk level where the risk probability of the target user is located according to the risk probability of the target user, and output the service suggestion corresponding to the risk level.
According to the risk conduction association map optimization device, on the basis of an initial risk conduction association map, equipment label information of a risk user corresponding to a risk node is analyzed through the existence of association factors among directly associated risk nodes to obtain equipment label risk weight parameters, reference weight parameters of the association factors are determined through the existence of the association factors among the directly associated risk nodes, the risk conduction weight parameters of the association factors under the association levels are determined through the association levels of the association factors in association factor combinations among indirectly associated risk nodes, the initial risk conduction association map is optimized, deep connection among the nodes of the association map is fully mined, specific conduction parameters among the risk nodes are determined, the risk conduction association map optimized through the parameters can be used for conducting risk directly, the combing and real-time calculating processes of the association relations among the nodes are simplified, the equipment label risk weight parameters obtained through analysis are used as evaluation parameters of node data, the node basic data volume is simplified, the risk conduction analysis is facilitated, and the risk analysis efficiency is improved.
For specific limitations of the risk conductance-associated map optimization device, reference may be made to the above limitations of the risk conductance-associated map optimization method, which is not described herein again. The various modules in the risk transmission correlation map optimization device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile 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 operating system and the computer program to run on the non-volatile storage medium. The database of the computer device is used for storing risk conductance association map optimization data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a risk conductance association map optimization method.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program:
acquiring risk nodes in the initial risk conduction association graph and user risk data corresponding to the risk nodes;
acquiring equipment label information of a risk user corresponding to the risk node, and determining an equipment label risk weight parameter of the risk node according to the equipment label information and user risk data;
determining association factors among directly associated risk nodes, association factor combinations among indirectly associated risk nodes and association levels of all association factors in the association factor combinations according to association relations among the risk nodes, and determining reference weight parameters of the association factors according to user risk data corresponding to the risk nodes;
determining risk conduction weight parameters of the association factors under each association level according to the reference weight parameters of the association factors in the association factor combination and the association levels of the association factors;
and updating the parameters of the initial risk transmission associated map according to the equipment label risk weight parameters, the reference weight parameters of the associated factors and the risk transmission weight parameters of the associated factors at different association levels to obtain an optimized risk transmission associated map.
In other embodiments, the processor, when executing the computer program, further implements the steps corresponding to the embodiments of the risk conductance association map optimization method described above.
According to the computer equipment for realizing the risk conduction association graph optimization method, on the basis of an initial risk conduction association graph, equipment label information of a risk user corresponding to a risk node is analyzed through the existence of association factors among directly associated risk nodes to obtain equipment label risk weight parameters, reference weight parameters of the association factors are determined through the existence of the association factors among the directly associated risk nodes, the risk conduction weight parameters of the association factors under the association levels are determined through the association levels of the association factors in association factor combinations among indirectly associated risk nodes, the initial risk conduction association graph is optimized, deep connection among the nodes of the association graph is fully mined, specific conduction parameters among the risk nodes are determined, the risk conduction association graph optimized through the parameters can be used for conducting risks directly, the combing and real-time calculation processes of the association relations among the nodes are simplified, the equipment label risk weight parameters obtained through analysis are used as evaluation parameters of node data, the quantity of the node basic data is simplified, the risk conduction analysis is facilitated, and the risk analysis efficiency is improved.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring risk nodes in the initial risk conduction association graph and user risk data corresponding to the risk nodes;
acquiring equipment label information of a risk user corresponding to the risk node, and determining an equipment label risk weight parameter of the risk node according to the equipment label information and user risk data;
determining association factors among directly associated risk nodes, association factor combinations among indirectly associated risk nodes and association levels of all association factors in the association factor combinations according to association relations among the risk nodes, and determining reference weight parameters of the association factors according to user risk data corresponding to the risk nodes;
determining risk conduction weight parameters of the association factors under each association level according to the reference weight parameters of the association factors in the association factor combination and the association levels of the association factors;
and updating the parameters of the initial risk transmission associated map according to the equipment label risk weight parameters, the reference weight parameters of the associated factors and the risk transmission weight parameters of the associated factors at different association levels to obtain an optimized risk transmission associated map.
In other embodiments, the computer program, when executed by the processor, further implements the steps corresponding to the embodiments of the risk conductance association map optimization method described above.
The computer-readable storage medium for implementing the risk conduction association graph optimization method analyzes equipment label information of a risk user corresponding to a risk node through the existence of association factors among directly associated risk nodes on the basis of an initial risk conduction association graph to obtain equipment label risk weight parameters, determines reference weight parameters of the association factors through the existence of the association factors among the directly associated risk nodes, determines risk conduction weight parameters of the association factors under the association levels through the association levels of the association factors in association factor combinations among the indirectly associated risk nodes, optimizes the initial risk conduction association graph, fully excavates deep connections among the nodes of the association graph, defines specific conduction parameters among the risk nodes, utilizes the risk conduction association graph optimized by the parameters to directly conduct risks, simplifies the carding and real-time calculation processes of the association relationships among the nodes, and uses the equipment label risk weight parameters obtained through analysis as evaluation parameters of node data to simplify the quantity of node basic data, facilitate risk conduction analysis and improve the risk analysis efficiency.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not to be construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A method of risk-conductance association map optimization, the method comprising:
acquiring risk nodes in an initial risk conduction association graph and user risk data corresponding to the risk nodes;
acquiring equipment label information of a risk user corresponding to the risk node, and determining an equipment label risk weight parameter of the risk node according to the equipment label information and the user risk data;
determining association factors among directly associated risk nodes, association factor combinations among indirectly associated risk nodes and association levels of all association factors in the association factor combinations according to the association relationship among the risk nodes, and determining benchmark weight parameters of the association factors according to user risk data corresponding to the risk nodes;
determining risk conduction weight parameters of the association factors under each association level according to the reference weight parameters of the association factors in the association factor combination and the association levels of the association factors;
updating the parameters of the initial risk transmission associated map according to the equipment label risk weight parameters, the reference weight parameters of the associated factors and the risk transmission weight parameters of the associated factors under different association levels to obtain an optimized risk transmission associated map;
before the obtaining of the risk node in the initial risk conduction associated graph and the user risk data corresponding to the risk node, the method further includes:
acquiring user data information of each user for constructing an initial risk conduction associated graph, marking each user as an associated graph node, screening risk users carrying user risk data in each user, and marking the associated graph node corresponding to the risk user as a risk node;
extracting a plurality of data dimension information carried in a message according to the acquired data information, and extracting a data value corresponding to each data dimension in the user data information;
searching each feature association graph node containing the same data value, and marking the data dimension corresponding to the data value as an association factor among the feature association graph nodes;
constructing the initial risk conduction associated map according to the associated map nodes and the associated factors, wherein the initial risk conduction associated map is labeled with risk nodes;
before extracting a plurality of data dimension information carried in a message according to the obtained data information and extracting a data value corresponding to each data dimension in the user data information, the method further includes:
acquiring sample data of an existing risk user, and carrying out data dimension marking on risk data in the sample data;
counting the co-occurrence frequency of each dimension data in each sample data, and screening out the data dimension of which the co-occurrence frequency meets a set threshold;
and generating the data information extraction message carrying the data dimension information according to the data dimension obtained by screening.
2. The method according to claim 1, wherein the obtaining device tag information of a risk user corresponding to the risk node, and determining a device tag risk weight parameter of the risk node according to the device tag information and the user risk data comprises:
acquiring equipment label information of a risk user corresponding to a risk node, and extracting risk identifiers carried by equipment labels in the equipment label information, wherein the risk identifiers comprise risks and no risks;
obtaining the influence weight of each risk label on the user risk data according to the combination result corresponding to the risk identification carried by each risk label and the user risk data corresponding to the risk node;
and determining equipment label risk weight parameters of the risk nodes according to risk labels carrying risk identifications in the risk nodes and the influence weights of the risk labels.
3. The method according to claim 1, wherein the determining the risk conductance weight parameter of the correlation factor at each correlation level according to the benchmark weight parameter of each correlation factor in the correlation factor combination and the correlation level of the correlation factor comprises:
acquiring a combination weight parameter corresponding to the association factor combination according to the association level of each association factor in the association factor combination and user risk data corresponding to a corresponding risk node in the association factor combination;
and acquiring risk conduction weight parameters of the association factors under each association level according to the combination weight parameters and the reference weight parameters of the association factors in the association factor combination.
4. The method according to claim 1, wherein the updating the parameters of the initial risk transmission association map according to the device label risk weight parameters, the benchmark weight parameters of the association factors and the risk transmission weight parameters of the association factors at different association levels to obtain an optimized risk transmission association map further comprises:
when a risk analysis request of a target user is received, acquiring equipment tag information of the target user;
acquiring first risk data of a target user according to the equipment label information;
searching the associated risk user of the target user according to the optimized risk conduction associated map;
acquiring the conduction risk probability of the associated risk user to the target user according to the reference weight parameters of the associated factors and the risk conduction weight parameters of the associated factors at different association levels to obtain second risk data;
and obtaining the risk probability of the target user according to the first risk data and the second risk data.
5. The method of claim 4, wherein after obtaining the risk probability of the target user based on the first risk data and the second risk data, further comprising:
according to the risk probability of each user in the obtained sample data and the default condition of each user, dividing risk levels and determining a service suggestion corresponding to each risk level;
and searching the risk level of the risk probability of the target user according to the risk probability of the target user, and outputting a service suggestion corresponding to the risk level.
6. A risk transmission correlation map optimization apparatus, the apparatus comprising:
the risk node acquisition module is used for acquiring risk nodes in the initial risk conduction association graph and user risk data corresponding to the risk nodes;
the equipment tag risk weight parameter determining module is used for acquiring equipment tag information of a risk user corresponding to the risk node and determining an equipment tag risk weight parameter of the risk node according to the equipment tag information and the user risk data;
the benchmark weight parameter determination module is used for determining association factors among directly associated risk nodes, association factor combinations among indirectly associated risk nodes and association levels of all association factors in the association factor combinations according to the association relation among the risk nodes, and determining benchmark weight parameters of the association factors according to user risk data corresponding to the risk nodes;
a risk conduction weight parameter determination module, configured to determine a risk conduction weight parameter of each association factor in the association factor combination according to a reference weight parameter of each association factor and an association level of the association factor;
the initial risk conduction associated map optimizing module is used for updating the parameters of the initial risk conduction associated map according to the equipment label risk weight parameters, the reference weight parameters of the associated factors and the risk conduction weight parameters of the associated factors under different association levels to obtain an optimized risk conduction associated map;
the initial risk conduction associated map building module is used for obtaining user data information of each user for building an initial risk conduction associated map, marking each user as an associated map node, screening risk users carrying user risk data in each user, and marking the associated map node corresponding to the risk user as a risk node; extracting a plurality of data dimension information carried in a message according to the acquired data information, and extracting data values corresponding to the data dimensions in the user data information; searching each feature association graph node containing the same data value, and marking the data dimension corresponding to the data value as an association factor among the feature association graph nodes; constructing the initial risk conduction associated map according to the associated map nodes and the associated factors, wherein the initial risk conduction associated map is marked with risk nodes;
the initial risk conduction associated map building module is also used for acquiring sample data of existing risk users and carrying out data dimension marking on risk data in the sample data; counting the co-occurrence frequency of each dimension data in each sample data, and screening out the data dimension of which the co-occurrence frequency meets a set threshold; and generating the data information extraction message carrying the data dimension information according to the data dimension obtained by screening.
7. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910419723.8A CN110245165B (en) | 2019-05-20 | 2019-05-20 | Risk conduction associated graph optimization method and device and computer equipment |
| PCT/CN2019/102962 WO2020232879A1 (en) | 2019-05-20 | 2019-08-28 | Risk conduction association map optimization method and apparatus, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910419723.8A CN110245165B (en) | 2019-05-20 | 2019-05-20 | Risk conduction associated graph optimization method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110245165A CN110245165A (en) | 2019-09-17 |
| CN110245165B true CN110245165B (en) | 2023-04-11 |
Family
ID=67884540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910419723.8A Active CN110245165B (en) | 2019-05-20 | 2019-05-20 | Risk conduction associated graph optimization method and device and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110245165B (en) |
| WO (1) | WO2020232879A1 (en) |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021078300A1 (en) | 2019-10-24 | 2021-04-29 | 先临三维科技股份有限公司 | Three-dimensional scanner and three-dimensional scanning method |
| CN110796394A (en) * | 2019-11-13 | 2020-02-14 | 北京顶象技术有限公司 | Marking method and device for node to be calibrated |
| CN111091287A (en) * | 2019-12-13 | 2020-05-01 | 南京三百云信息科技有限公司 | Risk object identification method and device and computer equipment |
| CN111401700B (en) * | 2020-03-05 | 2023-09-19 | 平安科技（深圳）有限公司 | Data analysis method, device, computer system and readable storage medium |
| CN111753517A (en) * | 2020-06-30 | 2020-10-09 | 北京来也网络科技有限公司 | Document comparison method, device, equipment and medium based on RPA and AI |
| CN112395351A (en) * | 2020-11-19 | 2021-02-23 | 平安普惠企业管理有限公司 | Visual identification group complaint risk method, device, computer equipment and medium |
| CN114595909A (en) * | 2020-12-03 | 2022-06-07 | 国家电网有限公司大数据中心 | Electricity charge recovery risk assessment method and system |
| CN112668836B (en) * | 2020-12-07 | 2024-04-05 | 数据地平线（广州）科技有限公司 | Risk spectrum-oriented associated risk evidence efficient mining and monitoring method and apparatus |
| CN113762684A (en) * | 2020-12-14 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | New user risk assessment method and device, electronic equipment and medium |
| CN112734270B (en) * | 2021-01-19 | 2024-01-23 | 中国科学院地理科学与资源研究所 | Energy risk conduction measurement method, system and data platform |
| CN112785320B (en) * | 2021-02-01 | 2023-09-19 | 北京互金新融科技有限公司 | Credit risk determination method and device, storage medium and electronic equipment |
| CN113139101A (en) * | 2021-05-17 | 2021-07-20 | 清华大学 | Data processing method and device, computer equipment and storage medium |
| CN113240304B (en) * | 2021-05-20 | 2024-10-01 | 北京百度网讯科技有限公司 | Feature construction method, device, equipment and storage medium |
| CN113344405B (en) * | 2021-06-18 | 2024-05-17 | 北京百度网讯科技有限公司 | Method, device, equipment, medium and product for generating information based on knowledge graph |
| CN113449921A (en) * | 2021-07-06 | 2021-09-28 | 中国工商银行股份有限公司 | Risk cause identification method and device and storage medium |
| CN113742495B (en) * | 2021-09-07 | 2024-02-23 | 平安科技（深圳）有限公司 | Rating feature weight determining method and device based on prediction model and electronic equipment |
| CN114022270B (en) * | 2021-10-29 | 2024-05-24 | 平安银行股份有限公司 | Asset data processing method, related equipment and medium |
| CN115146901A (en) * | 2022-05-09 | 2022-10-04 | 石溪信息科技(上海)有限公司 | Marketing cost loss recovery method and system |
| CN117353966A (en) * | 2022-06-29 | 2024-01-05 | 华为技术有限公司 | Network risk assessment method and related device |
| CN115034520B (en) * | 2022-08-09 | 2023-01-10 | 太平金融科技服务(上海)有限公司深圳分公司 | Risk prediction method, device, equipment and storage medium |
| CN115345727B (en) * | 2022-08-19 | 2023-04-28 | 中电金信软件有限公司 | Method and device for identifying fraudulent loan application |
| CN116094974B (en) * | 2023-01-28 | 2024-06-25 | 北京京航计算通讯研究所 | Method and device for generating test case of network communication parameter configuration and test method |
| CN116452130B (en) * | 2023-03-17 | 2023-09-05 | 国网山东省电力公司淄博供电公司 | Knowledge graph-based substation equipment information management system and method |
| CN116934507B (en) * | 2023-09-19 | 2023-12-26 | 国任财产保险股份有限公司 | Intelligent claim settlement method and system based on big data driving |
| CN118337716B (en) * | 2024-06-12 | 2024-08-30 | 杭州我知科技有限公司 | Safety guarantee method of cloud PLC network architecture based on TSN |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572904A (en) * | 2014-12-25 | 2015-04-29 | 微梦创科网络科技（中国）有限公司 | Method and device for determining relevance level between tags |
| 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 |
| CN109657917A (en) * | 2018-11-19 | 2019-04-19 | 平安科技（深圳）有限公司 | Assess method for prewarning risk, device, computer equipment and the storage medium of object |
| CN109753527A (en) * | 2019-01-03 | 2019-05-14 | 深圳壹账通智能科技有限公司 | Abnormal enterprise's method for digging, device, computer equipment and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1816595A1 (en) * | 2006-02-06 | 2007-08-08 | MediaKey Ltd. | A method and a system for identifying potentially fraudulent customers in relation to network based commerce activities, in particular involving payment, and a computer program for performing said method |
| CN109636565A (en) * | 2018-10-16 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Processing method, device, equipment and the computer readable storage medium of risk data |
| CN109685355A (en) * | 2018-12-19 | 2019-04-26 | 重庆百行智能数据科技研究院有限公司 | Business risk recognition methods, device and computer readable storage medium |
-
2019
- 2019-05-20 CN CN201910419723.8A patent/CN110245165B/en active Active
- 2019-08-28 WO PCT/CN2019/102962 patent/WO2020232879A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572904A (en) * | 2014-12-25 | 2015-04-29 | 微梦创科网络科技（中国）有限公司 | Method and device for determining relevance level between tags |
| 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 |
| CN109657917A (en) * | 2018-11-19 | 2019-04-19 | 平安科技（深圳）有限公司 | Assess method for prewarning risk, device, computer equipment and the storage medium of object |
| CN109753527A (en) * | 2019-01-03 | 2019-05-14 | 深圳壹账通智能科技有限公司 | Abnormal enterprise's method for digging, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110245165A (en) | 2019-09-17 |
| WO2020232879A1 (en) | 2020-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245165B (en) | Risk conduction associated graph optimization method and device and computer equipment | |
| CN110020422B (en) | Feature word determining method and device and server | |
| CN109829628A (en) | Method for prewarning risk, device and computer equipment based on big data | |
| US20190179966A1 (en) | Method and apparatus for identifying demand | |
| CN109325118B (en) | Unbalanced sample data preprocessing method and device and computer equipment | |
| CN112148305B (en) | Application detection method, device, computer equipment and readable storage medium | |
| CN108334625B (en) | User information processing method and device, computer equipment and storage medium | |
| CN112394908A (en) | Method and device for automatically generating embedded point page, computer equipment and storage medium | |
| CN110321437B (en) | Corpus data processing method and device, electronic equipment and medium | |
| CN111259952A (en) | Abnormal user identification method and device, computer equipment and storage medium | |
| CN112328802A (en) | Data processing method and device and server | |
| CN111177481B (en) | User identifier mapping method and device | |
| CN110197426B (en) | Credit scoring model building method, device and readable storage medium | |
| CN116151954A (en) | Real-time group-partner anti-fraud detection method and system | |
| CN112463859A (en) | User data processing method based on big data and business analysis and big data platform | |
| CN107943906A (en) | Information collection and display method and device | |
| CN112817816B (en) | Embedded point processing method and device, computer equipment and storage medium | |
| CN110443044A (en) | Block chain client bug excavation method, device, equipment and storage medium | |
| CN115757900B (en) | User demand analysis method and system applying artificial intelligent model | |
| CN111339317A (en) | User registration identification method and device, computer equipment and storage medium | |
| CN111460268A (en) | Method and device for determining database query request and computer equipment | |
| CN109995605B (en) | Flow identification method and device and computer readable storage medium | |
| CN115291762A (en) | Service item triggering method and device, storage medium and computer equipment | |
| CN115329195A (en) | Artificial intelligence-based intention mining method, device, equipment and storage medium | |
| CN112231454B (en) | Question prediction and answer feedback method, device, computer 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |