Methods, devices, equipment, media and products for determining signature verification methods

Abstract

The present application belongs to the field of information security technology, and specifically provides a method, device, equipment, medium and product for determining a signature verification method. The method includes: obtaining the current transaction-related data generated by the user between triggering the current transaction process and triggering the previous transaction process; extracting features from the current transaction-related data to generate current transaction-related features; inputting the current transaction-related features into a preset signature verification method determination model to determine the corresponding signature verification method. The signature verification method determination method of the present application reflects the user's current security status through the current transaction-related data generated by the user between triggering the current transaction process and triggering the previous transaction process, and determines a matching signature verification method in combination with a preset signature verification method determination model, thereby improving the matching of the signature verification method with the user's transaction behavior process.

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular to a method, device, equipment, medium and product for determining a signature verification method. Background Art

[0002] With the continuous development of network technology, online transactions have gradually become a common choice for users. For online transactions such as large transactions in mobile banking, a signature verification process is required before the transaction to ensure the security of online information. Different signature verification methods consume different amounts of time and have different security.

[0003] The existing signature verification selection method generally provides the same set of signature verification methods for all users, and the information security and signature verification time are relatively fixed. Therefore, the matching between the signature verification method and the user transaction behavior process is low. Summary of the invention

[0004] The present application provides a method, device, equipment, medium and product for determining a signature verification method, so as to solve the problem that the current signature verification method has low compatibility with the user transaction behavior process.

[0005] The first aspect of the present application provides a method for determining a signature verification method, comprising:

[0006] Obtain the current transaction-related data generated by the user between triggering the current transaction process and triggering the previous transaction process;

[0007] Extracting features from the current transaction related data to generate current transaction related features;

[0008] The current transaction related features are input into a preset signature verification method determination model to determine the corresponding signature verification method.

[0009] Furthermore, in the method as described above, inputting the current transaction-related features into a preset signature verification method determination model to determine the corresponding signature verification method includes:

[0010] Inputting the current transaction related features into a preset signature verification method determination model to determine a corresponding signature verification method identifier;

[0011] The corresponding signature verification method is determined according to the signature verification method identifier.

[0012] Furthermore, in the above method, the step of inputting the current transaction-related features into a preset signature verification method determination model to determine a corresponding signature verification method identifier includes:

[0013] The preset signature verification method is used to determine the model to determine the origin of the preset signature verification coordinate system according to the historical transaction related features stored in the preset database;

[0014] The preset signature verification method is used to determine the model to determine the corresponding coordinate offset value according to the current transaction related characteristics;

[0015] The signature verification method identifier is determined according to the origin and the coordinate offset value.

[0016] Furthermore, in the above method, the historical transaction related features include: historical transaction behavior features and historical transaction flow features;

[0017] The method of using the preset signature verification method to determine the origin of the preset signature verification coordinate system according to the historical transaction behavior characteristics and historical transaction flow characteristics stored in the preset database includes:

[0018] The preset signature verification method is used to determine the model to determine the algorithm expression of the corresponding separating hyperplane according to the historical transaction behavior characteristics and the historical transaction flow characteristics;

[0019] The origin of the preset signature verification coordinate system is determined according to the algorithm expression.

[0020] Furthermore, in the method described above, the preset signature verification method determination model further includes: a preset classification decision function; the current transaction related features include: current transaction behavior features and current transaction flow features;

[0021] The using the preset signature verification method to determine the model to determine the corresponding coordinate offset value according to the current transaction related features includes:

[0022] Inputting the current transaction behavior feature into the preset classification decision function to determine the corresponding x-axis coordinate offset value;

[0023] The current transaction flow characteristics are input into the preset classification decision function to determine the corresponding y-axis coordinate offset value.

[0024] Furthermore, in the method as described above, determining the signature verification mode identifier according to the origin and the coordinate offset value includes:

[0025] Summing the origin, the x-axis coordinate offset value and the determined y-axis coordinate offset value to determine a final offset coordinate;

[0026] Determine the quadrant to which the final offset coordinate belongs in the preset signature verification coordinate system;

[0027] A corresponding signature verification method identifier is determined according to the quadrant; and the quadrant and the signature verification method identifier have a mapping relationship.

[0028] Furthermore, the method as described above, before obtaining the current transaction-related data of the user before triggering the transaction process, further includes:

[0029] Obtaining a training data set of the user; the training data set includes: transaction-related features to be trained and their corresponding classification labels;

[0030] Classifying the transaction-related features to be trained according to the classification labels;

[0031] Determine an algorithm expression corresponding to a separating hyperplane according to the classified transaction-related features to be trained;

[0032] Constructing a corresponding classification decision function according to the algorithm expression of the corresponding separating hyperplane;

[0033] The preset signature verification method determination model is constructed according to the algorithm expression of the corresponding separating hyperplane and the classification decision function.

[0034] Furthermore, the method as described above, after inputting the current transaction-related features into a preset signature verification method determination model to determine the corresponding signature verification method, further includes:

[0035] The corresponding signature verification method is used as the primary recommended signature verification method, and other signature verification methods are used as secondary recommended signature verification methods, and all signature verification methods are sent to the user terminal.

[0036] A second aspect of the present application provides a signature verification method determination device, comprising:

[0037] The acquisition module is used to obtain the current transaction related data generated by the user between triggering the current transaction process and triggering the previous transaction process;

[0038] A generating module, used for extracting features from the current transaction related data to generate current transaction related features;

[0039] The determination module is used to input the current transaction related features into a preset signature verification method determination model to determine the corresponding signature verification method.

[0040] Further, in the above device, the determining module is specifically used for:

[0041] The current transaction related features are input into a preset signature verification method determination model to determine a corresponding signature verification method identifier; and the corresponding signature verification method is determined according to the signature verification method identifier.

[0042] Furthermore, in the above-mentioned device, when the determination module inputs the current transaction-related features into a preset signature verification method determination model to determine the corresponding signature verification method identifier, it is specifically used to:

[0043] The preset signature verification method is used to determine the model to determine the origin of the preset signature verification coordinate system according to the historical transaction related characteristics stored in the preset database; the preset signature verification method is used to determine the model to determine the corresponding coordinate offset value according to the current transaction related characteristics; the signature verification method identifier is determined according to the origin and the coordinate offset value.

[0044] Furthermore, in the above device, the historical transaction related features include: historical transaction behavior features and historical transaction flow features;

[0045] When the determination module adopts the preset signature verification method to determine the origin of the preset signature verification coordinate system according to the historical transaction behavior characteristics and historical transaction flow characteristics stored in the preset database, it is specifically used to:

[0046] The preset signature verification method is used to determine the model to determine the algorithm expression of the corresponding separating hyperplane according to the historical transaction behavior characteristics and the historical transaction flow characteristics; and the origin of the preset signature verification coordinate system is determined according to the algorithm expression.

[0047] Furthermore, in the above-mentioned device, the preset signature verification method determination model further includes: a preset classification decision function; the current transaction related features include: current transaction behavior features and current transaction flow features;

[0048] When the determination module adopts the preset signature verification method to determine the model to determine the corresponding coordinate offset value according to the current transaction related features, it is specifically used to:

[0049] The current transaction behavior feature is input into the preset classification decision function to determine the corresponding x-axis coordinate offset value; the current transaction flow feature is input into the preset classification decision function to determine the corresponding y-axis coordinate offset value.

[0050] Furthermore, in the above-mentioned device, when the determination module determines the signature verification mode identifier according to the origin and the coordinate offset value, it is specifically used to:

[0051] The origin, the x-axis coordinate offset value and the determined y-axis coordinate offset value are summed to determine the final offset coordinate; the quadrant to which the final offset coordinate belongs in the preset signature verification coordinate system is determined; the corresponding signature verification method identifier is determined according to the quadrant; the quadrant and the signature verification method identifier have a mapping relationship.

[0052] Furthermore, the device as described above further comprises:

[0053] A construction module is used to obtain a training data set of the user; the training data set includes: transaction-related features to be trained and their corresponding classification labels; classifying the transaction-related features to be trained according to the classification labels; determining the algorithm expression of the corresponding separating hyperplane according to the classified transaction-related features to be trained; constructing the corresponding classification decision function according to the algorithm expression of the corresponding separating hyperplane; constructing the preset signature verification method determination model according to the algorithm expression of the corresponding separating hyperplane and the classification decision function.

[0054] Furthermore, the device as described above further comprises:

[0055] The sending module is used to recommend the corresponding signature verification method as a primary signature verification method and other signature verification methods as secondary recommended signature verification methods, and send all signature verification methods to the user terminal.

[0056] A third aspect of the present application provides an electronic device, including: a memory and a processor;

[0057] The memory stores computer-executable instructions;

[0058] The processor executes the computer-executable instructions stored in the memory to implement the method for determining the signature verification method as described in any one of the first aspects.

[0059] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method for determining the signature verification method described in any one of the first aspects.

[0060] The fifth aspect of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for determining the signature verification method described in any one of the first aspects.

[0061] The present application provides a method, device, equipment, medium and product for determining a signature verification method, the method comprising: obtaining current transaction-related data generated by the user between triggering the current transaction process and triggering the previous transaction process; performing feature extraction on the current transaction-related data to generate current transaction-related features; inputting the current transaction-related features into a preset signature verification method determination model to determine the corresponding signature verification method. The signature verification method determination method of the present application reflects the user's current security status through the current transaction-related data generated by the user between triggering the current transaction process and triggering the previous transaction process, and determines a matching signature verification method in combination with a preset signature verification method determination model, thereby improving the matching of the signature verification method with the user's transaction behavior process. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0063] Figure 1 A scene diagram of the method for determining the signature verification method in the embodiment of the present application can be implemented;

[0064] Figure 2 Schematic diagram of the process of determining the signature verification method provided for this application Figure 1 ;

[0065] Figure 3 Schematic diagram of the process of determining the signature verification method provided for this application Figure 2 ;

[0066] Figure 4 A schematic diagram of the overall user transaction process for the method for determining the signature verification method provided in this application;

[0067] Figure 5 A schematic diagram of the preset signature verification coordinate system and quadrants for the method for determining the signature verification method provided in this application;

[0068] Figure 6 A schematic diagram of the structure of the device for determining the signature verification method provided in this application;

[0069] Figure 7 A schematic diagram of the structure of the electronic device provided in this application.

[0070] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0071] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0072] In the technical solutions of the embodiments of the present application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0073] It should be noted that the method, device, equipment, medium and product for determining the signature verification method disclosed herein can be used in the field of information security. It can also be used in any field other than information security, such as the financial field. The application field of the method, device, equipment, medium and product for determining the signature verification method disclosed herein is not limited.

[0074] The technical solution of the present application is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0075] In order to clearly understand the technical solution of the present application, the solution of the prior art is first introduced in detail. Signature verification is a way to improve information security, and there are many ways to verify signatures, such as public key, private key, digital signature, etc. The security of each signature verification method and the time consumed for verification are different. In an environment where online transactions have become a regular choice for users, signature verification has become a regular way to improve online information security. Existing signature verification selection methods generally provide the same set of signature verification methods for all users, and the information security and signature verification time are relatively fixed, and the flexibility is poor, such as signature verification methods that are both highly secure but time-consuming, or less secure and time-consuming. As a result, the matching between the signature verification method and the user transaction behavior process is low.

[0076] Therefore, in order to solve the problem of low matching between the signature verification method in the prior art and the user's transaction behavior process, the inventors found through research that a signature verification method with a higher matching rate with the user's transaction behavior process can be determined by combining a preset signature verification method determination model with the user's transaction-related data.

[0077] Specifically, the current transaction-related data generated by the user between triggering the current transaction process and triggering the previous transaction process is obtained. Feature extraction is performed on the current transaction-related data to generate current transaction-related features. The current transaction-related features are input into the preset signature verification method determination model to determine the corresponding signature verification method.

[0078] The signature verification method determination method of the present application reflects the user's current security status through the current transaction-related data generated between the user triggering the current transaction process and triggering the previous transaction process, and determines the matching signature verification method in combination with the preset signature verification method determination model, thereby improving the matching of the signature verification method with the user's transaction behavior process.

[0079] Based on the above creative findings, the inventor proposed the technical solution of the present application.

[0080] The following is an introduction to the application scenarios of the method for determining the signature verification method provided in the embodiment of the present application. Figure 1As shown, 1 is an electronic device and 2 is a user terminal. The network architecture of the application scenario corresponding to the method for determining the signature verification mode provided in the embodiment of the present application includes: an electronic device 1 and a user terminal 2. In this embodiment, the user terminal 2 can be a terminal device such as a smart phone or a computer.

[0081] When the user performs transaction-related behaviors through the user terminal 2, the user terminal 2 will send the current transaction-related data generated during the transaction-related behaviors to the electronic device 1. Transaction-related behaviors include user login, user viewing data, account balance changes, etc. When the user triggers the current transaction process, the electronic device 1 will extract features from the acquired current transaction-related data to generate current transaction-related features, and input the current transaction-related features into the preset signature verification method determination model to determine the corresponding signature verification method. After determining the signature verification method, the electronic device 1 can provide the signature verification method to the user terminal 2 to perform the signature verification process. The provided signature verification method can be a determined signature verification method, or it can be a plurality of signature verification methods including the determined signature verification method, with the determined signature verification method being the primary signature verification method and other signature verification methods being secondary signature verification methods for the user to choose, thereby further improving the matching of the signature verification method with the user's transaction behavior.

[0082] The embodiments of the present application are introduced below in conjunction with the drawings in the specification.

[0083] Figure 2 Schematic diagram of the process of determining the signature verification method provided for this application Figure 1 ,like Figure 2 As shown, in this embodiment, the execution subject of the embodiment of the present application is a signature verification method determination device, which can be integrated in an electronic device, such as a signature verification server. The signature verification method determination method provided in this embodiment includes the following steps:

[0084] Step S101, obtaining the current transaction related data generated by the user between triggering the current transaction process and triggering the previous transaction process.

[0085] In this embodiment, when the current transaction process is such as triggering the process of trading a certain product, the data generated between triggering the previous transaction process and triggering the process of trading a certain product is the current transaction-related data, such as transaction behavior data, including clicking on pictures, viewing product details, login time, login location, device identification, historical signature verification records, etc., transaction flow data, including user accounts, account balances, account limits, etc.

[0086] The current transaction-related data can be collected in real time and stored in a preset database. When the current transaction-related data is needed, it can be directly obtained from the preset database, thereby improving the overall efficiency of the signature verification process.

[0087] Users can perform transaction-related actions and trigger the current transaction process through user terminals such as mobile phones, computers, etc.

[0088] Step S102: extracting features from the current transaction related data to generate current transaction related features.

[0089] In this embodiment, the method of extracting features from the current transaction related data may use a convolutional neural network to further improve the accuracy of the current transaction related features. The current transaction related features may include current transaction behavior features and current transaction flow features, and may also include other transaction related features, such as user attribute features.

[0090] Step S103: input the current transaction related features into a preset signature verification method determination model to determine the corresponding signature verification method.

[0091] The preset signature verification method determination model can analyze the current transaction-related features to match the appropriate signature verification method, so that the determined signature verification method is highly compatible with the user's transaction behavior process. The preset signature verification method determination model can be constructed and trained based on the user's historical transaction-related features.

[0092] The embodiment of the present application provides a method for determining a signature verification method, the method comprising: obtaining current transaction related data generated by a user between triggering the current transaction process and triggering the previous transaction process. Performing feature extraction on the current transaction related data to generate current transaction related features. Inputting the current transaction related features into a preset signature verification method determination model to determine the corresponding signature verification method.

[0093] The signature verification method determination method of the present application reflects the user's current security status through the current transaction-related data generated between the user triggering the current transaction process and triggering the previous transaction process, and determines the matching signature verification method in combination with the preset signature verification method determination model, thereby improving the matching of the signature verification method with the user's transaction behavior process.

[0094] Figure 3 Schematic diagram of the process of determining the signature verification method provided for this application Figure 2 ,like Figure 3 As shown, the method for determining the signature verification method provided in this embodiment is a further refinement of the method for determining the signature verification method provided in the previous embodiment of the present application. The method for determining the signature verification method provided in this embodiment includes the following steps.

[0095] Step S201, obtaining a user's training data set. The training data set includes: transaction-related features to be trained and their corresponding classification labels.

[0096] Exemplarily, the training data set established may be T = {(x1, y1), (x2, y2), ... (xN, yN)}, where xi∈Rn is the feature space composed of the transaction-related features to be trained, yi∈{+1, -1}, xi is an instance based on the feature space, yi is the classification label corresponding to xi, and yi is set by the model builder based on prior knowledge. For example, +1 corresponds to increased information security, such as commonly used mobile phones, commonly used login locations, etc., and -1 corresponds to reduced information security, such as uncommon mobile phones, uncommon login locations, etc. Thus, the transaction-related features to be trained are divided into two categories. At the same time, the training data set can also be divided into more categories, such as classification according to specific detailed categories in the transaction-related features.

[0097] Step S202: classify the transaction-related features to be trained according to the classification labels.

[0098] In this embodiment, as shown in the above example, the transaction-related features to be trained can be classified into corresponding categories according to the classification label corresponding to each transaction-related feature to be trained, so as to facilitate the subsequent determination of the corresponding separating hyperplane and its algorithm expression.

[0099] Step S203, determining an algorithm expression corresponding to a separating hyperplane according to the classified transaction-related features to be trained.

[0100] Since the training set is linearly separable, the separating hyperplane is a linear subspace in the feature space, so it must pass through the origin of the preset signature verification coordinate system, where the preset signature verification coordinate system is constructed by transaction-related features.

[0101] The algorithm expression of the corresponding separation hyperplane can be determined by the maximum interval processing method according to the classified transaction-related features to be trained. The meaning of the maximum interval is: if the sample is linearly separable, many solutions that can correctly divide the sample can always be found. Which one is the best, that is, to find the optimal separation interface. The algorithm expression is as follows:

[0102] w * ·x+b * =0

[0103] Among them, w * is one of the algorithm parameters, x is the transaction-related feature, b * is another algorithm parameter.

[0104] The process of determining the algorithmic expression of the separating hyperplane is similar to finding a line that has the largest separation between the relevant features of different categories of transactions and passes through the origin of the coordinate system. * and b * The value of is used to meet the conditions, thereby determining the final algorithm parameter value and obtaining the algorithm expression of the separating hyperplane. If there are many transaction-related feature categories, then w* It can be expressed in the form of a matrix.

[0105] Step S204: construct a corresponding classification decision function according to the algorithm expression of the corresponding separating hyperplane.

[0106] The classification decision function is closely related to the algorithmic expression of the separating hyperplane. Optionally, in this embodiment, the sign function can be used as the classification decision function, as shown below:

[0107] f(x)=sign(w * ·x+b * )

[0108] Among them, f(x) is the constructed classification decision function.

[0109] Step S205: construct a preset signature verification method determination model according to the algorithm expression of the corresponding separating hyperplane and the classification decision function.

[0110] In this embodiment, the preset signature verification method determination model can adopt a support vector machine, which includes an algorithm expression of a separating hyperplane, a classification decision function, and a processing flow module. The processing flow module is used to determine the corresponding origin according to transaction-related features, determine the corresponding coordinate offset value according to transaction-related features, determine the signature verification method, and other process processing.

[0111] Step S206, obtaining the current transaction related data generated by the user between triggering the current transaction process and triggering the previous transaction process.

[0112] like Figure 4 As shown, when a user logs into a transaction-related application such as a bank's application through a user terminal such as a smart phone, the user will start to obtain current transaction-related data generated by the user's transaction behavior in the figure until entering the transaction process.

[0113] Step S207: extracting features from the current transaction related data to generate current transaction related features.

[0114] like Figure 4 As shown, by extracting features from the current transaction-related data and processing the generated current transaction-related features, the signature verification method is determined (as shown in steps S208 and S209). After the user triggers the transaction process, he will enter the account information, such as the transaction amount data, and then enter the signature verification process. After the signature verification is completed, the subsequent transaction process will be carried out.

[0115] Step S208: input the current transaction related features into a preset signature verification method determination model to determine the corresponding signature verification method identifier.

[0116] There are multiple signature verification methods. Through the mapping relationship between the signature verification method identifier and the signature verification method, the corresponding signature verification method can be determined according to the signature verification method identifier, thereby further improving the efficiency of determining the signature verification method.

[0117] Optionally, in this embodiment, step S208 specifically includes:

[0118] Step S2081, using a preset signature verification method to determine the model to determine the origin of a preset signature verification coordinate system according to historical transaction related features stored in a preset database.

[0119] The historical transaction-related features are relative to the current transaction-related features, and refer to the transaction-related features generated historically before the current transaction-related features were generated. The historical transaction-related features can reflect the changes in the user's transaction behavior and the changes in the user's transaction flow, so that the origin of the corresponding preset signature verification coordinate system can be determined based on the historical transaction-related features. If the current transaction-related features deviate greatly from the historical transaction-related features, the offset value corresponding to the current transaction-related features is larger; if the current transaction-related features deviate slightly from the historical transaction-related features, the offset value corresponding to the current transaction-related features is smaller.

[0120] Optionally, in this embodiment, the historical transaction-related features are similar to the current transaction-related features, including: historical transaction behavior features and historical transaction flow features.

[0121] Then the step S2081 of determining the origin of the preset signature verification coordinate system may be specifically as follows:

[0122] The preset signature verification method is used to determine the model and the algorithm expression of the corresponding separating hyperplane is determined according to the historical transaction behavior characteristics and historical transaction flow characteristics.

[0123] Determine the origin of the preset signature verification coordinate system based on the algorithm expression.

[0124] The method of determining the algorithmic expression corresponding to the separating hyperplane is similar to that of constructing a model for determining the preset signature verification method. The algorithmic expression corresponding to the separating hyperplane can be determined according to the historical transaction behavior characteristics and historical transaction flow characteristics through the maximum interval processing method. The process of determining the algorithmic expression of the separating hyperplane is similar to finding a line with the largest interval and passing through the origin of the coordinate system in this embodiment. The conditions are met by adjusting the numerical values ​​of the algorithmic parameters to determine the final algorithmic parameter values ​​and obtain the algorithmic expression of the separating hyperplane.

[0125] Step S2082: Use the preset signature verification method to determine the model to determine the corresponding coordinate offset value according to the current transaction-related characteristics.

[0126] The coordinate offset value can reflect the difference between the current transaction-related features and the historical transaction-related features. For example, if the user usually uses user terminal A for the transaction process, and currently uses user terminal B for the transaction process, a large negative coordinate offset value will be generated. Since the offset value can be positive or negative, the coordinate offset value can be used to determine in which quadrant of the preset signature verification coordinate system the coordinates generated by the current transaction-related features are located, thereby determining the corresponding signature verification method and improving the matching with the user's transaction behavior process.

[0127] Optionally, in this embodiment, the preset signature verification method determination model further includes: a preset classification decision function. The current transaction related features include: current transaction behavior features and current transaction flow features.

[0128] Step S2082 may specifically include:

[0129] The current transaction behavior characteristics are input into the preset classification decision function to determine the corresponding x-axis coordinate offset value.

[0130] The current transaction flow characteristics are input into the preset classification decision function to determine the corresponding y-axis coordinate offset value.

[0131] In this embodiment, the current transaction behavior feature is used as the x variable, and the current transaction flow feature is used as the y variable, so that the coordinate offset values ​​f(x) and f(y) can be obtained. If the value of f(x) is positive, it will be offset in the positive direction of the x-axis. If the value of f(x) is negative, it will be offset in the negative direction of the x-axis. If the value of f(y) is positive, it will be offset in the positive direction of the y-axis. If the value of f(y) is negative, it will be offset in the negative direction of the y-axis. Since the current transaction behavior feature may include multiple features, such as transaction products, transaction time, login location, transaction address, model used, client version, original pressure distribution information collected by the pressure sensor of the touch screen mobile phone, etc., the coordinate offset value of each current transaction behavior feature can be superimposed. Similarly, the current transaction flow features include features such as capital card, capital balance, transaction quantity, transaction settlement amount, etc., and the coordinate offset value of each current transaction flow feature can also be superimposed to generate the final coordinate offset value.

[0132] Step S2083, determine the signature verification method identifier based on the origin and coordinate offset value.

[0133] The final offset coordinates can be obtained by accumulating the origin and the coordinate offset values. Then, the corresponding quadrant is determined according to the final offset coordinates to determine the signature verification method identifier that has a mapping relationship with the quadrant.

[0134] Optionally, in this embodiment, step S2083 may specifically be:

[0135] The origin, the x-axis coordinate offset value, and the determined y-axis coordinate offset value are summed to determine the final offset coordinates.

[0136] Determine the quadrant to which the final offset coordinates belong in the preset signature verification coordinate system.

[0137] The corresponding signature verification method identifier is determined according to the quadrant. The quadrant and the signature verification method identifier have a mapping relationship.

[0138] like Figure 5 As shown in the figure, the origin of the preset signature verification coordinate system is (x 0 ,y 0 ), in counterclockwise direction, they are the first quadrant A 1 、Second Quadrant A 2 、The third quadrant A 3 and the fourth quadrant A 4 In other application scenarios, it can also be set to eight quadrants, sixteen quadrants and other high-dimensional quadrants. After determining the quadrant to which the final offset coordinate belongs in the preset signature verification coordinate system, it is assumed that the quadrant belongs to the third quadrant A. 3 , the corresponding signature verification method is the public key and private key method, then the signature verification method is determined to be the public key and private key method.

[0139] The selection logic of signature verification methods in different quadrants is as follows:

[0140] If the X-axis deviates in the positive direction, it means that the customer's behavior accounts for a large proportion of the existing behaviors (such as entering frequently browsed transaction columns, using commonly used mobile phone models, etc.). At this time, a relatively low-security and high-convenience signature verification method (such as card password verification) can be provided. If it deviates in the negative direction, it means that the customer's behavior accounts for a small proportion of the existing behaviors (entering unfamiliar transactions, using new mobile phone models), at this time, a relatively high-security and low-convenience signature verification method (such as U-Shield) can be provided.

[0141] If the Y axis deviates in the positive direction, it means that the customer's transaction flow is lower than the existing transaction flow, the potential loss is lower, and the signature verification method is chosen for convenience. If it deviates in the negative direction, it means that the customer's transaction flow exceeds the existing transaction flow, the potential loss is higher, and the signature verification method is chosen for security.

[0142] Therefore, the signature verification method corresponding to the third quadrant may be a signature verification method with higher security, and the signature verification method corresponding to the first quadrant may be a signature verification method that consumes less time.

[0143] Step S209: determine the corresponding signature verification method according to the signature verification method identifier.

[0144] Optionally, in this embodiment, after the signature verification method is determined, other signature verification methods may be provided to the user terminal as secondary signature verification methods for the user to select, thereby providing richness of signature verification. The specific process is as follows:

[0145] The corresponding signature verification method is mainly recommended as the signature verification method, and other signature verification methods are secondarily recommended signature verification methods. All signature verification methods are sent to the user terminal.

[0146] At the same time, after each transaction and signature verification process, the preset signature verification method determination model can be updated according to the transaction-related characteristics and signature verification process result data, that is, the parameters in the classification decision function can be adjusted to update the origin coordinates for the next time.

[0147] Figure 6 The schematic diagram of the structure of the device for determining the signature verification method provided in this application is as follows: Figure 6 As shown, in this embodiment, the signature verification method determination device 300 can be set in an electronic device, and the signature verification method determination device 300 includes:

[0148] The acquisition module 301 is used to acquire the current transaction related data generated by the user between triggering the current transaction process and triggering the previous transaction process.

[0149] The generating module 302 is used to extract features from the current transaction related data to generate current transaction related features.

[0150] The determination module 303 is used to input the current transaction related features into a preset signature verification method determination model to determine the corresponding signature verification method.

[0151] The signature verification method determination device provided in this embodiment can be executed Figure 2 The technical solution of the method embodiment shown in the figure has the same implementation principle and technical effect as Figure 2 The method embodiments shown are similar and will not be described in detail here.

[0152] The signature verification method determination device provided in this application is further refined on the basis of the signature verification method determination device provided in the previous embodiment, and the signature verification method determination device 300 includes:

[0153] Optionally, in this embodiment, the determination module 303 is specifically used to:

[0154] Input the current transaction-related features into the preset signature verification method determination model to determine the corresponding signature verification method identifier. Determine the corresponding signature verification method based on the signature verification method identifier.

[0155] Optionally, in this embodiment, when the determination module 303 inputs the current transaction-related features into the preset signature verification method determination model to determine the corresponding signature verification method identifier, it is specifically used to:

[0156] The preset signature verification method is used to determine the model. The origin of the preset signature verification coordinate system is determined according to the historical transaction-related features stored in the preset database. The preset signature verification method is used to determine the model. The corresponding coordinate offset value is determined according to the current transaction-related features. The signature verification method identifier is determined based on the origin and the coordinate offset value.

[0157] Optionally, in this embodiment, the historical transaction related features include: historical transaction behavior features and historical transaction flow features.

[0158] When the determination module 303 adopts the preset signature verification method to determine the origin of the preset signature verification coordinate system according to the historical transaction behavior characteristics and historical transaction flow characteristics stored in the preset database, it is specifically used to:

[0159] The preset signature verification method is used to determine the model. The algorithm expression of the corresponding separation hyperplane is determined according to the historical transaction behavior characteristics and historical transaction flow characteristics. The origin of the preset signature verification coordinate system is determined according to the algorithm expression.

[0160] Optionally, in this embodiment, the preset signature verification method determination model further includes: a preset classification decision function. The current transaction related features include: current transaction behavior features and current transaction flow features.

[0161] When the determination module 303 adopts the preset signature verification method to determine the model to determine the corresponding coordinate offset value according to the current transaction-related characteristics, it is specifically used to:

[0162] Input the current transaction behavior characteristics into the preset classification decision function to determine the corresponding x-axis coordinate offset value. Input the current transaction flow characteristics into the preset classification decision function to determine the corresponding y-axis coordinate offset value.

[0163] Optionally, in this embodiment, when determining the signature verification method identifier according to the origin and the coordinate offset value, the determination module 303 is specifically used to:

[0164] The origin, the x-axis coordinate offset value, and the determined y-axis coordinate offset value are summed to determine the final offset coordinate. The quadrant to which the final offset coordinate belongs in the preset signature verification coordinate system is determined. The corresponding signature verification method identifier is determined according to the quadrant. The quadrant and the signature verification method identifier have a mapping relationship.

[0165] Optionally, in this embodiment, the signature verification method determination device 300 further includes:

[0166] A construction module is used to obtain a training data set of the user. The training data set includes: transaction-related features to be trained and their corresponding classification labels. The transaction-related features to be trained are classified according to the classification labels. The algorithm expression of the corresponding separating hyperplane is determined according to the classified transaction-related features to be trained. The corresponding classification decision function is constructed according to the algorithm expression of the corresponding separating hyperplane. The preset signature verification method determination model is constructed according to the algorithm expression of the corresponding separating hyperplane and the classification decision function.

[0167] Optionally, in this embodiment, the signature verification method determination device 300 further includes:

[0168] The sending module is used to recommend the corresponding signature verification method as the primary signature verification method and other signature verification methods as the secondary recommended signature verification methods, and send all signature verification methods to the user terminal.

[0169] The signature verification method determination device provided in this embodiment can be executed Figure 2-Figure 5 The technical solution of the method embodiment shown in the figure has the same implementation principle and technical effect as Figure 2-Figure 5 The method embodiments shown are similar and will not be described in detail here.

[0170] According to an embodiment of the present application, the present application also provides an electronic device, a computer-readable storage medium and a computer program product.

[0171] like Figure 7 As shown, Figure 7 is a schematic diagram of the structure of the electronic device provided by the present application. The electronic device is intended for various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0172] like Figure 7 As shown, the electronic device includes: a processor 401 and a memory 402. The various components are connected to each other using different buses and can be installed on a common mainboard or in other ways as required. The processor can process instructions executed in the electronic device.

[0173] The memory 402 is a non-transitory computer-readable storage medium provided in the present application. The memory stores instructions executable by at least one processor to enable at least one processor to perform the method for determining the signature verification method provided in the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, which are used to enable a computer to perform the method for determining the signature verification method provided in the present application.

[0174] The memory 402 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the signature verification method determination method in the embodiment of the present application (for example, the attached Figure 6 The processor 401 executes various functional applications and data processing of the electronic device by running the non-transient software programs, instructions and modules stored in the memory 402, that is, the method for determining the signature verification method in the above method embodiment is implemented.

[0175] At the same time, this embodiment also provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device can execute the method for determining the signature verification method of the above embodiment.

[0176] Those skilled in the art will readily come up with other implementations of the embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modifications, uses or adaptations of the embodiments of the present application, which follow the general principles of the embodiments of the present application and include common knowledge or customary technical means in the art that are not disclosed in the embodiments of the present application.

[0177] It should be understood that the embodiments of the present application are not limited to the precise structures described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the embodiments of the present application is limited only by the appended claims.

Claims

1. A method for determining a signature verification method, It is characterized in that include: Obtain the current transaction-related data generated by the user between triggering the current transaction process and triggering the previous transaction process; Extracting features from the current transaction related data to generate current transaction related features; The model uses the preset signature verification method to determine the origin of the preset signature verification coordinate system based on the historical transaction related features stored in the preset database; The preset signature verification method is used to determine the model to determine the corresponding coordinate offset value according to the current transaction related characteristics; Determine the signature verification method identifier corresponding to the current transaction related feature according to the origin and the coordinate offset value; The corresponding signature verification method is determined according to the signature verification method identifier.

2. The method according to claim 1, It is characterized in that The historical transaction related features include: historical transaction behavior features and historical transaction flow features; The method of using the preset signature verification method to determine the origin of the preset signature verification coordinate system according to the historical transaction behavior characteristics and historical transaction flow characteristics stored in the preset database includes: The preset signature verification method is used to determine the model to determine the algorithm expression of the corresponding separating hyperplane according to the historical transaction behavior characteristics and the historical transaction flow characteristics; The origin of the preset signature verification coordinate system is determined according to the algorithm expression.

3. The method according to claim 2, It is characterized in that The preset signature verification method determination model also includes: a preset classification decision function; the current transaction related features include: current transaction behavior features and current transaction flow features; The using the preset signature verification method to determine the model to determine the corresponding coordinate offset value according to the current transaction related features includes: Inputting the current transaction behavior feature into the preset classification decision function to determine the corresponding x-axis coordinate offset value; The current transaction flow characteristics are input into the preset classification decision function to determine the corresponding y-axis coordinate offset value.

4. The method according to claim 3, It is characterized in that The determining the signature verification mode identifier according to the origin and the coordinate offset value includes: Summing the origin, the x-axis coordinate offset value and the determined y-axis coordinate offset value to determine a final offset coordinate; Determine the quadrant to which the final offset coordinate belongs in the preset signature verification coordinate system; A corresponding signature verification method identifier is determined according to the quadrant; and the quadrant and the signature verification method identifier have a mapping relationship.

5. The method according to any one of claims 1 to 4, It is characterized in that Before obtaining the current transaction-related data of the user before triggering the transaction process, the method further includes: Obtaining a training data set of the user; the training data set includes: transaction-related features to be trained and their corresponding classification labels; Classifying the transaction-related features to be trained according to the classification labels; Determine an algorithm expression corresponding to a separating hyperplane according to the classified transaction-related features to be trained; Constructing a corresponding classification decision function according to the algorithm expression of the corresponding separating hyperplane; The preset signature verification method determination model is constructed according to the algorithm expression of the corresponding separating hyperplane and the classification decision function.

6. The method according to claim 5, It is characterized in that After inputting the current transaction related features into a preset signature verification method determination model to determine a corresponding signature verification method, the method further includes: The corresponding signature verification method is used as the primary recommended signature verification method, and other signature verification methods are used as secondary recommended signature verification methods, and all signature verification methods are sent to the user terminal.

7. A signature verification method determination device, It is characterized in that include: The acquisition module is used to obtain the current transaction related data generated by the user between triggering the current transaction process and triggering the previous transaction process; A generating module, used for extracting features from the current transaction related data to generate current transaction related features; A determination module, used to determine the origin of a preset signature verification coordinate system using a preset signature verification method determination model according to historical transaction related features stored in a preset database; The preset signature verification method is used to determine the model to determine the corresponding coordinate offset value according to the current transaction related characteristics; Determine the signature verification method identifier corresponding to the current transaction related feature according to the origin and the coordinate offset value; The corresponding signature verification method is determined according to the signature verification method identifier.

8. An electronic device, It is characterized in that include: Memory and processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method for determining the signature verification method according to any one of claims 1 to 6.

9. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method for determining the signature verification method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the method for determining the signature verification method as described in any one of claims 1 to 6 is implemented.

Images