CN112819476A - Risk identification method and device, nonvolatile storage medium and processor - Google Patents
Risk identification method and device, nonvolatile storage medium and processor Download PDFInfo
- Publication number
- CN112819476A CN112819476A CN202110212806.7A CN202110212806A CN112819476A CN 112819476 A CN112819476 A CN 112819476A CN 202110212806 A CN202110212806 A CN 202110212806A CN 112819476 A CN112819476 A CN 112819476A
- Authority
- CN
- China
- Prior art keywords
- analyzed
- information
- consumption
- grade
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
Abstract
The invention discloses a risk identification method, a risk identification device, a nonvolatile storage medium and a processor. Wherein, the method comprises the following steps: acquiring consumption information of an object to be analyzed; analyzing the consumption information by adopting a clustering model to obtain an object grade of the object to be analyzed, wherein the object grade is used for representing the credit risk of the object to be analyzed; acquiring object information of an object to be analyzed, order information corresponding to the target object and equipment information of equipment associated with the object to be analyzed, wherein the target object is an object corresponding to the object to be analyzed when the object to be analyzed executes consumption behaviors; and determining the risk type of the object to be analyzed according to the object grade, the object information, the equipment information and the order information. The risk identification method and the risk identification device solve the technical problem that the existing risk identification strategy cannot analyze the object without the historical sample.
Description
Technical Field
The invention relates to the field of risk identification, in particular to a risk identification method, a risk identification device, a nonvolatile storage medium and a processor.
Background
With the rapid development of information technology, many enterprises create applications or programs for selling products, including physical products and virtual electronic products, for the purpose of product promotion. In some post-validation by-product, there is a risk of user credit and a risk of fraud cash-out. For example, in a predetermined hotel scene, a user prepays a hotel order, deducts money before the hotel confirms resources, the user generally thinks that the order submitted can be confirmed to enter, and the hotel confirms resources before the hotel is full, so that the user cannot enter, the user experience is poor, the complaint is strong, in order to improve the customer experience, enterprises corresponding to many hotels currently adopt a pad to pay the hotel order funds, and deduct money from the user after the hotel confirms resources, so that the complaint rate of the user is reduced. However, after the hotel confirms the resources, the user is unsuccessfully deducted due to reasons such as unbinding or insufficient card balance, the order of the withholding failure cannot be cancelled, and the subsequent money recollection for the user fails, so that the hotel enterprises can suffer loss, and the credit risk of the user is caused. In addition, the hotel and the user collaborate to share, the order is paid after the hotel confirmation is intentionally reserved, and the deduction is failed, so that the hotel enterprises are charged with the loss.
In order to avoid the above risks, the prior art mainly evaluates the credit risk of the user through the integrity score of the user, the external data score and the like, and the lower the risk of the user is, the more chance the user can use the related credit product. However, for overseas users, there are no integrity scores and no external data scores, that is, the above existing schemes cannot be applied to overseas user groups, and overseas passenger groups also have no use records of credit products of enterprises, cannot obtain bad samples of user credit risks, and cannot evaluate user risk levels for overseas users by constructing classification models, predict default probabilities of users, and credit scores are mainly directed at users, and cannot identify fraud cash-out behaviors.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a risk identification method, a risk identification device, a nonvolatile storage medium and a processor, which are used for at least solving the technical problem that the existing risk identification strategy cannot analyze an object without a historical sample.
According to an aspect of an embodiment of the present invention, there is provided a risk identification method, including: acquiring consumption information of an object to be analyzed; analyzing the consumption information by adopting a clustering model to obtain an object grade of the object to be analyzed, wherein the object grade is used for representing the credit risk of the object to be analyzed; acquiring object information of an object to be analyzed, order information corresponding to the target object and equipment information of equipment associated with the object to be analyzed, wherein the target object is an object corresponding to the object to be analyzed when the object to be analyzed executes consumption behaviors; and determining the risk type of the object to be analyzed according to the object grade, the object information, the equipment information and the order information.
Further, the risk identification method comprises: acquiring consumption time, consumption times and consumption amount of an object to be analyzed within a first preset time length; analyzing the consumption time, consumption times and consumption amount of the object to be analyzed in a preset time length based on the clustering model to obtain the score of the object to be analyzed; and determining the object grade of the object to be analyzed according to the score.
Further, the risk identification method comprises: the method comprises the steps that a data source containing consumption information of a plurality of objects is obtained before consumption time, consumption times and consumption amount of an object to be analyzed in a preset time length are analyzed based on a clustering model to obtain a score of the object to be analyzed; performing data extraction on a data source to obtain first historical data; removing missing values and abnormal values in the first historical data to obtain second historical data; performing data transformation on the second historical data to obtain third historical data; and performing data modeling based on the third history data to obtain a clustering model.
Further, the object information includes at least one of: characteristic information and order behavior information of the object to be analyzed, wherein the order behavior information at least comprises one of the following information: order quantity, order amount and order cancellation information of the object to be analyzed; the device information includes at least one of: login information of the equipment and the number of objects of the object associated with the equipment; the order information includes at least one of: and the order quantity, the post-paid order proportion and the deduction failure proportion of the target object within a second preset time length.
Further, the risk identification method comprises: and under the condition that the object grade is greater than or equal to the preset grade, identifying the object information, the equipment information and the order information to obtain the risk type of the object to be analyzed.
Further, the risk identification method comprises: and if the object to be analyzed is determined to be an abnormal object according to the object information, and/or the equipment is determined to be abnormal equipment according to the equipment information, and/or the target object is determined to be an abnormal target object according to the order information, determining the risk type of the object to be analyzed to be a cash-out risk.
Further, the risk identification method comprises: under the condition that the grade of the object is smaller than the preset grade, detecting the grade duration of the object to be analyzed at the current grade; and determining the risk type of the object to be analyzed as a cash-out risk under the condition that the grade duration is greater than the preset duration.
According to another aspect of the embodiments of the present invention, there is also provided a risk identification apparatus, including: the first acquisition module is used for acquiring consumption information of an object to be analyzed; the analysis module is used for analyzing the consumption information by adopting a clustering model to obtain an object grade of the object to be analyzed, wherein the object grade is used for representing the credit risk of the object to be analyzed; the second acquisition module is used for acquiring object information of the object to be analyzed, order information corresponding to the target object and equipment information of equipment associated with the object to be analyzed, wherein the target object is an object corresponding to the object to be analyzed when the object to be analyzed executes consumption behaviors; and the identification module is used for determining the risk type of the object to be analyzed according to the object grade, the object information, the equipment information and the order information.
According to another aspect of the embodiments of the present invention, there is also provided a non-volatile storage medium having a computer program stored therein, wherein the computer program is configured to execute the above risk identification method when running.
According to another aspect of the embodiments of the present invention, there is also provided a processor for executing a program, wherein the program is configured to execute the above risk identification method when running.
In the embodiment of the invention, a clustering model is adopted to analyze the consumption information of the object to be analyzed so as to determine the credit risk of the object to be analyzed, after the consumption information of the object to be analyzed is obtained, the consumption information is analyzed by adopting the clustering model so as to obtain the object grade of the object to be analyzed, then the object information of the object to be analyzed, the order information corresponding to the target object and the equipment information of the equipment associated with the object to be analyzed are obtained, and finally the risk type of the object to be analyzed is determined according to the object grade, the object information, the equipment information and the order information. The object grade is used for representing credit risks of the object to be analyzed, and the target object is an object corresponding to the object to be analyzed when the consumption behavior is executed.
In the above process, the consumption information of the object to be analyzed is analyzed by using the clustering model, and the consumption information represents the consumption behavior of the object to be analyzed, that is, in the present application, the consumption behavior of the object to be analyzed is analyzed by using the clustering method to determine the credit risk of the object to be analyzed without using a history sample. In addition, the risk type corresponding to the object to be analyzed is determined by analyzing the object to be analyzed from multiple dimensions, so that the classification type of the object to be analyzed is accurately analyzed, the problem that the risk type cannot be identified in the prior art is solved, the accuracy of credit risk identification is improved, and the probability of credit risk occurrence is effectively reduced.
Therefore, the scheme provided by the application achieves the purpose of identifying the credit risk of the object without the historical sample, so that the technical effect of reducing the occurrence rate of the credit risk is achieved, and the technical problem that the existing risk identification strategy cannot analyze the object without the historical sample is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of a risk identification method according to an embodiment of the present invention;
FIG. 2 is a dimensional schematic of an alternative risk identification according to an embodiment of the invention;
FIG. 3 is a schematic diagram of an alternative clustering model modeling and application according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a risk identification device according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
In accordance with an embodiment of the present invention, there is provided an embodiment of a risk identification method, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than that presented herein.
In addition, it should be noted that the risk identification terminal may execute the risk identification method in this embodiment, where the risk identification terminal may be a computer device running an application or program, or may be a server. Optionally, in the case that the risk identification terminal is a computer device, the risk identification terminal may further have a display unit that may display an identification result of the risk identification terminal. In this embodiment, a risk identification terminal is taken as an example of a computer device for explanation.
Fig. 1 is a flowchart of a risk identification method according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S102, acquiring consumption information of the object to be analyzed.
In step S102, the object to be analyzed is an object for consumption, for example, in a hotel reservation scenario, the object to be analyzed is a user who reserves a hotel through an application or program. In addition, the consumption information of the object to be analyzed includes at least one of: the last consumption time, the consumption times of the object to be analyzed in the last period of time and the purchase amount of the object to be analyzed in the last period of time.
In an optional embodiment, when the object to be analyzed accesses the current consumption platform, the risk identification terminal automatically acquires the consumption information of the object to be analyzed within a preset time length through the internet. The risk identification terminal acquires consumption information of the object to be analyzed on other consumption platforms through the Internet under the condition that the risk identification terminal detects that the object to be analyzed does not have a historical record of consumption, reservation or browsing on the current consumption platform.
And step S104, analyzing the consumption information by adopting a clustering model to obtain the object grade of the object to be analyzed, wherein the object grade is used for representing the credit risk of the object to be analyzed.
In step S104, the clustering model may be an RFM clustering model, where r (recency) represents the last time of consumption of the object to be analyzed, f (frequency) represents the number of consumption of the object to be analyzed in the last period of time, and m (monetary) represents the purchase amount of the object to be analyzed in the last period of time.
It should be noted that different object levels correspond to different degrees of credit risks, the client group can be divided into 8 types, such as important value clients, important recall clients, important deep ploughing clients, important saving clients, potential clients, new clients, general maintenance clients, lost clients and the like, through the RFM clustering model, the corresponding credit risks are measured according to the user value, and the admission standard is gradually relaxed depending on the subsequent risk performance of the product.
Step S106, obtaining object information of the object to be analyzed, order information corresponding to the target object and equipment information of equipment associated with the object to be analyzed, wherein the target object is an object corresponding to the object to be analyzed when the object to be analyzed executes consumption behaviors.
In step S106, in the hotel reservation scenario, the target object may be a hotel reserved for the object to be analyzed. The risk identification terminal obtains the object information, the order information and the equipment information, so that abnormal behaviors of the object to be analyzed in all dimensions are comprehensively considered from multiple dimensions, and the risk type corresponding to the object to be analyzed is accurately identified. The object information corresponds to user dimensions, the order information corresponds to product dimensions, and the equipment information corresponds to equipment dimensions.
Optionally, the object information (i.e. the user dimension) includes at least one of the following: characteristic information and order behavior information of the object to be analyzed, wherein the order behavior information at least comprises one of the following information: order quantity, order amount and order cancellation information of the object to be analyzed; the device information (i.e., device dimensions) includes at least one of: login information of the equipment and the number of objects of the object associated with the equipment; the order information (i.e., product dimensions) includes at least one of: and the order quantity, the post-paid order proportion and the deduction failure proportion of the target object within a second preset time length. For example, in the dimension diagram of risk identification shown in fig. 2, the user dimension is mainly summarized based on the personal characteristics and order behavior of the user, such as the order quantity, order amount, order cancellation, and other characteristics of each business line; the device dimension is mainly summarized from the characteristics of login address, associated user number (namely device information) and the like; the product dimension is mainly summarized from characteristics such as short-time order quantity, post-paid order proportion, deduction failure proportion (namely deduction characteristics) and hotel information, and corresponding strategies are formulated to identify fraud cash register risks by combining abnormal behaviors of the dimension.
And step S108, determining the risk type of the object to be analyzed according to the object grade, the object information, the equipment information and the order information.
In step S108, the risk type of the object to be analyzed at least includes a fraud cash-out risk.
It should be noted that, since different object grades represent the user value of the object, in step S108, the risk identification model may perform risk identification on the object with high value, but not perform risk identification on the object with low value, or directly determine that the object is a high-risk object, or determine whether to perform risk identification on the object according to the duration of the object grade where the object is located.
By comprehensively performing risk analysis on the object to be analyzed by combining the user value and the plurality of dimensions of the object to be analyzed in step S108, accurate identification of the risk type of the object to be analyzed is realized.
Based on the schemes defined in steps S102 to S108, it can be known that, in the embodiment of the present invention, a clustering model is adopted to analyze consumption information of an object to be analyzed to determine a credit risk of the object to be analyzed, after the consumption information of the object to be analyzed is obtained, the consumption information is analyzed by adopting the clustering model to obtain an object level of the object to be analyzed, then, object information of the object to be analyzed, order information corresponding to a target object, and device information of a device associated with the object to be analyzed are obtained, and finally, a risk type of the object to be analyzed is determined according to the object level, the object information, the device information, and the order information. The object grade is used for representing credit risks of the object to be analyzed, and the target object is an object corresponding to the object to be analyzed when the consumption behavior is executed.
It is easy to note that in the above process, the consumption information of the object to be analyzed is analyzed by using the clustering model, and the consumption information represents the consumption behavior of the object to be analyzed, that is, in the present application, the consumption behavior of the object to be analyzed is analyzed by using the clustering method to determine the credit risk of the object to be analyzed without using a history sample. In addition, the risk type corresponding to the object to be analyzed is determined by analyzing the object to be analyzed from multiple dimensions, so that the classification type of the object to be analyzed is accurately analyzed, the problem that the risk type cannot be identified in the prior art is solved, the accuracy of credit risk identification is improved, and the probability of credit risk occurrence is effectively reduced.
Therefore, the scheme provided by the application achieves the purpose of identifying the credit risk of the object without the historical sample, so that the technical effect of reducing the occurrence rate of the credit risk is achieved, and the technical problem that the existing risk identification strategy cannot analyze the object without the historical sample is solved.
In an optional embodiment, after the consumption information of the object to be analyzed is obtained, the risk identification terminal analyzes the consumption information by using a clustering model to obtain the object grade of the object to be analyzed. Specifically, the risk identification terminal firstly obtains consumption time, consumption times and consumption amount of an object to be analyzed within a first preset time length, analyzes the consumption time, consumption times and consumption amount of the object to be analyzed within the preset time length based on a clustering model to obtain a score of the object to be analyzed, and finally determines the object grade of the object to be analyzed according to the score.
Optionally, in a scene that the overseas hotel confirms the cold start of the post-paid product, the consumption platform corresponding to the overseas hotel has no historical bad sample and cannot perform default probability prediction, and in this case, the risk identification terminal can evaluate the user value by adopting an RFM clustering model, so as to measure the credit risk of the user. The RFM clustering model emphasizes that the customers are distinguished by the behaviors of the customers, and the customer value and the customer profit creating capability are measured. And (4) screening high-value users for admission aiming at the products after the confirmation of the overseas hotel, wherein the risk corresponding to the high-quality active users (namely the high-value users) is lower. For example, in the schematic diagram of cluster model modeling and application shown in fig. 3, the risk identification terminal obtains customer groups with different value grades (i.e., object grades) by using an RFM cluster model, analyzes an object to be analyzed based on the RFM cluster model, determines a score corresponding to the object to be analyzed, the score represents a value corresponding to the object to be analyzed, and determines the customer group to which the object to be analyzed belongs according to the score, i.e., determines the object grade of the object to be analyzed. Wherein, the value grade corresponding to each customer group is represented in a form of score, for example, the score of the customer group with the highest value is 90-100.
In an optional embodiment, before analyzing the consumption time, consumption times and consumption amount of the object to be analyzed within a preset time length based on the clustering model to obtain the score of the object to be analyzed, the risk identification terminal needs to construct the clustering model. Specifically, the risk identification terminal firstly acquires a data source containing consumption information of a plurality of objects, performs data extraction on the data source to obtain first historical data, then eliminates missing values and abnormal values in the first historical data to obtain second historical data, performs data transformation on the second historical data to obtain third historical data, and finally performs data modeling based on the third historical data to obtain a clustering model.
For example, in the schematic diagram shown in fig. 3, the risk identification terminal obtains data from a data source, wherein the data source is from an IBU (International Business Union) order summary table. Then, data extraction is carried out on the data source to obtain first historical data, exploration and pretreatment are carried out on the first historical data, namely missing value and abnormal value analysis is carried out on the first historical data, data cleaning, attribute stipulation and data transformation are carried out on the data obtained after analysis to obtain modeling data needed by modeling, and finally, modeling is carried out on the modeling data to obtain a clustering model.
Further, after the clustering model is obtained, the risk identification terminal determines the risk type of the object to be analyzed according to the object grade, the object information, the equipment information and the order information. And under the condition that the object grade is greater than or equal to the preset grade, identifying the object information, the equipment information and the order information to obtain the risk type of the object to be analyzed. And if the object to be analyzed is determined to be an abnormal object according to the object information, and/or the equipment is determined to be abnormal equipment according to the equipment information, and/or the target object is determined to be an abnormal target object according to the order information, determining the risk type of the object to be analyzed to be a cash-out risk.
In addition, under the condition that the grade of the object is smaller than the preset grade, the grade duration of the object to be analyzed at the current grade is detected; and deleting the object information of the object to be analyzed under the condition that the grade duration is greater than the preset duration. When the object grade is smaller than the preset grade, the object to be analyzed is determined to be a low-value user, and if the object grade of the object to be analyzed is in a low-value user state for a long time, the object can be directly determined to have cash register risks.
According to the scheme, when the credit product is in cold start, under the conditions that no user credit score exists and no credit risk is generated in a bad sample, the user value is embodied on the basis of the RFM clustering model, the risk condition of the user is simply measured, and meanwhile, the fraud cash register behavior can be effectively identified by comprehensively judging the multi-dimensional abnormal behavior.
In the application, the RFM clustering model is applied to the confirmed post-paid products of the overseas hotel, the credit risk of the user is reflected by judging the user value, and the bad account rate of the overseas hotel meets the expectation under the condition of no collection. The multidimensional fraud cash registering strategy is simulated in the process of flashing cash registering identification, the rule capturing effect is good, and the strategy performance during the simulated cash registering period is shown in table 1.
TABLE 1
| Policy | Rule accuracy rate | Cash registerCoverage rate |
| Rule 1 | 61.19％ | 87.50％ |
| Rule 2 | 42.42％ | 100％ |
| Rule 3 | 25.90％ | 80.03％ |
Example 2
According to an embodiment of the present invention, there is also provided an embodiment of a risk identification device, where fig. 4 is a schematic diagram of a risk identification device according to an embodiment of the present invention, as shown in fig. 4, the device includes: a first acquisition module 401, an analysis module 403, a second acquisition module 405, and an identification module 407.
The first obtaining module 401 is configured to obtain consumption information of an object to be analyzed; the analysis module 403 is configured to analyze the consumption information by using a clustering model to obtain an object grade of the object to be analyzed, where the object grade is used to represent a credit risk of the object to be analyzed; a second obtaining module 405, configured to obtain object information of an object to be analyzed, order information corresponding to a target object, and device information of a device associated with the object to be analyzed, where the target object is an object corresponding to the object to be analyzed when a consumption behavior is executed; the identification module 407 is configured to determine a risk type of the object to be analyzed according to the object level, the object information, the device information, and the order information.
It should be noted that the first obtaining module 401, the analyzing module 403, the second obtaining module 405, and the identifying module 407 correspond to steps S102 to S108 in the above embodiment, and the four modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the disclosure in embodiment 1.
Optionally, the analysis module includes: the device comprises a third acquisition module, an analysis submodule and a first determination module. The third acquisition module is used for acquiring the consumption time, the consumption times and the consumption amount of the object to be analyzed within the first preset time length; the analysis submodule is used for analyzing the consumption time, consumption times and consumption amount of the object to be analyzed in a preset time length based on the clustering model to obtain the score of the object to be analyzed; and the first determining module is used for determining the object grade of the object to be analyzed according to the score.
Optionally, the risk identification device further includes: the device comprises a fourth acquisition module, an extraction module, a rejection module, a transformation module and a modeling module. The fourth acquisition module is used for acquiring a data source containing consumption information of a plurality of objects before analyzing the consumption time, consumption times and consumption amount of the object to be analyzed in a preset time length based on the clustering model to obtain the score of the object to be analyzed; the extraction module is used for extracting data from the data source to obtain first historical data; the removing module is used for removing missing values and abnormal values in the first historical data to obtain second historical data; the transformation module is used for carrying out data transformation on the second historical data to obtain third historical data; and the modeling module is used for carrying out data modeling based on the third history data to obtain a clustering model.
Optionally, the object information at least includes one of the following: characteristic information and order behavior information of the object to be analyzed, wherein the order behavior information at least comprises one of the following information: order quantity, order amount and order cancellation information of the object to be analyzed; the device information includes at least one of: login information of the equipment and the number of objects of the object associated with the equipment; the order information includes at least one of: and the order quantity, the post-paid order proportion and the deduction failure proportion of the target object within a second preset time length.
Optionally, the identification module includes: and the first identification module is used for identifying the object information, the equipment information and the order information to obtain the risk type of the object to be analyzed under the condition that the object grade is greater than or equal to the preset grade.
Optionally, the first identification module includes: the first sub-identification module is used for determining that the risk type of the object to be analyzed is the cash-out risk if the object to be analyzed is determined to be an abnormal object according to the object information, and/or the equipment is determined to be abnormal equipment according to the equipment information, and/or the target object is determined to be an abnormal target object according to the order information.
Optionally, the risk identification device further includes: the device comprises a detection module and a second determination module. The device comprises a detection module, a detection module and a processing module, wherein the detection module is used for detecting the grade duration of an object to be analyzed at the current grade under the condition that the grade of the object is less than the preset grade; and the second determining module is used for determining the risk type of the object to be analyzed as the cash-out risk under the condition that the grade duration is greater than the preset duration.
Example 3
According to another aspect of the embodiments of the present invention, there is also provided a non-volatile storage medium having a computer program stored therein, wherein the computer program is configured to execute the risk identification method in embodiment 1 described above when running.
Example 4
According to another aspect of the embodiments of the present invention, there is also provided a processor for executing a program, wherein the program is configured to execute the risk identification method in embodiment 1 when running.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for risk identification, comprising:
acquiring consumption information of an object to be analyzed;
analyzing the consumption information by adopting a clustering model to obtain an object grade of the object to be analyzed, wherein the object grade is used for representing the credit risk of the object to be analyzed;
acquiring object information of the object to be analyzed, order information corresponding to a target object and equipment information of equipment associated with the object to be analyzed, wherein the target object is an object corresponding to the object to be analyzed when the object to be analyzed executes consumption behaviors;
and determining the risk type of the object to be analyzed according to the object grade, the object information, the equipment information and the order information.
2. The method of claim 1, wherein analyzing the consumption information using a clustering model to obtain an object rating of the object to be analyzed comprises:
acquiring consumption time, consumption times and consumption amount of the object to be analyzed within a first preset time length;
analyzing the consumption time, consumption times and consumption amount of the object to be analyzed in the preset time length based on the clustering model to obtain the score of the object to be analyzed;
and determining the object grade of the object to be analyzed according to the score.
3. The method according to claim 2, wherein before analyzing the consumption time, consumption times and consumption amount of the object to be analyzed within the preset time period based on the clustering model to obtain the score of the object to be analyzed, the method further comprises:
acquiring a data source containing consumption information of a plurality of objects;
performing data extraction on the data source to obtain first historical data;
removing missing values and abnormal values in the first historical data to obtain second historical data;
performing data transformation on the second historical data to obtain third historical data;
and performing data modeling based on the third history data to obtain the clustering model.
4. The method of claim 1, wherein the object information comprises at least one of: the characteristic information and the order behavior information of the object to be analyzed, wherein the order behavior information at least comprises one of the following information: the order quantity, the order amount and the order cancellation information of the object to be analyzed; the device information includes at least one of: login information of the device and the number of objects associated with the object of the device; the order information includes at least one of: and the order quantity, the post-paid order proportion and the deduction failure proportion of the target object within a second preset time length.
5. The method of claim 4, wherein determining the risk type of the object to be analyzed according to the object rating, the object information, the equipment information, and the order information comprises:
and under the condition that the object grade is greater than or equal to a preset grade, identifying the object information, the equipment information and the order information to obtain the risk type of the object to be analyzed.
6. The method of claim 5, wherein identifying the object information, the device information, and the order information to obtain a risk type of the object to be analyzed comprises:
and if the object to be analyzed is determined to be an abnormal object according to the object information, and/or the equipment is determined to be abnormal equipment according to the equipment information, and/or the target object is determined to be an abnormal target object according to the order information, determining the risk type of the object to be analyzed to be a cash-out risk.
7. The method of claim 5, further comprising:
under the condition that the object grade is smaller than the preset grade, detecting the grade duration of the object to be analyzed at the current grade;
and determining the risk type of the object to be analyzed as a cash-out risk under the condition that the grade duration is greater than the preset duration.
8. A risk identification device, comprising:
the first acquisition module is used for acquiring consumption information of an object to be analyzed;
the analysis module is used for analyzing the consumption information by adopting a clustering model to obtain an object grade of the object to be analyzed, wherein the object grade is used for representing the credit risk of the object to be analyzed;
the second acquisition module is used for acquiring object information of the object to be analyzed, order information corresponding to a target object and equipment information of equipment associated with the object to be analyzed, wherein the target object is an object corresponding to the object to be analyzed when the object to be analyzed executes consumption behaviors;
and the identification module is used for determining the risk type of the object to be analyzed according to the object grade, the object information, the equipment information and the order information.
9. A non-volatile storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the risk identification method as claimed in any one of claims 1 to 7 when run.
10. A processor for running a program, wherein the program is arranged to perform the risk identification method of any of claims 1 to 7 when running.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110212806.7A CN112819476A (en) | 2021-02-25 | 2021-02-25 | Risk identification method and device, nonvolatile storage medium and processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110212806.7A CN112819476A (en) | 2021-02-25 | 2021-02-25 | Risk identification method and device, nonvolatile storage medium and processor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112819476A true CN112819476A (en) | 2021-05-18 |
Family
ID=75863884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110212806.7A Pending CN112819476A (en) | 2021-02-25 | 2021-02-25 | Risk identification method and device, nonvolatile storage medium and processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112819476A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115345533A (en) * | 2022-10-20 | 2022-11-15 | 阿里健康科技(杭州)有限公司 | Order data processing method, device, equipment and storage medium |
| CN116664238A (en) * | 2023-06-02 | 2023-08-29 | 北京科码先锋互联网技术股份有限公司 | Retail industry risk order auditing management method and system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407305A (en) * | 2016-08-30 | 2017-02-15 | 国信优易数据有限公司 | Data mining system and method |
| CN109064175A (en) * | 2018-06-11 | 2018-12-21 | 阿里巴巴集团控股有限公司 | A kind of account takeover risk prevention system method and device |
| CN109741065A (en) * | 2019-01-28 | 2019-05-10 | 广州虎牙信息科技有限公司 | A kind of payment risk recognition methods, device, equipment and storage medium |
| WO2019104868A1 (en) * | 2017-11-30 | 2019-06-06 | 平安科技（深圳）有限公司 | Client risk level determining method, device and equipment, and readable storage medium |
| CN110009432A (en) * | 2019-04-15 | 2019-07-12 | 武汉理工大学 | A kind of personal consumption behavior prediction technique |
| CN110111198A (en) * | 2019-04-23 | 2019-08-09 | 上海淇玥信息技术有限公司 | User's financial risks predictor method, device, electronic equipment and readable medium |
| WO2019153486A1 (en) * | 2018-02-07 | 2019-08-15 | 平安科技（深圳）有限公司 | Customer risk assessment method, apparatus and device, and computer-readable storage medium |
| CN110706090A (en) * | 2019-08-26 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Credit fraud identification method and device, electronic equipment and storage medium |
| WO2020015484A1 (en) * | 2018-07-18 | 2020-01-23 | 阿里巴巴集团控股有限公司 | Risk identification method and apparatus, and server |
| CN111179023A (en) * | 2019-12-10 | 2020-05-19 | 北京互金新融科技有限公司 | Order identification method and device |
| CN111967779A (en) * | 2020-08-19 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Risk assessment method, device and equipment |
| WO2020238535A1 (en) * | 2019-05-28 | 2020-12-03 | 深圳壹账通智能科技有限公司 | Cash-out risk detection method and apparatus for aggregation payment merchant, and electronic device |
| CN112101721A (en) * | 2020-08-10 | 2020-12-18 | 南京领行科技股份有限公司 | Risk assessment method and device |
-
2021
- 2021-02-25 CN CN202110212806.7A patent/CN112819476A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407305A (en) * | 2016-08-30 | 2017-02-15 | 国信优易数据有限公司 | Data mining system and method |
| WO2019104868A1 (en) * | 2017-11-30 | 2019-06-06 | 平安科技（深圳）有限公司 | Client risk level determining method, device and equipment, and readable storage medium |
| WO2019153486A1 (en) * | 2018-02-07 | 2019-08-15 | 平安科技（深圳）有限公司 | Customer risk assessment method, apparatus and device, and computer-readable storage medium |
| CN109064175A (en) * | 2018-06-11 | 2018-12-21 | 阿里巴巴集团控股有限公司 | A kind of account takeover risk prevention system method and device |
| WO2020015484A1 (en) * | 2018-07-18 | 2020-01-23 | 阿里巴巴集团控股有限公司 | Risk identification method and apparatus, and server |
| CN109741065A (en) * | 2019-01-28 | 2019-05-10 | 广州虎牙信息科技有限公司 | A kind of payment risk recognition methods, device, equipment and storage medium |
| CN110009432A (en) * | 2019-04-15 | 2019-07-12 | 武汉理工大学 | A kind of personal consumption behavior prediction technique |
| CN110111198A (en) * | 2019-04-23 | 2019-08-09 | 上海淇玥信息技术有限公司 | User's financial risks predictor method, device, electronic equipment and readable medium |
| WO2020238535A1 (en) * | 2019-05-28 | 2020-12-03 | 深圳壹账通智能科技有限公司 | Cash-out risk detection method and apparatus for aggregation payment merchant, and electronic device |
| CN110706090A (en) * | 2019-08-26 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Credit fraud identification method and device, electronic equipment and storage medium |
| CN111179023A (en) * | 2019-12-10 | 2020-05-19 | 北京互金新融科技有限公司 | Order identification method and device |
| CN112101721A (en) * | 2020-08-10 | 2020-12-18 | 南京领行科技股份有限公司 | Risk assessment method and device |
| CN111967779A (en) * | 2020-08-19 | 2020-11-20 | 支付宝(杭州)信息技术有限公司 | Risk assessment method, device and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 闫春;孙海棠;李亚琪;: "基于随机森林与RFM模型的财险客户分类管理研究", 科技与经济, no. 01, pages 60 - 64 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115345533A (en) * | 2022-10-20 | 2022-11-15 | 阿里健康科技(杭州)有限公司 | Order data processing method, device, equipment and storage medium |
| CN116664238A (en) * | 2023-06-02 | 2023-08-29 | 北京科码先锋互联网技术股份有限公司 | Retail industry risk order auditing management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109242261B (en) | Method for evaluating security risk based on big data and terminal equipment | |
| US8170998B2 (en) | Methods, systems, and computer program products for estimating accuracy of linking of customer relationships | |
| US10580010B2 (en) | Method, system and program product for measuring customer satisfaction and applying post concern resolution | |
| CN106611321B (en) | False mobile phone number identification method and device | |
| CN110060053B (en) | Identification method, equipment and computer readable medium | |
| CN112819476A (en) | Risk identification method and device, nonvolatile storage medium and processor | |
| CN111340606A (en) | Full-process income auditing method and device | |
| CN111695938B (en) | Product pushing method and system | |
| CN110991650A (en) | Method and device for training card maintenance identification model and identifying card maintenance behavior | |
| CN115438821A (en) | Intelligent queuing method and related device | |
| CN110866698A (en) | Device for assessing service score of service provider | |
| CN111062770A (en) | Merchant identification method, equipment and computer readable medium | |
| CN112950359B (en) | User identification method and device | |
| US8078529B1 (en) | Evaluating customers' ability to manage revolving credit | |
| CN110348983B (en) | Transaction information management method and device, electronic equipment and non-transitory storage medium | |
| CN107330709B (en) | Method and device for determining target object | |
| CN116402596A (en) | Data analysis method, device, computer equipment and readable storage medium | |
| CN113870021B (en) | Data analysis method and device, storage medium and electronic equipment | |
| CN110827137A (en) | Credit evaluation method and device | |
| CN115034685A (en) | Customer value evaluation method, customer value evaluation device and computer-readable storage medium | |
| CN110570301B (en) | Risk identification method, device, equipment and medium | |
| CN114298172A (en) | Early warning method and system based on economic value and risk prediction | |
| CN109360032B (en) | Customer evaluation method, apparatus, device and storage medium | |
| CN113269412A (en) | Risk assessment method and related device | |
| CN117217830B (en) | Advertisement bill monitoring and identifying method, system and readable 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 |