CN107563588A - A kind of acquisition methods of personal credit and acquisition system - Google Patents
A kind of acquisition methods of personal credit and acquisition system Download PDFInfo
- Publication number
- CN107563588A CN107563588A CN201710612361.5A CN201710612361A CN107563588A CN 107563588 A CN107563588 A CN 107563588A CN 201710612361 A CN201710612361 A CN 201710612361A CN 107563588 A CN107563588 A CN 107563588A
- Authority
- CN
- China
- Prior art keywords
- credit
- personal
- personal credit
- score
- dimension
- 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
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention relates to a kind of acquisition methods of personal credit and obtain system.The acquisition methods of personal credit of the present invention, including：Initial personal credit file model is established, the collage-credit data generation collage-credit data storehouse in mobile operator database, the collage-credit data storehouse is to repay wish, repaying ability and real-name authentication information as dimension；The revision parameter of the personal credit file model of preset time period is obtained, the personal credit file model is revised according to the revision parameter, obtains revised personal credit file model；Receive personal user's feature of outside input, is obtained according to personal user's feature from the revised personal credit file model corresponding to personal credit score.Personal credit scoring can be fast and accurately obtained using the acquisition methods and acquisition system of personal credit of the present invention, simultaneously because each relevant parameter of personal credit file model can enter Mobile state change according to actual conditions, the accuracy of personal credit scoring is also increased.
Description
Technical Field
The invention belongs to the field of credit acquisition, and particularly relates to a method and a system for acquiring personal credit.
Background
Current data for personal credits includes: personal income, assets, household registration, work experience, education level, credit records, utility service records, loan information, communication consumption, etc., and is to be within the limits permitted by law. The collection of personal credit investigation data, some european countries and south east asia, australia, korea, taiwan and hong kong etc. have required to provide only negative data, and some countries and regional financial institutions have provided only positive data, the united states allows credit investigation institutions to provide complete personal credit investigation data.
Domestic personal credit data is scattered in various enterprises and governments at all levels, including banks, telecommunications, electric power, water conservancy, public security, industrial and commercial affairs, tax and the like, wherein most organizations enclose respective information and do not share the information, so that an information island is formed, and the difficulty of collecting data by credit investigation companies is increased.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method and a system for acquiring personal credit. The method and the system can lead the acquisition of personal credit to be comprehensive and rapid.
In order to achieve the above purposes, the invention adopts the technical scheme that: a method for acquiring personal credit, comprising the steps of:
establishing an initial personal credit evaluation model, and generating a credit investigation database according to credit investigation data in a database of a mobile operator, wherein the credit investigation database takes a repayment willingness, a repayment capacity and real name authentication information as dimensions, and the credit investigation data comprises: business operation support system BOSS credit investigation data, business analysis system credit investigation data and signaling platform system credit investigation data;
acquiring revision parameters of a personal credit evaluation model in a preset time period, revising the personal credit evaluation model according to the revision parameters, and acquiring the revised personal credit evaluation model;
and receiving the personal user characteristics input from the outside, and acquiring the corresponding personal credit score from the revised personal credit evaluation model according to the personal user characteristics.
Further, the generating a credit investigation database according to credit investigation data in the database of the mobile operator includes:
establishing a personal credit assessment model according to the dimensions:
wherein CreditScore is the credit score of an individual user, n is the number of dimensions, and m i Is the number of dimensional space variables, C, when the dimension is i ij Credit score of dimension i and variable j, W ij Is C ij Are weighted within the dimension of, andweight _ i is the dimension total Weight of the credit score with dimension i;
calculating a personal credit score for each person in the database according to the personal credit assessment model;
and acquiring the personal credit score of each person to generate a credit investigation database.
Further, the dimension space variables of the repayment willingness include: the online time, the historical defaulting times, the historical defaulting time, the number of connections of the delivery circle and the historical loan repayment condition.
Further, the dimensional space variables of the repayment capacity include: income condition, expenditure condition, monthly ARPU value and credit card number.
Further, the dimensional space variables of the real-name authentication information include: mobile phone number, name, identification card number, age, contact mobile phone number, contact ID card number, micro-signal, taobao account number, microblog account number
A system for acquiring personal credits, the system comprising:
the credit investigation database generation unit is used for establishing an initial personal credit evaluation model and generating a credit investigation database according to credit investigation data in a database of a mobile operator, wherein the credit investigation database takes a repayment willingness, a repayment capacity and real name authentication information as dimensions, and the credit investigation data comprises: business operation support system BOSS credit investigation data, business analysis system credit investigation data and signaling platform system credit investigation data;
the revised personal credit evaluation model acquisition unit is used for acquiring revision parameters of the personal credit evaluation model in a preset time period, revising the personal credit evaluation model according to the revision parameters and acquiring the revised personal credit evaluation model;
and the personal credit score acquisition unit is used for receiving the externally input personal user characteristics and acquiring the corresponding personal credit score from the revised personal credit evaluation model according to the personal user characteristics.
Further, the credit investigation database generation unit includes:
the personal credit evaluation model establishing subunit is used for establishing a personal credit evaluation model according to the dimensionality:
wherein CreditScore is the credit score of an individual user, n is the number of dimensions, m i Is the number of dimensional space variables with dimension i, C ij Credit score of dimension i and variable j, W ij Is C ij Are weighted within the dimension of, andweight _ i is the dimension total Weight of the credit score with dimension i;
a personal credit score calculating subunit, configured to calculate a personal credit score of each person in the database according to the personal credit evaluation model;
and the credit investigation database generation subunit is used for acquiring the personal credit scores of each person and generating a credit investigation database.
Further, the dimension space variables of the repayment willingness include: the online time, the historical defaulting times, the historical defaulting time, the number of connections of the delivery circle and the historical loan repayment condition.
Further, the dimensional space variables of the repayment capacity include: income condition, expenditure condition, monthly ARPU value and credit card number.
Further, the dimensional space variables of the real-name authentication information include: the mobile phone number, the name, the identification card number, the age, the contact mobile phone number, the contact ID card number, the micro signal, the Taobao account number and the microblog account number.
The invention has the following effects: by adopting the method, the personal credit score can be quickly and accurately obtained through the comprehensiveness of the mobile operator database, and meanwhile, as each relevant parameter of the personal credit evaluation model can be dynamically changed according to the actual situation, the personal credit score is more accurate.
Drawings
FIG. 1 is a flow chart illustrating a method for acquiring personal credits according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for acquiring personal credits according to another embodiment of the present invention;
FIG. 3 is a block diagram illustrating a personal credit acquisition system in accordance with one embodiment of the present invention;
fig. 4 is a block diagram illustrating a system for acquiring personal credits according to another embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and detailed description.
As shown in fig. 1, a flowchart of a method for acquiring personal credits according to an embodiment of the present invention includes the following steps:
step S101, establishing an initial personal credit evaluation model, and generating a credit investigation database according to credit investigation data in a database of a mobile operator, wherein the credit investigation database takes a repayment willingness, a repayment capability and real name authentication information as dimensions, and the credit investigation data comprises: business operation support system BOSS letter data, operation analysis system letter data, signaling platform system letter data.
In the present embodiment, people have more applied life-related information to mobile devices due to the advancement of the times, and thus a large amount of personal data is generally stored in the database of the mobile operator. Acquiring credit investigation data from a database of a mobile operator, and generating a credit investigation database according to the credit investigation data, wherein the credit investigation database takes the repayment will, the repayment capability and real-name authentication information as dimensions, and the credit investigation data comprises but is not limited to: BOSS (Business Operations Support System) credit investigation data, business analysis System credit investigation data and signaling platform System credit investigation data.
Step S102, obtaining the revised parameters of the personal credit evaluation model in the preset time period, revising the personal credit evaluation model according to the revised parameters, and obtaining the revised personal credit evaluation model.
In the invention, because the credit investigation database is established according to credit investigation data of a mobile operator, and data which is not in good conformity with the latest credit investigation of an individual may exist, revision parameters of the personal credit assessment model within a period of time can be obtained, the personal credit assessment model is revised through the revision parameters, and then the revised personal credit assessment model which is in good conformity with the latest behavior of the individual is obtained.
For example:
by monitoring the running data of the loan repayment situation of the user in a certain period, a repayment default user list can be obtained, and aiming at the repayment default users, data mining analysis (such as correlation analysis, cluster analysis, decision tree, neural network, logic regression and the like) is carried out on each relevant parameter variable and all service details of the credit evaluation model of the repayment default users, so that the correlation coefficient of each relevant parameter variable, a repayment default prediction model and corresponding parameters can be obtained, and the corresponding weight setting of the personal credit evaluation model is corrected. Namely:
and Wij' is a corrected value of each corresponding parameter variable weight Wij in the original initial credit evaluation model after data mining analysis. And also satisfy
Similarly, weight _ i' is the modified result of the dimension total Weight _ i of the credit score with dimension i in the credit evaluation model.
And after the weight value setting of the personal user credit evaluation model is updated, recalculating the personal credit score PCreditScore () of the updated whole network user so as to obtain the latest credit score at any time.
And step S103, receiving the personal user characteristics input from the outside, and acquiring the corresponding personal credit score from the revised personal credit evaluation model according to the personal user characteristics.
In the invention, the personal credit scores in the revised personal credit evaluation model are all associated with personal user characteristics, and the received personal user characteristics are added into the revised personal credit evaluation model for searching, so that the corresponding personal credit scores can be obtained, wherein the personal user characteristics include but are not limited to: identification card number, mobile phone number.
The credit investigation database is established through credit investigation data in the database of the mobile operator, the personal credit assessment model is modified through revision parameters obtained in a preset time period, the revised personal credit assessment model is obtained, and the corresponding personal credit score is obtained from the revised personal credit assessment model according to the characteristics of the individual user.
Fig. 2 is a flowchart of a method for acquiring personal credit according to another embodiment of the present invention, where the method establishes an initial personal credit evaluation model, and generates a credit investigation database according to credit investigation data in a database of a mobile operator, and includes:
step S201, establishing a personal credit evaluation model according to the dimensionality:
wherein CreditScore is the credit score of an individual user, n is the number of dimensions, and m i Is the number of dimensional space variables with dimension i, C ij Credit score of dimension i and variable j, W ij Is C ij Are weighted within the dimension of, andweight _ i is the dimension total Weight of the credit score for dimension i.
In the invention, firstly, a personal credit evaluation model is established according to preset dimensionality:in this model, creditScore is the credit score of an individual user, n is the number of dimensions, m i Is the number of dimensional space variables with dimension i, C ij Credit score of dimension i and variable j, W ij Is C ij Are weighted within the dimension of, andweight _ i is the dimension total Weight of the credit score for dimension i. As can be seen from the foregoing description, the dimension is 3 (willingness to repay, repayment ability, and real-name authentication information), and the number of n being 3,n can be expanded according to the actual use requirement.
It is to be noted that W ij And Weight _ i can be set according to the actual use requirement, for which the present invention does notAnd (5) limiting.
Step S202, calculating the personal credit score of each person in the database according to the personal credit evaluation model.
In the invention, the data of each person in the database is obtained and added into the established personal credit evaluation modelIn this way, the personal credit score of each person can be calculated.
The personal credit score can be specifically calculated by the following three aspects:
1. willingness to repay
The redemption will is represented by W, and the personal credit score of the redemption will be:
wherein CreditScore _ W is the score of the dimension of repayment willingness in the personal credit score, and m is i In order to repay the number of dimensional space variables of the dimension to which the will belongs, m in the present invention i For 5, weight _ i = Weight _ W, where Weight _ W is a preset parameter and can be adjusted according to actual needs.
The dimension space variables of the repayment willingness (W) dimension specifically include:
duration (month) on net W1: the credit score C of the number of months from the beginning of network entry to the present ij (i =1, j = 1) is C _ W1.
Historical number of defaulting times W2: number of times of arrears recorded since last X months, its credit score C ij (i =1, j = 2) is C _ W2.
Historical arrearage duration (month) W3: the total number of months in which arrearage records have occurred since the last X months, with a credit score of C ij (i =1, j = 3) is C _ W3.
Number of connection of reciprocal circle W4: the number of different mobile users who have called and calling in each month is averaged since the last X months, and the credit score C is ij (i =1, j = 4) is C _ W4. The data can pass through BOSS usersAnd the call record details are obtained through calculation, and the call record details can also be obtained through calculation in a user call record details of a signaling platform.
Historical loan repayment condition W5: since the last X months, the loan repayment condition of the loan applicant is mainly checked, and the credit score C of the credit record of the loan applicant is ij (i =1, j = 5) is C _ W5.
The dimension space variable of the repayment willingness is graded according to the following grading rule:
c _ W1= { if W1< W1_ L, C _ W1_ L; else if W1_ M > W1> = W1_ L, C _ W1_ M; else if W1> = W1_ M, C _ W1_ H; else C _ W1_ Default }. Wherein, W1_ L and W1_ M are preset segment threshold parameters, and can be modified according to the requirements of practical application. C _ W1_ L, C _ W1_ M, C _ W1_ H, and C _ W1_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
C _ W2= { if W2> = W2_ M, C _ W2_ L; else if W2_ M > W2> = W2_ L, C _ W2_ M; else if W2< W2_ L, C _ W2_ H; else C _ W2_ Default }. W2_ L and W2_ M are preset segment threshold parameters, and can be modified according to the requirements of practical application. C _ W2_ L, C _ W2_ M, C _ W2_ H, and C _ W2_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
C _ W3= { if W3> = W3_ M, C _ W3_ L; else if W3_ M > W3> = W3_ L, C _ W3_ M; else if W3< W3_ L, C _ W3_ H; else C _ W3_ Default }. Wherein, W3_ L and W3_ M are preset segment threshold parameters, and can be modified according to the requirements of practical application. C _ W3_ L, C _ W3_ M, C _ W3_ H, and C _ W3_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
C _ W4= { if W4< W4_ L, C _ W4_ L; else if W4_ M > W4> = W4_ L, C _ W4_ M; else if W4> = W4_ M, C _ W4_ H; else C _ W4_ Default }. Wherein, W4_ L and W4_ M are preset segment threshold parameters, and can be modified according to the requirements of practical application. C _ W4_ L, C _ W4_ M, C _ W4_ H, and C _ W4_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
C _ W5= { if a loan default occurs, C _ W5_ L; the loan repayment delay time of else if is more than 1 time, C _ W5_ M; else if loan past but no loan repayment delay, C _ W5_ H; else C _ W5_ Default }. Wherein, C _ W5_ L, C _ W5_ M, C _ W5_ H, and C _ W5_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
2. Reimbursement capability
Denoted by C, the repayment ability, then the personal credit score for the repayment ability is:
wherein CreditScore _ C is the score of the dimensionality of the repayment capacity in the personal credit score, and m i For the number of dimensional space variables of the dimension to which the repayment ability belongs, m in the present invention i In the value of 4, weight _ i = Weight _ C, and Weight _ C is a preset parameter, and can be adjusted according to actual use requirements.
The dimension space variables of the repayment ability (C) dimension specifically include:
income (ten thousand yuan) C1: the monthly total income of all the bank debit cards from the last X months is averaged from the short message, and the credit score Cij (i =2, j = 1) is C _ C1. The short message obtained from the operator signaling platform refers to content data of a user sending and receiving short messages, which is acquired through an operator signaling platform, and in order to prevent privacy disclosure and misuse of the user, the system only collects and analyzes the short message content data of a specific opposite terminal number, such as a number notified by a short message of services such as a bank debit card, a bank credit card, consumption of the bank debit card, transaction, transfer, remittance, credit payment and the like, of 95533,95555,95559,1065795555 and the like. Note that: the bank short message notification numbers need to be collected and sorted in advance according to different banks, different areas and service classifications, and not all short message special service numbers are the short message notification numbers described herein. The related technologies of text analysis and machine learning are required to be adopted for the content of the intercepted short message so as to obtain the related structured data record. The calculation formula for C1 is as follows:
wherein, X is the data acquisition period of the credit evaluation model and is the number of months traced back from the current application time point Z month, namely the data acquisition period is Z-1, Z-2, \ 8230, Z-X, and the total number of X months. XMin is the preset month number of the minimum data acquisition cycle and can be modified subsequently. Bi is the number of the bank debit cards corresponding to each data acquisition cycle month (corresponding to the number of the short message notification numbers of different bank debit cards, at most one bank exists in each bank), and the condition that a user has a plurality of bank debit cards in the same bank needs to be merged and counted, and the bank debit cards are marked as the bank debit cards of the same bank. InCome [ i, j ] is the total revenue amount for each bank debit card j for month i of each data acquisition cycle.
Expenditure case (ten thousand yuan) C2: the monthly total expenditure of all the bank debit cards from the last X months is averaged from the short message, and the credit score Cij (i =2, j = 2) is C _ C2. The short message obtained from the operator signaling platform refers to content data of a user sending and receiving short messages, which is acquired through an operator signaling platform, and in order to prevent privacy disclosure and misuse of the user, the system only collects and analyzes the short message content data of a specific opposite terminal number, such as a number notified by a short message of services such as a bank debit card, a bank credit card, consumption of the bank debit card, transaction, transfer, remittance, credit payment and the like, of 95533,95555,95559,1065795555 and the like. Note that: the bank short message notification numbers need to be collected and sorted in advance according to different banks, different areas and service classifications, and not all short message special service numbers are the short message notification numbers described herein. The related technologies of text analysis and machine learning are needed to be adopted for the content of the intercepted short message so as to obtain the related structured data record. The calculation formula for C2 is as follows:
wherein, X is the data acquisition period of the credit evaluation model and is the number of months traced back from the current application time point Z month, namely the data acquisition period is Z-1, Z-2, \ 8230, Z-X, and the total number of X months. XMin is the preset month number of the minimum data acquisition cycle and can be modified subsequently. Bi is the number of bank debit cards corresponding to each data acquisition cycle month (corresponding to the number of short message notification numbers of different bank debit cards, at most one bank exists in each bank), and the condition that a user has a plurality of bank debit cards in the same bank needs to be merged and counted, and the number is recorded as the bank debit card of the same bank. Payment [ i, j ] is the total payout amount per bank debit card j per data acquisition cycle month i.
Monthly ARPU value (meta) C3: since the last X months, the average ARPU value per month (with the highest and lowest values removed) has a credit score Cij (i =2, j = 3) of C _ C3.
Number of credit cards C4: the number of credit cards issued since the last X months, which is obtained from the sms message, has a credit score Cij (i =2, j = 4) of C _ C4. The short message obtained from the operator signaling platform refers to content data of a user sending and receiving short messages, which is acquired through an operator signaling platform, and in order to prevent privacy disclosure and misuse of the user, the system only collects and analyzes the short message content data of a specific opposite terminal number, such as a number notified by a short message of services such as a bank debit card, a bank credit card, consumption of the bank debit card, transaction, transfer, remittance, credit payment and the like, of 95533,95555,95559,1065795555 and the like. Note that: the bank short message notification numbers need to be collected and sorted in advance according to different banks, different areas and service classifications, and not all short message special service numbers are the short message notification numbers described herein. The related technologies of text analysis and machine learning are needed to be adopted for the content of the intercepted short message so as to obtain the related structured data record. The calculation formula for C4 is as follows:
c4= number of different bank note notification numbers all during X, X > = XMin
Wherein, X is the data acquisition period of the credit evaluation model and is the number of months traced back from the current application time point Z month, namely the data acquisition period is Z-1, Z-2, \ 8230, Z-X, and the total number of X months. XMin is a preset month number of the minimum data acquisition cycle, and can be modified subsequently. C4 corresponds to the number of the short message notification numbers of different bank credit cards, each bank has at most one short message notification number, and the condition that a user has a plurality of bank credit cards in the same bank needs to be merged and counted and recorded as the bank credit card of the same bank.
The dimensional space variable of the repayment capacity is graded according to the following grading rule:
c _ C1= { if C1< C1_ L, C _ C1_ L; else if C1_ M > C1> = C1_ L, C _ C1_ M; else if C1> = C1_ M, C _ C1_ H; else C _ C1_ Default }. Wherein, C1_ L and C1_ M are preset segment threshold parameters, and can be modified according to actual use requirements. C _ C1_ L, C _ C1_ M, C _ C1_ H, and C _ C1_ Default are preset segment score parameters, and can be modified according to actual use requirements.
C _ C2= { if C2< C2_ L, C _ C2_ L; else if C2_ M > C2> = C2_ L, C _ C2_ M; else if C2> = C2_ M, C _ C2_ H; else C _ C2_ Default }. Wherein, C2_ L and C2_ M are preset segment threshold parameters, and can be modified according to actual use requirements. C _ C2_ L, C _ C2_ M, C _ C2_ H, and C _ C2_ Default are preset segment score parameters, and can be modified according to actual use requirements.
C _ C3= { if C3< C3_ L, C _ C3_ L; else if C3_ M > C3> = C3_ L, C _ C3_ M; else if C3> = C3_ M, C _ C3_ H; else C _ C3_ Default }. Wherein, C3_ L and C3_ M are preset segment threshold parameters, and can be modified according to actual use requirements. C _ C3_ L, C _ C3_ M, C _ C3_ H, and C _ C3_ Default are preset segment score parameters, and can be modified according to actual use requirements.
C _ C4= { if C4> = C4_ M, C _ C4_ L; else if C4_ M > C4> = C4_ L, C _ C4_ M; else if C4< C4_ L, C _ C4_ H; else C _ C4_ Default }. Wherein, C4_ L and C4_ M are preset segment threshold parameters, and can be modified subsequently. C _ C4_ L, C _ C4_ M, C _ C4_ H, and C _ C4_ Default are preset segment score parameters, and can be modified according to actual use requirements.
3. Real name authentication information
When the real-name authentication information is represented by a, the personal credit score of the real-name authentication information is as follows:
wherein, creditScore _ A is the score of the dimension of the real name authentication information in the personal credit score, m i The number of dimension space variables of the dimension to which the real-name authentication information belongs, m in the present invention i Weight _ i = Weight _ a, where Weight _ a is a preset parameter, and can be adjusted according to actual needs.
The dimension space variable of the dimension of the real name authentication information (a) specifically includes:
mobile phone number A1: the credit score Cij (i =3, j = 1) of the mobile phone number of the person is C _ A1.
Name A2: an account opening register name with a credit score Cij (i =3, j = 2) of C _ A2.
Identification number A3: the account-opening registered identification number has a credit score Cij (i =3, j = 3) of C _ A3.
Age A4: the age resolved from the identification number has a credit score Cij (i =3, j = 4) of C _ A4.
Contact mobile phone number A5: an option, other contact information of the same operator, whose credit score Cij (i =3, j = 5) is C _ A5. And if A5< > is empty, then A6 and A7 are the necessary options and cannot be empty.
Contact name A6: an option, other contact information of the same operator, whose credit score Cij (i =3, j = 6) is C _ A6.
Contact identification card number A7: an option, other contact information of the same operator, has a credit score Cij (i =3, j = 7) of C _ A7.
Micro signal A8: if there are multiple, fill out most often, its credit score Cij (i =3, j = 8) is C _ A8.
Taobao account number A9: if there are multiple, fill out most often, its credit score Cij (i =3, j = 9) is C _ A9.
Microblog account a10: if there are multiple, the most common filling, its credit score Cij (i =3, j = 10) is C _ a10.
The dimension space variable of the real-name authentication information is scored according to the following scoring rules:
c _ A1= C _ A1_ Default. Wherein, the C _ A1_ Default is a preset parameter and can be modified according to the requirements of practical application.
C _ A2= { if the real name authentication of the person name and the identity card number passes, C _ A2_ H; else C _ A2_ L }. Wherein, C _ A2_ L and C _ A2_ H are preset conditional score parameters, and can be modified according to the requirements of practical application. The real name authentication of the personal name and the identity card number is passed, which means that the comparison result of the personal name information and the identity card number information with a national citizen identity card database of the ministry of public security is true.
C _ A3= C _ A3_ Default. Wherein, the C _ A3_ Default is a preset parameter and can be modified according to the requirements of practical application.
C _ A4= { if A4< A4_ Min, C _ FireWall; else if A4_ Min < A4_ L, C _ A4_ L1; else if A4_ M1> A4> = A4_ L, C _ A4_ M1; else if A4_ M2> A4> = A4_ M1, C _ A4_ H; else if A4_ M3> A4> = A4_ M2, C _ A4_ M2; else if A4> = A4_ M3, C _ A4_ L2; else C _ A4_ Default }. The parameters A4_ Min, A4_ L, A4_ M1, A4_ M2, and A4_ M3 are preset segment threshold parameters, and can be modified according to the requirements of practical applications. C _ Firewall, C _ A4_ L1, C _ A4_ M1, C _ A4_ H, C _ A4_ M2, C _ A4_ L2, C _ A4_ Default are preset segmentation score parameters, and can be modified according to the requirements of practical application. C _ FireWall is typically set to a negative number with a very large absolute value.
C _ A5= { if provides contact cell phone number, C _ A5_ H; else C _ A5_ Default }. Wherein, C _ A5_ H and C _ A5_ Default are preset conditional score parameters, and can be modified according to the requirements of practical application. The providing of the contact mobile phone number means that the user provides a non-self mobile phone number with a proving capability.
C _ A6= { if contact name and identity card number real-name authentication pass, C _ A6_ H; else-C _ A5_ H }. Wherein, C _ A6_ H and C _ A5_ H are preset conditional score parameters, and can be modified according to the requirements of practical application. The real-name authentication of the contact name and the identification card number is passed, which means that the comparison result of the name information and the identification card number information of the contact provided by the user and the national citizen identity card database of the ministry of public security is true.
C _ A7= C _ A7_ Default. Wherein, the C _ A7_ Default is a preset parameter, and can be modified according to the requirements of practical application.
C _ A8= { if A8< > null, C _ A8_ H; else C _ A8_ Default }. Wherein, C _ A8_ H and C _ A8_ Default are preset conditional score parameters, and can be modified according to the requirements of actual application.
C _ A9= { if A9< > null, C _ A9_ H; else C _ A9_ Default }. Wherein, C _ A9_ H and C _ A9_ Default are preset conditional score parameters, and can be modified according to the requirements of practical application.
C _ a10= { if a10< > empty, C _ a10_ H; else C _ a10_ Default }. Wherein, C _ a10_ H and C _ a10_ Default are preset conditional score parameters, and can be modified according to the requirements of practical application.
The above dimensional space variables of each dimension can be looked up through table 1:
TABLE 1
The above scoring rule of the dimensional space variable of each dimension can be searched through table 2:
TABLE 2
And step S203, acquiring the personal credit score of each person, and generating a credit investigation database.
In the invention, the credit investigation database can be generated by acquiring the personal credit score of each person in the calculated database, and the credit investigation database is a personal credit investigation database generated according to credit investigation data, namely an original personal credit investigation database.
As shown in fig. 3, a block diagram of a system for acquiring personal credits according to an embodiment of the present invention is shown, where the system includes:
a credit investigation database generation unit 301, configured to establish an initial personal credit evaluation model, and generate a credit investigation database according to credit investigation data in a database of a mobile operator, where the credit investigation database has a willingness to repay, a repayment capability, and real-name authentication information as dimensions, and the credit investigation data includes: business operation support system BOSS letter data, operation analysis system letter data, signaling platform system letter data.
In this embodiment, due to the advancement of the times, people apply more life-related information to mobile devices, and thus a large amount of personal data is generally stored in the database of the mobile operator. Acquiring credit investigation data from a database of a mobile operator, and generating a credit investigation database according to the credit investigation data, wherein the credit investigation database takes the repayment willingness, the repayment capacity and real name authentication information as multiple dimensions, and the credit investigation data comprises but is not limited to: BOSS (Business Operations Support System) credit investigation data, business analysis System credit investigation data and signaling platform System credit investigation data.
A revised personal credit assessment model obtaining unit 302, configured to obtain a revised parameter of the personal credit assessment model for a preset time period, revise the personal credit assessment model according to the revised parameter, and obtain the revised personal credit assessment model.
In the invention, because the credit investigation database is established according to credit investigation data of a mobile operator, and data which is not in good conformity with the latest credit investigation of an individual may exist, revision parameters of the personal credit assessment model within a period of time can be obtained, the personal credit assessment model pair is revised through the revision parameters, and then the revised personal credit assessment model which is in good conformity with the latest behavior of the individual is obtained.
And a personal credit score obtaining unit 303, configured to receive an externally input personal user characteristic, and obtain a corresponding personal credit score from the revised personal credit evaluation model according to the personal user characteristic.
In the invention, the personal credit scores in the revised personal credit evaluation model are all associated with the personal user characteristics, and the received personal user characteristics are added into the revised personal credit evaluation model for searching, so that the corresponding personal credit scores can be obtained, wherein the personal user characteristics include but are not limited to: identity card number, cell-phone number.
The invention establishes the credit investigation database through credit investigation data in the database of the mobile operator, modifies the personal credit assessment model pair through the revision parameter obtained in the preset time period, obtains the revised personal credit assessment model, and obtains the corresponding personal credit score from the revised personal credit assessment model according to the personal user characteristics.
As shown in fig. 4, which is a structural diagram of a system for acquiring personal credit according to another embodiment of the present invention, the credit investigation database generation unit 301 includes:
a personal credit assessment model building subunit 3011, configured to build a personal credit assessment model according to the dimensions:
wherein CreditScore is the credit score of an individual user, n is the number of dimensions, m i Is the number of dimensional space variables, C, when the dimension is i ij Credit score of dimension i and variable j, W ij Is C ij Is weighted within the dimension of (1), andweight _ i is the dimension total Weight of the credit score for dimension i.
In the invention, firstly, the dimension is established according to the preset dimensionEstablishing a personal credit evaluation model:in this model, creditScore is the credit score of an individual user, n is the number of dimensions, m i Is the number of dimensional space variables with dimension i, C ij Credit score of dimension i and variable j, W ij Is C ij Are weighted within the dimension of, andweight _ i is the dimension total Weight of the credit score for dimension i. As can be seen from the foregoing description, the dimension is 3 (willingness to repay, repayment capability, and real-name authentication information), and the number of n is 3, n can be expanded according to the actual use requirement.
It is to be noted that W ij And Weight _ i can be set according to actual use requirements, and the invention does not limit the Weight _ i.
And the personal credit score calculating subunit 3012 is configured to calculate a personal credit score of each person in the database according to the personal credit evaluation model.
In the invention, the data of each person in the database is obtained, and the data is added into the established personal credit evaluation modelIn this way, the personal credit score of each person can be calculated respectively.
The personal credit score can be specifically calculated by the following three aspects:
1. willingness to repay
The willingness to repay is represented by W, and the personal credit score of the willingness to repay is:
wherein, creditScore _ W is the score of the dimension of repayment willingness in the personal credit score, m i Number of dimension space variables of dimension to which will be paidIn the present invention, m i For 5, weight _ i = Weight _ W, where Weight _ W is a preset parameter and can be adjusted according to actual needs.
The dimension space variables of the repayment willingness (W) dimension specifically include:
duration in web (month) W1: the credit score C of the number of months from the beginning of network entry to the present ij (i =1, j = 1) is C _ W1.
Historical number of defaulting times W2: number of times of arrearage records occurred since last X months, credit score C ij (i =1, j = 2) is C _ W2.
Historical arrearage period (month) W3: the total number of months in which arrearage records have occurred since the last X months, with a credit score of C ij (i =1, j = 3) is C _ W3.
Number of turns of intersection W4: the number of different mobile users who have called and calling in each month is averaged since the last X months, and the credit score C is ij (i =1, j = 4) is C _ W4. The data can be obtained by calculation in BOSS user call record details, and also can be obtained by calculation in user call record details of a signaling platform.
Historical loan repayment situation W5: since the last X months, the loan repayment situation of the loan applicant is mainly checked on the credit record of the loan applicant, and the credit score C is obtained ij (i =1,j = 5) is C _ W5.
The dimension space variable of the repayment willingness is graded according to the following grading rule:
c _ W1= { if W1< W1_ L, C _ W1_ L; else if W1_ M > W1> = W1_ L, C _ W1_ M; else if W1> = W1_ M, C _ W1_ H; else C _ W1_ Default }. Wherein, W1_ L and W1_ M are preset segment threshold parameters, and can be modified according to the requirements of practical application. C _ W1_ L, C _ W1_ M, C _ W1_ H, and C _ W1_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
C _ W2= { if W2> = W2_ M, C _ W2_ L; else if W2_ M > W2> = W2_ L, C _ W2_ M; else if W2< W2_ L, C _ W2_ H; else C _ W2_ Default }. Wherein, W2_ L and W2_ M are preset segment threshold parameters, and can be modified according to the requirements of practical application. C _ W2_ L, C _ W2_ M, C _ W2_ H, and C _ W2_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
C _ W3= { if W3> = W3_ M, C _ W3_ L; else if W3_ M > W3> = W3_ L, C _ W3_ M; else if W3< W3_ L, C _ W3_ H; else C _ W3_ Default }. Wherein, W3_ L and W3_ M are preset segment threshold parameters, and can be modified according to the requirements of practical application. C _ W3_ L, C _ W3_ M, C _ W3_ H, and C _ W3_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
C _ W4= { if W4< W4_ L, C _ W4_ L; else if W4_ M > W4> = W4_ L, C _ W4_ M; else if W4> = W4_ M, C _ W4_ H; else C _ W4_ Default }. Wherein, W4_ L and W4_ M are preset segment threshold parameters, and can be modified according to the requirements of practical application. C _ W4_ L, C _ W4_ M, C _ W4_ H, and C _ W4_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
C _ W5= { if a loan default, C _ W5_ L; the loan repayment delay time of else if is more than 1 time, C _ W5_ M; else if loan past but no loan repayment delay, C _ W5_ H; else C _ W5_ Default }. Wherein, C _ W5_ L, C _ W5_ M, C _ W5_ H, and C _ W5_ Default are preset segment score parameters, and can be modified according to the requirements of practical application.
2. Reimbursement capability
Denoted by C, the repayment ability has a personal credit score of:
wherein CreditScore _ C is the score of the dimension of repayment ability in the personal credit score, m i For the number of dimensional space variables of the dimension to which the repayment ability belongs, m in the present invention i For 4, weight _ i = Weight _ C, and Weight _ C is a preset parameter, and can be adjusted according to the actual use requirement.
Dimensional space variables of the repayment ability (C) dimension specifically include:
income (ten thousand yuan) C1: the monthly total income of all the bank debit cards from the last X months is averaged from the short message, and the credit score Cij (i =2, j = 1) is C _ C1. The short message obtained from the operator signaling platform refers to content data of a user sending and receiving short messages, which is acquired through an operator signaling platform, and in order to prevent privacy disclosure and misuse of the user, the system only collects and analyzes the short message content data of a specific opposite terminal number, such as a number notified by a short message of services such as a bank debit card, a bank credit card, consumption of the bank debit card, transaction, transfer, remittance, credit payment and the like, of 95533,95555,95559,1065795555 and the like. Note that: the bank short message notification numbers need to be collected and sorted in advance according to different banks, different areas and service classifications, and not all short message special service numbers are the short message notification numbers described herein. The related technologies of text analysis and machine learning are needed to be adopted for the content of the intercepted short message so as to obtain the related structured data record. The calculation formula for C1 is as follows:
wherein X is a data acquisition period of the credit evaluation model, and is the number of months traced back from the current application time point Z month, namely the data acquisition period is Z-1, Z-2, \8230, Z-X, and the total is X months. XMin is the preset month number of the minimum data acquisition cycle and can be modified subsequently. Bi is the number of bank debit cards corresponding to each data acquisition cycle month (corresponding to the number of short message notification numbers of different bank debit cards, at most one bank exists in each bank), and the condition that a user has a plurality of bank debit cards in the same bank needs to be merged and counted, and the number is recorded as the bank debit card of the same bank. InCome [ i, j ] is the total revenue amount for each bank debit card j for month i of each data acquisition cycle.
Expenditure case (ten thousand yuan) C2: the monthly total expenditure of all the bank debit cards since the last X months is averaged from the short message, and the credit score Cij (i =2, j = 2) is C _ C2. The short message obtained from the operator signaling platform refers to content data of a user sending and receiving short messages, which is acquired through an operator signaling platform, and in order to prevent the privacy of the user from being leaked and abused, the system only collects and analyzes the short message content data of a specific opposite terminal number, such as short message notification numbers of businesses such as a bank debit card, a bank credit card and the like, consumption of the bank debit card, transaction, transfer remittance, credit repayment and the like. Note that: the bank short message notification numbers need to be collected and sorted in advance according to different banks, different areas and service classifications, and not all short message special service numbers are the short message notification numbers described herein. The related technologies of text analysis and machine learning are required to be adopted for the content of the intercepted short message so as to obtain the related structured data record. The calculation formula for C2 is as follows:
wherein, X is the data acquisition period of the credit evaluation model and is the number of months traced back from the current application time point Z month, namely the data acquisition period is Z-1, Z-2, \ 8230, Z-X, and the total number of X months. XMin is the preset month number of the minimum data acquisition cycle and can be modified subsequently. Bi is the number of the bank debit cards corresponding to each data acquisition cycle month (corresponding to the number of the short message notification numbers of different bank debit cards, at most one bank exists in each bank), and the condition that a user has a plurality of bank debit cards in the same bank needs to be merged and counted, and the bank debit cards are marked as the bank debit cards of the same bank. Payment [ i, j ] totals the total payout of each bank debit card j per month i of the data acquisition cycle.
Monthly ARPU value (meta) C3: since the last X months, the average ARPU value per month (with the highest and lowest values removed) has a credit score Cij (i =2, j = 3) of C _ C3.
Number of credit cards C4: the number of credit cards issued since the last X months, which is obtained from the sms message, has a credit score Cij (i =2, j = 4) of C _ C4. The short message obtained from the operator signaling platform refers to content data of a user sending and receiving short messages, which is acquired through an operator signaling platform, and in order to prevent privacy disclosure and misuse of the user, the system only collects and analyzes the short message content data of a specific opposite terminal number, such as a number notified by a short message of services such as a bank debit card, a bank credit card, consumption of the bank debit card, transaction, transfer, remittance, credit payment and the like, of 95533,95555,95559,1065795555 and the like. Note that: the bank short message notification numbers need to be collected and sorted in advance according to different banks, different areas and service classifications, and not all short message special service numbers are the short message notification numbers described herein. The related technologies of text analysis and machine learning are needed to be adopted for the content of the intercepted short message so as to obtain the related structured data record. The calculation formula for C4 is as follows:
c4= number of different bank note notification numbers all during X, X > = XMin
Wherein, X is the data acquisition period of the credit evaluation model and is the number of months traced back from the current application time point Z month, namely the data acquisition period is Z-1, Z-2, \ 8230, Z-X, and the total number of X months. XMin is the preset month number of the minimum data acquisition cycle and can be modified subsequently. C4 corresponds to the number of the short message notification numbers of different bank credit cards, each bank has at most one short message notification number, and the condition that a user has a plurality of bank credit cards in the same bank needs to be merged and counted and recorded as the bank credit card of the same bank.
The dimensional space variable of the repayment ability is scored according to the following scoring rules:
c _ C1= { if C1< C1_ L, C _ C1_ L; else if C1_ M > C1> = C1_ L, C _ C1_ M; else if C1> = C1_ M, C _ C1_ H; else C _ C1_ Default }. Wherein, C1_ L and C1_ M are preset segment threshold parameters, and can be modified according to actual use requirements. C _ C1_ L, C _ C1_ M, C _ C1_ H, and C _ C1_ Default are preset segment score parameters, and can be modified according to actual use requirements.
C _ C2= { if C2< C2_ L, C _ C2_ L; else if C2_ M > C2> = C2_ L, C _ C2_ M; else if C2> = C2_ M, C _ C2_ H; else C _ C2_ Default }. Wherein, C2_ L and C2_ M are preset segment threshold parameters, and can be modified according to actual use requirements. C _ C2_ L, C _ C2_ M, C _ C2_ H, and C _ C2_ Default are preset segment score parameters, and can be modified according to actual use requirements.
C _ C3= { if C3< C3_ L, C _ C3_ L; else if C3_ M > C3> = C3_ L, C _ C3_ M; else if C3> = C3_ M, C _ C3_ H; else C _ C3_ Default }. Wherein, C3_ L and C3_ M are preset segment threshold parameters, and can be modified according to actual use requirements. C _ C3_ L, C _ C3_ M, C _ C3_ H, and C _ C3_ Default are preset segment score parameters, and can be modified according to actual use requirements.
C _ C4= { if C4> = C4_ M, C _ C4_ L; else if C4_ M > C4> = C4_ L, C _ C4_ M; else if C4< C4_ L, C _ C4_ H; else C _ C4_ Default }. Wherein, C4_ L and C4_ M are preset segment threshold parameters, and can be modified subsequently. C _ C4_ L, C _ C4_ M, C _ C4_ H, and C _ C4_ Default are preset segment score parameters, and can be modified according to actual use requirements.
3. Real name authentication information
When the real-name authentication information is denoted by a, the personal credit score of the real-name authentication information is:
wherein, creditScore _ A is the score of the dimension of the real name authentication information in the personal credit score, m i The number of dimension space variables of the dimension to which the real-name authentication information belongs, m in the present invention i Weight _ i = Weight _ a, where Weight _ a is a preset parameter, and can be adjusted according to actual needs.
The dimension space variable of the dimension of the real name authentication information (a) specifically includes:
mobile phone number A1: the credit score Cij (i =3, j = 1) of the mobile phone number of the person is C _ A1.
Name A2: an account opening register name whose credit score Cij (i =3,j = 2) is C _ A2.
Identification number A3: the account-opening registered identification number has a credit score Cij (i =3, j = 3) of C _ A3.
Age A4: the age analyzed from the identification number has a credit score Cij (i =3, j = 4) of C _ A4.
Contact mobile phone number A5: an option, other contact information of the same operator, whose credit score Cij (i =3, j = 5) is C _ A5. And if A5< > is empty, then A6 and A7 are the necessary options and cannot be empty.
Contact name A6: an option, other contact information of the same operator, whose credit score Cij (i =3, j = 6) is C _ A6.
Contact identification card number A7: an option, other contact information of the same operator, whose credit score Cij (i =3, j = 7) is C _ A7.
Micro signal A8: if there are multiple, fill out most often, its credit score Cij (i =3, j = 8) is C _ A8.
Panning account number A9: if there are multiple, the most common filling, its credit score Cij (i =3, j = 9) is C _ A9.
Microblog account a10: if there are multiple, fill out most often, its credit score Cij (i =3, j = 10) is C _ a10.
The dimensional space variable of the real-name authentication information is scored according to the following scoring rules:
c _ A1= C _ A1_ Default. Wherein, the C _ A1_ Default is a preset parameter, and can be modified according to the requirements of practical application.
C _ A2= { if the personal name and the identification number pass real-name authentication, C _ A2_ H; else C _ A2_ L }. Wherein, C _ A2_ L and C _ A2_ H are preset conditional score parameters, and can be modified according to the requirements of practical application. The real name authentication of the personal name and the identity card number is passed, which means that the comparison result of the personal name information and the identity card number information with a national citizen identity card database of the ministry of public security is true.
C _ A3= C _ A3_ Default. Wherein, the C _ A3_ Default is a preset parameter, and can be modified according to the requirements of practical application.
C _ A4= { if A4< A4_ Min, C _ FireWall; else if A4_ Min < A4_ L, C _ A4_ L1; else if A4_ M1> A4> = A4_ L, C _ A4_ M1; else if A4_ M2> A4> = A4_ M1, C _ A4_ H; else if A4_ M3> A4> = A4_ M2, C _ A4_ M2; else if A4> = A4_ M3, C _ A4_ L2; else C _ A4_ Default }. The parameters A4_ Min, A4_ L, A4_ M1, A4_ M2, and A4_ M3 are preset segment threshold parameters, and can be modified according to the requirements of practical applications. C _ Firewall, C _ A4_ L1, C _ A4_ M1, C _ A4_ H, C _ A4_ M2, C _ A4_ L2, C _ A4_ Default are preset segmentation score parameters, and can be modified according to the requirements of practical application. C _ FireWall is typically set to a negative number with a very large absolute value.
C _ A5= { if provides contact cell phone number, C _ A5_ H; else C _ A5_ Default }. Wherein, C _ A5_ H and C _ A5_ Default are preset conditional score parameters, and can be modified according to the requirements of practical application. The providing of the contact mobile phone number means that the user provides a non-self mobile phone number with certification capability.
C _ A6= { if contact name and identity card number real-name authentication pass, C _ A6_ H; else-C _ A5_ H }. Wherein, C _ A6_ H and C _ A5_ H are preset conditional score parameters, and can be modified according to the requirements of practical application. The real name authentication of the contact name and the identity card number is passed, which means that the comparison result between the name information and the identity card number information of the contact provided by the user and the national citizen identity card database of the Ministry of public Security is true.
C _ A7= C _ A7_ Default. Wherein, the C _ A7_ Default is a preset parameter, and can be modified according to the requirements of practical application.
C _ A8= { if A8< > empty, C _ A8_ H; else C _ A8_ Default }. Wherein, C _ A8_ H and C _ A8_ Default are preset conditional score parameters, and can be modified according to the requirements of actual application.
C _ A9= { if A9< > empty, C _ A9_ H; else C _ A9_ Default }. Wherein, C _ A9_ H and C _ A9_ Default are preset conditional score parameters, and can be modified according to the requirements of actual application.
C _ a10= { if a10< > empty, C _ a10_ H; else C _ a10_ Default }. Wherein, C _ a10_ H and C _ a10_ Default are preset conditional score parameters, and can be modified according to the requirements of practical application.
And a credit investigation database generation subunit 3013, configured to obtain the personal credit score of each person, and generate a credit investigation database.
In the invention, the credit investigation database can be generated by acquiring the personal credit score of each person in the calculated database, and the credit investigation database is a personal credit investigation database generated according to credit investigation data, namely an original personal credit investigation database.
It will be appreciated by those skilled in the art that the method and system of the present invention are not limited to the embodiments described in the detailed description, which is for the purpose of explanation and not limitation. Other embodiments will be apparent to those skilled in the art from the following detailed description, which is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method for acquiring personal credit is characterized by comprising the following steps:
establishing an initial personal credit evaluation model, and generating a credit investigation database according to credit investigation data in a database of a mobile operator, wherein the credit investigation database takes a repayment willingness, a repayment capacity and real name authentication information as dimensions, and the credit investigation data comprises: business operation support system BOSS credit investigation data, business analysis system credit investigation data and signaling platform system credit investigation data;
acquiring revision parameters of a personal credit evaluation model in a preset time period, revising the personal credit evaluation model according to the revision parameters, and acquiring the revised personal credit evaluation model;
and receiving the personal user characteristics input from the outside, and acquiring the corresponding personal credit score from the revised personal credit evaluation model according to the personal user characteristics.
2. The method as claimed in claim 1, wherein the establishing of the initial personal credit evaluation model and the generation of the credit investigation database according to the credit investigation data in the database of the mobile operator comprises:
establishing a personal credit assessment model according to the dimensions:
wherein CreditScore is the credit score of an individual user, n is the number of dimensions, m i Is the number of dimensional space variables with dimension i, C ij Is a credit score with dimension i and variable j, W ij Is C ij Are weighted within the dimension of, andweight _ i is the dimension total Weight of the credit score with the dimension i;
calculating a personal credit score for each person in the database according to the personal credit assessment model;
and acquiring the personal credit score of each person to generate a credit investigation database.
3. The method for acquiring personal credit as claimed in any one of claims 1-2, wherein the dimension space variables of the repayment willingness include: the online time, the historical defaulting times, the historical defaulting time, the number of connections of the delivery circle and the historical loan repayment condition.
4. The method according to any one of claims 1-2, wherein the dimension space variables of the repayment ability comprise: income condition, expenditure condition, monthly ARPU value and credit card number.
5. The method for acquiring personal credit as claimed in any one of claims 1-2, wherein the dimensional space variables of the real name authentication information include: the mobile phone number, the name, the identification card number, the age, the contact mobile phone number, the contact ID card number, the micro signal, the Taobao account number and the microblog account number.
6. A system for acquiring personal credits, said system comprising:
the credit investigation database generation unit is used for establishing an initial personal credit evaluation model and generating a credit investigation database according to credit investigation data in a database of a mobile operator, wherein the credit investigation database takes a repayment willingness, a repayment capacity and real name authentication information as dimensions, and the credit investigation data comprises: business operation support system BOSS credit investigation data, business analysis system credit investigation data and signaling platform system credit investigation data;
the revised personal credit evaluation model acquisition unit is used for acquiring a revised parameter of the personal credit evaluation model in a preset time period, revising the personal credit evaluation model according to the revised parameter and acquiring the revised personal credit evaluation model;
and the personal credit score acquisition unit is used for receiving the externally input personal user characteristics and acquiring the corresponding personal credit score from the revised personal credit evaluation model according to the personal user characteristics.
7. The system for acquiring personal credit of claim 6, wherein the credit database generating unit comprises:
the personal credit evaluation model establishing subunit is used for establishing a personal credit evaluation model according to the dimensionality:
wherein CreditScore is the credit score of an individual user, n is the number of dimensions, and m i Is the number of dimensional space variables, C, when the dimension is i ij Credit score of dimension i and variable j, W ij Is C ij Are weighted within the dimension of, andweight _ i is the dimension total Weight of the credit score with dimension i;
a personal credit score calculating subunit, configured to calculate a personal credit score of each person in the database according to the personal credit evaluation model;
and the credit investigation database generation subunit is used for acquiring the personal credit scores of each person and generating a credit investigation database.
8. The system for acquiring personal credits according to any one of claims 6 to 7, wherein the dimensional space variables of the repayment willingness include: the online time, the historical defaulting times, the historical defaulting time, the number of connections of the delivery circle and the historical loan repayment condition.
9. The system for acquiring personal credits according to any one of claims 6 to 7, wherein the dimensional space variables of the repayment capacity include: income condition, expenditure condition, monthly ARPU value and credit card number.
10. The system for acquiring personal credit of any one of claims 6 to 7, wherein the dimensional space variables of the real name authentication information include: the mobile phone number, the name, the identification card number, the age, the contact mobile phone number, the contact ID card number, the micro signal, the Taobao account number and the microblog account number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612361.5A CN107563588A (en) | 2017-07-25 | 2017-07-25 | A kind of acquisition methods of personal credit and acquisition system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710612361.5A CN107563588A (en) | 2017-07-25 | 2017-07-25 | A kind of acquisition methods of personal credit and acquisition system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107563588A true CN107563588A (en) | 2018-01-09 |
Family
ID=60974642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710612361.5A Pending CN107563588A (en) | 2017-07-25 | 2017-07-25 | A kind of acquisition methods of personal credit and acquisition system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107563588A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108364218A (en) * | 2018-02-11 | 2018-08-03 | 中国银行股份有限公司 | A kind of sharing method and device of user's collage-credit data |
| CN108416664A (en) * | 2018-01-29 | 2018-08-17 | 广州越秀金融科技有限公司 | Methods of risk assessment and system based on consumptive credit scene are realized |
| CN108629379A (en) * | 2018-05-10 | 2018-10-09 | 北京天元创新科技有限公司 | A kind of individual's reference appraisal procedure and system |
| CN108921686A (en) * | 2018-06-19 | 2018-11-30 | 阿里巴巴集团控股有限公司 | A kind of credit-graded approach and device of personal user |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070111853A (en) * | 2006-05-19 | 2007-11-22 | 인하대학교 산학협력단 | Separately trained system and method using two-layered neural network with target values of hidden nodes |
| CN101493913A (en) * | 2008-01-23 | 2009-07-29 | 阿里巴巴集团控股有限公司 | Method and system for assessing user credit in internet |
| US20100010930A1 (en) * | 2008-07-11 | 2010-01-14 | American Express Travel Related Services Company, Inc. | Providing a real time credit score as part of a transaction request |
| CN102779297A (en) * | 2012-06-28 | 2012-11-14 | 浪潮(山东)电子信息有限公司 | Credit rating model configuration management system based on cloud computing and application method thereof |
| KR20150052468A (en) * | 2013-11-05 | 2015-05-14 | 삼성전자주식회사 | Method and system of evaluating credibility |
| CN105243566A (en) * | 2015-10-28 | 2016-01-13 | 联动优势科技有限公司 | Method and apparatus for evaluating credit of users through different mobile phone number information from operators |
| CN105528465A (en) * | 2016-02-03 | 2016-04-27 | 天弘基金管理有限公司 | Credit status assessment method and device |
| CN105869035A (en) * | 2016-04-07 | 2016-08-17 | 中国联合网络通信集团有限公司 | Mobile user credit evaluation method and apparatus |
| CN106097043A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | The processing method of a kind of credit data and server |
| CN106296389A (en) * | 2016-07-28 | 2017-01-04 | 联动优势科技有限公司 | The appraisal procedure of a kind of user credit degree and device |
-
2017
- 2017-07-25 CN CN201710612361.5A patent/CN107563588A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070111853A (en) * | 2006-05-19 | 2007-11-22 | 인하대학교 산학협력단 | Separately trained system and method using two-layered neural network with target values of hidden nodes |
| CN101493913A (en) * | 2008-01-23 | 2009-07-29 | 阿里巴巴集团控股有限公司 | Method and system for assessing user credit in internet |
| US20100010930A1 (en) * | 2008-07-11 | 2010-01-14 | American Express Travel Related Services Company, Inc. | Providing a real time credit score as part of a transaction request |
| CN102779297A (en) * | 2012-06-28 | 2012-11-14 | 浪潮(山东)电子信息有限公司 | Credit rating model configuration management system based on cloud computing and application method thereof |
| KR20150052468A (en) * | 2013-11-05 | 2015-05-14 | 삼성전자주식회사 | Method and system of evaluating credibility |
| CN105243566A (en) * | 2015-10-28 | 2016-01-13 | 联动优势科技有限公司 | Method and apparatus for evaluating credit of users through different mobile phone number information from operators |
| CN105528465A (en) * | 2016-02-03 | 2016-04-27 | 天弘基金管理有限公司 | Credit status assessment method and device |
| CN105869035A (en) * | 2016-04-07 | 2016-08-17 | 中国联合网络通信集团有限公司 | Mobile user credit evaluation method and apparatus |
| CN106097043A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | The processing method of a kind of credit data and server |
| CN106296389A (en) * | 2016-07-28 | 2017-01-04 | 联动优势科技有限公司 | The appraisal procedure of a kind of user credit degree and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416664A (en) * | 2018-01-29 | 2018-08-17 | 广州越秀金融科技有限公司 | Methods of risk assessment and system based on consumptive credit scene are realized |
| CN108364218A (en) * | 2018-02-11 | 2018-08-03 | 中国银行股份有限公司 | A kind of sharing method and device of user's collage-credit data |
| CN108629379A (en) * | 2018-05-10 | 2018-10-09 | 北京天元创新科技有限公司 | A kind of individual's reference appraisal procedure and system |
| CN108921686A (en) * | 2018-06-19 | 2018-11-30 | 阿里巴巴集团控股有限公司 | A kind of credit-graded approach and device of personal user |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA2821095C (en) | System and method for detecting fraudulent account access and transfers | |
| CN109670936A (en) | Loan examination & approval processing method, platform, equipment and computer readable storage medium | |
| CN108616654B (en) | Message reminding method, device, terminal and computer readable storage medium | |
| CN107563588A (en) | A kind of acquisition methods of personal credit and acquisition system | |
| CN106408412A (en) | Mobile phone-based loan system | |
| CN108921686A (en) | A kind of credit-graded approach and device of personal user | |
| US20080109314A1 (en) | Method and apparatus for determining a customer's likelihood of reusing a financial account | |
| CN111506801A (en) | Sequencing method and device for sub-applications in application App | |
| CN108416670A (en) | Credit matches folk prescription method and server | |
| CN109145050B (en) | Computing device | |
| CN109711801A (en) | A kind of Internetbank account checking method and device | |
| CN109961309B (en) | Service recommendation method and system | |
| CN107193974A (en) | Localized information based on artificial intelligence determines method and apparatus | |
| CN107644098A (en) | A kind of fraud recognition methods, device, equipment and storage medium | |
| CN109325845A (en) | A kind of financial product intelligent recommendation method and system | |
| CN113989019A (en) | Method, device, equipment and storage medium for identifying risks | |
| CN109389501A (en) | A kind of calculating equipment, computing system | |
| CN110197426B (en) | Credit scoring model building method, device and readable storage medium | |
| CN111061948A (en) | User label recommendation method and device, computer equipment and storage medium | |
| CN111105064A (en) | Method and device for determining suspected information of fraud event | |
| CN109711984B (en) | Pre-loan risk monitoring method and device based on collection urging | |
| CN116645134A (en) | Method, device, equipment and medium for recommending credit card in stages | |
| CN112819613B (en) | Loan information processing method, device and storage medium | |
| CN110619564A (en) | Anti-fraud feature generation method and device | |
| CN110197074B (en) | User authority control method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180109 |
|
| RJ01 | Rejection of invention patent application after publication |