CN112330468B - Method, device, equipment and storage medium for identifying risk clients - Google Patents
Method, device, equipment and storage medium for identifying risk clients Download PDFInfo
- Publication number
- CN112330468B CN112330468B CN202011212795.4A CN202011212795A CN112330468B CN 112330468 B CN112330468 B CN 112330468B CN 202011212795 A CN202011212795 A CN 202011212795A CN 112330468 B CN112330468 B CN 112330468B
- Authority
- CN
- China
- Prior art keywords
- client
- risk
- clients
- association
- code
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application relates to a big data processing technology, and discloses a method, a device, equipment and a storage medium for identifying risk clients, which comprises the following steps: acquiring prestored client information of each risk client, acquiring associated clients with association relation with each risk client, and constructing a risk association model; when the insurance client is insuring, if the insurance client is not a risk client, analyzing whether the insurance client exists in a pre-constructed risk relation model; if yes, acquiring an associated client of the insurance client, and analyzing whether the associated client is a risk client; if so, acquiring a first code of an insurance product which is applied by an application client, acquiring a second code corresponding to the insurance product which is applied by a risk client with an association relationship with the application client, and calculating a risk value of the application client based on the first code and the second code; whether the insured client is a risk client is identified based on the risk value of the insured client. The risk situation of the client can be prejudged, and the risk client can be effectively identified.
Description
Technical Field
The present application relates to the field of big data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for identifying a risk client.
Background
With the rapid development of the internet industry, various businesses, products and transaction types are more and more, and the business risks generated by the business are also higher and higher. At present, a method for identifying the risk of a client is generally analyzed through the behavior of the client, and the client can be judged to be the risk client when obvious fraudulent behaviors occur to the client.
Disclosure of Invention
The application aims to provide a method, a device, equipment and a storage medium for identifying risk clients, which aim to pre-judge the risk conditions of clients and effectively identify the risk clients.
The application provides a method for identifying risk clients, which comprises the following steps:
acquiring pre-stored client information of each risk client, respectively acquiring associated clients with association relation with each risk client based on the client information, and constructing a risk association model for each corresponding risk client based on the associated clients;
when an insurance client applies for an insurance product, if the insurance client is not a risk client, analyzing whether the insurance client exists in a pre-constructed risk relation model;
if yes, acquiring a corresponding association client of the application client in the risk relation model, and analyzing whether the association client is a risk client or not;
if yes, acquiring a first code of an insurance product which is applied by the application client, acquiring a second code corresponding to the insurance product which is applied by a risk client with an association relation with the application client, and calculating a risk value of the application client based on the first code and the second code, wherein the code of the insurance product is obtained after processing based on a preset product similarity code rule;
identifying whether the insuring client is a risk client based on the risk value of the insuring client.
The application also provides a device for identifying risk clients, comprising:
the model construction module is used for acquiring prestored client information of each risk client, respectively acquiring associated clients with association relation with each risk client based on the client information, and constructing a risk association model for each corresponding risk client based on the associated clients;
the first analysis module is used for analyzing whether the insuring client exists in a pre-constructed risk relation model or not if the insuring client is not a risk client when the insuring client insuring a insurance product;
the second analysis module is used for acquiring the associated client corresponding to the insuring client in the risk relation model if yes, and analyzing whether the associated client is a risk client or not;
the risk processing module is used for acquiring a first code of an insurance product which is applied by the application client and a second code corresponding to the insurance product which is applied by the risk client and has an association relation with the application client if the insurance product is applied by the application client, and calculating a risk value of the application client based on the first code and the second code, wherein the code of the insurance product is obtained after processing based on a preset product similarity coding rule;
and the risk identification module is used for identifying whether the application client is a risk client or not based on the risk value of the application client.
The application also provides a computer device comprising a memory and a processor connected to the memory, wherein the memory stores a computer program which can be run on the processor, and the processor realizes the steps of the method for identifying risk clients when executing the computer program.
The present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above-described method of identifying a risk client.
The beneficial effects of the application are as follows: according to the method, a risk association model is built according to the relation between the risk clients and the associated clients thereof, when the insurance clients are applied, if the insurance clients do not belong to one of prestored risk clients and are in the risk association model, the risk values of the insurance clients are determined by analyzing the relation between the associated clients of the insurance clients and the risk clients and the similarity degree of insurance products applied by the insurance clients and the insurance products applied by the associated clients, so that whether the insurance clients are risk clients or not is identified.
Drawings
FIG. 1 is a schematic view of an application environment of an embodiment of a method for identifying risk customers according to the present application;
FIG. 2 is a flow chart of a first embodiment of a method for identifying a risk client according to the present application;
FIG. 3 is the risk client A of FIG. 2 1 Constructing a schematic diagram of a risk correlation model;
FIG. 4 is a flowchart of a second embodiment of a method for identifying a risk client according to the present application;
FIG. 5 is a flowchart of a third embodiment of a method for identifying a risk client according to the present application;
FIG. 6 is a schematic diagram illustrating an embodiment of an apparatus for identifying risk customers according to the present application;
fig. 7 is a schematic diagram of a hardware architecture of an embodiment of a computer device according to the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the description of "first", "second", etc. in this disclosure is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implying an indication of the number of technical features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present application.
Referring to fig. 1, a schematic view of an application environment of an embodiment of a method for identifying a risk client according to the present application is shown. In this embodiment, the risk client identifying device 1 is connected to a plurality of computers 2 through a network, each computer 2 operates one or more service systems, client information related to the risk client is stored in the service systems, the risk client identifying device 1 obtains pre-stored client information of the risk client from each computer 2, and obtains associated clients associated with the risk client according to the client information, thereby constructing a risk association model, and when other clients are underwriting, the relationship degree between the risk association model and the risk client is analyzed through the risk association model.
The method for identifying the risk client provided by the application can be applied to the application environment as shown in fig. 1. Referring to fig. 2, a flowchart of a first embodiment of a method for identifying a risk client according to the present application is shown. Taking the application of the method for identifying risk clients as an example in the environment of fig. 1, the method includes:
step S1, acquiring pre-stored client information of each risk client, respectively acquiring associated clients with association relation with each risk client based on the client information, and constructing a risk association model for each corresponding risk client based on the associated clients;
the associated clients comprise direct associated clients and indirect associated clients, and the step of constructing a risk associated model for each corresponding risk client based on the associated clients comprises the following steps of:
acquiring prestored policy information of each risk client, acquiring direct association clients and indirect association clients corresponding to each risk client based on the policy information, and constructing a risk association model for each corresponding risk client based on the direct association clients and the indirect association clients, wherein the direct association clients are clients appearing in the policy of the risk client, and the indirect association clients are clients appearing in the policy of the direct association client of the risk client.
In this embodiment, all risk clients are labeled, and if there are m risk clients, the risk clients are recorded as a 1 A 2 A 3 ……A m . Constructing a risk association model for each risk client, wherein the direct association client is a client appearing in a policy of the risk client and is connected through a straight line; an indirect associated client is a client that appears in the policy of the direct associated client of the risk client, which is connected by a straight line with the direct associated client, e.g., A 1 For risk clients, A 1 The risk correlation model of (a) is shown in FIG. 3, B 1 B 2 For risk client A 1 Directly associated clients of B 3 B 4 For risk client A 1 Is a client indirectly associated with the client.
In the risk association model, if a certain client (for example, a risk client) has only one associated client, the associated client is a direct associated client, and if a certain client has a plurality of associated clients, at least one direct associated client is included in the plurality of associated clients.
Step S2, when an insurance client applies for an insurance product, if the insurance client is not a risk client, analyzing whether the insurance client exists in a pre-constructed risk relation model;
when an insurance client applies for an insurance product, if the insurance client is a risk client, namely one of all prestored risk clients, direct refusing is realized; if the insuring client is not a risk client, i.e. does not belong to one of the prestored individual risk clients, then it is analyzed whether the insuring client is in the risk relationship model to analyze how closely the insuring client is in relationship with the risk client.
Step S3, if so, acquiring an associated client corresponding to the insuring client in the risk relation model, and analyzing whether the associated client is a risk client or not;
wherein, if the application client has one association client, the association client is a direct association client, and if the application client has two or more association clients, the association client can be a plurality of direct association clients or a combination of the direct association client and the indirect association client. If the client is in the risk relation model, determining whether the client is a risk client or not according to the policy information of the associated client of the client, and further analyzing the relation between the associated client and the risk client.
Step S4, if yes, acquiring a first code of an insurance product which is applied by the application client, acquiring a second code corresponding to the insurance product which is applied by a risk client with an association relation with the application client, and calculating a risk value of the application client based on the first code and the second code, wherein the code of the insurance product is obtained after processing based on a preset product similarity code rule;
and step S5, identifying whether the insuring client is a risk client or not based on the risk value of the insuring client.
Further, if the client is identified as a risk client, refusing the underwriting, and constructing a corresponding risk association model for the client; if the application client is identified as not a risk client, underwriting.
The preset product similarity coding rule comprises the following steps:
randomly selecting a first insurance product, selecting a second insurance product similar to the first insurance product according to a preset similarity rule, and selecting a third insurance product similar to the second insurance product according to the preset similarity rule until all insurance products are selected;
and taking the first insurance product as a first insurance product, sorting all insurance products according to the similarity degree, and coding the sorted insurance products in a gradually increasing mode.
For example, the preset product similarity coding rule is:
(1) Randomly selecting one insurance product P 1 The record code is 1.
(2) Then according to the information of the liability and the risk information of the insurance products, namely the similarity of the insurance products with the same risk, the same responsibility or similar liability is high, and the similarity of the insurance products with different risk and different responsibility is low, the insurance products are selected to be P 1 Most similar insurance product P 2 Recording insurance product P 2 The code is 2.
(3) Selecting and P according to the mode of (2) 2 Most similar insurance product P 3 The record code is 3.
(4) And so on, all insurance products are ordered as P 1 P 2 P 3 ……P m The corresponding codes are 1,2,3, …, m.
The coded insurance products are the most similar to adjacent insurance products, namely, the insurance products with smaller coded difference values are more similar, and the insurance products with larger coded difference values are more dissimilar.
The preset similarity rule at least comprises the degree of similarity of the responsibility and risk information of the insurance product in two dimensions, and of course, the preset similarity rule can also comprise information of other dimensions.
When the insurance client C applies for a certain insurance product, the direct association client of the insurance client C or the direct association client and the indirect association client are obtained through the risk association model of the existing risk client, and the insurance product applied by the insurance client C can be obtained through the policy information of the direct association client or the policy information corresponding to the direct association client and the indirect association client, so that the code of the insurance product is obtained, for example, the direct association client of the insurance client C is assumed to be e, f and g, and the indirect association client is assumed to be m and n. The risk value of the insurance client C characterizes the relative risk relationship between the insurance client C and the risk client, and the smaller the risk value is, the closer the risk value is to the risk client, the greater the possibility that the insurance client is the risk client, otherwise, if the larger the risk value is, the less the risk value is to the risk client, and the smaller the possibility that the insurance client is the risk client. The risk value for insurance product that is applied to customer C is calculated by using Pro as the code for insurance product that customer applies to:
if the direct association client or the indirect association client has a risk client and only one risk client, and the risk client is assumed to be e, calculating the risk value=Pro (C) -Pro (e) of the insurance client C, if the insurance client C and the risk client e apply the same insurance product, the risk value of the insurance client C is 0, defining the risk client by the insurance client C, directly refusing the insurance client, and establishing a risk association model of the insurance client.
Further, if there are multiple risk clients j, h, k in the direct association client or the indirect association client, calculating corresponding risk values: pro (C) -Pro (j), pro (C) -Pro (h), pro (C) -Pro (k), the smallest risk value of which is obtained as the risk value of the insuring client C.
In step S5, a risk threshold (for example, a risk threshold of 2) may be preset, if the risk value of the obtained client C is calculated to be smaller than the risk threshold, the client C is identified as a risk client, and if the risk value of the obtained client C is calculated to be greater than or equal to the risk threshold, the client C is identified as a non-risk client.
In the embodiment, a risk association model is built according to the relationship between a risk client and an associated client thereof, when an insurance client is ensured, if the insurance client does not belong to one of prestored risk clients and exists in the risk association model, the risk value of the insurance client is determined by analyzing the relationship between the associated client of the insurance client and the risk client and the similarity degree of an insurance product ensured by the insurance client and the insurance product ensured by the associated client, so that whether the insurance client is the risk client is identified.
In one embodiment, as shown in fig. 4, after obtaining the associated client corresponding to the insuring client in the risk relation model in step S3 and analyzing whether the associated client is a risk client, the method further includes:
step S6, if the associated clients are not risk clients, calculating the risk difference degree between the insuring client and the associated clients, and obtaining one associated client with the minimum risk difference degree as a similar client of the insuring client;
step S7, if the similar clients are direct association clients of the insuring clients, obtaining the direct association clients and indirect association clients corresponding to the similar clients in the risk relation model, and analyzing whether risk clients exist in the direct association clients or the indirect association clients corresponding to the similar clients;
and S8, if so, acquiring a third code of the insurance product applied by the risk client with the association relation with the similar client, and calculating the risk value of the applied client based on the first code and the third code.
If the direct association client or the indirect association client of the application client is not the risk client, the risk difference degree between the application client and each direct association client is required to be calculated, or the risk difference degree between the application client and each direct association client or each indirect association client is calculated, and the client with the minimum risk difference degree with the application client is found to be used as the similar client. Of course, if there is only one associated client, then that associated client is the similar client with the least risk variance.
In steps S7 and S8, if the similar client is a direct association client of the insuring client, acquiring a direct association client and an indirect association client corresponding to the similar client in the risk relationship model, and analyzing whether a risk client exists in the direct association client or the indirect association client corresponding to the similar client; if so, acquiring a third code of the insurance product which is applied by the existing risk client, and calculating the risk value of the applied client based on the first code and the third code: risk value of insuring client C = Pro (C) -Pro (b), b is the direct or indirect associated client corresponding to the similar client, and b is the risk client.
Of course, if there are a plurality of similar clients, such as similar clients o, p and q, the direct association clients and the indirect association clients corresponding to the direct similar clients o, p and q analyze whether there is a risk client in the clients; in addition, if a plurality of risk clients r, s and t exist in the direct association clients or the indirect association clients corresponding to the similar clients, respectively acquiring third codes of insurance products applied by the risk clients r, s and t, and calculating corresponding risk values: pro (C) -Pro (r), pro (C) -Pro(s), pro (C) -Pro (t), the smallest risk value among them is obtained as the risk value of the insuring client C.
According to the method and the system, the similar clients of the insuring clients in the risk association model are determined based on the risk difference, and whether the direct association clients of the similar clients are risk clients or not is analyzed, so that the degree of closeness of the relationship between the insuring clients and the risk clients is analyzed to determine the risk value of the insuring clients, the risk condition of the clients can be further analyzed, and the risk clients are identified.
Further, assigning risk scores to clients in the model when constructing the risk correlation model includes: assigning a first risk score to the risk client, assigning a second risk score to a directly associated client of the risk client, and assigning a third risk score to an indirectly associated client of the risk client, wherein the first risk score is far greater than the second risk score, and the second risk score is greater than the third risk score, and calculating the risk difference between the guaranteeing client and the associated client in the step S6 specifically includes:
if the associated client is a direct associated client of the insuring client, a fourth code of the insurance product insured by the associated client is obtained, and the risk difference degree is calculated based on the first code, the fourth code and the second risk score;
and if the associated client is an indirect associated client of the insuring client, acquiring a fifth code of the insurance product insured by the associated client, and calculating the risk difference degree based on the first code, the fifth code and the third risk score.
For the risk clients, the risk score of the clients not appearing in the risk association model may be infinite, the risk score of the clients is 0, the risk score of the clients directly associated with the risk clients is greater than that of the clients indirectly associated with the risk clients, for example, the risk score of the clients directly associated with the risk clients is 2, and the risk score of the clients indirectly associated with the risk clients is 1.
Representing the Risk score of the customer with Risk, calculating the Risk variance comprises:
risk variability= [ Pro (C) -Pro (a) ]/Risk (a), where a is the direct or indirect associated client of the insuring client C, and a is valued as the second or third Risk score, respectively.
The smaller the risk difference degree is, the more similar the insuring client C is to a, and the client with the smallest risk difference degree is taken as the similar client of the insuring client C. Of course, there may be multiple clients with minimum risk variability, all of which are the same, i.e., multiple similar clients of the insuring client C.
In one embodiment, as shown in fig. 5, after calculating the risk difference between the insuring client and the associated client in step S6, obtaining an associated client with the smallest risk difference as a similar client of the insuring client, the method further includes:
step S9, if the similar clients are indirect association clients of the insuring clients, obtaining direct association clients corresponding to the similar clients in the risk relation model, and analyzing whether risk clients exist in the direct association clients corresponding to the similar clients;
and step S10, if so, obtaining a sixth code of the insurance product applied by the risk client with the association relation with the similar client, and calculating the risk value of the applied client based on the first code and the sixth code.
If the similar clients are indirect association clients of the insurance client, obtaining corresponding direct association clients of the similar clients in the risk relation model, and analyzing whether risk clients exist in the direct association clients corresponding to the similar clients; if one risk client exists, a sixth code of the insurance product which is applied by the existing risk client is obtained, and the risk value of the applied client is calculated based on the first code and the sixth code: risk value = Pro (C) -Pro (d) for the insuring client C, d being the direct associated client corresponding to the similar client, and d being the risk client.
Of course, if there are multiple risk clients u and v in the direct associated clients corresponding to the similar clients, respectively obtaining sixth codes of the risk clients u and v, and calculating risk values of the insuring clients: pro (C) -Pro (u), pro (C) -Pro (v), the smallest risk value among them is obtained as the risk value of the insuring client C.
According to the method and the system, the similar clients of the insuring clients in the risk association model are determined based on the risk difference, and whether the indirect association clients of the similar clients are risk clients or not is analyzed, so that the degree of closeness of the relationship between the insuring clients and the risk clients is analyzed to determine the risk value of the insuring clients, the risk condition of the clients can be further analyzed, and the risk clients are identified.
In one embodiment, the present application provides a device for identifying a risk client, where the device for identifying a risk client corresponds to the method for identifying a risk client in the foregoing embodiment one by one. As shown in fig. 6, the apparatus for identifying a risk client includes:
the model construction module 101 is configured to obtain pre-stored client information of each risk client, obtain association clients having association relationships with each risk client based on the client information, and construct a risk association model for each corresponding risk client based on the association clients;
the first analysis module 102 is configured to, when an insurance product is applied by an application client, analyze whether the application client exists in a pre-built risk relationship model if the application client is not a risk client;
the second analysis module 103 is configured to, if yes, obtain an associated client corresponding to the application client in the risk relationship model, and analyze whether the associated client is a risk client;
the risk processing module 104 is configured to obtain a first code of an insurance product that is applied by the application client if the first code is positive, obtain a second code corresponding to the insurance product that is applied by the risk client that has an association relationship with the application client, and calculate a risk value of the application client based on the first code and the second code, where the code of the insurance product is obtained after processing based on a preset product similarity coding rule;
and a risk identification module 105, configured to identify whether the client is a risk client based on the risk value of the client.
Specific limitations of the means for identifying risk customers may be found in the limitations of the method for identifying risk customers hereinabove and will not be described in detail herein. The various modules in the means for identifying risk customers described above may be implemented in whole or in part in software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which is a device capable of automatically performing numerical calculation and/or information processing in accordance with instructions set or stored in advance. The computer device may be a PC (Personal Computer ), or a smart phone, a tablet computer, a server group formed by a single network server, a plurality of network servers, or a cloud based on cloud computing, where the cloud computing is a kind of distributed computing, and is a super virtual computer formed by a group of loosely coupled computer sets.
As shown in fig. 7, the computer device may include, but is not limited to, a memory 11, a processor 12, and a network interface 13, which may be communicatively connected to each other through a system bus, the memory 11 storing a computer program executable on the processor 12. It should be noted that FIG. 7 only shows a computer device having components 11-13, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead.
Wherein the memory 11 may comprise non-volatile and/or volatile memory. The nonvolatile 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), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others. In this embodiment, the readable storage medium of the memory 11 is typically used for storing an operating system and various application software installed on a computer device, for example, for storing program codes of a computer program in an embodiment of the present application. Further, the memory 11 may be used to temporarily store various types of data that have been output or are to be output.
The processor 12 may in some embodiments be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip for executing program code stored in the memory 11 or for processing data, such as executing a computer program or the like.
The network interface 13 may comprise a standard wireless network interface, a wired network interface, which network interface 13 is typically used to establish communication connections between the computer device and other electronic devices.
The computer program is stored in the memory 11 and comprises at least one computer readable instruction stored in the memory 11, the at least one computer readable instruction being executable by the processor 12 to implement the method of identifying risk customers according to embodiments of the application, comprising:
acquiring pre-stored client information of each risk client, respectively acquiring associated clients with association relation with each risk client based on the client information, and constructing a risk association model for each corresponding risk client based on the associated clients;
when an insurance client applies for an insurance product, if the insurance client is not a risk client, analyzing whether the insurance client exists in a pre-constructed risk relation model;
if yes, acquiring a corresponding association client of the application client in the risk relation model, and analyzing whether the association client is a risk client or not;
if yes, acquiring a first code of an insurance product which is applied by the application client, acquiring a second code corresponding to the insurance product which is applied by a risk client with an association relation with the application client, and calculating a risk value of the application client based on the first code and the second code, wherein the code of the insurance product is obtained after processing based on a preset product similarity code rule;
identifying whether the insuring client is a risk client based on the risk value of the insuring client.
In one embodiment, the present application provides a computer readable storage medium having a computer program stored thereon, which when executed by a processor, implements the steps of the method for identifying a risk client in the above embodiment, such as steps S1 to S5 shown in fig. 2. Alternatively, the computer program, when executed by the processor, implements the functions of the modules/units of the apparatus for identifying risk customers in the above embodiments, such as the functions of the modules 101 to 105 shown in fig. 6. In order to avoid repetition, a description thereof is omitted.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (7)
1. A method of identifying a risk client, comprising:
acquiring pre-stored client information of each risk client, respectively acquiring associated clients with association relation with each risk client based on the client information, and constructing a risk association model for each corresponding risk client based on the associated clients;
when an insurance client applies for an insurance product, if the insurance client is not a risk client, analyzing whether the insurance client exists in a pre-constructed risk relation model;
if yes, acquiring a corresponding association client of the application client in the risk relation model, and analyzing whether the association client is a risk client or not;
if yes, acquiring a first code of an insurance product which is applied by the application client, acquiring a second code corresponding to the insurance product which is applied by a risk client with an association relation with the application client, and calculating a risk value of the application client based on the first code and the second code, wherein the code of the insurance product is obtained after processing based on a preset product similarity code rule;
identifying whether the insuring client is a risk client based on the risk value of the insuring client;
the step of constructing a risk association model for each corresponding risk client based on the association client comprises the following steps: acquiring prestored policy information of each risk client, acquiring direct association clients and indirect association clients corresponding to each risk client based on the policy information, and constructing a risk association model for each corresponding risk client based on the direct association clients and the indirect association clients, wherein the direct association clients are clients appearing in the policy of the risk client, and the indirect association clients are clients appearing in the policy of the direct association client of the risk client;
the step of obtaining the associated client corresponding to the insuring client in the risk relation model and analyzing whether the associated client is a risk client further comprises the following steps: if the associated clients are not risk clients, calculating the risk difference degree between the insuring client and the associated clients, and acquiring one associated client with the minimum risk difference degree as a similar client of the insuring client; if the similar clients are direct association clients of the insuring clients, obtaining the direct association clients and indirect association clients corresponding to the similar clients in the risk relation model, and analyzing whether risk clients exist in the direct association clients or the indirect association clients corresponding to the similar clients; if yes, acquiring a third code of the insurance product applied by the risk client with the association relation with the similar client, and calculating a risk value of the application client based on the first code and the third code;
the step of constructing a risk association model for each corresponding risk client based on the associated client further comprises: assigning a first risk score to the risk client, assigning a second risk score to a directly associated client of the risk client, and assigning a third risk score to an indirectly associated client of the risk client, wherein the first risk score is greater than the second risk score, and the second risk score is greater than the third risk score;
the step of calculating the risk difference degree between the insuring client and the associated client specifically comprises the following steps: if the associated client is a direct associated client of the insuring client, a fourth code of the insurance product insured by the associated client is obtained, and the risk difference degree is calculated based on the first code, the fourth code and the second risk score; and if the associated client is an indirect associated client of the insuring client, acquiring a fifth code of the insurance product insured by the associated client, and calculating the risk difference degree based on the first code, the fifth code and the third risk score.
2. The method of identifying risk customers according to claim 1, wherein the step of calculating a risk variance between the insuring customer and the associated customer, and obtaining an associated customer with the smallest risk variance as a similar customer to the insuring customer further comprises:
if the similar clients are indirect association clients of the insuring clients, obtaining direct association clients corresponding to the similar clients in the risk relation model, and analyzing whether risk clients exist in the direct association clients corresponding to the similar clients;
if so, a sixth code of the insurance product applied by the risk client with the association relation with the similar client is obtained, and the risk value of the application client is calculated based on the first code and the sixth code.
3. The method of identifying risk customers according to any of the claims 1 to 2, wherein the pre-set product similarity coding rules comprise:
randomly selecting a first insurance product, selecting a second insurance product similar to the first insurance product according to a preset similarity rule, and selecting a third insurance product similar to the second insurance product according to the preset similarity rule until all insurance products are selected;
and taking the first insurance product as a first insurance product, sorting all insurance products according to the similarity degree, and coding the sorted insurance products in a gradually increasing mode.
4. The method of identifying a risk client according to any one of claims 1 to 2, further comprising, after the step of identifying whether the application client is a risk client based on the risk value of the application client: and if the client is identified as a risk client, refusing the underwriting, and constructing a corresponding risk association model for the client.
5. An apparatus for identifying a risk client for implementing a method of identifying a risk client as claimed in any one of claims 1 to 4, comprising:
the model construction module is used for acquiring prestored client information of each risk client, respectively acquiring associated clients with association relation with each risk client based on the client information, and constructing a risk association model for each corresponding risk client based on the associated clients;
the first analysis module is used for analyzing whether the insuring client exists in a pre-constructed risk relation model or not if the insuring client is not a risk client when the insuring client insuring a insurance product;
the second analysis module is used for acquiring the associated client corresponding to the insuring client in the risk relation model if yes, and analyzing whether the associated client is a risk client or not;
the risk processing module is used for acquiring a first code of an insurance product which is applied by the application client and a second code corresponding to the insurance product which is applied by the risk client and has an association relation with the application client if the insurance product is applied by the application client, and calculating a risk value of the application client based on the first code and the second code, wherein the code of the insurance product is obtained after processing based on a preset product similarity coding rule;
and the risk identification module is used for identifying whether the application client is a risk client or not based on the risk value of the application client.
6. A computer device comprising a memory and a processor connected to the memory, the memory having stored therein a computer program executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method of identifying a risk client as claimed in any one of claims 1 to 4.
7. A computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method of identifying a risk client according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011212795.4A CN112330468B (en) | 2020-11-03 | 2020-11-03 | Method, device, equipment and storage medium for identifying risk clients |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011212795.4A CN112330468B (en) | 2020-11-03 | 2020-11-03 | Method, device, equipment and storage medium for identifying risk clients |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112330468A CN112330468A (en) | 2021-02-05 |
| CN112330468B true CN112330468B (en) | 2023-10-27 |
Family
ID=74323283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011212795.4A Active CN112330468B (en) | 2020-11-03 | 2020-11-03 | Method, device, equipment and storage medium for identifying risk clients |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112330468B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544266A (en) * | 2018-10-19 | 2019-03-29 | 中国平安人寿保险股份有限公司 | Product data method for pushing, device and computer readable storage medium |
| CN109670937A (en) * | 2018-09-26 | 2019-04-23 | 平安科技（深圳）有限公司 | Risk subscribers recognition methods, user equipment, storage medium and device |
| CN110349039A (en) * | 2019-06-13 | 2019-10-18 | 中国平安人寿保险股份有限公司 | Complaint risk appraisal procedure, system, computer equipment and readable storage medium storing program for executing |
| CN110675268A (en) * | 2019-08-14 | 2020-01-10 | 中国平安财产保险股份有限公司 | Risk client identification method and device and server |
| CN111210109A (en) * | 2019-12-20 | 2020-05-29 | 上海淇玥信息技术有限公司 | Method and device for predicting user risk based on associated user and electronic equipment |
| CN111353901A (en) * | 2020-02-24 | 2020-06-30 | 阳光保险集团股份有限公司 | Risk identification monitoring method and device and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130211983A1 (en) * | 2012-02-15 | 2013-08-15 | Bank Of America Corporation | On-going customer risk assessment of a financial institution customer population |
-
2020
- 2020-11-03 CN CN202011212795.4A patent/CN112330468B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670937A (en) * | 2018-09-26 | 2019-04-23 | 平安科技（深圳）有限公司 | Risk subscribers recognition methods, user equipment, storage medium and device |
| CN109544266A (en) * | 2018-10-19 | 2019-03-29 | 中国平安人寿保险股份有限公司 | Product data method for pushing, device and computer readable storage medium |
| CN110349039A (en) * | 2019-06-13 | 2019-10-18 | 中国平安人寿保险股份有限公司 | Complaint risk appraisal procedure, system, computer equipment and readable storage medium storing program for executing |
| CN110675268A (en) * | 2019-08-14 | 2020-01-10 | 中国平安财产保险股份有限公司 | Risk client identification method and device and server |
| CN111210109A (en) * | 2019-12-20 | 2020-05-29 | 上海淇玥信息技术有限公司 | Method and device for predicting user risk based on associated user and electronic equipment |
| CN111353901A (en) * | 2020-02-24 | 2020-06-30 | 阳光保险集团股份有限公司 | Risk identification monitoring method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112330468A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858737B (en) | Grading model adjustment method and device based on model deployment and computer equipment | |
| CN109766534B (en) | Report generation method and device, computer equipment and readable storage medium | |
| CN110349039B (en) | Complaint risk assessment method, system, computer device and readable storage medium | |
| CN108287823B (en) | Message data processing method and device, computer equipment and storage medium | |
| CN110083634B (en) | Order processing method, device, equipment and storage medium based on data analysis | |
| CN114020578A (en) | User portrait-based abnormal account detection method, device, equipment and medium | |
| CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
| CN113178071B (en) | Driving risk level identification method and device, electronic equipment and readable storage medium | |
| CN112035775B (en) | User identification method and device based on random forest model and computer equipment | |
| WO2019192101A1 (en) | Customer protection analysis method, electronic device, and computer readable storage medium | |
| CN108985755B (en) | Account state identification method and device and server | |
| CN112330468B (en) | Method, device, equipment and storage medium for identifying risk clients | |
| CN110597977B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN110598124B (en) | Numerical attribute mining method, device, computer equipment and storage medium | |
| CN112348371A (en) | Cloud asset security risk assessment method, device, equipment and storage medium | |
| CN111737320A (en) | Method and device for establishing group user behavior baseline and computer equipment | |
| CN116610821A (en) | Knowledge graph-based enterprise risk analysis method, system and storage medium | |
| CN111340365A (en) | Enterprise data processing method and device, computer equipment and storage medium | |
| CN110827144B (en) | Application risk evaluation method and application risk evaluation device for user and electronic equipment | |
| CN110598090B (en) | Interest tag generation method and device, computer equipment and storage medium | |
| CN109885710B (en) | User image depicting method based on differential evolution algorithm and server | |
| CN113328988A (en) | Network security verification method and system based on big data and cloud computing | |
| CN109377213B (en) | Self-service card activation method and device, computer equipment and storage medium | |
| CN110674129A (en) | Abnormal event processing method, system, computer equipment and storage medium | |
| CN111125685A (en) | Method and device for predicting network security situation |
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 |