Intelligent cloud watch system for bank service library

Abstract

The application relates to the field of bank service library management, and particularly discloses an intelligent cloud value keeping system for a bank service library. The system collects the time, geographical position, device type, identifier, identity verification mode, identity verification failure times, accessed information subitems and access duration of a bank customer logging into a bank platform, and collects the time, geographical position, frequency, amount, transaction type, identity verification failure times and operation duration of the bank customer in bank platform transaction, evaluates whether the bank customer logging into the bank platform and transaction exist risks from multiple indexes, thereby perfecting the risk evaluation system of the bank customer logging into the bank platform and transaction, avoiding supervision loopholes, and improving the accuracy and reliability of the account login and transaction risk evaluation; meanwhile, the historical login and transaction habits of the bank customer are taken as references, the credibility of the result of the customer login and transaction risk evaluation is improved.

Description

Technical Field

[0001] The present invention relates to the field of banking business database management, in particular to an intelligent cloud on-call system for banking business databases. Background Art

[0002] Banking business database on-duty refers to the process of real-time monitoring and maintenance of the banking business database to ensure its stable operation and timely response to any abnormal situations. It plays a vital role in banking business continuity and risk management.

[0003] Among them, bank customer data security is an important aspect of bank business database duty. Existing methods identify security risks and conduct early warnings and processing by monitoring bank customers' login and transaction behaviors on bank platforms. However, the existing methods have the following shortcomings: On the one hand, the indicators used by existing methods to monitor bank customers' logins and transactions on bank platforms are not comprehensive enough and the coverage is not wide enough, which makes the risk assessment system incomplete and prone to regulatory loopholes, and thus makes it difficult to determine whether there are security risks when bank customers log in and trade on bank platforms. Accurate and reliable.

[0004] On the other hand, when existing methods judge whether bank customers' login and transaction behaviors on bank platforms are risky, they only use the relevant data of the set login and transaction behaviors as evaluation criteria, and then draw conclusions. They do not take into account the historical behavioral habits of bank customers and use the customers' historical login and transaction behaviors as a reference. As a result, the results of the existing methods in evaluating whether customer login and transaction behaviors are risky are not credible and are prone to misjudgment. Summary of the Invention

[0005] In response to the above problems, the present invention proposes an intelligent cloud-based on-call system for a banking business database to implement the management function of the banking business database.

[0006] The technical solution adopted by the present invention to solve its technical problems is: the present invention provides an intelligent cloud on-duty system for a bank business database, including: a bank customer login basic information collection module, a bank customer login risk analysis module, a bank customer transaction details information collection module, a bank customer transaction risk analysis module, a bank business database on-duty feedback module and a database.

[0007] The bank customer login basic information collection module is connected to the bank customer login risk analysis module, the bank customer transaction details information collection module is connected to the bank customer transaction risk analysis module, the bank business database duty feedback module is respectively connected to the bank customer login risk analysis module and the bank customer transaction risk analysis module, and the database is respectively connected to the bank customer login risk analysis module and the bank customer transaction risk analysis module.

[0008] Bank customer login basic information collection module: used to collect the basic information of bank customers currently logging into the banking platform, including login time, login location, device type and identifier, authentication method, number of authentication failures, various information sub-items accessed, and access duration.

[0009] Bank customer login risk analysis module: used to analyze the first risk coefficient, second risk coefficient and third risk coefficient of the bank customer's current login to the bank platform based on the basic information of the bank customer currently logging into the bank platform, and further analyze the risk index of the bank customer's current login to the bank platform.

[0010] Bank customer transaction details information collection module: used to collect detailed information of bank customers' current transactions on the bank platform, including transaction time, transaction location, transaction frequency, transaction amount, transaction type, number of identity verification failures and transaction operation duration.

[0011] Bank customer transaction risk analysis module: used to analyze the first risk coefficient, second risk coefficient and third risk coefficient of bank customers' current transactions on the bank platform based on the detailed information of bank customers' current transactions on the bank platform, and further analyze the risk index of bank customers' current transactions on the bank platform.

[0012] Bank business database duty feedback module: used to judge whether there are security risks in the bank customer's current login and current transactions based on the risk index of the bank customer's current login to the bank platform and the risk index of the bank customer's current transactions on the bank platform. If there are security risks, an early warning will be issued and feedback will be given to the bank's information security department.

[0013] Database: used to store bank customers' historical login basic information and historical transaction details on the bank platform.

[0014] Compared with the prior art, the intelligent cloud duty system for the banking business library described in the present invention has the following beneficial effects: 1. The present invention collects the time, geographic location, device type and identifier, authentication method, number of authentication failures, various information sub-items accessed and access duration when the bank customer logs into the banking platform, and evaluates whether there is a risk in the bank customer logging into the banking platform from multiple indicators, thereby improving the bank customer login risk assessment system, avoiding regulatory loopholes, and thus improving the accuracy and reliability of account login risk assessment.

[0015] 2. The present invention collects the time, geographic location, frequency, amount, transaction type, number of identity verification failures and operation duration of bank customers' transactions on the bank platform, and evaluates whether there are risks in bank customers' transactions on the bank platform from multiple indicators, thereby improving the bank customer transaction risk assessment system, avoiding regulatory loopholes, and improving the accuracy and reliability of account transaction risk assessment.

[0016] 3. When judging whether a bank customer's login behavior and transaction behavior on the bank platform are risky, the present invention takes into account the bank customer's historical login and transaction habits and uses them as a reference, thereby improving the credibility of the results of assessing the customer's login and transaction risks and avoiding misjudgments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 This is a system module connection diagram of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0020] See also Figure 1 As shown, the present invention provides an intelligent cloud on-duty system for a banking business library, comprising a bank customer login basic information collection module, a bank customer login risk analysis module, a bank customer transaction details information collection module, a bank customer transaction risk analysis module, a banking business library on-duty feedback module and a database.

[0021] The bank customer login basic information collection module is connected to the bank customer login risk analysis module, the bank customer transaction details information collection module is connected to the bank customer transaction risk analysis module, the bank business database duty feedback module is respectively connected to the bank customer login risk analysis module and the bank customer transaction risk analysis module, and the database is respectively connected to the bank customer login risk analysis module and the bank customer transaction risk analysis module.

[0022] The bank customer login basic information collection module is used to collect the basic information of the bank customer currently logging into the bank platform, where the basic information includes login time, login geographical location, device type and identifier, identity authentication method, number of identity authentication failures, various information sub-items accessed and access duration.

[0023] As a preferred option, the banking platform includes but is not limited to: an internet banking platform and a mobile banking platform. The internet banking platform allows customers to conduct account inquiries, transfers, payments and other operations through the Internet, and the mobile banking platform provides mobile applications or mobile websites so that customers can perform banking operations on mobile devices.

[0024] The bank customer login risk analysis module is used to analyze the first risk coefficient, second risk coefficient and third risk coefficient of the bank customer's current login to the bank platform based on the basic information of the bank customer currently logging into the bank platform, and further analyze the risk index of the bank customer's current login to the bank platform.

[0025] Furthermore, the specific working process of the bank customer login risk analysis module includes: S1: extracting the basic information of the bank customer's historical login on the bank platform stored in the database, obtaining the login time of each historical login of the bank customer on the bank platform, and analyzing the login tendency ratio coefficient of each time period of a single day.

[0026] As an optimal solution, the login tendency ratio coefficient of each time period of a single day is analyzed. The specific method is: according to the login time of each historical login of the bank customer on the bank platform, the single day is divided into each time period according to the preset principle, the historical login number corresponding to each time period of a single day is counted, and the historical login number corresponding to each time period of a single day is divided by the total number of historical logins to obtain the login tendency ratio coefficient of each time period of a single day.

[0027] In a specific embodiment, a single day is divided into time periods according to a preset principle of equal duration.

[0028] According to the current login time of the bank customer logging into the bank platform, the login tendency ratio coefficient of the time period in which the current login time of the bank customer logging into the bank platform falls is obtained by screening, and is recorded as α.

[0029] S2: Obtain a set of geographical locations commonly used by bank customers to log in.

[0030] As a preferred solution, the basic information of historical logins of bank customers on the bank platform stored in the database is extracted to obtain the geographical locations of each historical login of the bank customer on the bank platform, and the geographical locations commonly used by bank customers for login are summarized.

[0031] As a preferred solution, the geographical location may be an IP address or GPS coordinates.

[0032] The current login geographical location of the bank customer logging into the bank platform is compared with a set of geographical locations commonly used by the bank customer to log in, and it is determined whether the current login geographical location of the bank customer logging into the bank platform is a common login geographical location or an uncommon login geographical location.

[0033] As a preferred solution, if the current geographical location of the bank customer logging into the bank platform does not belong to the set of geographical locations commonly used by bank customers for login, the current geographical location of the bank customer logging into the bank platform will be recorded as an uncommon geographical location; otherwise, the current geographical location of the bank customer logging into the bank platform will be recorded as a common geographical location.

[0034] Set risk factors corresponding to uncommon login geographical locations and common login geographical locations, filter the risk factor corresponding to the geographical location where the bank customer currently logs into the bank platform, and record it as β.

[0035] S3: Obtain the device types and identifiers commonly used by bank customers to log in.

[0036] As a preferred solution, the basic information of the bank customers' historical logins on the bank platform stored in the database is extracted to obtain the types and identifiers of the devices used by the bank customers for each historical login on the bank platform, and the types and identifiers of the devices commonly used by the bank customers for login are summarized.

[0037] As a preferred solution, the types of devices used include but are not limited to: mobile phones, computers, tablets, etc.

[0038] As a preferred solution, the device identifier used includes but is not limited to: MAC address, IMEI number, etc.

[0039] The device type and identifier currently used by the bank customer to log in to the bank platform are compared with the device types and identifiers commonly used by the bank customer to log in, and the risk factor corresponding to the device currently used by the bank customer to log in to the bank platform is analyzed and recorded as γ.

[0040] As a preferred solution, the risk factors corresponding to the device currently used by the bank customer to log in to the bank platform are analyzed. The specific method is: compare the type and identifier of the device currently used by the bank customer to log in to the bank platform with the types and identifiers of devices commonly used by the bank customer to log in. If the type and identifier of the device currently used by the bank customer to log in to the bank platform are consistent with a certain device type and identifier commonly used by the bank customer to log in, then the device currently used by the bank customer to log in to the bank platform is recorded as a commonly used login device. If the type and identifier of the device currently used by the bank customer to log in to the bank platform are inconsistent with all the types and identifiers of devices commonly used by the bank customer to log in, then the device currently used by the bank customer to log in to the bank platform is recorded as an uncommon login device.

[0041] Set risk factors corresponding to infrequently used login devices and frequently used login devices, and filter risk factors corresponding to the devices currently used by bank customers to log in to the banking platform.

[0042] S4: By analyzing the formula The first risk coefficient φ1 of the bank customer currently logging into the bank platform is obtained, where b1, b2, and b3 represent the weights of the preset login time, login geographical location, and login device, respectively, and b1+b2+b3=1.

[0043] Furthermore, the specific working process of the bank customer login risk analysis module also includes: obtaining a set of identity authentication methods commonly used by bank customers for login.

[0044] As a preferred solution, the basic information of historical logins of bank customers on the bank platform stored in the database is extracted to obtain the identity authentication methods of each historical login of the bank customer on the bank platform, and a set of identity authentication methods commonly used by bank customers for login is summarized.

[0045] As a preferred solution, identity authentication methods include but are not limited to: passwords, one-time verification codes such as SMS verification codes and email verification codes, biometrics such as fingerprint recognition, face recognition, and iris scanning, etc.

[0046] Compare the bank customer's current authentication method for logging into the bank platform with the set of commonly used identity methods for bank customers to log in, analyze the risk factor corresponding to the bank customer's current authentication method for logging into the bank platform, and record it as ε1.

[0047] As a preferred solution, the risk factors corresponding to the identity verification method currently used by bank customers to log into the bank platform are analyzed. The specific method is: the identity verification method currently used by bank customers to log into the bank platform is compared with the set of identity verification methods commonly used by bank customers to log in. If the identity verification method currently used by the bank customer to log into the bank platform does not belong to the set of identity verification methods commonly used by bank customers to log in, the identity verification method currently used by the bank customer to log into the bank platform is recorded as an uncommon identity verification method. Otherwise, the identity verification method currently used by the bank customer to log into the bank platform is recorded as a common identity verification method.

[0048] Set risk factors corresponding to uncommon and common authentication methods, and filter the risk factors corresponding to the authentication methods currently used by bank customers to log into the banking platform.

[0049] Set the security levels of various identity authentication methods and the risk factors corresponding to each security level, and screen the risk factor corresponding to the security level of the identity authentication method currently used by bank customers to log into the bank platform, which is recorded as ε2.

[0050] The number of identity authentication failures of the bank customer currently logging into the bank platform is recorded as c.

[0051] By analyzing the formula φ2=(ε1+ε2)*(1+c*δ Δc ) to obtain the second risk coefficient φ2 of the bank customer currently logging into the bank platform, where δ Δc Indicates the impact factor corresponding to the preset number of unit login identity authentication failures.

[0052] Furthermore, the specific working process of the bank customer login risk analysis module also includes: D1: obtaining a set of information sub-items frequently accessed by bank customers during login.

[0053] As a preferred solution, the basic historical login information of bank customers on the bank platform stored in the database is extracted to obtain the information sub-items that the bank customers visited during each historical login on the bank platform, and the information sub-items that the bank customers frequently visit are summarized to obtain a set of information sub-items.

[0054] Compare each information sub-item currently accessed by the bank customer when logging into the bank platform with the set of information sub-items frequently accessed by the bank customer when logging into the bank platform, and obtain the number of non-commonly accessed information sub-items currently accessed by the bank customer when logging into the bank platform, which is recorded as d1.

[0055] As a preferred solution, the number of information sub-items that the bank customer currently accesses when logging into the bank platform and that do not belong to the set of information sub-items that the bank customer frequently accesses when logging into the bank platform is recorded as the number of non-commonly accessed information sub-items that the bank customer currently accesses when logging into the bank platform.

[0056] D2: Set a set of sensitive information sub-items in the banking platform, compare each information sub-item currently accessed by the bank customer logging into the banking platform with the set of sensitive information sub-items, and filter the number of sensitive information sub-items currently accessed by the bank customer logging into the banking platform, which is recorded as d2.

[0057] D3: The duration of the bank customer's current login to the bank platform is recorded as t.

[0058] Get the average access time of bank customers' historical single logins and record it as t 均 .

[0059] As an optimal solution, the basic information of historical logins of bank customers on the bank platform stored in the database is extracted to obtain the access duration of each historical login of the bank customer on the bank platform, and further obtain the average access duration of each historical single login of the bank customer.

[0060] D4: By analyzing the formula Get the third risk coefficient φ3 of the bank customer currently logging into the bank platform, where They respectively represent the impact factors of the preset number of unit non-habitually accessed information sub-items and the number of unit sensitive information sub-items.

[0061] Furthermore, the specific working process of the bank customer login risk analysis module also includes: calculating the weighted average of the first risk coefficient, the second risk coefficient and the third risk coefficient of the bank customer currently logging into the bank platform to obtain the risk index of the bank customer currently logging into the bank platform.

[0062] As a preferred solution, the weights of the first risk coefficient, the second risk coefficient and the third risk coefficient of the bank customer currently logging into the bank platform are set values, and the cumulative sum is 1.

[0063] It should be noted that the present invention collects the time, geographic location, device type and identifier, identity authentication method, number of identity authentication failures, various information sub-items accessed and access duration when the bank customer logs into the bank platform, and evaluates whether there is a risk when the bank customer logs into the bank platform from multiple indicators, thereby improving the bank customer login risk assessment system, avoiding regulatory loopholes, and thus improving the accuracy and reliability of account login risk assessment.

[0064] The bank customer transaction details information collection module is used to collect detailed information of bank customers' current transactions on the bank platform, where the detailed information includes transaction time, transaction location, transaction frequency, transaction amount, transaction type, number of identity authentication failures and transaction operation duration.

[0065] As a preferred solution, the transaction frequency of the bank customer's current transactions on the bank platform is obtained. The specific method is: obtain the interval between the bank customer's current transaction on the bank platform and the last transaction, and perform the inverse calculation to obtain the transaction frequency of the bank customer's current transactions on the bank platform.

[0066] The bank customer transaction risk analysis module is used to analyze the first risk coefficient, second risk coefficient and third risk coefficient of the bank customer's current transactions on the bank platform based on the detailed information of the bank customer's current transactions on the bank platform, and further analyze the risk index of the bank customer's current transactions on the bank platform.

[0067] Furthermore, the specific working process of the bank customer transaction risk analysis module includes: F1: extracting the historical transaction details of the bank customer on the bank platform stored in the database, obtaining the transaction time of each historical transaction of the bank customer on the bank platform, dividing the single day into time periods according to preset principles, and further counting the number of historical transactions corresponding to each time period of the single day.

[0068] According to the transaction time of the bank customer's current transaction on the bank platform, the number of historical transactions corresponding to the time period of the transaction time of the bank customer's current transaction on the bank platform is filtered and recorded as q.

[0069] F2: Gets a set of geographical locations commonly used by bank customers for transactions.

[0070] As a preferred solution, the historical transaction details of bank customers on the bank platform stored in the database are extracted to obtain the transaction geographical locations of each historical transaction of the bank customer on the bank platform, and the geographical locations commonly used by bank customers for transactions are summarized.

[0071] The geographical location of the bank customer's current transactions on the bank platform is compared with the set of geographical locations commonly used by bank customers for transactions, and the risk factor corresponding to the geographical location of the bank customer's current transactions on the bank platform is analyzed and recorded as η.

[0072] As a preferred solution, the risk factors corresponding to the bank customer's current transaction geographical location on the bank platform are analyzed. The specific method is: compare the bank customer's current transaction geographical location on the bank platform with the set of geographical locations commonly used by the bank customer for transactions. If the bank customer's current transaction geographical location on the bank platform does not belong to the set of geographical locations commonly used for transactions, then the bank customer's current transaction geographical location on the bank platform is recorded as an uncommon transaction geographical location; otherwise, the bank customer's current transaction geographical location on the bank platform is recorded as a commonly used transaction geographical location.

[0073] Set risk factors corresponding to uncommon transaction locations and common transaction locations, and filter risk factors corresponding to the transaction locations of bank customers currently trading on the bank platform.

[0074] F3: By analyzing the formula The first risk coefficient κ1 of the bank customer's current transaction on the bank platform is obtained, where q0 represents the threshold value of the number of historical transactions corresponding to the time period of the transaction moment.

[0075] Furthermore, the specific working process of the bank customer transaction risk analysis module also includes: G1: obtaining the average transaction frequency of the bank customer's historical single transactions, which is recorded as f 均 .

[0076] As an optimal solution, the historical transaction details of bank customers on the bank platform stored in the database are extracted to obtain the transaction frequency of each historical transaction of the bank customer on the bank platform, and the average value is calculated to obtain the average transaction frequency of each historical single transaction of the bank customer.

[0077] G2: Get the average transaction amount of a bank customer's historical single transaction and record it as p 均 .

[0078] As a preferred solution, the historical transaction details of bank customers on the bank platform stored in the database are extracted to obtain the transaction amounts of each historical transaction of the bank customer on the bank platform, and the average value is calculated to obtain the average transaction amount of each historical single transaction of the bank customer.

[0079] As a preferred option, large transactions may carry higher risks than small transactions.

[0080] G3: Gets a set of transaction types commonly used by bank customers.

[0081] As a preferred solution, the historical transaction details of bank customers on the bank platform stored in the database are extracted to obtain the transaction types of each historical transaction of the bank customer on the bank platform, and the transaction types commonly used by the bank customer are summarized to obtain a set of transaction types.

[0082] As a preferred solution, transaction types include but are not limited to: deposits, withdrawals, transfers, payments, etc.

[0083] Compare the transaction types currently traded by bank customers on the bank platform with the set of transaction types commonly used by bank customers, analyze the risk factors corresponding to the transaction types currently traded by bank customers on the bank platform, and record them as λ1.

[0084] Set the hidden danger factors corresponding to various transaction types, filter the hidden danger factors corresponding to the transaction types currently traded by bank customers on the bank platform, and record them as λ2.

[0085] As a preferred solution, the risk factors corresponding to the transaction types currently traded by bank customers on the bank platform are analyzed. The specific method is: compare the transaction types currently traded by bank customers on the bank platform with the set of transaction types commonly used by bank customers. If the transaction type currently traded by the bank customer on the bank platform does not belong to the set of transaction types commonly used by the bank customer, then the transaction type currently traded by the bank customer on the bank platform is recorded as an uncommon transaction type; otherwise, the transaction type currently traded by the bank customer on the bank platform is recorded as a common transaction type.

[0086] Set risk factors corresponding to uncommon and common transaction types, and filter the risk factors corresponding to the transaction types currently traded by bank customers on the bank platform.

[0087] G4: By analyzing the formula The second risk coefficient κ2 of the bank customer's current transactions on the bank platform is obtained, where e represents a natural constant, and f and p represent the transaction frequency and transaction amount of the bank customer's current transactions on the bank platform, respectively.

[0088] Furthermore, the specific working process of the bank customer transaction risk analysis module also includes: H1: the number of identity authentication failures and transaction operation duration of the bank customer's current transactions on the bank platform are recorded as n and t' respectively.

[0089] H2: Obtain the reference operation time of the bank customer's current transaction on the bank platform, and record it as t′ 参 .

[0090] As an optimal solution, the historical transaction details of bank customers on the bank platform stored in the database are extracted to obtain the average operation time of various types of transactions conducted by bank customers on the bank platform in the past, and the average operation time is recorded as the reference operation time for various types of transactions. According to the transaction type currently conducted by the bank customer on the bank platform, the reference operation time of the bank customer's current transactions on the bank platform is screened.

[0091] H3: Obtain the credit score level of bank customers from credit rating agencies, set the credit score impact factor corresponding to each credit score level, screen and obtain the credit score impact factor of bank customers, and record it as μ.

[0092] As a preference, bank customers with lower credit scores may be considered higher risk.

[0093] H4: By analyzing the formula Get the third risk coefficient κ3 of the bank customer's current transaction on the bank platform, where σ ΔnIt represents the impact factor corresponding to the preset number of identity verification failures per unit transaction, and Δκ3 represents the compensation amount of the third risk coefficient of the preset bank customer's current transactions on the bank platform.

[0094] Furthermore, the specific working process of the bank customer transaction risk analysis module also includes: calculating the weighted average of the first risk coefficient, the second risk coefficient and the third risk coefficient of the bank customer's current transactions on the bank platform to obtain the risk index of the bank customer's current transactions on the bank platform.

[0095] As a preferred solution, the weights of the first risk coefficient, the second risk coefficient and the third risk coefficient of the bank customer's current transactions on the bank platform are set values, and the cumulative sum is 1.

[0096] It should be noted that the present invention collects the time, geographic location, frequency, amount, transaction type, number of identity verification failures and operation duration of bank customers' transactions on the bank platform, and evaluates whether there are risks in bank customers' transactions on the bank platform from multiple indicators, thereby improving the bank customer transaction risk assessment system, avoiding regulatory loopholes, and thus improving the accuracy and reliability of account transaction risk assessment.

[0097] The bank business database on-duty feedback module is used to determine whether there are security risks in the bank customer's current login and current transactions based on the risk index of the bank customer's current login to the bank platform and the risk index of the bank customer's current transactions on the bank platform. If there are security risks, an early warning will be issued and feedback will be given to the bank's information security department.

[0098] Furthermore, the specific working process of the bank business database on-duty feedback module is: comparing the risk index of the bank customer currently logging into the bank platform with the preset risk index threshold. If the risk index of the bank customer currently logging into the bank platform is greater than the preset risk index threshold, there is a security risk in the bank customer's current login, and an early warning is issued. Similarly, it is determined whether there is a security risk in the bank customer's current transaction, and further feedback is provided to the bank's information security department.

[0099] As a preferred solution, if it is identified that there is a risk in the bank customer's login, the bank platform can send a text message to notify the bank customer.

[0100] As a preferred solution, if a bank customer's transaction is identified as risky, the bank platform can send a text message to notify the bank customer and add additional verification steps, such as two-factor authentication and manual review.

[0101] It should be noted that when judging whether there are risks in the login and transaction behaviors of bank customers on the bank platform, the present invention takes into account the bank customer's historical login and transaction habits and uses them as a reference, thereby improving the credibility of the results of assessing customer login and transaction risks and avoiding misjudgments.

[0102] The database is used to store basic historical login information and historical transaction details of bank customers on the bank platform.

[0103] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. An intelligent cloud-based on-call system for a banking service database, characterized in that: include: Bank customer login basic information collection module: used to collect basic information of bank customers currently logging into the banking platform, including login time, login location, device type and identifier, authentication method, number of authentication failures, various information sub-items accessed, and access duration; Bank customer login risk analysis module: used to analyze the first risk factor, second risk factor, and third risk factor of the bank customer's current login to the bank platform based on the basic information of the bank customer currently logging into the bank platform, and further analyze the risk index of the bank customer's current login to the bank platform; Bank customer transaction details collection module: used to collect detailed information about bank customers' current transactions on the bank platform, including transaction time, transaction location, transaction frequency, transaction amount, transaction type, number of identity verification failures, and transaction operation duration; Bank customer transaction risk analysis module: used to analyze the first risk coefficient, second risk coefficient and third risk coefficient of the bank customer's current transactions on the bank platform based on the detailed information of the bank customer's current transactions on the bank platform, and further analyze the risk index of the bank customer's current transactions on the bank platform; Banking business database on-duty feedback module: This module is used to determine whether a bank customer's current login and current transaction have security risks based on the risk index of the bank customer's current login to the banking platform and the risk index of the bank customer's current transaction on the banking platform. If there is a security risk, an early warning will be issued and feedback will be provided to the bank's information security department. Database: used to store bank customers' historical login basic information and historical transaction details on the bank platform; The specific working process of the bank customer login risk analysis module includes: S1: Extract the basic historical login information of bank customers on the bank platform stored in the database, obtain the login time of each historical login of the bank customer on the bank platform, and analyze the login tendency ratio coefficient of each time period of a single day; According to the current login time of the bank customer, the login tendency coefficient of the time period in which the bank customer currently logs into the bank platform is obtained, and recorded as ; S2: Obtain a set of geographical locations commonly used by bank customers for login; Comparing the current geographical location of the bank customer logging into the banking platform with a set of geographical locations commonly used by the bank customer to determine whether the current geographical location of the bank customer logging into the banking platform is a common geographical location or an uncommon geographical location; Set the risk factors corresponding to the uncommon login geographical location and the common login geographical location, filter the risk factors corresponding to the current login geographical location of the bank customer logging into the bank platform, and record them as ; S3: Obtain the device types and identifiers commonly used by bank customers to log in; Compare the device type and identifier currently used by the bank customer to log in to the bank platform with the device types and identifiers commonly used by the bank customer to log in, analyze the risk factor corresponding to the device currently used by the bank customer to log in to the bank platform, and record it as ; S4: By analyzing the formula Get the first risk factor of the bank customer currently logging into the bank platform ,in Respectively represent the weights of the preset login time, login geographical location and login device. ; The specific working process of the bank customer transaction risk analysis module includes: F1: Extract the historical transaction details of the bank customer on the bank platform stored in the database, obtain the transaction time of each historical transaction of the bank customer on the bank platform, divide the single day into different time periods according to the preset principle, and further calculate the historical transaction count corresponding to each time period of the single day; According to the transaction time of the bank customer's current transaction on the bank platform, the number of historical transactions corresponding to the time period of the bank customer's current transaction time on the bank platform is filtered and recorded as ; F2: Get the set of geographical locations commonly used by bank customers for transactions; Compare the current geographical location of bank customers’ transactions on the bank platform with the geographical location set commonly used by bank customers for transactions, analyze the risk factor corresponding to the current geographical location of bank customers’ transactions on the bank platform, and record it as ; F3: By analyzing the formula Get the first risk factor of the bank customer's current transaction on the bank platform ,in Indicates the threshold of the number of historical transactions corresponding to the time period of the transaction moment.

2. The intelligent cloud-based on-call system for a banking service database according to claim 1, characterized in that: The specific working process of the bank customer login risk analysis module also includes: Get a collection of common authentication methods used by bank customers to log in; Compare the current authentication method used by bank customers to log into the bank platform with the set of commonly used authentication methods for bank customers to log in, analyze the risk factor corresponding to the current authentication method used by bank customers to log into the bank platform, and record it as ; Set the security level of various identity authentication methods and the risk factors corresponding to each security level, filter the risk factors corresponding to the security level of the identity authentication method currently used by bank customers to log in to the bank platform, and record them as ; The number of times a bank customer fails to log in to the bank platform is recorded as ; By analyzing the formula Get the second risk factor of the bank customer currently logging into the bank platform ,in Indicates the impact factor corresponding to the preset number of unit login identity authentication failures.

3. The intelligent cloud-based on-call system for a banking service database according to claim 1, characterized in that: The specific working process of the bank customer login risk analysis module also includes: D1: Get the information sub-item collection that bank customers frequently access when logging in; Compare the information sub-items that the bank customer currently accesses when logging into the bank platform with the set of information sub-items that the bank customer frequently accesses when logging into the bank platform, and obtain the number of non-commonly accessed information sub-items that the bank customer currently accesses when logging into the bank platform, and record it as ; D2: Set the sensitive information sub-item set in the bank platform, compare the information sub-items currently accessed by the bank customer logging into the bank platform with the sensitive information sub-item set, and filter the number of sensitive information sub-items currently accessed by the bank customer logging into the bank platform, and record it as ; D3: Record the duration of the bank customer's current login to the bank platform as ; Get the average access time of bank customers' historical single logins and record it as ; D4: By analyzing the formula Get the third risk factor of the bank customer currently logging into the bank platform ,in They respectively represent the impact factors of the preset number of unit non-habitually accessed information sub-items and the number of unit sensitive information sub-items.

4. The intelligent cloud-based on-call system for a banking service database according to claim 1, characterized in that: The specific working process of the bank customer login risk analysis module also includes: A weighted average of the first risk coefficient, the second risk coefficient, and the third risk coefficient of the bank customer currently logging into the bank platform is calculated to obtain a risk index of the bank customer currently logging into the bank platform.

5. The intelligent cloud-based on-call system for a banking service database according to claim 1, characterized in that: The specific working process of the bank customer transaction risk analysis module also includes: G1: Get the average transaction frequency of a bank customer's historical single transaction and record it as ; G2: Get the average transaction amount of a bank customer's historical single transaction and record it as ; G3: Gets a set of transaction types commonly used by bank customers; Compare the transaction types currently traded by bank customers on the bank platform with the transaction types commonly used by bank customers, analyze the risk factors corresponding to the transaction types currently traded by bank customers on the bank platform, and record them as ; Set the risk factors corresponding to various transaction types, filter the risk factors corresponding to the transaction types currently traded by bank customers on the bank platform, and record them as ; G4: By analyzing the formula Get the second risk coefficient of the bank customer's current transaction on the bank platform ,in represents a natural constant, 、 They respectively represent the transaction frequency and transaction amount of bank customers currently trading on the bank platform.

6. The intelligent cloud-based on-call system for a banking service database according to claim 1, characterized in that: The specific working process of the bank customer transaction risk analysis module also includes: H1: The number of identity authentication failures and transaction operation duration of bank customers in the current bank platform transactions are recorded as 、 ; H2: Obtain the reference operation time of the bank customer's current transaction on the bank platform and record it as ; H3: Obtain the credit score level of bank customers from the credit rating agency, set the credit score impact factor corresponding to each credit score level, filter out the credit score impact factor of bank customers, and record it as ; H4: By analyzing the formula Get the third risk coefficient of the bank customer's current transactions on the bank platform ,in, Indicates the impact factor corresponding to the preset number of failed identity authentications per unit transaction. Indicates the compensation amount for the third risk factor of the preset bank customer's current transactions on the bank platform.

7. The intelligent cloud-based on-call system for a banking service database according to claim 1, characterized in that: The specific working process of the bank customer transaction risk analysis module also includes: A weighted average of the first risk coefficient, the second risk coefficient, and the third risk coefficient of the bank customer's current transactions on the bank platform is calculated to obtain a risk index for the bank customer's current transactions on the bank platform.

8. The intelligent cloud-based on-call system for a banking service database according to claim 1, characterized in that: The specific working process of the banking business database on-duty feedback module is as follows: Compare the risk index of the bank customer currently logging into the bank platform with the preset risk index threshold. If the risk index of the bank customer currently logging into the bank platform is greater than the preset risk index threshold, there is a security risk in the bank customer's current login and an early warning is issued; The risk index of the bank customer's current transactions on the bank platform is compared with the preset risk index threshold. If the risk index of the bank customer's current transactions on the bank platform is greater than the preset risk index threshold, there is a security risk in the bank customer's current transactions, which is further fed back to the bank's information security department.

Images