Financial data access identity authentication method and system

Abstract

The invention provides a financial data access identity authentication method and system, and relates to the technical field of data processing. The method comprises the following steps: acquiring a plurality of identity verification modes, and determining a plurality of combined verification modes based on each identity verification mode; determining the combination complexity of each combination verification mode; obtaining a to-be-verified access identity, inputting the to-be-verified access identity into a pre-trained fraud coefficient model, and determining a fraud coefficient of the to-be-verified access identity; wherein the fraud coefficient is used for indicating the probability that the corresponding access identity has fraud suspicion; and based on the fraud coefficient of the to-be-verified access identity and the combination complexity of each combination verification mode, determining a target combination verification mode from each combination verification mode, and performing identity verification on the to-be-verified access identity based on the target combination verification mode. Different identity verification modes are adopted for users with different fraud coefficients, the verification efficiency is improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for authenticating access to financial data. Background Art

[0002] Financial data usually refers to various types of data related to financial markets, economy, enterprises and financial instruments. It is usually an important basis for banks and financial institutions to manage customer accounts, financial settlement and achieve financial supervision. Therefore, when accessing financial data, it is particularly important to ensure its security, integrity and compliance.

[0003] In the related art, the security, integrity and compliance of the data are ensured by authenticating the identity of users who access financial data, and only users who have passed the authentication can access the corresponding financial data. However, the prior art usually uses a fixed combination of authentication methods to authenticate the identity of users. That is, the same set of authentication methods is used for any user to authenticate the identity. Since the probability of fraud suspicion varies among different users, if a fixed verification combination is used, it may lead to a contradiction between security and efficiency. For example, for users with a low fraud coefficient, the use of complex verification methods not only wastes a lot of computing resources and time, but the cumbersome and lengthy authentication process will also reduce the user experience and affect the user's operating efficiency; for users with a high fraud coefficient, if a simple verification method is used, it will lead to the problem of not being able to provide sufficient security and increase potential security risks. Summary of the invention

[0004] In order to solve the problem in the related art that the probability of fraud suspicion of different users is different, and the use of a fixed verification combination may lead to a contradiction between security and efficiency, the present invention provides an access identity authentication method for financial data, and the technical solution adopted is as follows: Acquire multiple identity authentication methods, and determine multiple combined authentication methods based on the identity authentication methods; wherein the combined authentication method includes at least one of the identity authentication methods, and the identity authentication method is used to authenticate the user who accesses the financial data; Determine the combination complexity of each of the combined verification methods; wherein the combination complexity is used to indicate the verification accuracy of the corresponding combined verification method; Obtaining an access identity to be verified, inputting the access identity to be verified into a pre-trained fraud coefficient model, and determining a fraud coefficient of the access identity to be verified; wherein the fraud coefficient is used to indicate the probability that the corresponding access identity is suspected of fraud; Based on the fraud coefficient of the access identity to be verified and the combination complexity of each of the combination verification methods, a target combination verification method is determined from the combination verification methods, and the identity of the access identity to be verified is authenticated based on the target combination verification method.

[0005] Correspondingly, the present invention also provides a financial data access identity authentication system, which specifically includes: An acquisition unit, used to acquire multiple identity authentication methods, and determine multiple combined authentication methods based on the identity authentication methods; wherein the combined authentication method includes at least one of the identity authentication methods, and the identity authentication method is used to authenticate the user who accesses the financial data; A processing unit, used to determine the combination complexity of each of the combined verification methods; wherein the combination complexity is used to indicate the verification accuracy of the corresponding combined verification method; The acquisition unit is further used to acquire the access identity to be verified, input the access identity to be verified into a pre-trained fraud coefficient model, and determine the fraud coefficient of the access identity to be verified; wherein the fraud coefficient is used to indicate the probability that the corresponding access identity is suspected of fraud; The authentication unit is used to determine a target combination verification method from each of the combination verification methods based on the fraud coefficient of the access identity to be verified and the combination complexity of each of the combination verification methods, and to authenticate the access identity to be verified based on the target combination verification method.

[0006] The present invention may have some or all of the following beneficial effects: In the access identity authentication method for financial data provided by the present invention, multiple identity authentication methods are obtained, and multiple combined authentication methods are determined based on the above identity authentication methods; wherein the above combined authentication methods include at least one identity authentication method, and the above identity authentication methods are used to authenticate users who access financial data; the combined complexity of each combined authentication method is determined, and the combined complexity is used to indicate the verification accuracy of the corresponding combined authentication method; the access identity to be verified is obtained, and the access identity to be verified is input into a pre-trained fraud coefficient model to determine the fraud coefficient of the access identity to be verified, and the fraud coefficient is used to indicate the probability that the corresponding access identity is suspected of fraud; based on the fraud coefficient of the access identity to be verified and the combined complexity of each combined authentication method, a target combined authentication method is determined from each combined authentication method, and the access identity to be verified is authenticated based on the target combined authentication method. The present invention obtains a corresponding combined authentication method by combining multiple identity authentication methods, and determines the combined complexity of each combined authentication method, and determines the fraud coefficient of the access identity to be verified through the above fraud coefficient model, so that the target combined authentication method with a suitable combined complexity can be determined based on the fraud coefficient of the access identity to be verified to authenticate the access identity to be verified. By selecting a combination verification method of appropriate complexity according to different fraud coefficients, while ensuring the security of financial data, it solves the contradiction between security and efficiency caused by the fixed verification combination in the existing technology, avoids unnecessary waste of resources, and improves user experience and verification efficiency.

[0007] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 paying creative work.

[0009] Figure 1 A flow chart showing a method for authenticating access to financial data according to an exemplary embodiment of the present disclosure is shown; Figure 2 A flowchart of training a fraud coefficient model in a method for authenticating access to financial data according to an exemplary embodiment of the present disclosure is shown; Figure 3 A schematic diagram of a financial data access authentication system according to an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0010] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the access identity authentication method for financial data proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0011] 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.

[0012] The specific scheme of the access identity authentication method for financial data provided by the present invention is described in detail below with reference to the accompanying drawings.

[0013] See also Figure 1 , which shows a method flow chart of a method for access identity authentication of financial data provided by an embodiment of the present invention, such as Figure 1 As shown, the financial data access identity authentication method specifically includes the following steps: S110: Acquire multiple identity authentication methods, and determine multiple combined authentication methods based on the identity authentication methods; wherein the combined authentication method includes at least one identity authentication method, and the identity authentication method is used to authenticate the user who accesses the financial data; S120: Determine the combination complexity of each combination verification method; wherein the combination complexity is used to indicate the verification accuracy of the corresponding combination verification method; S130: obtaining an access identity to be verified, inputting the access identity to be verified into a pre-trained fraud coefficient model, and determining a fraud coefficient of the access identity to be verified; wherein the fraud coefficient is used to indicate the probability that the corresponding access identity is suspected of fraud; S140: Based on the fraud coefficient of the access identity to be verified and the combination complexity of each combination verification method, determine a target combination verification method from each combination verification method, and perform identity authentication on the access identity to be verified based on the target combination verification method.

[0014] The present invention combines multiple identity authentication methods to obtain a corresponding combination authentication method, determines the combination complexity of each combination authentication method, and determines the fraud coefficient of the access identity to be authenticated through the above-mentioned fraud coefficient model, so that the target combination authentication method with a suitable combination complexity can be determined based on the fraud coefficient of the access identity to be authenticated to authenticate the access identity to be authenticated. Selecting a combination authentication method with appropriate complexity according to different fraud coefficients solves the contradiction between security and efficiency caused by fixed authentication combinations in the prior art while ensuring the security of financial data, avoids unnecessary waste of resources, and improves user experience and verification efficiency.

[0015] The following is a detailed description of each step of the above financial data access authentication method: In step S110, multiple identity authentication methods are obtained, and multiple combined authentication methods are determined based on the identity authentication methods; wherein the above-mentioned combined authentication method includes at least one identity authentication method, and the above-mentioned identity authentication method is used to authenticate the user who accesses financial data.

[0016] In the embodiment of the present application, the above-mentioned identity authentication method is a method for authenticating the identity of a user accessing financial data. Exemplarily, the above-mentioned identity authentication method may include password authentication, SMS verification code verification, fingerprint recognition or dynamic password and other methods for implementing identity authentication.

[0017] In the embodiments of the present application, the above-mentioned financial data refers to various types of data generated, recorded and analyzed in the financial field, usually data related to financial markets, economy, enterprises and financial instruments, etc. For example, the financial data may include bank transaction records, stock market data, credit records, investment portfolios, financial statements, risk analysis data, etc.

[0018] In an embodiment of the present application, the above-mentioned combined verification method is an identity verification method combined by the above-mentioned identity verification methods. The combined verification method is composed of at least one identity verification method. Exemplarily, assuming that the identity verification methods provided in the embodiment of the present application include three types: password verification, SMS verification code verification and fingerprint recognition, then the process of determining multiple combined verification methods based on the identity verification method can be obtained by arranging and combining the three identity verification methods. Specifically, the combined verification method obtained based on the three identity verification methods may include the following situations: {password verification}, {SMS verification code verification}, {fingerprint recognition}, {password verification, SMS verification code verification}, {password verification, fingerprint recognition}, {SMS verification code verification, fingerprint recognition}, {password verification, SMS verification code verification, fingerprint recognition}. It should be noted that the above-mentioned scenario is only an exemplary description, and the protection scope of the embodiment of the present application is not limited to this. For example, the above-mentioned identity verification method can be other verification methods, and their number can also be any other integer greater than 0.

[0019] In step S120, the combination complexity of each combination verification method is determined; wherein the combination complexity is used to indicate the verification accuracy of the corresponding combination verification method.

[0020] In the embodiment of the present application, the above-mentioned combination complexity is used to indicate the verification accuracy of the corresponding combination verification method. The higher the combination complexity, the higher the accuracy of identity authentication through the combination verification method.

[0021] In an embodiment of the present application, the process of determining the combined complexity of the combined verification method can be implemented as follows: obtaining historical access information based on financial data, the historical access information including historical access identities and first identity verification results corresponding to each historical access identity; determining the single complexity of each identity verification method based on the historical access identity and the first identity verification result; wherein the single complexity is used to indicate the verification accuracy when the corresponding identity verification method is used alone; determining the combined complexity of each combined verification method based on the single complexity of each identity verification method.

[0022] In the embodiment of the present application, the above historical access information is the historical information of accessing financial data, and the historical access information may include the historical access identity and the first identity verification result. The above historical access identity is the identity of the user who has historically accessed the financial data, and the above first identity verification result is the identity verification result obtained by authenticating the above historical access identity (that is, the known identity verification result obtained by identity verification during the historical access process).

[0023] In an embodiment of the present application, illustratively, the above historical access information can be obtained based on the transaction records of the financial company. Exemplarily, the verification results (that is, the above-mentioned first identity authentication results) of the access identity with known verification results in the historical financial company transaction records under different verification methods can be collected. Specifically, M access identities with known verification results can be collected in the historical financial company transaction records, and each access identity contains N features (such as identity ID, transaction frequency, IP address, etc.). After quantifying the N identity features of the above-mentioned M access identities, the historical access information shown in Table 1 below can be obtained: Table 1: In an embodiment of the present application, exemplarily, the above-mentioned process of determining the single complexity of each identity authentication method based on the historical access identity and the first identity authentication result can be implemented as follows: for each historical access identity, authenticate the historical access identity based on each identity authentication method, and determine the second identity authentication result of the historical access identity under each identity authentication method; determine the single complexity of each identity authentication method based on the first identity authentication result and the second identity authentication result corresponding to each historical access identity.

[0024] In the embodiment of the present application, the second identity authentication result is a verification result obtained by using a certain identity authentication method alone to authenticate the historical access identity, and the single complexity is used to indicate the verification accuracy of using the corresponding identity authentication method alone. Specifically, different identity authentication methods are used to authenticate the M access identities, where there are n types of identity authentication methods. The results of using n identity authentication methods to authenticate the M access identities can be shown in the following Table 2: Table 2: Among them, for the above-mentioned M access identities, the first identity authentication result is known. If the verification is successful, it is set to label 1, and if the verification fails, it is set to label 0. Afterwards, the above-mentioned n verification methods can be used to verify the above-mentioned M access identities to obtain the above-mentioned second identity authentication results. If the verification is successful, it is set to label 1, and if the verification fails, it is set to label 0.

[0025] In the embodiment of the present application, after determining the second identity authentication result of each identity authentication method for the historical access identity, illustratively, taking identity authentication method A among the above n identity authentication methods as an example, the process of determining the single complexity of identity authentication method A based on the first identity authentication result and the second identity authentication result corresponding to each historical access identity can be implemented as follows: Specifically, the complexity coefficient of identity authentication method A (that is, the single complexity of identity authentication method A) can be determined by the verification performance of the above M historical access identities under identity authentication method A. A historical access identity, if the verification result obtained through identity authentication method A (That is, The second identity authentication result obtained by verifying the historical access identity through identity authentication method A) and the Known authentication results for historical access identities (That is, The above first identity verification result of the historical access identity is consistent with the first identity verification result of the historical access identity. For a historical access identity, the verification result based on authentication method A is accurate, and the corresponding complexity coefficient is high. However, due to the different verification difficulties of different access identities, if the second authentication result obtained by a historical access identity under most authentication methods is significantly different from the known first authentication result, that is, The larger the value of , the more difficult it is to verify the historical access identity. Therefore, the complexity coefficients of the above M historical access identities under identity authentication method A can be weighted to obtain the complexity coefficient of identity authentication method A (that is, the single complexity of the above identity authentication method A). The formula for the weighted processing is as follows: in, represents the single complexity of the authentication method A, M represents the number of the above historical access identities, and n represents that there are n authentication methods in total. Indicates The verification result of the historical access identity under the authentication mode u, Indicates The first authentication result of the historical access identity, Indicates The difficulty of verifying the historical access identity, Indicates The verification result of the historical access identity under the authentication method A, Indicates whether the second identity authentication result of the historical access identity under identity authentication method A is consistent with the first identity authentication result, Indicates The complexity of authentication method A under historical access identities.

[0026] It should be noted that the above scenario is only an exemplary description, and the single complexity of other identity authentication methods can also be determined by the above method.

[0027] In an embodiment of the present application, after determining the single complexity of each identity authentication method, the combined complexity of each combined authentication method can be further determined based on the single complexity of each identity authentication method. Exemplarily, the process of determining the combined complexity of each combined authentication method can be implemented as follows: for any two identity authentication methods, based on the first identity authentication result and the second identity authentication result corresponding to each historical access identity, and the single complexity of the any two identity authentication methods, determine the complexity correlation between the any two identity authentication methods; determine the combined complexity of each combined authentication method based on the complexity correlation between each identity authentication method.

[0028] In the embodiment of the present application, since the above-mentioned identity authentication methods are not necessarily independent of each other, that is, different identity authentication methods may have correlations, the above-mentioned complexity correlation is used to describe this correlation between different identity authentication methods. When determining the combined complexity of the above-mentioned combined authentication methods, the correlation must be determined first so as to exclude the influence of this correlation when subsequently calculating the combined complexity. For example, taking the calculation of the complexity correlation between identity authentication method A and identity authentication method B as an example, the above-mentioned determination of the complexity correlation between any two identity authentication methods can be implemented as follows: Specifically, the authentication performance of the above-mentioned M types of historical access identities under authentication method A and authentication method B can be used to determine the correlation relationship between authentication method A and authentication method B. For any historical access identity, if the verification results of authentication method A and authentication method B are consistent, then under this historical access identity, the verification correlation between authentication method A and authentication method B is high. However, since the authentication difficulties of different historical access identities are different, for a certain historical access identity, if the second authentication results obtained under most authentication methods are greatly different from the known first authentication results, then it is judged that the verification difficulty of the historical access identity is high and the verification correlation is good. Therefore, the complexity correlation of authentication method A and authentication method B can be obtained by weighting the correlation of the verification results of the above-mentioned M types of historical access identities under authentication method A and authentication method B. The specific formula of the complexity correlation can be as follows: in, represents the complexity correlation between authentication method A and authentication method B, f represents the normalization function, M represents the total number of M historical access identities, n represents the total number of n authentication methods, Indicates The verification result of the historical access identity under the authentication mode u, Indicates The first authentication result of the historical access identity is known, Indicates The difficulty of verifying the historical access identity, Indicates The verification result of the historical access identity under the authentication method A, Indicates The verification result of the historical access identity under the authentication method B, Indicates The consistency of the historical access identity under authentication method A and under authentication method B, Indicates The complexity correlation between authentication method A and authentication method B under the historical access identity, Represents the single complexity of authentication method A, Indicates the single complexity of authentication method B.

[0029] It should be noted that the above scenario is only an exemplary description, and the complexity correlation between any other two identity authentication methods can also be determined by the above method.

[0030] In an embodiment of the present application, after determining the complexity correlation between any two identity authentication methods through the above process, further, the above-mentioned determination of the combined complexity of each combined verification method based on the complexity correlation between each identity authentication method can be implemented by the following method: for each combined verification method, the number of identity authentication methods in the combined verification method is obtained; according to the complexity correlation between the identity authentication methods in the combined verification method, the number of identity authentication methods, and the single complexity of each identity authentication method, the combined complexity of the combined verification method is determined.

[0031] Exemplarily, taking combined verification method i as an example, the process of determining the combined complexity of the combined verification method can be implemented as follows: for each identity authentication method in the above combined verification method i, based on the complexity correlation between each identity authentication method and other identity authentication methods, determine the pure verification of the corresponding identity authentication method without interference from other identity authentication methods; use the pure verification obtained by the above calculation to weight the single complexity of each identity authentication method in the combined verification method i, and determine the combined complexity of the combined verification method i. Specifically, assuming that the combined verification method i is composed of identity authentication methods i1, i2…ig, the combined complexity of the combined verification method i can be determined by the following formula: in, represents the combination complexity of combined authentication method i, g represents that combined authentication method i is composed of g authentication methods. It represents the complexity correlation between authentication method A and authentication method B in combined authentication method i. Indicates the pure verification of authentication method A in combined authentication method i, Represents the single complexity of authentication method A in combined authentication method i.

[0032] It should be noted that the above scenario is only an exemplary description, and the combination complexity of other verification combination methods can also be determined by the above method.

[0033] In step S130, the access identity to be verified is obtained, and the access identity to be verified is input into a pre-trained fraud coefficient model to determine the fraud coefficient of the access identity to be verified; wherein the fraud coefficient is used to indicate the probability that the corresponding access identity is suspected of fraud.

[0034] In the embodiment of the present application, the access identity to be verified is a user identity that needs to be authenticated. If the access identity to be verified passes the authentication, the corresponding financial data can be accessed.

[0035] In the embodiment of the present application, the above-mentioned fraud coefficient model is used to determine the probability that the user identity input into the model is suspected of fraud. Exemplarily, any access identity can be input into the fraud coefficient model, and after being processed by the model, a corresponding fraud coefficient is output, which is used to indicate the probability that the access identity input into the model is suspected of fraud.

[0036] In an embodiment of the present application, the above historical access information can be used as a training data set to train the above fraud coefficient model. Exemplarily, the training process of the above fraud coefficient model can be implemented as follows: determine the identity similarity between two historical access identities based on the identity feature information of the historical access identities; determine the fraud coefficient of each historical access identity based on the identity similarity; and train the fraud coefficient model based on the fraud coefficient of the historical access identities.

[0037] In the embodiment of the present application, the identity similarity is used to describe the similarity between each historical access identity and other historical access identities in the training data set, and can be determined based on the identity feature information of the historical access identity.

[0038] Exemplarily, the above-mentioned process of determining the identity similarity between two historical access identities based on the identity feature information of the historical access identities can be implemented as follows: for each piece of identity feature information, based on the first verification result corresponding to each feature value of the identity feature information, determine the availability of the identity feature information; wherein the availability is used to indicate the importance of the corresponding identity feature information for identity authentication; based on the availability of each piece of identity feature information, determine the identity similarity between two historical access identities.

[0039] The above-mentioned determination of the fraud coefficient of each historical access identity based on identity similarity can be implemented as follows: for each historical access identity, based on the identity similarity between the historical access identity and other historical access identities, and the first identity authentication results of each historical access identity, the fraud coefficient of the historical access identity is determined.

[0040] In a specific embodiment, Figure 2 The training process of the above fraud coefficient model is described in detail. Figure 2 As shown, the training process specifically includes the following steps: S210: Determine the identity similarity between each historical access identity and other historical access identities in the training data set.

[0041] In the embodiment of the present application, taking the above-mentioned M types of historical access identities as an example, each historical access identity includes N types of identity feature information, and the above-mentioned identity similarity can be calculated based on each identity feature information. However, due to the different availability of different identity feature information, for each type of identity feature information of any historical access identity, if the identity feature information has a greater influence on the identity authentication result, that is, the identity authentication result can be roughly determined only by the different feature values ​​under this identity feature information, then the purity of the verification result of each access value under this identity feature information is higher (that is, the difference between the total number of access identities with an identity authentication result of 1 and an identity authentication result of 0 is large), so it can be judged that the higher the availability of the identity feature information. Taking the above-mentioned identity feature information as transaction frequency as an example, the feature value under the identity feature information can be the number of transactions of the above-mentioned historical access identities within a certain time period. Exemplarily, the feature value can be obtained through the process of collecting historical access information in the above-mentioned step S120. If the historical access identity is verified only by different characteristic values ​​under the transaction frequency (that is, the number of transactions of each historical access identity in a certain period of time), and the difference between the total number of historical access identities with an identity authentication result of 1 and an identity authentication result of 0 is large, it proves that the availability of the identity characteristic information of transaction frequency is relatively high. For example, taking the Tth type of identity characteristic information as an example, the availability of the Tth type of identity characteristic information can be specifically determined by the following formula: in, Indicates the availability of the Tth identity feature information, Indicates the total number of eigenvalues ​​that appear in the T-th identity feature information, represents the total number of historical access identities with a known identity authentication result of 1 under the h-th feature value in the T-th identity feature information, It represents the total number of historical access identities with a known identity authentication result of 0 under the h-th feature value in the T-th identity feature information. represents the total number of access identities with different known identity authentication results under the h-th feature value in the T-th identity feature information, represents the total number of historical access identities under the h-th feature value in the T-th identity feature information, It represents the total number of relative access identities with different known identity authentication results under the h-th feature value in the T-th identity feature information.

[0042] In the embodiment of the present application, after determining the availability of each identity feature information based on the above method, further, the identity similarity between the historical access identity a and the historical access identity b in the training data set can be determined based on the availability of each identity feature information. The specific formula is as follows: in, represents the identity similarity between historical access identity a and historical access identity b in the training data set, N represents a total of N identity feature information, represents the availability of the T-th identity feature information, exp represents the exponential function with e as the base, Indicates the characteristic value of the historical access identity a under the Tth identity characteristic information (taking the Tth identity characteristic information as the identity ID as an example, here is the identity ID of historical access identity a), represents the characteristic value of the historical access identity b under the Tth identity characteristic information, Represents the similarity between historical access identity a and historical access identity b in the training dataset under the Tth identity feature information.

[0043] It should be noted that the above scenario is only an exemplary description, and the identity similarity between other historical access identities in the training data set can also be determined by the above method.

[0044] S220: Determine the overall fraud coefficient of each historical access identity in the training data set and construct an initial feature matrix.

[0045] In the embodiment of the present application, when the identity similarity between any two historical access identities is large, their known identity authentication results should be consistent. If the verification results are different, it means that there is a high possibility of fraud. Taking historical access identity a as an example, when other access identities have a high identity similarity with it, if their verification results are different, it can be considered that the historical access identity a is suspected of fraud. Exemplarily, the fraud coefficient of the historical access identity a can be determined by the following formula: in, represents the fraud coefficient of the historical access identity a in the training data set, M represents the total number of historical access identities in the training data set, Represents the historical access identity a and the first The identity similarity of the historical access identities, represents the authentication result of the known historical access identity A in the training dataset, Indicates the training data set Authentication result for a known historical access identity.

[0046] Similarly, the fraud coefficients of all historical access identities in the training data set are determined, and the initial feature matrix shown in Table 3 is constructed: Table 3: S230: Construct a fraud coefficient model.

[0047] In an embodiment of the present application, after the above-mentioned initial feature matrix is ​​constructed through the above-mentioned steps, an initial decision tree for predicting the fraud coefficient is determined based on the initial feature matrix; the gradient of the current model residual is calculated based on the gradient boosting decision tree algorithm (eXtremeGradient Boosting, XGBoost), and a new decision tree is trained using this gradient; after the training is completed, the new tree is added to the existing model to update the prediction value of the model, and the updated prediction result is obtained by the weighted sum of all decision trees. The process is repeated until a predetermined number of training rounds (i.e., the number of trees) is reached, so as to correct the prediction error of the previous model through each iteration, so that the model gradually becomes more accurate.

[0048] In the embodiment of the present application, the trained XGBoost fraud coefficient model includes all decision trees generated during the training process. For any new input sample (i.e., the access identity to be verified), the identity feature information of the sample is input into the trained fraud model, and the fraud model generates the final prediction value (i.e., the fraud coefficient of the access identity to be verified) through the weighted sum of all decision trees.

[0049] In step S140, based on the fraud coefficient of the access identity to be verified and the combination complexity of each combination verification method, a target combination verification method is determined from each combination verification method, and the identity of the access identity to be verified is authenticated based on the target combination verification method.

[0050] In an embodiment of the present application, after determining the combined complexity of each combined verification method and the fraud coefficient of the access identity to be verified based on the above steps, exemplarily, the process of determining the target combined verification method from each combined verification method based on the fraud coefficient of the access identity to be verified and the combined complexity of each combined verification method can be implemented as follows: for each historical access identity, determine the verification complexity required for the historical access identity based on each combined verification method; determine the unit complexity based on the verification complexity required for each historical access identity, the unit complexity being the verification complexity corresponding to the unit fraud coefficient; determine the verification complexity required for the access identity to be verified based on the fraud coefficient and the unit complexity of the access identity to be verified; determine the target combined verification method in each combined verification method based on the verification complexity and the combined complexity required for the access identity to be verified.

[0051] In the embodiment of the present application, the verification complexity is used to characterize the complexity required for identity authentication of the corresponding access identity. Generally, the verification complexity is in direct proportion to the fraud coefficient of the access identity, that is, the greater the fraud coefficient of the access identity, the higher the verification complexity required.

[0052] In an embodiment of the present application, exemplarily, the verification complexity required for the above-mentioned historical access identity can be determined by the following process: arrange the above-mentioned combined verification methods in order from low to high according to the combined verification complexity, assuming that there are u combined verification methods composed of the above-mentioned identity authentication methods, then a combined verification method sequence {1, 2, 3, 4...u} can be obtained through the above-mentioned sorting; substitute the above-mentioned historical access identities into each combined verification method in the above-mentioned combined verification method sequence in turn to perform identity authentication, and obtain the corresponding identity authentication result until the identity authentication result no longer changes, and use the combined complexity corresponding to the combined verification method at this time as the verification complexity required for the corresponding historical access identity.

[0053] In the embodiment of the present application, the above unit complexity is the verification complexity required for the unit fraud coefficient, which can be determined by the average value of the minimum complexity required for the unit fraud coefficient of all historical access identities in the training data set, and can be specifically calculated by the following formula: in, It represents the unit complexity, that is, the verification complexity required for the unit fraud coefficient. M represents the total number of historical access identities in the training set. Indicates the training set The fraud coefficient corresponding to the historical access identity, Indicates the training data set The complexity of verification required for historical access identities, Indicates the training data set The minimum complexity required for a unit fraud coefficient determined by a historical access identity.

[0054] In an embodiment of the present application, after determining the unit complexity, since the unit complexity is the verification complexity required for the unit fraud coefficient, the above-mentioned determination of the verification complexity required for the access identity to be verified based on the fraud coefficient of the access identity to be verified and the unit complexity can be implemented as follows: multiply the fraud coefficient of the access identity to be verified and the above-mentioned unit complexity to obtain the verification complexity required for the access identity to be verified.

[0055] Furthermore, based on the verification complexity required for the above-mentioned access identity to be verified, a combination verification method whose combination complexity can reach the verification complexity is selected from each combination verification method as the above-mentioned target verification method. Exemplarily, a combination verification method that includes the least number of identity authentication methods and whose combination complexity is greater than or equal to the verification complexity required for the access identity to be verified can be selected as the target verification method to authenticate the access identity with verification based on the target verification method.

[0056] The present invention combines multiple identity authentication methods to obtain a corresponding combination authentication method, determines the combination complexity of each combination authentication method, and determines the fraud coefficient of the access identity to be authenticated through the above-mentioned fraud coefficient model, so that the target combination authentication method with a suitable combination complexity can be determined based on the fraud coefficient of the access identity to be authenticated to authenticate the access identity to be authenticated. Selecting a combination authentication method with appropriate complexity according to different fraud coefficients solves the contradiction between security and efficiency caused by fixed authentication combinations in the prior art while ensuring the security of financial data, avoids unnecessary waste of resources, and improves user experience and verification efficiency.

[0057] The above mainly introduces the solution provided by the embodiment of the present invention from the perspective of the method. In order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0058] The present disclosure provides a financial data access identity authentication system. Figure 3 As shown, the financial data access identity authentication system 300 may include an acquisition unit 310, a processing unit 320 and an authentication unit 330, wherein: The acquisition unit 310 is used to acquire multiple identity authentication methods and determine multiple combined authentication methods based on the above identity authentication methods; wherein the above combined authentication method includes at least one identity authentication method, and the above identity authentication method is used to authenticate the user who accesses the financial data; The processing unit 320 is used to determine the combination complexity of each combination verification method; wherein the combination complexity is used to indicate the verification accuracy of the corresponding combination verification method; The acquisition unit 310 is further used to acquire the access identity to be verified, input the access identity to be verified into a pre-trained fraud coefficient model, and determine the fraud coefficient of the access identity to be verified; wherein the fraud coefficient is used to indicate the probability that the corresponding access identity is suspected of fraud; The authentication unit 330 is used to determine a target combination verification method from various combination verification methods based on the fraud coefficient of the access identity to be verified and the combination complexity of each combination verification method, and authenticate the access identity to be verified based on the target combination verification method.

[0059] In an embodiment of the present application, the above-mentioned processing unit is specifically used to: obtain historical access information based on financial data, the above-mentioned historical access information includes historical access identities and first identity authentication results corresponding to each historical access identity; determine the single complexity of each identity authentication method based on the historical access identity and the first identity authentication result; wherein the single complexity is used to indicate the verification accuracy when the corresponding identity authentication method is used alone; determine the combined complexity of each combined verification method based on the single complexity of each identity authentication method.

[0060] In an embodiment of the present application, the above-mentioned processing unit is specifically used to: for each historical access identity, authenticate the historical access identity based on each identity authentication method, and determine the second identity authentication result of the historical access identity under each identity authentication method; determine the single complexity of each identity authentication method based on the first identity authentication result and the second identity authentication result corresponding to each historical access identity.

[0061] In an embodiment of the present application, the above-mentioned processing unit is specifically used to: for any two identity authentication methods, determine the complexity correlation between the any two identity authentication methods based on the first identity authentication result and the second identity authentication result corresponding to each historical access identity, and the single complexity of the any two identity authentication methods; determine the combined complexity of each combined authentication method based on the complexity correlation between each identity authentication method.

[0062] In an embodiment of the present application, the above-mentioned processing unit is specifically used to: obtain the number of identity authentication methods in the combined verification method for each combined verification method; determine the combined complexity of the combined verification method based on the complexity correlation between the identity authentication methods in the combined verification method, the number of identity authentication methods in the combined verification method, and the single complexity of each identity authentication method in the combined verification method.

[0063] In an embodiment of the present application, the above-mentioned historical access information includes identity feature information of the historical access identity; the above-mentioned financial data access identity authentication system also includes a model training module, which is specifically used to: determine the identity similarity between historical access identities based on identity feature information; determine the fraud coefficient of each historical access identity based on identity similarity; and obtain a fraud coefficient model based on fraud coefficient training of historical access identities.

[0064] In an embodiment of the present application, the above-mentioned model training module is also used to: for each piece of identity feature information, determine the availability of the identity feature information based on the first verification result corresponding to each feature value of the identity feature information; wherein the above-mentioned availability is used to indicate the importance of the corresponding identity feature information for identity authentication; and determine the identity similarity between each pair of historical access identities based on the availability of each piece of identity feature information.

[0065] In an embodiment of the present application, the above-mentioned model training module is also used to: for each historical access identity, determine the fraud coefficient of the historical access identity based on the identity similarity between the historical access identity and other historical access identities, and the first identity authentication results of each historical access identity.

[0066] In an embodiment of the present application, the above-mentioned authentication unit is specifically used to: for each historical access identity, determine the verification complexity required for the historical access identity based on each combined verification method; determine the unit complexity based on the verification complexity required for each historical access identity, and the unit complexity is the verification complexity corresponding to the unit fraud coefficient; determine the verification complexity required for the access identity to be verified based on the fraud coefficient and unit complexity of the access identity to be verified; based on the verification complexity and combined complexity required for the access identity to be verified, determine the target combined verification method in each combined verification method.

[0067] The embodiment of the present invention can divide the functional modules of the access authentication system for financial data according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0068] In addition, the specific implementation details of the above-mentioned financial data access identity authentication system have been described in detail in the corresponding position of the financial data access identity authentication method, so they will not be repeated here.

[0069] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0070] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for authenticating access to financial data, characterized in that: The method comprises: Acquire multiple identity authentication methods, and determine multiple combined authentication methods based on the identity authentication methods; wherein the combined authentication method includes at least one of the identity authentication methods, and the identity authentication method is used to authenticate the user who accesses the financial data; Determine the combination complexity of each of the combined verification methods; wherein the combination complexity is used to indicate the verification accuracy of the corresponding combined verification method; Obtaining an access identity to be verified, inputting the access identity to be verified into a pre-trained fraud coefficient model, and determining a fraud coefficient of the access identity to be verified; wherein the fraud coefficient is used to indicate the probability that the corresponding access identity is suspected of fraud; Based on the fraud coefficient of the access identity to be verified and the combination complexity of each of the combination verification methods, determine a target combination verification method from each of the combination verification methods, and authenticate the access identity to be verified based on the target combination verification method; Based on the financial data, historical access information is obtained, the historical access information including historical access identities and first identity authentication results corresponding to each of the historical access identities, and identity feature information of the historical access identities; the fraud coefficient model is trained by the following method, including: For each piece of identity feature information, based on the first verification result corresponding to each feature value of the identity feature information, determine the availability of the identity feature information; wherein the availability is used to indicate the importance of the corresponding identity feature information for identity authentication; Determine the identity similarity between two of the historical access identities based on the availability of each of the identity feature information; For each of the historical access identities, based on the identity similarity between the historical access identity and other historical access identities, and the first identity authentication results of each of the historical access identities, determine a fraud coefficient of the historical access identity; The fraud coefficient model is obtained by training the fraud coefficient based on the historical access identity.

2. The method for access identity authentication of financial data according to claim 1, characterized in that: The determining the combination complexity of each of the combined verification modes includes: Determine the single complexity of each of the identity authentication methods based on the historical access identity and the first identity authentication result; wherein the single complexity is used to indicate the verification accuracy when the corresponding identity authentication method is used alone; The combined complexity of each of the combined authentication methods is determined based on the single complexity of each of the identity authentication methods.

3. The method for access identity authentication of financial data according to claim 2, characterized in that: The determining the single complexity of each of the identity authentication methods based on the historical access identity and the first identity authentication result includes: For each of the historical access identities, authenticate the historical access identity based on each of the identity authentication methods, and determine a second identity authentication result of the historical access identity under each of the identity authentication methods; The single complexity of each of the identity authentication methods is determined based on the first identity authentication result and the second identity authentication result corresponding to each of the historical access identities.

4. The method for access identity authentication of financial data according to claim 3, characterized in that: The determining the combined complexity of each of the combined authentication methods based on the single complexity of each of the identity authentication methods includes: For any two of the identity authentication methods, based on the first identity authentication result and the second identity authentication result corresponding to each of the historical access identities, and the single complexity of the any two identity authentication methods, determine the complexity correlation between the any two identity authentication methods; The combined complexity of each of the combined authentication modes is determined based on the complexity correlation between each of the identity authentication modes.

5. The method for access identity authentication of financial data according to claim 4, characterized in that: The determining the combined complexity of each of the combined authentication modes based on the complexity correlation between each of the identity authentication modes comprises: For each of the combined verification methods, obtaining the number of the identity verification methods in the combined verification method; The combined complexity of the combined verification method is determined according to the complexity correlation between the identity authentication methods in the combined verification method, the number of the identity authentication methods in the combined verification method, and the single complexity of each identity authentication method in the combined verification method.

6. The method for access identity authentication of financial data according to claim 2, characterized in that: The step of determining a target combined verification method from the combined verification methods based on the fraud coefficient of the access identity to be verified and the combined complexity of each of the combined verification methods includes: For each of the historical access identities, determining the verification complexity required for the historical access identity based on each of the combined verification modes; Determining a unit complexity based on the verification complexity required for each of the historical access identities, where the unit complexity is the verification complexity corresponding to the unit fraud coefficient; Determining the verification complexity required for the access identity to be verified based on the fraud coefficient of the access identity to be verified and the unit complexity; Based on the verification complexity required by the access identity to be verified and the combination complexity, the target combination verification method is determined in each of the combination verification methods.

7. A financial data access identity authentication system, characterized in that: The system comprises: An acquisition unit, used to acquire multiple identity authentication methods, and determine multiple combined authentication methods based on the identity authentication methods; wherein the combined authentication method includes at least one of the identity authentication methods, and the identity authentication method is used to authenticate the user who accesses the financial data; A processing unit, used to determine the combination complexity of each of the combined verification methods; wherein the combination complexity is used to indicate the verification accuracy of the corresponding combined verification method; The acquisition unit is further used to acquire the access identity to be verified, input the access identity to be verified into a pre-trained fraud coefficient model, and determine the fraud coefficient of the access identity to be verified; wherein the fraud coefficient is used to indicate the probability that the corresponding access identity is suspected of fraud; an authentication unit, configured to determine a target combination verification method from each of the combination verification methods based on the fraud coefficient of the access identity to be verified and the combination complexity of each of the combination verification methods, and authenticate the identity of the access identity to be verified based on the target combination verification method; Based on the financial data, historical access information is obtained, the historical access information including historical access identities and first identity authentication results corresponding to each of the historical access identities, and identity feature information of the historical access identities; the fraud coefficient model is trained by the following method, including: For each piece of identity feature information, based on the first verification result corresponding to each feature value of the identity feature information, determine the availability of the identity feature information; wherein the availability is used to indicate the importance of the corresponding identity feature information for identity authentication; Determine the identity similarity between two of the historical access identities based on the availability of each of the identity feature information; For each of the historical access identities, based on the identity similarity between the historical access identity and other historical access identities, and the first identity authentication results of each of the historical access identities, determine a fraud coefficient of the historical access identity; The fraud coefficient model is obtained by training the fraud coefficient based on the historical access identity.

Images