Fraud identification model generation method and system, terminal and storage medium
By building an independent encrypted storage area in the banking system and using blockchain to match and share the risk level of malicious overdraft, the cross-bank joint defense problem of malicious overdraft risk identification and defense of credit card malicious overdraft risk is solved, and the secure sharing of account information of credit card users is realized and tamper-proof, reducing the risk of malicious overdrafts in banks.
Patent Information
- Application Number
- CN202411175993.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-12-17
AI Technical Summary
The existing technology cannot effectively identify and defend against the risk of malicious overdrafts on credit cards, and lacks a cross-bank joint defense mechanism, which makes it difficult to effectively identify and manage credit cards' malicious overdrafts on credit cards.
Build independent encrypted multiple storage areas associated with the repayment date, and use blockchain and third-party regulatory platforms to match and share malicious overdraft risk levels to ensure the security and tamper-proof of credit card users’ account information.
It realizes the sharing and identification of cross-bank malicious overdraft risk information, reduces the risk of malicious overdraft in banks, improves the security of credit card users' accounts, and prevents information leakage and tampering.
Smart Images
Figure CN119151670A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of smart banking technology, and more specifically, to a fraud identification model generation method, system, terminal and storage medium. Background Art
[0002] Malicious credit card overdraft refers to the behavior of the cardholder who, for the purpose of illegal possession, overdraws beyond the prescribed limit or prescribed period, and fails to repay the money after two collection calls from the issuing bank for more than three months. This behavior is not only a breach of contract, and the holder must bear the liability for breach of contract in accordance with the credit card contract, but may also violate the law and bear the corresponding legal liability.
[0003] The identification criteria for malicious credit card overdraft mainly include the following aspects:
[0004] 1. Purpose of illegal possession: The cardholder must have the purpose of illegal possession, that is, he has no intention of repayment but hopes to obtain funds through overdraft.
[0005] 2. Overdraft exceeding the prescribed limit or period: The cardholder must exceed the limit stipulated in the credit card regulations or exceed the overdraft period allowed by the issuing bank.
[0006] 3. Bank collection is ineffective: The issuing bank must make two collection attempts, and the outstanding balance must not be repaid after more than 3 months.
[0007] At present, with the rapid development of China's financial industry, the threshold for applying for credit cards is getting lower and lower. Moreover, with the proliferation of POS machines, the risk of malicious credit card overdrafts has also greatly increased. Credit card issuers simply rely on each bank's own rules to identify and deal with it. There is no mature joint defense mechanism between the industry, and this risk cannot be well defended. There is an urgent need for a fraud identification model generation method, system, terminal and storage medium that can automatically identify this risk. Summary of the invention
[0008] The technical problem to be solved by the present invention is that, in view of the above-mentioned defects of the prior art, a fraud identification model generation method is provided, and a fraud identification model generation system, a fraud identification model generation terminal and a computer-readable storage medium are also provided.
[0009] The technical solution adopted by the present invention to solve its technical problem is:
[0010] A fraud identification model generation method is constructed, which includes the following steps:
[0011] Multiple independently encrypted storage areas associated with repayment dates are built within the banking system, and each of the multiple storage areas corresponds to a different malicious overdraft risk level;
[0012] Manage credit card user accounts and call repayment data, back up repayment data and store it in the corresponding storage area;
[0013] Each time the repayment data is backed up and stored, a matching and association adjustment of the storage area is performed according to the repayment date;
[0014] The data of the designated malicious overdraft risk level is stored on the blockchain regularly or irregularly, and the storage key is saved by the third-party supervision platform;
[0015] The third-party supervision platform regularly or irregularly accesses the data in the blockchain through the storage key to match whether there is the same credit card user information;
[0016] If the match is successful, the malicious overdraft risk level is compared, and according to the higher malicious overdraft risk level after comparison, the storage area where the repayment data of the credit card user account of each bank is located is adjusted accordingly;
[0017] If the match fails, no action is taken.
[0018] In the fraud identification model generation method of the present invention, the multiple storage areas respectively correspond to different malicious overdraft risk levels and adopt:
[0019] There are five risk levels: no risk, low risk, medium risk, high risk and overdraft, and they correspond to five repayment date ranges from low to high;
[0020] Each risk level corresponds to a different storage area.
[0021] In the fraud identification model generation method described in the present invention, each bank system can only access the storage area corresponding to all its credit card user accounts; the storage area and the blockchain are supervised by a third-party supervision platform to ensure that the secrets of all credit card user accounts of each bank are not leaked or stolen by other banks.
[0022] The fraud identification model generation method of the present invention further comprises the steps of:
[0023] Each bank regularly or irregularly checks the malicious overdraft risk level and takes action against the credit card user accounts in the storage area that reach the malicious overdraft risk level.
[0024] A fraud identification model generation system, wherein the system includes a plurality of independently encrypted storage areas associated with repayment dates, a third-party supervision platform, and a blockchain built in a banking system;
[0025] The plurality of storage areas correspond to different malicious overdraft risk levels respectively; the bank system manages the credit card user account and calls the repayment data, backs up the repayment data and stores it in the corresponding storage area; each time the repayment data is backed up and stored, the matching association of the storage area is adjusted according to the repayment date; the data of the designated malicious overdraft risk level is stored on the blockchain regularly or irregularly, and the storage key is saved by the third-party supervision platform;
[0026] The third-party supervision platform accesses the data in the blockchain through the storage key at regular or irregular intervals to match whether there is the same credit card user information; if the match is successful, the malicious overdraft risk level is compared, and according to the higher malicious overdraft risk level after the comparison, the storage area where the repayment data of the credit card user account of each bank is located is adjusted accordingly; if the match fails, no action is taken.
[0027] The fraud identification model generation system described in the present invention, wherein the malicious overdraft risk level includes five risk levels: no risk, low risk, medium risk, high risk and overdraft, and corresponds to five repayment date time ranges from low to high; each risk level corresponds to a different storage area.
[0028] In the fraud identification model generation system described in the present invention, each bank system can only access the storage area corresponding to all its credit card user accounts; the storage area and the blockchain are supervised by a third-party supervision platform to ensure that the secrets of all credit card user accounts of each bank are not leaked or stolen by other banks.
[0029] In the fraud identification model generation system of the present invention, each bank system checks the malicious overdraft risk level regularly or irregularly, and processes the credit card user accounts in the storage area that reach the malicious overdraft risk level.
[0030] A fraud identification model generation terminal comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
[0031] A computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the above method when executed by a processor.
[0032] The beneficial effect of the present invention is that: applying the method of the present application can not only break the regional restrictions between banks and realize the sharing of malicious overdraft risk information, but also prevent information from being tampered with through blockchain, and use a third-party supervision system to ensure that credit card user account information is not stolen by other banks except this bank. At the same time, the combination of the above three means constructs a set of fraud identification models that can truly achieve the purpose of joint defense, which can effectively reduce the risk of malicious overdraft of banks and improve security. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be further described below in conjunction with the accompanying drawings and embodiments. The drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work:
[0034] Figure 1 is a flow chart of a fraud identification model generation method according to a preferred embodiment of the present invention;
[0035] Figure 2 It is a principle block diagram of a fraud identification model generation system according to a preferred embodiment of the present invention. DETAILED DESCRIPTION
[0036] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the following will be described clearly and completely in combination with the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are partial embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of the present invention.
[0037] The fraud identification model generation method of the preferred embodiment of the present invention is as follows: Figure 1 As shown, the following steps are included:
[0038] S01: Multiple independently encrypted storage areas associated with repayment dates are constructed within the bank system, and the multiple storage areas correspond to different malicious overdraft risk levels;
[0039] S02: Manage the credit card user account and call the repayment data, back up the repayment data and store it in the corresponding storage area;
[0040] S03: Each time the repayment data is backed up and stored, a matching association adjustment is performed in the storage area according to the repayment date;
[0041] S04: Data of designated malicious overdraft risk levels are stored on the blockchain regularly or irregularly, and the storage key is saved by a third-party supervision platform;
[0042] S05: The third-party supervision platform periodically or irregularly accesses the data in the blockchain through the storage key to match whether there is the same credit card user information;
[0043] S06: If the match is successful, compare the malicious overdraft risk level, and adjust the storage area where the repayment data of the credit card user account of each bank is located according to the higher malicious overdraft risk level after comparison; if the match fails, no action is taken;
[0044] The application of the method and approach of this application can not only break the regional restrictions between banks and realize the sharing of malicious overdraft risk information, but also prevent information tampering through blockchain, and use a third-party supervision system to ensure that credit card user account information is not stolen by other banks except this bank. At the same time, the combination of the above three means constructs a fraud identification model that can truly achieve the purpose of joint defense, which can effectively reduce the risk of malicious overdraft of banks and improve security.
[0045] Preferably, multiple storage areas correspond to different malicious overdraft risk levels respectively and adopt:
[0046] There are five risk levels: no risk, low risk, medium risk, high risk and overdraft, and they correspond to five repayment date ranges from low to high; each risk level corresponds to a different storage area;
[0047] It should be noted that this level area can be increased or decreased according to the bank's own situation. During subsequent matching, time matching can be carried out according to the specific repayment time (or non-repayment time). Different standards of different banks can be matched smoothly.
[0048] Preferably, each bank system can only access the storage area corresponding to all its credit card user accounts; the storage area and the blockchain are supervised by a third-party supervision platform to ensure that the secrets of all credit card user accounts of each bank are not leaked or stolen by other banks.
[0049] Preferably, the method further comprises the steps of:
[0050] Each bank regularly or irregularly checks the malicious overdraft risk level and takes action against the credit card user accounts in the storage area that reach the malicious overdraft risk level.
[0051] A fraud identification model generation system, such as Figure 2 As shown, the system includes multiple independently encrypted storage areas 100 associated with repayment dates built in the banking system, a third-party supervision platform 101, and a blockchain 102;
[0052] Multiple storage areas 100 correspond to different malicious overdraft risk levels respectively; the bank system manages the credit card user account and calls the repayment data, backs up the repayment data and stores it in the corresponding storage area; each time the repayment data is backed up and stored, the matching association of the storage area is adjusted according to the repayment date; the data of the designated malicious overdraft risk level is stored on the blockchain regularly or irregularly, and the storage key is saved by the third-party supervision platform;
[0053] The third-party supervision platform 101 accesses the data in the blockchain 102 through the storage key at regular or irregular intervals to check whether there is the same credit card user information; if the match is successful, the malicious overdraft risk level is compared, and according to the higher malicious overdraft risk level after the comparison, the storage area where the repayment data of the credit card user account of each bank is located is adjusted accordingly; if the match fails, no action is taken;
[0054] The application of the system of this application can not only break the regional restrictions between banks and realize the sharing of malicious overdraft risk information, but also prevent information from being tampered with through blockchain, and use a third-party supervision system to ensure that credit card user account information is not stolen by other banks except this bank. At the same time, the combination of the above three means constructs a fraud identification model that can truly achieve the purpose of joint defense, which can effectively reduce the risk of malicious overdraft of banks and improve security.
[0055] Preferably, the malicious overdraft risk level includes five risk levels: no risk, low risk, medium risk, high risk, and overdraft, and corresponds to five repayment date time ranges from low to high; each risk level corresponds to a different storage area;
[0056] It should be noted that this level area can be increased or decreased according to the bank's own situation. During subsequent matching, time matching can be carried out according to the specific repayment time (or non-repayment time). Different standards of different banks can be matched smoothly.
[0057] Preferably, each bank system can only access the storage area corresponding to all its credit card user accounts; the storage area and the blockchain are supervised by a third-party supervision platform to ensure that the secrets of all credit card user accounts of each bank are not leaked or stolen by other banks.
[0058] Preferably, each bank system checks the malicious overdraft risk level regularly or irregularly, and processes the credit card user accounts in the storage area that reach the malicious overdraft risk level.
[0059] A fraud identification model generation terminal comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
[0060] A computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the above method when executed by a processor.
[0061] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all these improvements and changes should fall within the scope of protection of the appended claims of the present invention.
Claims
1. A fraud identification model generation method, characterized in that: The following steps are involved: Multiple independently encrypted storage areas associated with repayment dates are built within the banking system, and each of the multiple storage areas corresponds to a different malicious overdraft risk level; Manage credit card user accounts and call repayment data, back up repayment data and store it in the corresponding storage area; Each time the repayment data is backed up and stored, a matching and association adjustment of the storage area is performed according to the repayment date; The data of the designated malicious overdraft risk level is stored on the blockchain regularly or irregularly, and the storage key is saved by the third-party supervision platform; The third-party supervision platform regularly or irregularly accesses the data in the blockchain through the storage key to match whether there is the same credit card user information; If the match is successful, the malicious overdraft risk level is compared, and according to the higher malicious overdraft risk level after comparison, the storage area where the repayment data of the credit card user account of each bank is located is adjusted accordingly; If the match fails, no action is taken.
2. The fraud identification model generation method according to claim 1, characterized in that: The multiple storage areas correspond to different malicious overdraft risk levels respectively and adopt: There are five risk levels: no risk, low risk, medium risk, high risk and overdraft, and they correspond to five repayment date ranges from low to high; Each risk level corresponds to a different storage area.
3. The fraud identification model generation method according to claim 2, characterized in that: Each bank system can only access the storage area corresponding to all its credit card cardholder accounts; the storage area and the blockchain are supervised by a third-party supervision platform to ensure that the secrets of all credit card cardholder accounts of each bank are not leaked or stolen by other banks.
4. The fraud identification model generation method according to claim 1, characterized in that: The method further comprises the steps of: Each bank regularly or irregularly checks the malicious overdraft risk level and takes action against the credit card user accounts in the storage area that reach the malicious overdraft risk level.
5. A fraud identification model generation system, characterized in that: The system includes multiple independently encrypted storage areas associated with repayment dates, a third-party supervision platform and a blockchain built in a banking system; The plurality of storage areas correspond to different malicious overdraft risk levels respectively; The bank system manages the credit card user's account and calls the repayment data, backs up the repayment data and stores it in the corresponding storage area; each time the repayment data is backed up and stored, the matching association adjustment of the storage area is performed according to the repayment date; the data of the designated malicious overdraft risk level is stored on the blockchain regularly or irregularly, and the storage key is saved by the third-party supervision platform; The third-party supervision platform accesses the data in the blockchain through the storage key at regular or irregular intervals to match whether there is the same credit card user information; if the match is successful, the malicious overdraft risk level is compared, and according to the higher malicious overdraft risk level after the comparison, the storage area where the repayment data of the credit card user account of each bank is located is adjusted accordingly; if the match fails, no action is taken.
6. The fraud identification model generation system according to claim 5, characterized in that: The malicious overdraft risk levels include five risk levels: no risk, low risk, medium risk, high risk and overdraft, and correspond to five repayment date time ranges from low to high respectively; each risk level corresponds to a different storage area.
7. The fraud identification model generation system according to claim 6, characterized in that: Each bank system can only access the storage area corresponding to all its credit card cardholder accounts; the storage area and the blockchain are supervised by a third-party supervision platform to ensure that the secrets of all credit card cardholder accounts of each bank are not leaked or stolen by other banks.
8. The fraud identification model generation system according to claim 5, characterized in that: Each bank system checks the malicious overdraft risk level regularly or irregularly, and handles the credit card user accounts in the storage area that reach the malicious overdraft risk level.
9. A fraud identification model generation terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.