CN115330522A

CN115330522A - Credit card approval method and device based on clustering, electronic equipment and medium

Info

Publication number: CN115330522A
Application number: CN202210991776.9A
Authority: CN
Inventors: 汪辰; 胡永峰
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2022-08-17
Filing date: 2022-08-17
Publication date: 2022-11-11

Abstract

The invention discloses a credit card approval method, a credit card approval device, electronic equipment and a credit card approval medium based on clustering, wherein the method comprises the following steps: acquiring characteristic data corresponding to good users and bad account users respectively; clustering the characteristic data to obtain a plurality of clusters, wherein the characteristic data of the good users are represented by first color points, and the characteristic data of the bad account users are represented by second color points; analyzing according to the characteristic data in the class cluster to obtain a corresponding credible issuing range; and judging whether the characteristic data of the potential risk user is in the credible issuing range or not, and determining whether to issue a credit card to the potential risk user or not according to a judgment result. The invention reduces the probability of risk loan events, reduces the probability of bad accounts after the credit card is issued, and greatly improves the safety of the bank funds.

Description

Credit card approval method and device based on clustering, electronic equipment and medium

Technical Field

The invention relates to the technical field of data processing, in particular to a credit card approval method and device based on clustering, electronic equipment and a medium.

Background

With the continuous improvement of living standard of people, the demand for consumption is increasingly improved. Under the prospect, the credit card solves the consumption requirements of most of people.

Of course, as the popularity of credit cards increases, more and more consumers use credit cards for consumption, and credit cards are recommended to bring much convenience to users in handling credit cards. At present, a credit card recommendation method is generally to directly recommend available credit cards to users, and the method cannot perform accurate recommendation according to the personalized requirements of the users, so that the recommendation accuracy is poor, and the recommendation failure rate is high.

Disclosure of Invention

The embodiment of the invention aims to provide a credit card approval method and device based on clustering, electronic equipment and a computer readable storage medium, and the effects of reducing the credit card approval risk and improving the automatic credit card approval efficiency are achieved.

In a first aspect, to achieve the above object, an embodiment of the present invention provides a credit card approval method based on clustering, including:

acquiring characteristic data corresponding to good users and bad account users respectively;

clustering the characteristic data to obtain a plurality of clusters, wherein the characteristic data of the good users are represented by first color points, and the characteristic data of the bad account users are represented by second color points;

analyzing according to the characteristic data in the class cluster to obtain a corresponding credible issuing range;

judging whether the characteristic data of the potential risk user is in the credible issuing range or not, and determining whether to issue a credit card to the potential risk user or not according to a judgment result;

wherein the potential risk users comprise users with any one or more behavior types of good credit report and no illegal behaviors.

In a second aspect, to solve the same technical problem, an embodiment of the present invention provides a credit card approval apparatus based on clustering, including:

the data acquisition module is used for acquiring characteristic data corresponding to good users and bad account users respectively;

the clustering processing module is used for clustering the characteristic data to obtain a plurality of clusters, wherein the characteristic data of the good user is represented by a first color point, and the characteristic data of the bad account user is represented by a second color point;

the analysis module is used for analyzing and obtaining a corresponding credible issuing range according to the characteristic data in the class cluster;

the processing module is used for judging whether the characteristic data of the potential risk user is in the credible issuing range or not and determining whether to issue a credit card to the potential risk user or not according to a judgment result;

In a third aspect, to solve the same technical problem, an embodiment of the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the memory is coupled to the processor, and the processor implements the steps in the cluster-based credit card approval method according to any one of the above items when executing the computer program.

In a fourth aspect, to solve the same technical problem, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored, where the computer program, when running, controls an apparatus where the computer-readable storage medium is located to perform any one of the steps in the cluster-based credit card approval method described above.

The embodiment of the invention provides a credit card approval method based on clustering, a device, electronic equipment and a computer readable storage medium, which are used for clustering according to characteristic data respectively corresponding to good users and bad account users, analyzing according to a clustering result to obtain a corresponding credible issuing range, judging whether the characteristic data of potential risk users are in the credible issuing range, and further determining whether to issue a credit card to the potential risk users according to a judgment result, so that a bank can reduce the probability of bad accounts after the credit card is issued, and the safety of bank funds is greatly improved. In addition, the credibility of the bank user for applying the credit card is improved, the management cost and risk of the bank credit can be reduced, and the rights and interests of the bank are guaranteed.

Drawings

The above features, technical features, advantages and modes of realisation of the present invention will be further described in the following detailed description of preferred embodiments thereof, which is to be read in connection with the accompanying drawings.

FIG. 1 is a schematic flow chart of a method for approval of a credit card based on clustering according to an embodiment of the present application;

FIG. 2 is a schematic flow chart illustrating a method for cluster-based credit card approval according to an embodiment of the present disclosure;

FIG. 3 is a schematic flow chart illustrating a method for cluster-based credit card approval according to an embodiment of the present disclosure;

FIG. 4 is a schematic flow chart illustrating a method for cluster-based approval of credit cards according to an embodiment of the present application;

FIG. 5 is a schematic flow chart of another method for approval of a credit card based on clustering according to an embodiment of the present application;

FIG. 6 is a schematic flow chart illustrating a method for cluster-based approval of credit cards according to an embodiment of the present application;

FIG. 7 is a schematic flow chart illustrating a method for cluster-based credit card approval according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application;

fig. 10 is a schematic diagram illustrating color labeling by white points and black points after clustering of feature data of good users and feature data of bad account users in the credit card approval method based on clustering provided in the embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

For the sake of simplicity, the drawings only schematically show the parts relevant to the present invention, and they do not represent the actual structure as a product. In addition, in order to make the drawings concise and understandable, components having the same structure or function in some of the drawings are only schematically illustrated or only labeled. In this document, "a" means not only "only one of this but also a case of" more than one ".

It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

In addition, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not intended to indicate or imply relative importance.

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.

A user who does not have illegal activities is a user who does not violate the current legal regulations of the country and does not harm the social relationships protected by the laws. Credit reporting is well inclusive of two types, users who are logged for a non-credit application or users who have no credit reporting problems, respectively.

The user without the credit application record refers to a user without any credit record issued by a banking institution, and because the credit is incorporated into the credit investigation report, the user can be queried from the personal credit investigation report home page as to whether the user has the credit application record (such as a credit card application record, a house credit application record and the like), and of course, the user can also be queried through a background server of cloud flash payment as to whether the user has the credit application record at all the banking institutions, and if not, the user is determined to be the user without the credit application record.

A user without credit investigation problem is a user who has no record of overdue repayment although the user has a record of credit (e.g., credit card, flower, etc.). The credit investigation report of the user can be inquired from the personal credit investigation report home page, and whether the user is the user without the credit investigation problem is judged according to the repayment record in the credit investigation report. In a certain aspect, the credit-free application record is a good credit report because the user does not need to pay on time.

Referring to fig. 1, fig. 1 is a schematic flow chart of a credit card approval method based on clustering according to an embodiment of the present invention, including steps S101 to S104.

S101, acquiring characteristic data corresponding to a good account user and a bad account user respectively;

in particular, the high development of business credit is one of the important features of market economy, and the development of business credit inevitably leads to bad accounts while bringing about an increase in sales revenue for enterprises. The bad account refers to the account which should be collected and has little possibility of being collected or being collected, and the dead account can be called as the bad account. The bad account user refers to a user who does not return the payment to a financial institution such as a bank, and the good account user refers to a user who is informed that the report is good and returns the payment to the financial institution such as the bank on time. The good users (i.e. non-bad account users) may include users who pay on time and have no overdue payment record, so as to improve the comprehensiveness of credit card risk identification. Of course, good users are most preferably users who have completed a credit repayment to improve the accuracy of credit card risk identification.

Referring to fig. 2, fig. 2 is a schematic flow chart illustrating a process of acquiring feature data corresponding to a good user and a bad-account user respectively in the credit card approval method based on clustering according to an embodiment of the present invention, including steps S201 to S203.

S201, acquiring a historical application record of a credit card, wherein the historical application record comprises user attribute data of the good user and the bad account user;

specifically, a large number of historical application records of credit cards can be retrieved from a credit card database of a banking system server, and the historical application records comprise user attribute data of good users and user attribute data of bad-account users.

Wherein the user attribute data includes personal information and behavioral information, wherein the personal information includes, but is not limited to, one or more of identity information, physiological information, credit report, and preference information. The behavior information includes, but is not limited to, one or more of social information, consumption records, transaction records.

The identity information includes an identity ID (e.g., identification number), occupation, marital status, age, native place, etc. Identity information of both the candidate user and the target user can be called from a credit card database of a bank, and of course, the identity information of the candidate user and the target user can also be called from a third-party database (such as a data server of a human resource management department) according to the identity ID.

The physiological information includes height, weight, disease history, etc. The physiological information of the candidate user and the target user can be retrieved from a patient database of a medical institution (e.g., a hospital or a physical examination institution), and other ways of obtaining the physiological information are within the scope of the present invention.

The credit investigation report comprises default records or overdue records, repayment time and the like of the user. The credit investigation reports of the candidate user and the target user can be called from the data server of the credit investigation center of the people's bank of China, and other ways of obtaining the credit investigation reports are also within the protection scope of the invention.

The preference information includes sports preference, shopping preference, entertainment preference, etc. The preference information of the candidate user and the target user can be obtained by crawling and analyzing the user from the server of the program developer of the application program (such as a browser, a shopping APP, a video APP, and the like), and other ways of obtaining the preference information are also within the protection scope of the present invention.

The social information may be post content on a social platform, such as a forum, user comments, and the like, may also be chat room content of an instant messaging platform (e.g., a QQ group, a wechat group, and the like), and may also be pop-up content of video software (e.g., an Tencent video, and the like). The social information of the candidate user and the social information of the target user can be acquired from a social server predetermined by the user, such as a microblog server, a WeChat server or a QQ server, and the social account corresponds to the social server, such as a microblog account, a WeChat account or a QQ account.

The consumption records include daily consumption records (i.e. records of non-credit consumption, such as consumption information of daily shopping), credit consumption records and the like. The daily consumption records of the candidate user and the target user can be obtained from a third-party server of a third-party payment tool (such as a payment balance, a WeChat change and the like), and of course, the daily consumption records of the candidate user and the target user can also be directly obtained from a bank card (namely, a debit card) server. The credit consumption records of the candidate user and the target user can be obtained from a third-party server of a third-party payment tool (such as Paoyao, etc.), and of course, the credit consumption records of the candidate user and the target user can also be directly obtained from a credit card server. Of course, other ways of obtaining the consumption record are within the scope of the present invention.

The transaction records of the candidate user and the target user can be obtained from a third-party server of a third-party payment tool (such as a payment treasure, weChat, and the like), and of course, the transaction records of the candidate user and the target user can also be directly obtained from a bank server. Of course, other ways of obtaining the transaction record are within the scope of the present invention.

S202, cleaning the user attribute data of the good account user and the bad account user;

specifically, data cleaning is performed on user attribute data of good users and user attribute data of bad account users, that is, duplicate data, abnormal data and invalid data in original user attribute data are removed.

S203, extracting corresponding characteristic data according to the user attribute data of the good users and the bad account users after cleaning.

In particular, the characteristic data includes, but is not limited to, any one or more of identity characteristics (e.g., professional characteristics), physiological characteristics, credit, preference characteristics, social-type characteristics (e.g., active social type and passive social type), consumption characteristics, income characteristics, transaction characteristics, and credit card intent characteristics. The user attribute data after cleaning processing is used for feature extraction in the embodiment, the data volume of clustering can be greatly reduced, so that the clustering efficiency of the user attribute data is improved, and the automatic approval efficiency of the credit card is indirectly improved.

S102, clustering the feature data to obtain a plurality of clusters, wherein the feature data of the good users are represented by first color points, and the feature data of the bad account users are represented by second color points;

specifically, the first color point and the second color point are point data corresponding to feature data having widely different RGB color values. For example, as shown in fig. 10, including a plurality of cluster-like groups 3, the second color point 1 may be a black point when the first color point 2 is a white point. Of course, the second color point may be a blue point or a green point if the first color point is a red point.

And clustering feature words with the same attribute in the feature data of the good users and the feature data of the bad account users by adopting a clustering method to obtain a plurality of clusters. The clustering (Cluster) algorithm is also called Cluster analysis, is a statistical analysis method for sample or index classification problems, and is also an important algorithm for data mining, and the clustering algorithm includes but is not limited to: K-Means (K-Means) Clustering algorithm, mean shift Clustering algorithm, density-Based Clustering of applications with Noise (DBSCAN) method, gaussian mixture model-Based maximum expected Clustering, agglomerative hierarchical Clustering, and Graph Community Detection (Graph Community Detection) algorithm, etc. The clustering method adopted by the invention comprises a k-mean clustering algorithm, an ST-DBSCAN algorithm (belonging to one of density-based spatial clustering algorithms) and the like.

According to the technical scheme provided by the embodiment of the invention, the characteristic data of the good user and the bad account user are displayed through different visual colors, so that the effective distinguishing of the characteristic data is realized, the display forms are enriched, and the difference of the characteristic data between the good user and the bad account user can be intuitively known through the displayed colors.

Referring to fig. 3, fig. 3 is a schematic flow chart illustrating a process of clustering the feature data to obtain a plurality of clusters in the credit card approval method based on clustering provided in the embodiment of the present invention, including steps S301 to S204.

S301, setting a user type label for the feature data; the user type tags comprise good user tags and bad account user tags;

s302, clustering the marked feature data according to a preset clustering algorithm and the feature type of the feature data to obtain a corresponding cluster;

s303, marking the point data corresponding to the characteristic data of the excellent user label in the cluster according to the first color to obtain a first color point;

s304, point data corresponding to the feature data of the bad account user label in the cluster is marked according to the second color to obtain a second color point.

Specifically, all marked feature data marked with good user labels are marked with a preset first color, and then first class data corresponding to the feature data displayed as the first color are obtained. Marking all marked feature data marked with bad account user labels as a preset second color, and further obtaining second point data corresponding to the feature data displayed as the second color. Therefore, the point data corresponding to the characteristic data of the good account user and the point data corresponding to the characteristic data of the bad account user can be distinguished obviously and compared in visual display.

In the embodiment, the extracted feature data of the good users and the extracted feature data of the bad account users are subjected to color labeling processing, and the color and the feature data can be associated in a mode of distinguishing the feature data corresponding to the good users and the feature data corresponding to the bad account users by colors, so that the color has traditional objective definition, and a worker can visually observe, show and analyze the difference of the feature data between the good users and the bad account users through the color labeling in the later period.

S103, analyzing according to the feature data in the class cluster to obtain a corresponding credible issuing range;

referring to fig. 4, fig. 4 is a schematic flow chart illustrating a process of analyzing and obtaining a corresponding trusted issuance range according to feature data in a class cluster in the credit card approval method based on clustering according to the embodiment of the present invention, including steps S401 to S403.

S401, searching all target clusters which are first color points from the clusters, and carrying out assignment processing on each feature data in the target clusters according to a preset assignment mapping table;

in particular, the feature data includes, but is not limited to, any one or more of identity features (e.g., professional features), physiological features, income features, credits, preference features, social-type features (e.g., active social type and passive social type), consumption features, transaction features. Even, some black product groups illegally purchase names, identification numbers and photos, and use software to illegally break the approval process of the credit card to forge and steal the identity of other people to apply for the credit card, so the approval process of the credit card can also obtain an application scene picture, and obtain application environment characteristics according to the application scene picture.

The preset assignment mapping table is provided with corresponding relations between various feature data and different set values. Wherein, if the feature data is a numerical value, the assignment process for the feature data is such that the assignment result is equal to the numerical value of the feature data. Illustratively, when the feature data is an income feature, a value of 1.2 ten thousands of monthly income of a good user is assigned, that is, the monthly income is 1.2 ten thousands. For example, when the characteristic data is credit (for example, the sesame score of the pay treasure can be calculated as credit), the score 745 of a good user is assigned to be unchanged.

Of course, if the feature data is not a numerical value but an attribute, then the assignment is made in a positive correlation based on the magnitude of the attribute level. For example, when the feature data is professional features, and the professional features of a good user are company high-level general, since the company high-level general belongs to a high income group, the value of the professional features of the good user, namely, the company high-level general is assigned to obtain A1. For example, when the professional characteristic of a good user is a doctor, since the doctor belongs to the middle income group, the value of the professional characteristic of the good user, namely the middle income group, is assigned to be A2, and A1 is larger than A2.

S402, according to the assignment value of each feature data in the target class cluster, counting to obtain a first maximum value and a first minimum value corresponding to the current feature data respectively;

s403, obtaining a credible issuing range corresponding to the current feature data according to a first maximum value and a first minimum value respectively corresponding to the current feature data;

s403, obtaining a trusted issuing range corresponding to the current feature data according to the first maximum value and the first minimum value respectively corresponding to the current feature data.

Specifically, after the assignment processing is performed in the above manner to obtain the assignment values corresponding to different feature parameters in the target class cluster, all the assignment values corresponding to the current feature data are sorted, so that the first maximum value and the first minimum value corresponding to the current feature data in the target class cluster can be found, that is, the maximum value in the current feature data belonging to the good user is found to be the first maximum value, and the minimum value in the current feature data belonging to the good user is found to be the first minimum value. Finally, since all the target class clusters are the first color points, that is, all the point data in the target class clusters are the feature data of the good users, the found first maximum value and the first minimum value are the boundary values of the credible issuing range (or interval) of the current feature data.

For example, when the characteristic data is the income characteristic, the maximum value of the monthly income in the target class cluster is 3 ten thousand, and the minimum value of the monthly income is 1.2 ten thousand, then the credible issuing range corresponding to the income characteristic is 1.2 ten thousand to 2 ten thousand.

Referring to fig. 5, fig. 5 is a schematic flow chart illustrating a process of analyzing and obtaining a corresponding trusted issue range according to feature data in a class cluster in the credit card approval method based on a cluster according to the embodiment of the present invention, which includes steps S501 to S505.

S501, searching all target class clusters which are second color points from the class clusters, and carrying out assignment processing on each feature data in the reference class cluster according to a preset assignment mapping table;

s502, according to the assigned numerical value of each feature data in the reference cluster, obtaining a second maximum value and a second minimum value respectively corresponding to the current feature data to obtain a risk distribution range;

specifically, referring to the embodiment shown in fig. 4, after the assignment processing is performed in the foregoing manner to obtain the assignment values corresponding to different feature parameters in the reference cluster, all the assignment values corresponding to the current feature data are sorted, so that the second maximum value and the second minimum value corresponding to the current feature data in the reference cluster can be found, that is, the second maximum value is found in the current feature data belonging to the bad account user, and the second minimum value is found in the current feature data belonging to the bad account user. Finally, because all the bad account type clusters are second color points, that is, all the point data in the bad account type clusters are feature data of the bad account users, the found second maximum value and the second minimum value are boundary values of the unreliable issuing range (or interval) of the current feature data.

S503, performing intersection calculation on the credible issuing range and the risk issuing range to obtain a final credible issuing range.

Specifically, intersection calculation is performed on the credible issuing range and the risk issuing range, that is, the magnitude between the first maximum value and the second maximum value corresponding to the current feature data is compared to obtain a first comparison result, and the magnitude between the first minimum value and the second minimum value corresponding to the current feature data is compared to obtain a second comparison result. And then, obtaining a final credible issuing range corresponding to the current characteristic data according to the first comparison result and the second comparison result corresponding to the current characteristic data.

For example, continuing the above embodiment, assuming that the feature data is an income feature, the maximum value of the monthly income in the target class cluster is 3 ten thousand, and the minimum value of the monthly income is 1.2 ten thousand, that is, the initial trusted issuing range is monthly income [1.2 ten thousand, 3 ten thousand ], however, the maximum value of the monthly income in the reference class cluster is 1 ten thousand, and the minimum value of the monthly income is 0.5 ten thousand, that is, the risk issuing range is monthly income [0.5 ten thousand, 1 ten thousand ], then performing intersection calculation can obtain the trusted issuing range corresponding to the income feature as monthly income [1.2 ten thousand, 3 ten thousand ]. Of course, if the maximum value of the monthly income in the reference class cluster is 1.5 ten thousand and the minimum value of the monthly income is 0.3 ten thousand, that is, the risk issuing range is monthly income [0.3 ten thousand and 1.5 ten thousand ], the trusted issuing range corresponding to the income characteristics can be obtained by performing intersection calculation and is monthly income [1.5 ten thousand and 3 ten thousand ].

S404, switching to obtain the credible issuing range of the next feature data until the credible issuing ranges corresponding to all feature data are obtained through analysis.

S104, judging whether the characteristic data of the potential risk user is in the credible issuing range, and determining whether to issue a credit card to the potential risk user according to a judgment result;

Specifically, the credit card application request includes an identification number of the user, the background server may query whether the user initiating the application request is a potential risk user according to the identification number, and if the user initiating the application request belongs to the potential risk user, the background server may crawl user attribute data of the potential risk user from a third-party website, a credit investigation center server, a bank system, and the like, and further analyze and extract the user attribute data of the potential risk user to obtain feature data of the potential risk user. And once the characteristic data of the potential risk user is acquired, judging whether the characteristic data of the potential risk user is in a credible issuing range, and further determining whether to issue the credit card applied by the potential risk user for the potential risk user according to a judgment result.

Referring to fig. 6, fig. 6 is a schematic flow chart illustrating a process of determining whether to issue a credit card to a potentially risky user according to a determination result by determining whether the feature data of the potentially risky user is within the trusted issue range in the credit card approval method based on clustering according to the embodiment of the present invention, including steps S601 to S605.

S601, acquiring user attribute data of the potential risk user;

s602, extracting characteristic data of the potential risk user according to the user attribute data;

s603, carrying out assignment processing on the feature data of the potential risk user according to a preset assignment mapping table;

s604, judging whether the value to be assigned corresponding to the feature data of the potential risk user is in the corresponding credible issuing range;

s605 determines whether to issue a credit card to the potential risk user according to the weight coefficient corresponding to the characteristic data and the judgment result.

Specifically, the user attribute data and the feature data of the potentially risky user are obtained by referring to the above embodiment, and the assignment processing is performed on the feature data of the potentially risky user according to the preset assignment mapping table by referring to the above embodiment. And finally, determining whether the value to be assigned corresponding to the characteristic data of the potential risk user is in the corresponding credible issuing range or not according to the weight coefficient corresponding to the characteristic data and the judgment result.

Referring to fig. 7, fig. 7 is a schematic flowchart illustrating a process of determining whether to issue a credit card to the potentially risky user according to the weight coefficient corresponding to the feature data and the determination result in the credit card approval method based on clustering according to the embodiment of the present invention, including steps S701 to S706.

S701, if the characteristic data of the potential risk user is one and the value to be assigned is out of the corresponding credible issuing range, refusing to issue a credit card to the potential risk user;

s702, if the characteristic data of the potential risk user is one and the value of the value to be assigned is within the corresponding credible issuing range, allowing the credit card to be issued to the potential risk user;

s703, if the characteristic data of the potential risk user is at least two, carrying out weighted calculation on the weight coefficient corresponding to the characteristic data of the potential risk user and the judgment result to obtain an evaluation score;

s704, comparing the evaluation score with a preset score threshold value;

s705 if the evaluation score is lower than the preset score threshold value, refusing to issue a credit card to the potential risk user;

s706, if the evaluation score is higher than the preset score threshold value, allowing a credit card to be issued to the potential risk user.

Specifically, the weight coefficient corresponding to the feature data is positively correlated with the occurrence frequency of the feature data in the entire data set (including all the feature data of good users and all the feature data of bad account users), that is, the greater the occurrence frequency of the feature data, the greater the corresponding weight coefficient. Respectively counting the occurrence frequency of each feature data in the whole data set, judging whether the occurrence count of the current feature data exceeds a preset frequency threshold, if the occurrence count exceeds the preset frequency threshold, removing the current feature data is favorable for clustering, and if the occurrence count does not exceed the preset frequency threshold, the current feature data is irrelevant or noisy feature data which is not favorable for clustering, and the negative effect of the current feature data on clustering is larger. Therefore, all the feature data in the feature set can be sorted according to the size by counting the occurrence frequency of the feature data, and the weight coefficient corresponding to the feature data is set according to the sorted size. Then, weighting and calculating a weight coefficient corresponding to the feature data of the potential risk user and the judgment result to obtain an evaluation score, comparing the evaluation score with a preset score threshold, if the evaluation score is lower than the preset score threshold, refusing to issue the credit card to the potential risk user, and of course, if the evaluation score is higher than the preset score threshold, allowing to issue the credit card to the potential risk user.

It is known that the behavior concept of the user in different stages may change, that is, the user never has overdue or illegal behavior before, but may need to apply for a credit card for advanced consumption for external or personal reasons without willingness to pay, and such user may cause great loss to the bank. Therefore, the invention carries out clustering processing according to the characteristic data respectively corresponding to the good users and the bad account users, obtains the corresponding credible issuing range according to the clustering result analysis, judges whether the characteristic data of the potential risk users are in the credible issuing range, and further determines whether to issue the credit card to the potential risk users according to the judgment result, so that the bank can reduce the probability of bad accounts after the credit card is issued, and the safety of the bank funds is greatly improved. In addition, the credibility of the bank user for applying the credit card is improved, the management cost and risk of the bank credit can be reduced, and the rights and interests of the bank are guaranteed.

The invention avoids the condition that the manual checking mode adopted in the current industry examines and approves the credit card application request of the user, greatly saves manpower and material resources, improves the examination and approval efficiency, and avoids the condition that the loan efficiency is reduced because of overlong manual evaluation time. Meanwhile, clustering processing is carried out according to the characteristic data respectively corresponding to the good users and the bad account users, a corresponding credible issuing range is obtained according to the clustering result analysis, whether the characteristic data of the potential risk users are in the credible issuing range is judged, whether credit cards are issued to the potential risk users is determined according to the judgment result, and therefore risk assessment efficiency and assessment accuracy are greatly improved.

According to the method described in the foregoing embodiment, this embodiment will be further described from the perspective of a credit card approval apparatus based on clustering, where the credit card approval apparatus based on clustering may be specifically implemented as an independent entity, or may be implemented by being integrated in an electronic device, such as a terminal, and the terminal may include a mobile phone, a tablet computer, and the like.

In addition, this application still provides a credit card approval device based on clustering, includes:

In a specific implementation, each of the modules and/or units may be implemented as an independent entity, or may be implemented as one or several entities by any combination, where the specific implementation of each of the modules and/or units may refer to the foregoing method embodiment, and specific achievable beneficial effects also refer to the beneficial effects in the foregoing method embodiment, which are not described herein again.

In addition, referring to fig. 8, fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device may be a mobile terminal such as a smart phone and a tablet computer. As shown in fig. 8, the electronic device 800 includes a processor 801, a memory 802. The processor 801 is electrically connected to the memory 802.

The processor 801 is a control center of the electronic device 800, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device 800 and processes data by running or loading an application program stored in the memory 802 and calling data stored in the memory 802, thereby performing overall monitoring of the electronic device 800.

In this embodiment, the processor 801 in the electronic device 800 loads instructions corresponding to processes of one or more application programs into the memory 802, and the processor 801 executes the application programs stored in the memory 802 according to the following steps, so as to implement various functions:

The electronic device 800 may implement the steps in any embodiment of the method for approving credit cards based on clustering provided in the embodiment of the present invention, and therefore, the beneficial effects that can be achieved by any method for approving credit cards based on clustering provided in the embodiment of the present invention can be achieved, which are detailed in the foregoing embodiments and will not be described again here.

Referring to fig. 9, fig. 9 is a block diagram showing a specific structure of an electronic device according to an embodiment of the present application, where the electronic device may be used to implement the method for credit card approval based on clustering provided in the above embodiment. The electronic device 900 may be a mobile terminal such as a smart phone or a notebook computer.

The RF circuit 910 is used for receiving and transmitting electromagnetic waves, and interconverting the electromagnetic waves and electrical signals, so as to communicate with a communication network or other devices. RF circuit 910 may include various existing circuit elements for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption/decryption chip, a Subscriber Identity Module (SIM) card, memory, and so forth. The RF circuit 910 may communicate with various networks such as the internet, an intranet, a wireless network, or with other devices over a wireless network. The wireless network may comprise a cellular telephone network, a wireless local area network, or a metropolitan area network. The Wireless network may use various Communication standards, protocols and technologies, including but not limited to Global System for Mobile Communication (GSM), enhanced Data GSM Environment (EDGE), wideband Code Division Multiple Access (WCDMA), code Division Multiple Access (CDMA), time Division Multiple Access (TDMA), wireless Fidelity (Wi-Fi) (such as IEEE802.11a, IEEE802.11 b, IEEE802.11g and/or IEEE802.11 n), internet telephony (VoIP), world Interoperability for Microwave, and other suitable protocols for instant messaging, including any other protocols not currently developed.

The memory 920 may be used to store software programs and modules, such as program instructions/modules corresponding to the cluster-based credit card approval method in the above-mentioned embodiment, and the processor 980 may execute the cluster-based credit card approval process by operating the software programs and modules stored in the memory 920 as follows:

The memory 920 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 920 may further include memory located remotely from the processor 980, which may be connected to the electronic device 900 over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input unit 930 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. In particular, the input unit 930 may include a touch-sensitive surface 931 as well as other input devices 932. The touch-sensitive surface 931, also referred to as a touch screen or a touch pad, may collect touch operations by a user on or near the touch-sensitive surface 931 (e.g., operations by a user on or near the touch-sensitive surface 931 using a finger, a stylus, or any other suitable object or attachment) and drive the corresponding connecting device according to a predetermined program. Alternatively, the touch sensitive surface 931 may include both a touch detection device and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts the touch information into touch point coordinates, sends the touch point coordinates to the processor 980, and can receive and execute commands sent by the processor 980. In addition, the touch sensitive surface 931 may be implemented in various types, such as resistive, capacitive, infrared, and surface acoustic wave. The input unit 930 may comprise other input devices 932 in addition to the touch-sensitive surface 931. In particular, other input devices 932 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 940 may be used to display information input by or provided to the user and various graphical user interfaces of the electronic device 900, which may be made up of graphics, text, icons, video, and any combination thereof. The Display unit 940 may include a Display panel 941, and optionally, the Display panel 941 may be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or the like. Further, the touch-sensitive surface 931 may overlay the display panel 941, and when a touch operation is detected on or near the touch-sensitive surface 931, the touch operation is transmitted to the processor 980 to determine the type of touch event, and the processor 980 then provides a corresponding visual output on the display panel 941 according to the type of touch event. Although the touch-sensitive surface 931 and the display panel 941 are shown as two separate components to implement input and output functions, in some embodiments, the touch-sensitive surface 931 and the display panel 941 may be integrated to implement input and output functions.

The electronic device 900 may also include at least one sensor 950, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel 941 according to the brightness of ambient light, and a proximity sensor that may generate an interrupt when the folder is closed or closed. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of identifying the gesture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration identification related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which may be further configured to the electronic device 900, detailed descriptions thereof are omitted.

The audio circuitry 960, speaker 961, microphone 962 may provide an audio interface between a user and the electronic device 900. The audio circuit 960 may transmit the electrical signal converted from the received audio data to the speaker 961, and convert the electrical signal into a sound signal for output by the speaker 961; on the other hand, the microphone 962 converts the collected sound signal into an electric signal, converts the electric signal into audio data after being received by the audio circuit 960, and outputs the audio data to the processor 980 for processing, and then transmits the audio data to another terminal via the RF circuit 910, or outputs the audio data to the memory 920 for further processing. The audio circuit 960 may also include an earbud jack to provide communication of a peripheral headset with the electronic device 900.

The electronic device 900, via the transport module 970 (e.g., wi-Fi module), may assist the user in receiving requests, sending messages, etc., which provides the user with wireless broadband internet access. Although the transmission module 970 is shown in the drawings, it is understood that it does not belong to the essential constitution of the electronic device 900 and may be omitted entirely as needed within the scope not changing the essence of the invention.

The processor 980 is a control center of the electronic device 900, connects various parts of the entire cellular phone using various interfaces and lines, and performs various functions of the electronic device 900 and processes data by operating or executing software programs and/or modules stored in the memory 920 and calling data stored in the memory 920, thereby integrally monitoring the electronic device. Optionally, processor 980 may include one or more processing cores; in some embodiments, the processor 980 may integrate an application processor, which primarily handles operating systems, user interfaces, applications, etc., and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 980.

The electronic device 900 also includes a power supply 990 (e.g., a battery) that provides power to the various components and, in some embodiments, may be logically coupled to the processor 980 via a power management system that provides management of charging, discharging, and power consumption. Power supply 990 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and the like.

Although not shown, the electronic device 900 further includes a camera (e.g., a front camera, a rear camera), a bluetooth module, etc., which are not described in detail herein. Specifically, in this embodiment, the display unit of the electronic device is a touch screen display, the mobile terminal further includes a memory, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the one or more processors, where the one or more programs include instructions for:

In specific implementation, the above modules may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities, and specific implementation of the above modules may refer to the foregoing method embodiments, which are not described herein again.

It will be understood by those skilled in the art that all or part of the steps of the methods of the above embodiments may be performed by instructions or by associated hardware controlled by the instructions, which may be stored in a computer readable storage medium and loaded and executed by a processor. To this end, embodiments of the present application provide a storage medium having stored therein a plurality of instructions that can be loaded by a processor to perform the steps of any of the cluster-based credit card approval methods provided by embodiments of the present application.

Wherein the storage medium may include: read Only Memory (ROM), random Access Memory (RAM), magnetic or optical disks, and the like.

Since the instructions stored in the storage medium can execute the steps in any embodiment of the cluster-based credit card approval method provided in the embodiment of the present application, the beneficial effects that can be achieved by any cluster-based credit card approval method provided in the embodiment of the present application can be achieved, which are detailed in the foregoing embodiments and will not be described herein again.

The credit card approval, device, electronic device and storage medium based on clustering provided by the embodiment of the application are introduced in detail, a specific example is applied in the text to explain the principle and the implementation of the application, and the description of the embodiment is only used for helping to understand the method and the core idea of the application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application. Furthermore, it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention, and such modifications and adaptations are intended to be included within the scope of the present invention.

Claims

1. A credit card approval method based on clustering is characterized by comprising the following steps:

2. The cluster-based credit card approval method of claim 1, wherein the obtaining of the feature data corresponding to the good account user and the bad account user respectively comprises the steps of:

acquiring a historical application record of a credit card, wherein the historical application record comprises user attribute data of the good user and the bad account user;

cleaning the user attribute data of the good user and the bad account user;

and extracting corresponding characteristic data according to the user attribute data of the good users and the bad account users after cleaning.

3. The cluster-based credit card approval method of claim 1, wherein the clustering the feature data into a plurality of clusters comprises the steps of:

setting a user type label for the characteristic data; the user type tags comprise good user tags and bad account user tags;

clustering the marked feature data according to a preset clustering algorithm and the feature type of the feature data to obtain corresponding clusters;

marking the point data corresponding to the characteristic data of the excellent user label in the cluster according to the first color to obtain a first color point;

and marking the point data corresponding to the characteristic data of the bad account user label in the cluster according to the second color to obtain the second color point.

4. The cluster-based credit card approval method of claim 3, wherein the step of obtaining the corresponding trusted issuance range according to the analysis of the feature data in the class cluster comprises the steps of:

searching all target clusters which are first color points from the cluster, and carrying out assignment processing on each feature data in the target clusters according to a preset assignment mapping table;

according to the value of each feature data in the target cluster, calculating to obtain a first maximum value and a first minimum value corresponding to the current feature data respectively;

obtaining a credible issuing range corresponding to the current characteristic data according to a first maximum value and a first minimum value respectively corresponding to the current characteristic data;

and switching to obtain the credible issuing range of the next feature data until the credible issuing ranges corresponding to all the feature data are obtained through analysis.

5. The cluster-based credit card approval method of claim 4, wherein the step of obtaining the trusted issuance range corresponding to each feature data according to the first maximum value and the first minimum value respectively corresponding to the different feature data comprises the steps of:

searching target class clusters which are all second color points from the class clusters, and carrying out assignment processing on each feature data in the reference class clusters according to a preset assignment mapping table;

according to the assigned numerical value of each feature data in the reference cluster, obtaining a second maximum value and a second minimum value respectively corresponding to the current feature data to obtain a risk distribution range;

and performing intersection calculation on the credible issuing range and the risk issuing range to obtain a final credible issuing range.

6. The cluster-based credit card approval method of any one of claims 1 to 5, wherein the step of determining whether the characteristic data of the potentially risky user is within the trusted issuance range and deciding whether to issue a credit card to the potentially risky user according to the determination result comprises the steps of:

acquiring user attribute data of the potential risk user;

extracting characteristic data of the potential risk users according to the user attribute data;

assigning the characteristic data of the potential risk user according to a preset assignment mapping table;

judging whether the value to be assigned corresponding to the feature data of the potential risk user is within a corresponding credible issuing range or not;

and determining whether to issue a credit card to the potential risk user or not according to the weight coefficient corresponding to the characteristic data and the judgment result.

7. The cluster-based credit card approval method of claim 6, wherein the step of deciding whether to issue a credit card to the potentially risky user according to the weight coefficient corresponding to the feature data and the determination result comprises the steps of:

if the characteristic data of the potential risk user is one and the value to be assigned is out of the corresponding credible issuing range, refusing to issue a credit card to the potential risk user;

if the characteristic data of the potential risk user is one and the value of the value to be assigned is within the corresponding credible issuing range, allowing the credit card to be issued to the potential risk user;

if the number of the characteristic data of the potential risk user is at least two, carrying out weighted calculation on a weight coefficient corresponding to the characteristic data of the potential risk user and the judgment result to obtain an evaluation score;

comparing the evaluation score with a preset score threshold;

if the evaluation score is lower than the preset score threshold value, refusing to issue a credit card to the potential risk user;

and if the evaluation score is higher than the preset score threshold value, allowing a credit card to be issued to the potential risk user.

8. A credit card approval apparatus based on clustering, comprising:

9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the memory coupled to the processor, and the processor when executing the computer program performing the steps of the cluster-based credit card approval method of any one of claims 1 to 7.

10. A computer-readable storage medium, storing a computer program, wherein the computer program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the steps of the cluster-based credit card approval method according to any one of claims 1 to 7.