Credit card information processing method and device, readable storage medium and electronic equipment

Abstract

The invention discloses a credit card information processing method and device, a readable storage medium and electronic equipment. Relates to the field of artificial intelligence, and comprises the following steps: obtaining credit card information of a credit card of a user, the credit card information at least comprising transaction data of the credit card; the credit card information is processed through multiple processing models, processing results corresponding to the processing models are obtained, the multiple processing models at least comprise a support vector machine, a K neighbor model, a random forest model and a lifting method model, and the processing results represent the probability that illegal transactions exist in the credit card; and determining target information according to the processing results corresponding to the plurality of processing models and the weight coefficients corresponding to the plurality of processing models. Through the method and the device, the problem of low detection accuracy caused by detecting illegal transaction of a credit card based on a single mode in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and more specifically, to a method, device, readable storage medium and electronic device for processing credit card information. Background Art

[0002] With the widespread use of credit cards, the frequency of illegal credit card transactions has gradually increased, causing serious economic losses to financial institutions and users. Therefore, how to efficiently and accurately detect illegal credit card transactions is an urgent problem to be solved.

[0003] At present, most methods for detecting illegal credit card transactions usually rely on a single algorithm or model, such as rule-based methods, single machine learning algorithms, etc. These methods show limitations when faced with diversified transaction behaviors, thus affecting the accuracy of detecting illegal credit card transactions.

[0004] Currently, no effective solution has been proposed to address the problem of low detection accuracy due to the single-method detection of illegal credit card transactions in related technologies. Summary of the invention

[0005] The main purpose of this application is to provide a method, device, readable storage medium and electronic device for processing credit card information to solve the problem of low detection accuracy in the related art of detecting illegal credit card transactions based on a single method.

[0006] According to one aspect of an embodiment of the present invention, a method for processing credit card information is provided, comprising: obtaining credit card information of a user's credit card, wherein the credit card information at least includes transaction data of the credit card; processing the credit card information through multiple processing models to obtain processing results corresponding to each processing model, wherein the multiple processing models at least include: a support vector machine, a K nearest neighbor model, a random forest model, and a lifting method model, and the processing results represent the probability that an illegal transaction occurs on the credit card; determining target information based on the processing results corresponding to the multiple processing models and the weight coefficients corresponding to the multiple processing models, wherein the target information is used to represent whether an illegal transaction occurs on the credit card.

[0007] Furthermore, the method for processing credit card information also includes: obtaining a test sample set, wherein the test samples in the test sample set include first sample credit card information, and the true label of the test sample is used to characterize whether there is an illegal transaction in the first sample credit card corresponding to the first sample credit card information; using the test sample set to test multiple processing models to obtain the prediction accuracy corresponding to each processing model; and determining the weight coefficients corresponding to the multiple processing models based on the prediction accuracy corresponding to the multiple processing models.

[0008] Furthermore, the credit card information processing method also includes: summing the prediction accuracy rates of multiple processing models to obtain a first value; calculating the ratio between the prediction accuracy rate of each processing model and the first value to obtain a weight coefficient corresponding to each processing model.

[0009] Furthermore, the method for processing credit card information also includes: for each processing model, calculating the product between the probability value in the processing result of the processing model and the weight coefficient corresponding to the processing result to obtain a second numerical value corresponding to the processing model; adding the second numerical values ​​corresponding to multiple processing models to obtain a third numerical value; and determining the target information based on the third numerical value.

[0010] Furthermore, the credit card information processing method also includes: when the third value is greater than a preset threshold, determining that the target information indicates that the credit card has an illegal transaction; when the third value is less than or equal to the preset threshold, determining that the target information indicates that the credit card has no illegal transaction.

[0011] Furthermore, the method for processing credit card information also includes: obtaining a training sample set, wherein the training samples in the training sample set include second sample credit card information, and the true label of the training sample is used to characterize whether the second sample credit card corresponding to the second sample credit card information has illegal transactions; using the training sample set to train multiple initial processing models respectively to obtain multiple processing models, wherein the multiple initial processing models include at least: an initial support vector machine, an initial K nearest neighbor model, an initial random forest model, and an initial boosting model.

[0012] Furthermore, the credit card information processing method also includes: obtaining initial sample credit card information of a second sample credit card; preprocessing the initial sample credit card information to obtain second sample credit card information, wherein the preprocessing is at least one of the following: data denoising processing, outlier removal processing, and vector conversion processing; constructing a training sample set based on the second sample credit card information and the real label corresponding to the second sample credit card information.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for processing credit card information is provided. The device includes: a first acquisition module, used to obtain the credit card information of the user's credit card, wherein the credit card information at least includes the transaction data of the credit card; a first processing module, used to process the credit card information through multiple processing models to obtain the processing results corresponding to each processing model, wherein the multiple processing models at least include: support vector machine, K nearest neighbor model, random forest model, lifting method model, and the processing results represent the probability of illegal transactions in the credit card; a first determination module, used to determine the target information according to the processing results corresponding to the multiple processing models and the weight coefficients corresponding to the multiple processing models, wherein the target information is used to represent whether the credit card has illegal transactions.

[0014] Furthermore, the data processing device also includes: a second acquisition module, used to acquire a test sample set, wherein the test samples in the test sample set include first sample credit card information, and the true label of the test sample is used to characterize whether the first sample credit card corresponding to the first sample credit card information has any illegal transactions; a second processing module, used to test multiple processing models using the test sample set to obtain the prediction accuracy corresponding to each processing model; and a second determination module, used to determine the weight coefficients corresponding to multiple processing models based on the prediction accuracy corresponding to the multiple processing models.

[0015] Furthermore, the second determination module also includes: a first calculation submodule, used to sum the prediction accuracy of multiple processing models to obtain a first value; a second calculation submodule, used to calculate the ratio between the prediction accuracy of each processing model and the first value to obtain the weight coefficient corresponding to each processing model.

[0016] Furthermore, the first determination module also includes: a third calculation submodule, which is used to calculate, for each processing model, the product of the probability value in the processing result of the processing model and the weight coefficient corresponding to the processing result, to obtain a second numerical value corresponding to the processing model; a fourth calculation submodule, which is used to add the second numerical values ​​corresponding to multiple processing models to obtain a third numerical value; and a determination submodule, which is used to determine the target information based on the third numerical value.

[0017] Furthermore, the determination submodule also includes: a first determination unit, used to determine that the target information represents the existence of illegal transactions on the credit card when the third value is greater than a preset threshold; a second determination unit, used to determine that the target information represents the existence of illegal transactions on the credit card when the third value is less than or equal to the preset threshold.

[0018] Furthermore, the data processing device also includes: a third acquisition module, used to obtain a training sample set, wherein the training samples in the training sample set include second sample credit card information, and the true label of the training sample is used to characterize whether the second sample credit card corresponding to the second sample credit card information has illegal transactions; a third processing module, used to use the training sample set to train multiple initial processing models respectively to obtain multiple processing models, wherein the multiple initial processing models include at least: an initial support vector machine, an initial K nearest neighbor model, an initial random forest model, and an initial boosting model.

[0019] Furthermore, the third acquisition module also includes: an acquisition submodule, used to obtain initial sample credit card information of the second sample credit card; a first processing submodule, used to preprocess the initial sample credit card information to obtain second sample credit card information, wherein the preprocessing is at least one of the following: data denoising processing, outlier removal processing, and vector conversion processing; a second processing submodule, used to construct a training sample set based on the second sample credit card information and the real label corresponding to the second sample credit card information.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned credit card information processing method.

[0021] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, the electronic device comprising a memory storing an executable program; a processor for running the program, wherein the above-mentioned credit card information processing method is executed when the program is running.

[0022] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, including computer instructions, which implement the steps of the above-mentioned credit card information processing method when executed by a processor.

[0023] In the embodiment of the present application, a method based on multiple processing models and different weight coefficients is adopted to determine whether there is an illegal transaction on a credit card. By collecting user credit card information, a data basis is provided for subsequent model processing, ensuring the comprehensiveness and accuracy of the data so that the processing model can accurately analyze the usage of the credit card. By determining the probability of illegal transactions of the credit card based on multiple processing models, it is possible to analyze the credit card data from different angles and methods. By assigning a weight coefficient to the processing result of each processing model to determine whether there is an illegal transaction on the credit card, it is possible to summarize the processing results of multiple processing models based on the importance of each processing model to realize risk transaction identification, thereby improving the accuracy of detecting illegal credit card transactions.

[0024] It can be seen that the solution provided in the present application achieves the purpose of determining whether there is an illegal transaction on a credit card based on multiple processing models and different weight coefficients, thereby achieving the technical effect of improving the detection accuracy of illegal transactions on credit cards, and further solving the problem of low detection accuracy caused by detecting illegal transactions on credit cards based on a single method in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] Figure 1 is a hardware structure block diagram of a computer terminal provided according to an embodiment of the present application;

[0027] Figure 2 is a schematic diagram of a method for processing credit card information provided according to an embodiment of the present application;

[0028] Figure 3 is a detection schematic diagram of a processing model provided according to an embodiment of the present application;

[0029] Figure 4 is a schematic diagram of a credit card information processing device provided according to an embodiment of the present application;

[0030] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0034] Example 1

[0035] According to an embodiment of the present application, an embodiment of a method for processing credit card information is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for processing credit card information is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0037] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0038] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the credit card information processing method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned credit card information processing method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0039] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0041] Under the above operating environment, this application provides Figure 2 How credit card information is processed as indicated. Figure 2 It is a schematic diagram of a method for processing credit card information provided according to an embodiment of the present application.

[0042] Step S201, obtaining the credit card information of the user's credit card, wherein the credit card information at least includes the transaction data of the credit card.

[0043] Optionally, electronic devices, application systems, servers and other devices may be used as the execution subject of the present application. In this embodiment, a data processing system is used as the execution subject to execute the above-mentioned credit card information processing method.

[0044] Optionally, credit card information is important data related to the credit card, which may include the cardholder's personal information, credit card transaction data, etc.

[0045] Optionally, transaction data is a detailed record of payment, transfer, cash withdrawal and other operations performed by credit cards at different times or places, including transaction user information, transaction amount, transaction time, transaction location, etc.

[0046] Step S202, processing the credit card information through multiple processing models to obtain processing results corresponding to each processing model, wherein the multiple processing models at least include: support vector machine, K nearest neighbor model, random forest model, and lifting model, and the processing results represent the probability of illegal transactions involving the credit card.

[0047] Optionally, the multiple processing models are machine learning algorithms used for data processing and analysis, including at least four processing models: support vector machine, K nearest neighbor model, random forest model and boosting model. Each model has been trained and can process credit card information, obtain the probability of illegal transactions on the credit card and use it as the processing result.

[0048] In some embodiments, each processing model can be obtained through training, for example, first collecting the initial credit card data of the second sample credit card, pre-processing these data to obtain the second sample credit card information, and then constructing a training sample set based on the second sample credit card information and its corresponding true label, and inputting the training sample set into each initial processing model to train and obtain the corresponding processing model. Among them, the content form of the second sample credit card information is the same as the content form of the credit card information, so it will not be repeated here.

[0049] Optionally, the second sample credit card is a portion of sample credit cards for which illegal transactions are known to occur, and is used to train the initial processing model, and the other portion of the sample credit cards is the first sample credit card, and is used to test the processing model.

[0050] Optionally, target information may be determined based on processing results corresponding to each processing model and weight coefficients corresponding to each processing model, wherein the target information indicates whether there is any illegal transaction involving the credit card.

[0051] Step S203, determining target information according to the processing results corresponding to the multiple processing models and the weight coefficients corresponding to the multiple processing models, wherein the target information is used to characterize whether there is any illegal transaction in the credit card.

[0052] Optionally, the weight coefficient is the proportion or importance of each processing model in the multiple processing models. The weight coefficient corresponding to each processing model can be obtained by obtaining the prediction accuracy of each processing model based on the test sample set (first sample credit card information), summing all the accuracy rates and taking the result as the first value, and then calculating the ratio between the prediction accuracy of each processing model and the first value.

[0053] Optionally, for each processing model, a weighted sum method can be used to calculate the total probability of illegal transactions on the credit card, and then the total probability is compared with a preset illegal transaction probability threshold. When the total probability is greater than the preset threshold, it is determined that an illegal transaction has occurred on the credit card; otherwise, no illegal transaction has occurred.

[0054] In the embodiment of the present application, a method based on multiple processing models and different weight coefficients is adopted to determine whether there is an illegal transaction on a credit card. By collecting user credit card information, a data basis is provided for subsequent model processing, ensuring the comprehensiveness and accuracy of the data so that the processing model can accurately analyze the usage of the credit card. By determining the probability of illegal transactions of the credit card based on multiple processing models, it is possible to analyze the credit card data from different angles and methods. By assigning a weight coefficient to the processing result of each processing model to determine whether there is an illegal transaction on the credit card, it is possible to summarize the processing results of multiple processing models based on the importance of each processing model to realize risk transaction identification, thereby improving the accuracy of detecting illegal credit card transactions.

[0055] It can be seen that the solution provided in the present application achieves the purpose of determining whether there is an illegal transaction on a credit card based on multiple processing models and different weight coefficients, thereby achieving the technical effect of improving the detection accuracy of illegal transactions on credit cards, and further solving the problem of low detection accuracy caused by detecting illegal transactions on credit cards based on a single method in the related technology.

[0056] In an optional embodiment, before determining the target information based on the processing results corresponding to multiple processing models and the weight coefficients corresponding to the multiple processing models, the data processing system can obtain a test sample set, wherein the test samples in the test sample set include first sample credit card information, and the true label of the test sample is used to characterize whether the first sample credit card corresponding to the first sample credit card information has any illegal transactions; the test sample set is used to test the multiple processing models to obtain the prediction accuracy corresponding to each processing model; and the weight coefficients corresponding to the multiple processing models are determined based on the prediction accuracy corresponding to the multiple processing models.

[0057] Optionally, the data processing system may select a portion of sample credit cards known to have illegal transactions as the first sample credit cards, the credit card information of the first sample credit cards includes the cardholder's personal information, credit card transaction data, etc., and the first sample credit card information is obtained by preprocessing the credit card information of the first sample credit cards, wherein the preprocessing includes data denoising, outlier removal, vector conversion, etc. A test sample set is constructed from the first sample credit card information, each piece of the first sample credit card information is a test sample, and each test sample corresponds to a true label, which indicates whether the first sample credit card corresponding to the first sample credit card information has an illegal transaction, such as 1 for illegal transactions and 0 for legal transactions. The content format of the first sample credit card information is the same as that of the credit card information, so it will not be repeated here.

[0058] Optionally, after the test sample set is input into each processing model, each processing model processes each test sample to obtain a prediction result, which indicates whether the corresponding first sample credit card has an illegal transaction. The prediction result of the test sample is then compared with the true label. Test samples with the same comparison result indicate that the prediction is correct, and the number of test samples with correct predictions is counted. Finally, the ratio between the number of test samples with correct predictions and the number of samples in the test sample set is calculated and used as the prediction accuracy of the processing model. The calculation formula for the prediction accuracy is as follows:

[0059] Prediction accuracy = number of correctly predicted test samples / number of test sample sets

[0060] The number of test samples predicted correctly is the sum of the number of test samples of illegal transactions predicted as illegal transactions and the number of test samples of legal transactions predicted as legal transactions.

[0061] Optionally, based on the prediction accuracy of each processing model, the weight coefficient corresponding to each processing model is determined by the summation and ratio calculation method. The weight coefficient reflects the relative importance of each model in the final decision. A higher prediction accuracy indicates that the decision of the processing model is more reliable and will obtain a higher weight coefficient.

[0062] It should be noted that by constructing a test sample set containing real labels, a reliable data basis is provided for testing the performance of the model. By determining the weight coefficient based on the prediction accuracy, it is achieved that in the data processing system, the more accurate the prediction of the model is, the greater the contribution to the final detection result, which improves the accuracy of the system in detecting illegal credit card transactions, thereby improving the security of credit card transactions.

[0063] In an optional embodiment, in the process of determining the weight coefficients corresponding to multiple processing models based on the prediction accuracy rates corresponding to multiple processing models, the data processing system can sum the prediction accuracy rates of the multiple processing models to obtain a first value; calculate the ratio between the prediction accuracy rate of each processing model and the first value to obtain the weight coefficient corresponding to each processing model.

[0064] Optionally, each processing model (support vector machine, K nearest neighbor model, random forest model, boosting model) is tested based on the test sample set to obtain the prediction accuracy of each processing model. The prediction accuracy reflects the accuracy of the model in identifying whether a credit card transaction is illegal, that is, the sum of the number of illegal transactions correctly predicted by the model and the number of legal transactions correctly predicted by the model, divided by the total number of test samples.

[0065] Optionally, in the process of determining the weight coefficient corresponding to each processing model, the prediction accuracy of each processing model is first summed to obtain a first value, and then the ratio between the prediction accuracy of each processing model and the first value is calculated to obtain the weight coefficient corresponding to each processing model. The calculation formula of the weight coefficient is as follows:

[0066] Weight coefficient = prediction accuracy of processing model / first value

[0067] The first value is the sum of the prediction accuracy of each processing model, the sum of the weight coefficients of all processing models is 1, and the higher the prediction accuracy of the processing model, the greater the weight coefficient.

[0068] In some embodiments, assuming that the test sample set contains 200 data, the number of samples correctly predicted by each processing model in the test sample set is: 180 for support vector machine, 160 for K-nearest neighbor model, 190 for random forest model, and 170 for lifting method model, then the prediction accuracy of each processing model is: 90%, 80%, 95%, 85%, then the first value is 350%, and the weight coefficients corresponding to each processing model are: 0.257 (90% / 350%), 0.229 (80% / 350%), 0.271 (95% / 350%), 0.243 (85% / 350%), and 0.257+0.229+0.271+0.243=1. It can be seen from the prediction accuracy and weight coefficient that the processing model with higher prediction accuracy is assigned a higher weight coefficient.

[0069] It should be noted that the first value is obtained by summing the prediction accuracy of each processing model, and then the ratio between the prediction accuracy of each model and the first value is calculated to obtain the corresponding weight coefficient, thereby allocating different weights based on the performance of the model to participate in the detection of illegal transactions, thereby better integrating the advantages of each processing model and improving the overall ability to detect illegal transactions.

[0070] In an optional embodiment, in the process of determining target information based on processing results corresponding to multiple processing models and weight coefficients corresponding to multiple processing models, the data processing system can, for each processing model, calculate the product of the probability value in the processing result of the processing model and the weight coefficient corresponding to the processing result to obtain a second numerical value corresponding to the processing model; add the second numerical values ​​corresponding to the multiple processing models to obtain a third numerical value; and determine the target information based on the third numerical value.

[0071] Optionally, the processing result is the result output by the processing model after analyzing the input user's credit card transaction data, which is a probability value of illegal transactions for each credit card.

[0072] Optionally, the second value is the product of the probability value in the processing result of the processing model and the corresponding weight coefficient. Each processing model corresponds to a second value. The calculation formula of the second value is as follows:

[0073] Second value i = processing result of processing model i * weight coefficient i

[0074] Here, i represents different processing models, and the second value i makes the processing model with a high weight coefficient (ie, the processing model with a high accuracy) contribute more to determining the target information.

[0075] Optionally, the third value is a weighted comprehensive probability value obtained by summing all the second values ​​and integrating the processing results of all processing models. The calculation formula of the third value is as follows:

[0076] Third value = ∑(second value i)

[0077] Optionally, when determining the target information according to the third value, the third value is compared with a preset probability threshold to determine whether the credit card has any illegal transactions. When the third value is greater than the preset probability threshold, the determined target information indicates that the credit card has any illegal transactions; when the third value is less than or equal to the preset probability threshold, the determined target information indicates that the credit card has no illegal transactions.

[0078] In some embodiments, assuming that the weight coefficients corresponding to each processing model are: support vector machine 0.257, K-nearest neighbor model 0.229, random forest model 0.271, lifting model 0.243, and the probability values ​​in the processing results of each processing model are: 85%, 75%, 90%, 80%, respectively. Then the second numerical value of each processing model is: 0.218, 0.172, 0.244, 0.194, respectively. The third numerical value is 0.828, and then the third numerical value can be compared with the preset probability threshold to obtain the target information.

[0079] In some embodiments, Figure 3 is a detection schematic diagram of a processing model provided according to an embodiment of the present application, such as Figure 3 As shown, the obtained credit card information is input into four processing models, including support vector machine, random forest model, K nearest neighbor model and lifting method model, and each processing model outputs its processing result, indicating the probability of illegal transactions on the credit card. Then for each processing model, their processing results are multiplied by their corresponding weight coefficients to obtain the second value of each processing model, and all second values ​​are summed to obtain the third value. Finally, the target information is determined by comparing the third value with the preset threshold, that is, whether the credit card has illegal transactions. When the third target information is greater than the preset threshold, it indicates that the credit card has illegal transactions; when the third target information is less than or equal to the preset threshold, it indicates that the credit card has not illegal transactions.

[0080] It should be noted that by determining the second numerical value based on the product of the probability value in the processing result of the processing model and the corresponding weight coefficient, it is ensured that the processing model with high prediction accuracy has a higher voice in the decision-making of the data processing system. By adding all the second numerical values ​​to obtain the third numerical value and determine the target information, the processing results of all processing models are fully considered, and the detection capability of the integrated model is enhanced through the optimal weight distribution, avoiding the problem of low detection accuracy of a single model, thereby improving the accuracy of the system in detecting illegal credit card transactions.

[0081] In an optional embodiment, in the process of determining the target information based on the third value, the data processing system can determine that the target information indicates that there are illegal transactions on the credit card when the third value is greater than a preset threshold; and determine that the target information indicates that there are no illegal transactions on the credit card when the third value is less than or equal to the preset threshold.

[0082] Optionally, the preset threshold is a pre-set probability value, which indicates the minimum probability value that the credit card has illegal transactions. When determining the target information, the third value is compared with the preset threshold. If the third value is greater than the preset threshold, the determined target information indicates that the credit card has illegal transactions; if the third value is less than or equal to the preset threshold, the determined target information indicates that the credit card has not illegal transactions.

[0083] In some embodiments, assuming that the third value obtained by all processing models is 0.83 and the preset probability threshold is 0.65, since 0.83>0.65, the data processing system detects that there is illegal transaction behavior of the credit card.

[0084] It should be noted that by setting a threshold and determining the target information based on the third numerical value, accurate judgment of illegal credit card transactions is achieved, the system's ability to detect illegal transactions is improved, the risk of legal transactions being interrupted is reduced, and illegal transactions are interrupted in a timely manner, thereby improving the accuracy of the system's detection of illegal credit card transactions.

[0085] In an optional embodiment, the data processing system can determine multiple processing models in the following manner: obtain a training sample set, wherein the training samples in the training sample set include second sample credit card information, and the true label of the training sample is used to characterize whether the second sample credit card corresponding to the second sample credit card information has any illegal transactions; use the training sample set to train multiple initial processing models separately to obtain multiple processing models, wherein the multiple initial processing models include at least: an initial support vector machine, an initial K nearest neighbor model, an initial random forest model, and an initial boosting model.

[0086] Optionally, a portion of the sample credit cards is selected as the second sample credit cards, and the initial credit card information of the second sample credit cards includes the cardholder's personal information, credit card transaction data, etc. The second sample credit card information is obtained by preprocessing the initial credit card information of the second sample credit cards, wherein the preprocessing includes data denoising, outlier removal, and vector conversion. A training sample set is constructed from the second sample credit card information, and each piece of the second sample credit card information is a training sample, and each training sample corresponds to a true label, which indicates whether the second sample credit card corresponding to the second sample credit card information has any illegal transactions.

[0087] Optionally, multiple initial processing models are trained independently using a training sample set to obtain multiple processing models, including an initial support vector machine, an initial K-nearest neighbor model, an initial random forest model, and an initial boosting model. Through training, the processing model can learn features related to credit card transaction data, thereby detecting whether there are illegal transactions in the credit card. The training process of the four processing models is as follows:

[0088] (1) Support vector machine: A supervised learning algorithm that is trained based on labeled sample data.

[0089] 1. Select kernel function: Select a suitable kernel function, such as linear kernel (Linear Kernel) or Gaussian kernel (RBFKernel). Usually nonlinear data is suitable for Gaussian kernel function.

[0090] 2. Optimize hyperparameters: Use grid search or random search to optimize the hyperparameters C (regularization parameter) and γ (Gaussian kernel parameter). The value range of C and γ is generally: C∈[0.1,10], γ∈[0.01,1].

[0091] 3. Model training: The support vector machine is initialized based on the kernel function and hyperparameters, and the data is fitted on the training set. The parameters are optimized through multiple iterations of training to obtain the final support vector machine, which can find an optimal hyperplane in the data to maximize the distinction between legal and illegal transactions in credit card transactions.

[0092] (2) K nearest neighbor model: By calculating the distance between the input data and the training samples, the data category is determined by majority voting.

[0093] 1. Data standardization: Standardize or normalize the training data set to make the value ranges of all features in the data comparable.

[0094] 2. Optimize hyperparameters: Use cross-validation to optimize the number of neighbors k and distance metric (such as Euclidean distance or Manhattan distance). The value range of K is generally: k∈[3,15].

[0095] 3. Model construction: Initialize the K nearest neighbor model, set k and distance measurement method, and obtain the final K nearest neighbor model, which can determine the type of credit card transaction represented by the data through majority voting based on the k neighbors closest to the data.

[0096] (3) Random forest model: A decision tree-based ensemble learning method that constructs multiple decision trees through random sampling and feature selection, and outputs the final result through a voting mechanism.

[0097] 1. Optimize hyperparameters: choose the number of trees n estimators , maximum depth max_depthmax, minimum number of split samples min_samples_split, etc., n estimators The value range of max_depth is generally: n estimators ∈[100,500], max_depth∈[5,20].

[0098] 2. Model training: Initialize the random forest model, set hyperparameters, and fit the data on the training set. After multiple iterations of training, the final random forest model is obtained. It can determine whether there is an illegal transaction on the credit card by majority voting based on its own multiple decision trees.

[0099] (4) Boosting model: An ensemble learning method that trains multiple weak learners in a serial manner, with each weak learner improving on the error of the previous learner to create a strong learner.

[0100] 1. Select the algorithm: Use AdaBoost algorithm or Gradient Boosting algorithm.

[0101] 2. Optimize hyperparameters: determine the base learner type (such as decision tree) and the maximum number of iterations n iter , and set the learning rate learning_rate, n iter The value range of and learning_rate is generally: n iter ∈[50,200], learning_rate∈[0.01,0.1].

[0102] 3. Model training: Based on the selected boosting algorithm and hyperparameters, the boosting model is initialized and fitted on the training set. The errors of the previous learner are corrected through multiple iterative training to obtain the final boosting model.

[0103] Optionally, after training each initial processing model, a processing model that can be used to detect whether a credit card has illegal transactions is obtained, and then the prediction accuracy of each processing model can be calculated based on the test sample set to determine its corresponding weight coefficient. When detecting illegal transactions, the processing results of each processing model are weighted averaged based on the weight coefficient to obtain the final target information to determine whether the credit card has illegal transactions.

[0104] It should be noted that by constructing a training sample set containing real labels based on real credit card information, a real and reliable data foundation is provided for model training. By training each initial processing model based on the training sample set, the processing model can capture the complex features in real transaction scenarios, thereby improving the accuracy of the model in detecting illegal credit card transactions, thereby reducing social economic losses.

[0105] In an optional embodiment, in the process of obtaining a training sample set, the data processing system may obtain initial sample credit card information of a second sample credit card; preprocess the initial sample credit card information to obtain second sample credit card information, wherein the preprocessing is at least one of the following: data denoising processing, outlier removal processing, and vector conversion processing; and construct a training sample set based on the second sample credit card information and the true label corresponding to the second sample credit card information.

[0106] Optionally, the initial credit card information of the second sample credit card includes the personal information of the cardholder, the transaction data of the credit card, etc. The second sample credit card information is obtained by preprocessing the initial sample credit card information, wherein the preprocessing is at least one of the following: data denoising, outlier removal, and vector conversion, which can improve the quality of the training data. Then, the preprocessed second sample credit card information and the true label corresponding to each piece of information are used to construct a complete training sample set, wherein the true label indicates whether the second sample credit card corresponding to the second sample credit card information has any illegal transactions.

[0107] Optionally, the initial sample credit card information is preprocessed to obtain a second sample credit card information with higher quality, wherein the preprocessing process includes at least one of the following three:

[0108] (1) Data denoising: Remove noise data that is not helpful for model training, such as duplicate transaction records and irrelevant cardholder information, to reduce interference in the model training process.

[0109] First, determine which features have missing values ​​and calculate the proportion of missing values. If the proportion of missing values ​​is low (such as <5%), you can use the mean or median to fill in the numerical features and the mode to fill in the categorical features. If the proportion of missing values ​​is high (such as >30%), you can directly delete the feature or record.

[0110] (2) Outlier elimination: Identify and eliminate outliers that significantly deviate from normal trading patterns. These outliers may be data entry errors or transactions under extreme circumstances, which will have a negative impact on the stability of the model.

[0111] Assuming the data is normally distributed (such as transaction amount), the Z-score method is used to calculate the standard score If |z|>3, mark this data as an outlier, and finally delete all the outlier data.

[0112] (3) Vector conversion processing: Convert credit card information in text or categorical form into numerical vectors so that the initial processing model can perform numerical calculations and analysis. For example, convert categorical features (such as transaction type, region) into numerical values: Use One-Hot Encoding to convert each category into a binary feature.

[0113] It should be noted that preprocessing the data through data denoising and outlier removal improves the data quality of the training sample set and reduces the interference of noise and outliers on model training. Preprocessing the training sample set through vector conversion enhances the applicability and computability of the data, enabling the model to more effectively extract the features of transaction information from the data, thereby improving the accuracy of the model in detecting illegal credit card transactions and improving the detection capability of the data processing system.

[0114] In the embodiment of the present application, a method based on multiple processing models and different weight coefficients is adopted to determine whether there is an illegal transaction on a credit card. By collecting user credit card information, a data basis is provided for subsequent model processing, ensuring the comprehensiveness and accuracy of the data so that the processing model can accurately analyze the usage of the credit card. By determining the probability of illegal transactions of the credit card based on multiple processing models, it is possible to analyze the credit card data from different angles and methods. By assigning a weight coefficient to the processing result of each processing model to determine whether there is an illegal transaction on the credit card, it is possible to summarize the processing results of multiple processing models based on the importance of each processing model to realize risk transaction identification, thereby improving the accuracy of detecting illegal credit card transactions.

[0115] It can be seen that the solution provided in the present application achieves the purpose of determining whether there is an illegal transaction on a credit card based on multiple processing models and different weight coefficients, thereby achieving the technical effect of improving the detection accuracy of illegal transactions on credit cards, and further solving the problem of low detection accuracy caused by detecting illegal transactions on credit cards based on a single method in the related technology.

[0116] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0117] Example 2

[0118] The present application also provides a credit card information processing device. It should be noted that the credit card information processing device of the present application can be used to execute the credit card information processing method provided in the present application. The following is an introduction to the credit card information processing device provided in the present application.

[0119] According to an embodiment of the present application, a device for implementing the above-mentioned credit card information processing method is also provided. Figure 4 As shown, the device comprises:

[0120] The first acquisition module 401 is used to acquire the credit card information of the user's credit card, wherein the credit card information at least includes the transaction data of the credit card;

[0121] The first processing module 402 is used to process the credit card information through multiple processing models to obtain processing results corresponding to each processing model, wherein the multiple processing models at least include: support vector machine, K nearest neighbor model, random forest model, lifting method model, and the processing results represent the probability of illegal transactions in the credit card;

[0122] The first determination module 403 is used to determine target information according to the processing results corresponding to the multiple processing models and the weight coefficients corresponding to the multiple processing models, wherein the target information is used to characterize whether there is any illegal transaction in the credit card.

[0123] It should be noted that the above-mentioned first acquisition module 401, first processing module 402 and first determination module 403 correspond to steps S201 to S203 in the above-mentioned embodiment, and the examples and application scenarios implemented by the three modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0124] In the embodiment of the present application, a method based on multiple processing models and different weight coefficients is adopted to determine whether there is an illegal transaction on a credit card. By collecting user credit card information, a data basis is provided for subsequent model processing, ensuring the comprehensiveness and accuracy of the data so that the processing model can accurately analyze the usage of the credit card. By determining the probability of illegal transactions of the credit card based on multiple processing models, it is possible to analyze the credit card data from different angles and methods. By assigning a weight coefficient to the processing result of each processing model to determine whether there is an illegal transaction on the credit card, it is possible to summarize the processing results of multiple processing models based on the importance of each processing model to realize risk transaction identification, thereby improving the accuracy of detecting illegal credit card transactions.

[0125] It can be seen that the solution provided in the present application achieves the purpose of determining whether there is an illegal transaction on a credit card based on multiple processing models and different weight coefficients, thereby achieving the technical effect of improving the detection accuracy of illegal transactions on credit cards, and further solving the problem of low detection accuracy caused by detecting illegal transactions on credit cards based on a single method in the related technology.

[0126] Optionally, in the credit card information processing device provided in the embodiment of the present application, the data processing device also includes: a second acquisition module, used to acquire a test sample set, wherein the test samples in the test sample set include first sample credit card information, and the true label of the test sample is used to characterize whether there is an illegal transaction in the first sample credit card corresponding to the first sample credit card information; a second processing module, used to test multiple processing models using the test sample set to obtain the prediction accuracy rate corresponding to each processing model; and a second determination module, used to determine the weight coefficients corresponding to the multiple processing models based on the prediction accuracy rates corresponding to the multiple processing models.

[0127] Optionally, in the credit card information processing device provided in the embodiment of the present application, the second determination module also includes: a first calculation submodule, used to sum the prediction accuracy rates of multiple processing models to obtain a first numerical value; a second calculation submodule, used to calculate the ratio between the prediction accuracy rate of each processing model and the first numerical value to obtain the weight coefficient corresponding to each processing model.

[0128] Optionally, in the credit card information processing device provided in the embodiment of the present application, the first determination module also includes: a third calculation sub-module, used to calculate, for each processing model, the product of the probability value in the processing result of the processing model and the weight coefficient corresponding to the processing result, to obtain a second numerical value corresponding to the processing model; a fourth calculation sub-module, used to add the second numerical values ​​corresponding to multiple processing models to obtain a third numerical value; and a determination sub-module, used to determine the target information based on the third numerical value.

[0129] Optionally, in the credit card information processing device provided in the embodiment of the present application, the determination submodule also includes: a first determination unit, used to determine that the target information represents the existence of illegal transactions of the credit card when the third value is greater than a preset threshold; a second determination unit, used to determine that the target information represents the existence of illegal transactions of the credit card when the third value is less than or equal to the preset threshold.

[0130] Optionally, in the credit card information processing device provided in the embodiment of the present application, the data processing device also includes: a third acquisition module, used to obtain a training sample set, wherein the training samples in the training sample set include second sample credit card information, and the true label of the training sample is used to characterize whether the second sample credit card corresponding to the second sample credit card information has any illegal transactions; a third processing module, used to use the training sample set to train multiple initial processing models separately to obtain multiple processing models, wherein the multiple initial processing models include at least: an initial support vector machine, an initial K nearest neighbor model, an initial random forest model, and an initial boosting model.

[0131] Optionally, in the credit card information processing device provided in the embodiment of the present application, the third acquisition module also includes: an acquisition submodule, used to obtain the initial sample credit card information of the second sample credit card; a first processing submodule, used to preprocess the initial sample credit card information to obtain the second sample credit card information, wherein the preprocessing is at least one of the following: data denoising processing, outlier removal processing, and vector conversion processing; a second processing submodule, used to construct a training sample set based on the second sample credit card information and the real label corresponding to the second sample credit card information.

[0132] It should be noted that the first acquisition module 401, the first processing module 402 and the first determination module 403 correspond to steps S201 to S203 in Example 1, and the three modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units may be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules may also be part of the device and may be run in the computer terminal 10 provided in Example 1.

[0133] Example 3

[0134] An embodiment of the present application may provide an electronic device, Figure 5 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0135] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0136] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the credit card information of the user's credit card, wherein the credit card information at least includes the transaction data of the credit card; process the credit card information through multiple processing models to obtain the processing results corresponding to each processing model, wherein the multiple processing models at least include: support vector machine, K nearest neighbor model, random forest model, lifting method model, and the processing results represent the probability of illegal transactions involving the credit card; determine the target information based on the processing results corresponding to the multiple processing models and the weight coefficients corresponding to the multiple processing models, wherein the target information is used to represent whether there are illegal transactions involving the credit card.

[0137] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain a test sample set, wherein the test samples in the test sample set include first sample credit card information, and the true label of the test sample is used to characterize whether there is an illegal transaction in the first sample credit card corresponding to the first sample credit card information; use the test sample set to test multiple processing models to obtain the prediction accuracy corresponding to each processing model; determine the weight coefficients corresponding to the multiple processing models based on the prediction accuracy corresponding to the multiple processing models.

[0138] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: summing the prediction accuracy of multiple processing models to obtain a first value; calculating the ratio between the prediction accuracy of each processing model and the first value to obtain the weight coefficient corresponding to each processing model.

[0139] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: for each processing model, calculate the product between the probability value in the processing result of the processing model and the weight coefficient corresponding to the processing result to obtain a second numerical value corresponding to the processing model; add the second numerical values ​​corresponding to multiple processing models to obtain a third numerical value; and determine the target information based on the third numerical value.

[0140] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: when the third value is greater than a preset threshold, determine that the target information indicates that there is an illegal transaction on the credit card; when the third value is less than or equal to the preset threshold, determine that the target information indicates that there is no illegal transaction on the credit card.

[0141] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtaining a training sample set, wherein the training samples in the training sample set include second sample credit card information, and the true label of the training sample is used to characterize whether the second sample credit card corresponding to the second sample credit card information has illegal transactions; using the training sample set to train multiple initial processing models separately to obtain multiple processing models, wherein the multiple initial processing models include at least: an initial support vector machine, an initial K nearest neighbor model, an initial random forest model, and an initial boosting model.

[0142] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: obtain the initial sample credit card information of the second sample credit card; preprocess the initial sample credit card information to obtain the second sample credit card information, wherein the preprocessing is at least one of the following: data denoising processing, outlier removal processing, vector conversion processing; construct a training sample set based on the second sample credit card information and the real label corresponding to the second sample credit card information.

[0143] In the embodiment of the present application, a method based on multiple processing models and different weight coefficients is adopted to determine whether there is an illegal transaction on a credit card. By collecting user credit card information, a data basis is provided for subsequent model processing, ensuring the comprehensiveness and accuracy of the data so that the processing model can accurately analyze the usage of the credit card. By determining the probability of illegal transactions of the credit card based on multiple processing models, it is possible to analyze the credit card data from different angles and methods. By assigning a weight coefficient to the processing result of each processing model to determine whether there is an illegal transaction on the credit card, it is possible to summarize the processing results of multiple processing models based on the importance of each processing model to realize risk transaction identification, thereby improving the accuracy of detecting illegal credit card transactions.

[0144] It can be seen that the solution provided in the present application achieves the purpose of determining whether there is an illegal transaction on a credit card based on multiple processing models and different weight coefficients, thereby achieving the technical effect of improving the detection accuracy of illegal transactions on credit cards, and further solving the problem of low detection accuracy caused by detecting illegal transactions on credit cards based on a single method in the related technology.

[0145] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 5 The structure of the electronic device is not limited. Figure 5More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 5 Different configurations are shown.

[0146] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0147] Example 4

[0148] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the credit card information processing method provided in the first embodiment.

[0149] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0150] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program steps of the credit card information processing method.

[0151] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0152] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0156] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0157] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for processing credit card information, characterized in that: include: Acquire credit card information of a user's credit card, wherein the credit card information at least includes transaction data of the credit card; Processing the credit card information through multiple processing models to obtain processing results corresponding to each processing model, wherein the multiple processing models at least include: support vector machine, K nearest neighbor model, random forest model, and lifting method model, and the processing results represent the probability that the credit card has illegal transactions; Target information is determined according to the processing results corresponding to the multiple processing models and the weight coefficients corresponding to the multiple processing models, wherein the target information is used to characterize whether there is any illegal transaction with the credit card.

2. The method according to claim 1, characterized in that Before determining the target information according to the processing results corresponding to the multiple processing models and the weight coefficients corresponding to the multiple processing models, the method includes: Acquire a test sample set, wherein the test samples in the test sample set include first sample credit card information, and the true label of the test sample is used to indicate whether the first sample credit card corresponding to the first sample credit card information has any illegal transaction; Using the test sample set to test the multiple processing models to obtain the prediction accuracy corresponding to each processing model; The weight coefficients corresponding to the multiple processing models are determined based on the prediction accuracy rates corresponding to the multiple processing models.

3. The method according to claim 2, characterized in that Determining weight coefficients corresponding to the multiple processing models based on the prediction accuracy rates corresponding to the multiple processing models includes: Summing the prediction accuracy rates of the multiple processing models to obtain a first value; The ratio between the prediction accuracy of each processing model and the first value is calculated to obtain the weight coefficient corresponding to each processing model.

4. The method according to claim 1, characterized in that: Determining target information according to the processing results corresponding to the multiple processing models and the weight coefficients corresponding to the multiple processing models includes: For each processing model, calculate the product of the probability value in the processing result of the processing model and the weight coefficient corresponding to the processing result to obtain a second value corresponding to the processing model; Adding the second values ​​corresponding to the multiple processing models to obtain a third value; The target information is determined according to the third value.

5. The method according to claim 4, characterized in that Determining the target information according to the third value includes: When the third value is greater than a preset threshold, determining that the target information indicates that illegal transactions have occurred on the credit card; When the third value is less than or equal to the preset threshold, it is determined that the target information indicates that there is no illegal transaction of the credit card.

6. The method according to claim 1, characterized in that The multiple processing models are trained in the following manner: Obtaining a training sample set, wherein the training samples in the training sample set include second sample credit card information, and the true label of the training sample is used to indicate whether the second sample credit card corresponding to the second sample credit card information has any illegal transaction; The training sample set is used to train multiple initial processing models respectively to obtain the multiple processing models, wherein the multiple initial processing models at least include: an initial support vector machine, an initial K nearest neighbor model, an initial random forest model, and an initial boosting model.

7. The method according to claim 6, characterized in that Get the training sample set, including: Obtaining initial sample credit card information of a second sample credit card; Preprocessing the initial sample credit card information to obtain the second sample credit card information, wherein the preprocessing is at least one of the following: data denoising processing, outlier removal processing, and vector conversion processing; A training sample set is constructed according to the second sample credit card information and the true label corresponding to the second sample credit card information.

8. A credit card information processing device, characterized in that: include: A first acquisition module, used to acquire credit card information of a user's credit card, wherein the credit card information at least includes transaction data of the credit card; A first processing module, used to process the credit card information through multiple processing models to obtain processing results corresponding to each processing model, wherein the multiple processing models at least include: support vector machine, K nearest neighbor model, random forest model, lifting method model, and the processing results represent the probability of illegal transactions involving the credit card; The first determination module is used to determine target information according to the processing results corresponding to the multiple processing models and the weight coefficients corresponding to the multiple processing models, wherein the target information is used to characterize whether there is any illegal transaction with the credit card.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the credit card information processing method described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the credit card information processing method described in any one of claims 1 to 7.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the credit card information processing method described in any one of claims 1 to 7 are implemented.

Images