CN112991041A

CN112991041A - Credit line sharing method, device, terminal and storage medium based on big data

Info

Publication number: CN112991041A
Application number: CN202110202230.6A
Authority: CN
Inventors: 熊常春; 李海良; 王敬贵; 李国元; 刘昂; 吴江川; 李苗; 熊桥峰; 张富耕
Original assignee: Shenzhen Jilian Technology Co ltd
Current assignee: Shenzhen Jilian Technology Co ltd
Priority date: 2021-02-23
Filing date: 2021-02-23
Publication date: 2021-06-18

Abstract

The invention relates to the technical field of big data analysis, and provides a credit line sharing method, a device, a terminal and a storage medium based on big data, wherein the method comprises the following steps: responding to a limit application instruction of an applicant, and acquiring user data and an application limit of the applicant; calculating a first composite credit score based on the user data; calculating a risk score based on the user data and the first composite credit score using a long-short term memory network model; upon determining that the risk score is greater than a preset risk score threshold, constructing a social network graph of the applicant; determining a plurality of target quota sharing users based on the social network graph; and sending a quota sharing application to the plurality of target quota sharing users. The invention can improve the auditing efficiency of limit application and effectively ensure the safety of credit.

Description

Credit line sharing method, device, terminal and storage medium based on big data

Technical Field

The invention relates to the technical field of big data analysis, in particular to a credit line sharing method, device, terminal and storage medium based on big data.

Background

With the rapid development of the Chinese credit market, the credit service market is also well-being. The credit service market refers to various economic organizations and intermediaries that specialize in credit production and consumption to ensure that market trading activities proceed smoothly. The technical innovation of the internet credit service enables the credit service boundary to be extended, the basic credit service is assisted, and the social credit system is improved together. The credit score provides users with various service lines, such as deposit mortgage line, book lease line, credit card line, etc., and the application of the line is more and more extensive. At present, the credit service limit of a user is evaluated regularly, the user can apply for increasing the limit after using the credit service limit for a period of time, and the time consumed for applying the credit service limit is long. The phenomenon that the quota is insufficient for frequently used users and needs long auditing time for increasing the quota often occurs, but the phenomenon that the quota is redundant for less frequently used users occurs. In order to rapidly increase the limit for the user and solve the short-term emergency requirement, the idle limit of other users can be used for sharing.

The invention patent CN201711006632.9 discloses a credit card line transfer method and system, which judges whether the credit conditions of a credit card account of a lender and a credit card account of a borrower meet the requirements; judging whether the borrowing period is within a specified period; and judging whether the transfer amount is less than or equal to the residual amount of the credit card account of the lender to check whether the transfer amount passes, playing the role of bank credit amount assets and improving the utilization rate of the bank assets. However, the invention is only limited to credit card limit, and the considered aspects are too few, so that the user can not be guaranteed to be certain, the safety can not be guaranteed, and the risk of bad account of the limit asset is increased.

Disclosure of Invention

In view of the above, it is necessary to provide a credit line sharing method, device, terminal and storage medium based on big data, which can improve the auditing efficiency of the line application, effectively ensure the security of the credit, and reduce the risk of bad accounts.

The invention provides a credit line sharing method based on big data, which comprises the following steps:

responding to a limit application instruction of an applicant, and acquiring user data and an application limit of the applicant;

calculating a first composite credit score based on the user data;

calculating a risk score based on the user data and the first composite credit score using a long-short term memory network model;

upon determining that the risk score is greater than a preset risk score threshold, constructing a social network graph of the applicant;

determining a plurality of target quota sharing users based on the social network graph;

and sending a quota sharing application to the plurality of target quota sharing users.

In an alternative embodiment, the user data includes basic data, credit line usage data, historical credit data, third party credit score data, user social data, and the calculating a first composite credit score based on the user data includes:

computing a user representation based on the base data;

predicting a user consumption capacity based on the credit usage data;

predicting user performance capabilities based on the historical credit data;

calculating the first composite credit score based on the user representation, the user consumption capacity, the user performance capacity, the third party credit score data, and the user social data.

In an alternative embodiment, said computing a user representation based on said base data comprises:

acquiring first data corresponding to a first data tag and second data corresponding to a second data tag in the basic data;

extracting a first feature vector of the first data and extracting a second feature vector of the second data by using a BERT model;

and calculating the user portrait according to the first feature vector and the corresponding first weight, the second feature vector and the corresponding second weight.

In an optional embodiment, the predicting the user's consumption ability based on the credit usage data comprises:

calculating using habits, using frequency, limit using rate and limit overdraft rate based on the limit using data;

constructing a user behavior preference vector according to the using habit, the using frequency, the quota using rate and the quota overdraft rate;

predicting the user consumption capacity based on the user behavior preference vector by using a trained consumption capacity prediction model.

In an alternative embodiment, said predicting user performance capabilities based on said historical credit data comprises:

acquiring a performance date and credit card liability in the historical credit data;

performing first binning processing on the contract date to obtain a binning date;

carrying out second box separation processing on the credit card liability to obtain box separation liability;

splicing the box separation date and the box separation liability to obtain a user performance vector;

predicting user performance based on the user performance vector using a trained performance prediction model.

In an alternative embodiment, the third party credit score data calculation process includes:

receiving credit scoring data of the applicant sent by a plurality of preset data service structures;

distributing scoring weight according to the sending time of the preset data service mechanism;

and calculating according to the credit scoring data and the corresponding scoring weight to obtain the third-party credit scoring data.

In an alternative embodiment, said constructing said applicant's social network graph comprises:

obtaining a plurality of contacts of the applicant;

calculating the social relevance of the applicant and each contact;

and constructing a social network graph by taking the applicant as a central node in the social network graph, taking the contact as a network node and taking the social association degree as the weight of an edge between the central node and the corresponding network node.

In an alternative embodiment, said calculating the social relevance of the applicant to each contact comprises:

calculating the social frequency and the social time of the applicant and each contact;

extracting the social frequency and the social time to construct a social feature vector;

calculating a social relevance of the applicant to each contact based on the social feature vector using a social relevance calculation model.

In an optional embodiment, the determining a plurality of target quota sharing users based on the social network graph comprises:

acquiring the residual amount and a second comprehensive credit score of the contact;

constructing a contact person feature vector based on the social relevance, the surplus limit and the second comprehensive credit score;

calculating a matching goodness of fit between the contact and the applicant based on the contact feature vector using a matching goodness of fit calculation model;

updating the social network graph according to the matching goodness of fit to obtain a target social network graph;

searching the target social network map according to a preset search rule to obtain a plurality of target network nodes;

and determining the target network nodes as target line sharing users.

In an optional embodiment, the preset search rule is that, starting from the central node, contacts with search paths not more than a preset number of network nodes correspond to are used as target line sharing users of the applicant.

In an optional embodiment, after sending the line sharing application to the target line sharing users, the method further includes:

receiving the quota shared by the target quota sharing user;

judging whether the quota shared by any target quota sharing user is equal to the application quota or not;

when the shared line of any target line sharing user is equal to the application line, receiving the shared line of any target line sharing user;

when the amount shared by any target amount sharing user is smaller than the application amount, selecting a plurality of target amounts from the amounts shared by the target amounts sharing users, so that the sum of the target amounts can be equal to the application amount.

In an optional embodiment, the method further comprises:

acquiring a first target matching goodness of fit which is greater than a preset first matching goodness of fit threshold value in the target social network graph, and providing a line sharing reservation function for a contact corresponding to the first target matching goodness of fit; or

Obtaining a second target matching goodness of fit which is smaller than a preset second matching goodness of fit threshold value in the target social network graph, displaying a line sharing permission option on a network node corresponding to the second target matching goodness of fit, receiving a determined selection of the applicant in the line sharing permission option, and refusing to receive a line sharing application of a contact corresponding to the determined selection.

In an optional embodiment, the method further comprises:

performing additional interest calculation and revenue allocation according to the risk score, comprising: calculating the additional interest based on the risk score, the original quota of the applicant and the application quota by using an additional interest calculation model; and calculating the distribution income of the target amount sharing users corresponding to the plurality of target amounts according to the additional interest and the second comprehensive credit score.

In an alternative embodiment, the additional interest calculation model is the following formula: y ═ X1+ X2)/X3, where Y represents additional interest, X1 represents risk score, X2 represents application quota, and X3 represents original quota.

In an optional embodiment, the method further comprises:

obtaining the credit behavior of the applicant on the line shared by the target line sharing user;

and updating the first comprehensive credit score of the applicant and the second comprehensive credit score of the target line sharing user according to the credit behavior.

In an optional embodiment, the method further comprises:

acquiring account information of the applicant;

judging whether the remaining credit limit in the account information is a preset limit threshold value or not;

when the remaining credit line is determined to be the preset line threshold value, executing a response to the line application instruction;

and when the remaining credit line is determined not to be the preset line threshold value, refusing the response to the line application instruction.

In an optional embodiment, the method further comprises:

and determining the target line sharing user as the applicant's guarantor.

The second aspect of the present invention provides a credit line sharing device based on big data, the device comprising:

the application response module is used for responding to the limit application instruction of the applicant, and acquiring the user data and the application limit of the applicant;

a first calculation module for calculating a first composite credit score based on the user data;

a second calculation module for calculating a risk score based on the user data and the first composite credit score using a long-short term memory network model;

a graph construction module for constructing a social network graph of the applicant when it is determined that the risk score is greater than a preset risk score threshold;

the target determination module is used for determining a plurality of target line sharing users based on the social network graph;

and the sharing sending module is used for sending the quota sharing application to the plurality of target quota sharing users.

A third aspect of the present invention provides a terminal, where the terminal includes a processor, and the processor is configured to implement the credit line sharing method based on big data when executing a computer program stored in a memory.

A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, where the computer program, when executed by a processor, implements the big-data-based credit line sharing method.

In summary, the credit line sharing method, device, terminal and storage medium based on big data according to the present invention obtain the user data and the application line of the applicant when receiving the line application instruction of the applicant; calculating a first composite credit score based on the user data, and calculating a risk score based on the user data and the first composite credit score by using a long-short term memory network model; and when it is determined that the risk score is greater than a preset risk score threshold, constructing a social network graph of the applicant; determining a plurality of target quota sharing users based on the social network graph; and sending a quota sharing application to the plurality of target quota sharing users. The credit service system can solve the technical problems of line redundancy and long line auditing time improvement of the existing credit service, provides sharing of lines among different users in the same platform, reduces auditing time for line application improvement, improves auditing efficiency for line application improvement, enables the security of credit to be effectively guaranteed and reduces risks of bad accounts through risk assessment and score updating.

Drawings

Fig. 1 is a flowchart of a credit line sharing method based on big data according to an embodiment of the present invention.

Fig. 2 is a structural diagram of a credit line sharing device based on big data according to a second embodiment of the present invention.

Fig. 3 is a schematic structural diagram of a social network graph provided in an embodiment of the present invention.

Fig. 4 is a schematic structural diagram of a terminal according to a third embodiment of the present invention.

Detailed Description

In order that the above objects, features and advantages of the present invention can be more clearly understood, a detailed description of the present invention will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

The credit line sharing method based on the big data provided by the embodiment of the invention is executed by the terminal, and correspondingly, the credit line sharing device based on the big data runs in the terminal.

Fig. 1 is a flowchart of a credit line sharing method based on big data according to an embodiment of the present invention. The credit line sharing method based on the big data specifically comprises the following steps, and the sequence of the steps in the flow chart can be changed and some steps can be omitted according to different requirements.

S11, responding to the request instruction of the applicant for quota, obtaining the user data and the quota request of the applicant.

The terminal can provide a limit application user interface, and the applicant can log in the limit application user interface and touch the limit application virtual icon on the limit application user interface so as to trigger a limit application instruction. And the terminal responds to the limit application instruction of the applicant to acquire the user data and the application limit of the applicant.

The applicant can be a user needing to increase the quota, and can also share the quota to other users needing to increase the quota.

User data may include, but is not limited to: and (4) basic data. The basic data may include: gender, age, marital status, academic history, occupation, income stream, bank card holding status, social security, etc. can reflect the objective data of the personal credit information of the applicant.

In an optional embodiment, the method further comprises:

acquiring account information of the applicant;

When receiving a credit line application instruction of an applicant, a terminal acquires account information of the applicant, wherein the account information may include: account name, credit per cycle, remaining credit.

The terminal determines whether the credit line of the current period in the account information of the applicant has been exhausted, i.e., whether the remaining credit line is a preset line threshold (e.g., 0). And if the credit line of the applicant in the current period is exhausted, namely the remaining credit line is a preset credit line threshold value, responding to the credit line application instruction of the applicant so as to determine the credit line applied by the applicant. And if the credit line of the applicant in the current period is not used up, namely the remaining credit line is not a preset credit line threshold value, refusing the response to the credit line application instruction. For example, the credit card limit is taken as an example, the general credit card limit is calculated according to a month period, assuming that the monthly credit card limit of the applicant is 3000, when the remaining credit card limit of the month is 0, indicating that the current periodic credit limit of the applicant is exhausted, the terminal responds to the limit application instruction, so that the limit application is prevented from overflowing, and the waste of resources caused by random limit application of the user is avoided.

S12, a first composite credit score is calculated based on the user data.

In an alternative embodiment, the user data includes, in addition to the basic data described above, credit line usage data, historical credit data, third party credit score data, user social data. Basic data, quota usage data, historical credit data, third party credit score data, and user social data provide data basis for calculating the credit score of the user.

In an alternative embodiment, said calculating a first composite credit score based on said user data comprises:

computing a user representation based on the base data;

predicting a user consumption capacity based on the credit usage data;

predicting user performance capabilities based on the historical credit data;

And after the terminal calculates the user portrait and predicts the user consumption capacity and the user performance capacity, the terminal adds and averages the user portrait, the user consumption capacity, the user performance capacity, the third-party credit score data and the user social data to obtain a first comprehensive credit score of the applicant.

Each datum in the base datum is identified with a data tag, some of the data are identified with a first data tag, and some of the data are identified with a second data tag. For example, a scholarly, profession, income stream, holding bank card status, social security, etc. in the base data identify a first data tag, and a gender, age, marital status, etc. in the base data identify a second data tag.

The BRET (Bidirectional Encoder representation from Transformer based) model is a pre-trained language model. The BRET model can process each character in the data to obtain a feature vector of each character.

Since data identified with the first data tag such as academic calendar, profession, income flow, status of holding bank card, social security, etc. can strongly reflect the personal credit information of the applicant, the data identified with the first data tag is determined as strongly related data, while data identified with the second data tag such as gender, age, marital status, etc. cannot strongly reflect the personal credit information of the applicant, and thus, the data identified with the second data tag is determined as weakly related data. And configuring a first weight for the first eigenvector and a second weight for the second eigenvector, wherein the first weight is greater than the second weight. And calculating a first product between the first feature vector and the corresponding first weight, calculating a second product between the second feature vector and the corresponding second weight, and calculating the sum of the products between the first product and the second product to obtain the user portrait.

According to the optional implementation mode, different data labels are identified for the data, different weights are configured based on the different data labels, the user portrait is calculated based on the data identifying the different data labels and the corresponding weights, people who pay for the ability but do not have too many credit history records, such as people who should be graduate, can be concerned about, and therefore the practicability is high, and the application prospect is wide.

The terminal obtains the use date, the use amount and the use types in the limit use data, the use frequency can be calculated according to the use date, the use habit can be determined according to the use types, the limit use rate and the limit overdraft rate can be calculated according to the use amount, and then the use habit, the use frequency, the limit use rate and the limit overdraft rate are spliced to obtain the user behavior preference vector. And inputting the user behavior preference vector into a consumption capability prediction model trained in advance, and predicting the consumption capability of the user through the consumption capability prediction model, so that the future use potential of the user is evaluated.

The terminal obtains the performance date and the credit card liability in the historical credit data, can perform equal frequency binning on the performance date to obtain binning date, can perform card-side binning on the credit card liability to obtain binning liability, and then splices the binning date and the binning liability to obtain a user performance vector. And inputting a user performance vector into the performance capability prediction after pre-training, and predicting the performance capability of the user through the performance capability prediction so as to evaluate the future repayment potential of the user.

The predetermined data service structure may be, for example, sesame credit, Tencent credit, orange credit, etc. The terminal can be preset with a plurality of data service mechanisms, and when responding to the limit application instruction of the applicant, the terminal sends the credit scoring data request of the applicant to the preset data service structure, so that the preset data service structure sends the credit scoring data of the applicant to the terminal. Because different data service organizations have different response speeds when sending credit scoring data of an applicant, generally, the data service organizations with higher response speeds have more authority, the data service organizations with lower response speeds have less authority, different scoring weights are distributed according to the sending time of a preset data service organization, and the third-party credit scoring data is obtained by performing weighted calculation according to the credit scoring data and the corresponding scoring weights.

Wherein the user social data may include: social activity, social density and the like, and the user social data can evaluate the social circle and the interpersonal relationship network of the user.

S13, calculating a risk score based on the user data and the first composite credit score using a long-short term memory network model.

For credit service products, credit risk is strictly controlled, and the phenomenon of delinquent is avoided, so that the benefit of a credit service organization is lost.

The terminal trains the long-term and short-term memory network model in advance according to basic data, limit use data, historical credit data, third-party credit score data, user social data and credit scores of other applicants.

And calculating and inputting the user data and the credit score into a trained long-short term memory network model, and outputting a risk score through the long-short term memory network model.

In an optional embodiment, the method further comprises:

comparing the risk score to a risk score threshold;

when the risk score is determined to be smaller than or equal to the preset risk score threshold, triggering a limit sharing application instruction;

and when the risk score is determined to be larger than the preset risk score threshold value, forbidding triggering the limit sharing application instruction.

And the terminal judges the risk condition of the limit application of the applicant by comparing the risk score with a preset risk score threshold value, so as to judge whether the applicant can return the limit on time. When the risk score is determined to be smaller than or equal to the preset risk score threshold, the applicant is indicated to have lower risk of applying for the quota, and quota sharing application instructions are triggered to allow the applicant to seek quota sharing from other people, so that the quota of the applicant is increased. And when the risk score is determined to be larger than the preset risk score threshold value, indicating that the credit line application risk of the applicant is higher, forbidding triggering a credit line sharing application instruction to forbid the applicant to seek credit line sharing from other people, thereby guaranteeing the credit lines of other people.

For example, assuming that the credit card amount of the applicant is 3000 per month and the remaining credit card amount of the current period is 0, the applicant proposes the amount application 1000, and since the risk score obtained through the long-term and short-term memory network model is greater than the preset risk score threshold, the triggering of the amount sharing application instruction is prohibited, and the benefit of other people and credit service institutions, such as a sharing bicycle, a library, a bank and the like, is guaranteed. If the credit behavior of the applicant is good, the overdraft rate is low, the income is high, and when the requirement of line turnover suddenly occurs, the risk score obtained through the long-short term memory network model is smaller than or equal to the preset risk score threshold value, the line sharing application instruction is triggered, so that the line sharing application is carried out for the user, and the line turnover problem of the applicant is solved. Therefore, the credit service organization can obtain the benefit obtained by using the corresponding quota without waiting for the long auditing time of quota application improvement, the phenomenon of market quota redundancy is reduced, and the utilization rate of resources is improved.

S14, when the risk score is determined to be larger than a preset risk score threshold value, constructing the social network graph of the applicant.

The terminal establishes a social network map with an applicant as a center for the applicant, and determines a plurality of target line sharing users based on the social network map, so that line sharing invitation is sent to the target line sharing users.

obtaining a plurality of contacts of the applicant;

calculating the social relevance of the applicant and each contact;

As shown in fig. 3, an applicant is used as a central node in a social network graph, each contact is used as a network node in the social network graph, a non-directional edge is established between the central node and each network node, and the weight of the edge is the social association degree between the central node and the network node.

The terminal can obtain the social frequency and the social time of the applicant and each contact through the communication record of the call dialed by the operator, the communication record of communication software and the like, so that a social characteristic vector is constructed based on the social frequency and the social time, and the social association degree of the applicant and each contact is calculated by using a pre-trained social association degree calculation model based on the social characteristic vector.

And S15, determining a plurality of target line sharing users based on the social network graph.

and determining the target network nodes as target line sharing users.

The terminal may obtain the user data of the contact, calculate the second composite credit score based on the user data of the contact, and calculate the second composite credit score in the same process as the first composite credit score, for details, refer to step S12 and its related description.

The terminal can pre-train a matching goodness of fit calculation model, input the contact person feature vector into the trained matching goodness of fit calculation model, and output the matching goodness of fit through the trained matching goodness of fit calculation model as the matching goodness of fit between the corresponding contact person and the applicant.

The social association degree in the social network graph is replaced by the matching goodness of fit, so that the social network graph is updated, a target social network graph is obtained, and the weight of the edge between the central node and the network node in the target social network graph is the matching goodness of fit.

In an optional embodiment, the preset search rule may be a contact corresponding to a network node, starting from the central node, whose search path is not more than a preset number (e.g., 5), as the target quota sharing user of the applicant.

And S16, sending a quota sharing application to the target quota sharing users.

The searched target line sharing user is a contact person with more remaining lines, high social association degree and high second comprehensive credit score, and the willingness of the contact person to accept the line sharing application is larger.

The terminal can use the target quota sharing user who receives quota sharing application most quickly as a sharer.

In an optional implementation manner, the terminal can also determine the target line sharing user as a policyholder of the applicant, so that the technical problem that the applicant defaults nobody for guaranteeing can be effectively solved.

receiving the quota shared by the target quota sharing user;

It should be understood that the target quota sharing quota shared by the user is not larger than the application quota.

When the shared quota of a certain target quota sharing user is equal to the application quota, directly receiving the quota shared by the target quota sharing user which is equal to the application quota. When the shared quota of any target quota sharing user is smaller than the application quota, the terminal allocates the quota of the multiple target quota sharing users when the remaining quota of all the target quota sharing users is not enough to be shared by the application person, so that the quota sharing application of the applicant is completed by the target quota sharing users corresponding to the multiple selected target quota sharing users.

In an optional embodiment, the method further comprises: and acquiring a first target matching goodness of fit which is greater than a preset first matching goodness of fit threshold value in the target social network graph, and providing a line sharing reservation function for a contact corresponding to the first target matching goodness of fit.

In practical application, when the credit of the applicant is high and is often not used up, the credit can be invited to share by one or more contacts. The terminal can enable the contact person of the applicant to make the quota reservation by providing a quota sharing reservation function, so that the applicant can plan own quota in advance. Because the first contact corresponding to the first target matching goodness of fit which is greater than the preset first matching goodness of fit threshold value in the target social network graph may have a very close relationship with the applicant, in order to be able to send the quota sharing to the first contact, the terminal may provide the quota sharing reservation function to the contact corresponding to the first target matching goodness of fit, so that the first contact corresponding to the first target matching goodness of fit can send a quota sharing application to the applicant as early as possible, and the applicant can reserve the quota to the first contact.

In an optional embodiment, the method further comprises: obtaining a second target matching goodness of fit which is smaller than a preset second matching goodness of fit threshold value in the target social network graph, displaying a line sharing permission option on a network node corresponding to the second target matching goodness of fit, receiving a determined selection of the applicant in the line sharing permission option, and refusing to receive a line sharing application of a contact corresponding to the determined selection.

Wherein the preset first matching goodness-of-fit threshold is greater than the preset second matching goodness-of-fit threshold.

And in order to avoid receiving the line sharing application of the second contact and disturbing the applicant, a line sharing permission option is displayed on a network node corresponding to the second target matching goodness of fit in the target social network map, so that the applicant can select whether to reject the line sharing application sent by the second contact or not. When the applicant clicks the line sharing authority option, the terminal receives a determination selection instruction of the applicant in the line sharing authority option, so that when a line sharing application for determining to select a corresponding contact is received, the line sharing application for determining to select the corresponding contact is directly intercepted, and the line sharing application for determining to select the corresponding contact is refused to be received.

In an optional embodiment, the method further comprises:

and performing additional interest calculation and revenue distribution according to the risk score.

In order to solve the problem that the excess is overdrawn and the excess is urgently needed to be circulated, the applicant should pay additional interest as the commission fee of the information service organization and the income of the sharer, so that the three parties are benefited and achieve three purposes.

In an alternative embodiment, said performing additional interest calculations and revenue allocations based on said risk score comprises:

calculating the additional interest based on the risk score, the original quota of the applicant and the application quota by using an additional interest calculation model;

and calculating the distribution income of the target amount sharing users corresponding to the plurality of target amounts according to the additional interest and the second comprehensive credit score.

Wherein, the additional interest calculation model can be the following formula: y ═ X1+ X2)/X3, where Y represents additional interest, X1 represents risk score, X2 represents application quota, and X3 represents original quota. Therefore, the higher the risk score is, the larger the application amount is, the smaller the original amount is, and the more interest is added; the lower the risk score, the smaller the application amount, the larger the original amount, and the less interest accrued.

And the terminal calculates the credit score and value of the second comprehensive credit score of the target line sharing users corresponding to the target lines, calculates the ratio of the second comprehensive credit score of the target line sharing users corresponding to each target line to the credit score and value, and obtains the income of the corresponding target line sharing users according to the product of the ratio and the additional interest. The higher the second comprehensive credit score is, the larger the corresponding ratio is, and the higher the corresponding target amount shares the income of the user; the lower the second comprehensive credit score is, the smaller the corresponding ratio is, and the lower the corresponding target amount shares the income of the user.

In the optional implementation mode, additional interest calculation and income distribution are carried out according to the risk scores, the line sharing willingness of the user can be improved, the trust-keeping behavior of the user is stimulated, the credit scores of the user are improved, and the credit service market is perfected.

The terminal can also share the income of the user as the corresponding target amount according to the product of the ratio and the preset proportion of the additional interest.

In an optional embodiment, the method further comprises:

After the target line sharing user shares the line with the applicant, the result shows that the applicant successfully applies for the line, and the terminal acquires credit behaviors of the applicant after the line, wherein the credit behaviors can include whether to return the book on time or whether to pay on time. And if the applicant returns the book or pays back on time, the credit behavior is regarded as the credit-keeping behavior, and if the applicant does not return the book or pay back on time, the credit behavior is regarded as the non-credit-keeping behavior.

And the crediting behavior of the applicant is also taken as the crediting behavior of the target line sharing user, the first comprehensive credit score of the applicant and the second comprehensive credit score of the target line sharing user are respectively updated, and the social association degree of the applicant and the target line sharing user is updated, so that the matching degree of the applicant and the target line sharing user is updated, and further the social network map of the applicant is updated. Therefore, the effect that the target line sharing user guarantees the credit of the applicant is achieved, the credit-keeping behavior of the applicant is promoted, and the benefit of a credit service mechanism is guaranteed.

In an optional embodiment, the terminal may further store line sharing, and when the applicant sends a second line sharing application to the target line sharing user again, the weight of the edge in the social network graph of the applicant is increased, so that the second line sharing application of the applicant is easier to succeed, the computational complexity is reduced, and the risk score is reduced.

In some embodiments, the big data based credit line sharing device 20 may include a plurality of functional modules composed of computer program segments. The computer programs of the various program segments in the big data based credit line sharing apparatus 20 may be stored in the memory of the terminal and executed by at least one processor to perform (see fig. 1 for details) the big data based credit line sharing function.

In this embodiment, the credit line sharing device 20 based on big data may be divided into a plurality of functional modules according to the functions performed by the device. The functional module may include: the system comprises an application response module 201, a first calculation module 202, a second calculation module 203, a map construction module 204, a target determination module 205, a sharing and sending module 206, a limit receiving module 207, a function providing module 208, an interest distribution module 209 and a score updating module 210. The module referred to herein is a series of computer program segments capable of being executed by at least one processor and capable of performing a fixed function and is stored in memory. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.

The application response module 201 is configured to respond to a quota application instruction of an applicant, and obtain user data and a quota application of the applicant.

In an optional implementation manner, the application response module 201 is further configured to:

acquiring account information of the applicant;

The first calculation module 202 is configured to calculate a first composite credit score based on the user data.

In an alternative embodiment, the first calculation module 202 calculating a first composite credit score based on the user data comprises:

computing a user representation based on the base data;

predicting a user consumption capacity based on the credit usage data;

predicting user performance capabilities based on the historical credit data;

extracting a first feature vector of the first data and extracting a second feature vector of the second data by using a BERT pre-training model;

The BERT (Bidirectional Encoder representation from Transformer based) model is a pre-trained language model. The BERT model can process each character in the data to obtain the feature vector of each character. Similarly, the BERT pre-training model may be replaced with the GPT3 model.

The second calculation module 203 is configured to calculate a risk score based on the user data and the first composite credit score using a long-short term memory network model.

In an optional implementation, the second calculating module 203 is further configured to:

comparing the risk score to a risk score threshold;

The graph construction module 204 is configured to construct a social network graph of the applicant when it is determined that the risk score is greater than a preset risk score threshold.

In an alternative embodiment, the graph building module 204 builds the social network graph of the applicant by:

obtaining a plurality of contacts of the applicant;

calculating the social relevance of the applicant and each contact;

The target determination module 205 is configured to determine a plurality of target quota sharing users based on the social network graph.

and determining the target network nodes as target line sharing users.

The sharing sending module 206 is configured to send a share application of the line to the target line sharing users.

In an optional embodiment, after sending the line sharing application to the target line sharing users, the line receiving module 207 is configured to: receiving the quota shared by the target quota sharing user; judging whether the quota shared by any target quota sharing user is equal to the application quota or not; when the shared line of any target line sharing user is equal to the application line, receiving the shared line of any target line sharing user; when the amount shared by any target amount sharing user is smaller than the application amount, selecting a plurality of target amounts from the amounts shared by the target amounts sharing users, so that the sum of the target amounts can be equal to the application amount.

In an optional embodiment, the function providing module 208 is configured to obtain a first target matching goodness of fit in the target social network graph, where the first target matching goodness of fit is greater than a preset first matching goodness of fit threshold, and provide a quota sharing reservation function for a contact corresponding to the first target matching goodness of fit.

In an optional embodiment, the function providing module 208 is further configured to obtain a second target matching goodness of fit in the target social network graph, which is smaller than a preset second matching goodness of fit threshold, display a line sharing permission option on a network node corresponding to the second target matching goodness of fit, receive a determination selection of the applicant in the line sharing permission option, and refuse to receive a line sharing application of a contact corresponding to the determination selection.

In an optional embodiment, the interest allocation module 209 is configured to perform additional interest calculation and revenue allocation according to the risk score.

In an optional embodiment, the interest allocation module 209 performing additional interest calculation and revenue allocation according to the risk score includes:

In an optional embodiment, the score updating module 210 is configured to obtain a credit behavior of the applicant on the target line sharing user's shared line; and updating the first comprehensive credit score of the applicant and the second comprehensive credit score of the target line sharing user according to the credit behavior.

Fig. 4 is a schematic structural diagram of a terminal according to a third embodiment of the present invention. In the preferred embodiment of the present invention, the terminal 3 includes a memory 31, at least one processor 32, at least one communication bus 33, and a transceiver 34. The terminal may comprise a computer device.

It will be appreciated by those skilled in the art that the configuration of the terminal shown in fig. 4 is not limiting to the embodiments of the present invention, and may be a bus-type configuration or a star-type configuration, and the terminal 3 may include more or less hardware or software than those shown, or a different arrangement of components.

In some embodiments, the terminal 3 is a device capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions, and the hardware includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The terminal 3 may further include a client device, which includes, but is not limited to, any electronic product capable of performing human-computer interaction with a client through a keyboard, a mouse, a remote controller, a touch panel, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, and the like.

It should be noted that the terminal 3 is only an example, and other existing or future electronic products, such as those that can be adapted to the present invention, should also be included in the scope of the present invention, and are included herein by reference.

In some embodiments, the memory 31 has stored therein a computer program that, when executed by the at least one processor 32, implements all or part of the steps of the big data based credit line sharing method as described. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

In some embodiments, the at least one processor 32 is a Control Unit (Control Unit) of the terminal 3, connects various components of the entire terminal 3 by using various interfaces and lines, and executes various functions and processes data of the terminal 3 by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31. For example, when the at least one processor 32 executes the computer program stored in the memory, all or part of the steps of the credit line sharing method based on big data according to the embodiment of the present invention are implemented; or all or part of functions of the credit line sharing device based on the big data are realized. The at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips.

In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.

Although not shown, the terminal 3 may further include a power supply (such as a battery) for supplying power to various components, and preferably, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The terminal 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a terminal, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the specification may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A credit line sharing method based on big data is characterized by comprising the following steps:

calculating a first composite credit score based on the user data;

2. The big data-based credit line sharing method of claim 1, wherein the user data comprises basic data, line usage data, historical credit data, third party credit score data, user social data, and the calculating a first composite credit score based on the user data comprises:

computing a user representation based on the base data;

predicting a user consumption capacity based on the credit usage data;

predicting user performance capabilities based on the historical credit data;

3. The big data based credit line sharing method of claim 2, wherein the calculating a user representation based on the base data comprises:

extracting a first feature vector of the first data and extracting a second feature vector of the second data by using a pre-training model;

4. The big data-based credit line sharing method of claim 2, wherein the predicting the user's consumption ability based on the line usage data comprises:

5. The big data-based credit line sharing method of claim 2, wherein the predicting the performance capability of the user based on the historical credit data comprises:

6. The big data-based credit line sharing method as claimed in claim 2, wherein the third party credit score data calculation process comprises:

7. The big-data-based credit line sharing method as claimed in claim 1, wherein the constructing the social network graph of the applicant comprises:

obtaining a plurality of contacts of the applicant;

calculating the social relevance of the applicant and each contact;

8. The big-data-based credit line sharing method as claimed in claim 7, wherein the calculating the social association degree of the applicant with each contact comprises:

9. The big-data-based credit line sharing method of claim 8, wherein the determining a plurality of target line sharing users based on the social network graph comprises:

and determining the target network nodes as target line sharing users.

10. The credit line sharing method based on big data as claimed in claim 9, wherein the preset search rule is that from the central node, contacts with a search path not more than a preset number of network nodes are searched as the target line sharing users of the applicant.

11. The credit line sharing method based on big data as claimed in claim 9, wherein after sending the line sharing application to the plurality of target line sharing users, the method further comprises:

receiving the quota shared by the target quota sharing user;

12. The big data-based credit line sharing method as claimed in claim 9, wherein the method further comprises:

13. The big data-based credit line sharing method according to any one of claims 1 to 12, further comprising:

14. The big data-based credit line sharing method of claim 13, wherein the additional interest calculation model is the following formula: y = (X1+ X2)/X3, wherein Y represents additional interest, X1 represents risk score, X2 represents application quota, and X3 represents original quota.

15. The big data-based credit line sharing method as claimed in claim 14, wherein the method further comprises:

16. The big data-based credit line sharing method as claimed in claim 14, wherein the method further comprises:

acquiring account information of the applicant;

17. The big data-based credit line sharing method as claimed in claim 14, wherein the method further comprises:

and determining the target line sharing user as the applicant's guarantor.

18. A credit line sharing device based on big data, the device comprising:

19. A terminal, characterized in that the terminal comprises a processor, and the processor is used for implementing the credit line sharing method based on big data according to any one of claims 1 to 17 when executing a computer program stored in a memory.

20. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the big data-based credit line sharing method according to any one of claims 1 to 17.