Internet of Things card number risk level identification method and device, server and medium

Abstract

The embodiment of the invention provides an Internet of Things card number risk level identification method and device, a server and a medium. The method comprises the following steps: collecting Internet of Things card data in any time period; wherein the Internet of Things card data comprises a plurality of Internet of Things card numbers, and extracting Internet of Things card features; inputting the features of the Internet of Things card into the trained risk level identification model, and enabling the trained risk level identification model to execute the following steps: carrying out matrix rank reduction processing on the features of the Internet of Things card, and obtaining low-dimensional features of the Internet of Things card; calculating a risk score of each Internet of Things card number according to the low-dimensional Internet of Things card features and the customer identifier and the account identifier corresponding to each Internet of Things card number; according to the risk score of each Internet of Things card number, identifying the risk level of each Internet of Things card number; and outputting the plurality of Internet of Things card numbers and the risk level of each Internet of Things card number according to the sequence of the risk levels from high to low. According to the method, the efficiency of identifying the risk level of the card number of the Internet of Things is improved.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Things, and in particular to a method, device, server and medium for identifying the risk level of an Internet of Things card number. Background Art

[0002] In the field of Internet of Things, security monitoring and control of IoT cards are crucial. IoT card numbers with high risk levels need to be shut down to curb the occurrence of risks in a timely manner.

[0003] Currently, existing technologies analyze the full features of IoT card data to identify the risk level of IoT card numbers.

[0004] However, this method of the prior art increases the recognition time, resulting in low efficiency in identifying the risk level of the IoT card number. Summary of the invention

[0005] The embodiments of the present application provide a method, device, server and medium for identifying the risk level of an Internet of Things card number, so as to improve the efficiency of identifying the risk level of an Internet of Things card number.

[0006] In a first aspect, an embodiment of the present application provides a method for identifying the risk level of an Internet of Things card number, comprising: collecting Internet of Things card data within any time period; wherein the Internet of Things card data includes multiple Internet of Things card numbers, wherein each Internet of Things card number includes a customer identifier and an account identifier; extracting Internet of Things card features from the Internet of Things card data; inputting the Internet of Things card features into a trained risk level identification model, so that the trained risk level identification model performs the following steps: performing matrix rank reduction processing on the Internet of Things card features to obtain low-dimensional Internet of Things card features; based on the low-dimensional Internet of Things card features, according to the customer identifier and account identifier corresponding to each Internet of Things card number, calculating the risk score of each Internet of Things card number; based on the risk score of each Internet of Things card number, identifying the risk level of each Internet of Things card number; based on the risk level of each Internet of Things card number, outputting multiple Internet of Things card numbers and the risk level of each Internet of Things card number in order from high to low risk levels.

[0007] In a possible implementation, matrix rank reduction processing is performed on the IoT card features to obtain low-dimensional IoT card features, including: mapping the IoT card features from a four-dimensional space to a two-dimensional space to obtain low-dimensional IoT card features.

[0008] In a possible implementation, before collecting IoT card data within any time period, it also includes: collecting historical IoT card data, wherein the historical IoT card data includes multiple IoT card numbers; marking the risk level of IoT card numbers with risks in the historical IoT card data, and using the historical IoT card data corresponding to the IoT card numbers with marked risk levels as positive samples, and using the historical IoT card data corresponding to the IoT card numbers without marked risk levels as negative samples; extracting positive sample features from the positive samples, and extracting negative sample features from the negative samples; using a recursive feature elimination method to screen the positive sample features and the negative sample features to obtain a sample training feature set; and inputting the sample training feature set into a risk level recognition model for iterative training to obtain a trained risk level recognition model.

[0009] In one possible implementation, the sample training feature set is input into the risk level identification model for iterative training to obtain a trained risk level identification model, including: mapping the sample training feature set from a four-dimensional space to a two-dimensional space to obtain a low-dimensional sample training feature set; obtaining a position coefficient based on the low-dimensional sample training feature set; and iteratively training a regression tree based on a gradient boosting decision tree algorithm based on ranking learning according to the low-dimensional sample training feature set and the position coefficient until the number of regression trees reaches a preset value.

[0010] In a possible implementation, the position coefficient is obtained according to the low-dimensional sample training feature set, and the formula is:

[0011]

[0012] In the formula, represents the position coefficient, Indicates location The low-dimensional sample training features, Indicates location Low-dimensional sample training features.

[0013] In a second aspect, an embodiment of the present application provides a device for identifying the risk level of an IoT card number, including:

[0014] A collection module, used to collect IoT card data within any time period; wherein the IoT card data includes multiple IoT card numbers, wherein each IoT card number includes a customer identifier and an account identifier;

[0015] An extraction module, used to extract IoT card features from IoT card data;

[0016] An input module is used to input the IoT card features into the trained risk level identification model, so that the trained risk level identification model performs the following steps;

[0017] The input module includes:

[0018] An acquisition unit, used for performing matrix rank reduction processing on the IoT card features to obtain low-dimensional IoT card features;

[0019] A calculation unit, used to calculate the risk score of each IoT card number according to the low-dimensional IoT card features and the customer identifier and account identifier corresponding to each IoT card number;

[0020] an identification unit, used to identify the risk level of each IoT card number according to the risk score of each IoT card number;

[0021] The output unit is used to output multiple Internet of Things card numbers and the risk level of each Internet of Things card number in order from high to low risk levels according to the risk level of each Internet of Things card number.

[0022] In a possible implementation, the acquisition unit is used to map the IoT card features from a four-dimensional space to a two-dimensional space to obtain low-dimensional IoT card features.

[0023] In a third aspect, an embodiment of the present application provides a server, including: a memory, a processor;

[0024] The memory stores computer-executable instructions;

[0025] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0026] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0027] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0028] The method, device, server and medium for identifying the risk level of the Internet of Things card number provided in the embodiment of the present application perform matrix rank reduction processing on the characteristics of the Internet of Things card through the trained risk level identification model to obtain low-dimensional characteristics of the Internet of Things card; the Internet of Things card numbers under the customer and the account often have a certain correlation, and the risk score of each Internet of Things card number is calculated according to the customer ID and account ID corresponding to each Internet of Things card number. Through the low-dimensional characteristics of the Internet of Things card, the amount of features involved in the calculation is reduced, and the risk level of the Internet of Things card number is identified in the customer and account dimensions, which reduces the time for calculating the risk score, thereby improving the efficiency of identifying the risk level of the Internet of Things card number. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] 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.

[0030] Figure 1 A schematic diagram of a scenario of a method for identifying the risk level of an IoT card number provided in an embodiment of the present application;

[0031] Figure 2 A flowchart of a method for identifying the risk level of an Internet of Things card number provided in an embodiment of the present application;

[0032] Figure 3 A schematic diagram of the structure of a device for identifying the risk level of an Internet of Things card number provided in an embodiment of the present application;

[0033] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present application.

[0034] 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

[0035] 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.

[0036] Figure 1 A schematic diagram of a scenario of a method for identifying the risk level of an IoT card number provided in an embodiment of the present application, such as Figure 1As shown, the specific application scenario of the present application includes: a receiving device 101, a processor 102 and a display device 103.

[0037] It is understandable that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the method for identifying the risk level of the IoT card number. In other feasible implementations of the present application, the above architecture may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown may be implemented in hardware, software, or a combination of software and hardware.

[0038] In the specific implementation process, the receiving device 101 can be an input / output interface or a communication interface, which is used to collect IoT card data within any time period.

[0039] The processor 102 can process the IoT card data within any time period to obtain the risk level of each IoT card number.

[0040] The display device 103 can be used to display the risk level of each Internet of Things card number.

[0041] It should be understood that the above-mentioned processor can be implemented by the processor reading instructions in the memory and executing the instructions, or it can be implemented by a chip circuit.

[0042] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0043] In the field of IoT, security monitoring and control of IoT cards is extremely important. IoT card numbers with high risk levels need to be shut down to curb the occurrence of risks in a timely manner. Currently, existing technologies analyze the full features of IoT card data to identify the risk level of IoT card numbers. However, this method of existing technologies increases the identification time, resulting in low efficiency in identifying the risk level of IoT card numbers.

[0044] In order to solve the above technical problems, the embodiments of the present application propose the following technical concept: considering that analyzing the full features of the Internet of Things card data will increase the recognition time, the inventors thought of performing matrix rank reduction processing on the Internet of Things card features through a trained risk level recognition model to obtain a low-dimensional Internet of Things card, thereby reducing the number of features involved in the calculation; in addition, since there is often a certain correlation between the Internet of Things card numbers under the customer and the account, according to the customer ID and account ID corresponding to each Internet of Things card number, the risk level of the Internet of Things card number is identified in the customer and account dimensions to reduce the recognition time, thereby improving the efficiency of identifying the risk level of the Internet of Things card number.

[0045] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. 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.

[0046] Figure 2 A flow chart of a method for identifying the risk level of an IoT card number provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method includes:

[0047] S201: Collect IoT card data within any time period; wherein the IoT card data includes multiple IoT card numbers, wherein each IoT card number includes a customer identifier and an account identifier.

[0048] Optionally, the IoT card data for any time period may be all IoT card data for that day, including but not limited to real-time call bill data, traffic data, SMS data, and billing information.

[0049] S202: Extract IoT card features from IoT card data.

[0050] Optionally, features relevant to risk assessment are extracted from IoT card data, including but not limited to call frequency, traffic usage pattern, SMS volume, and device location changes.

[0051] Optionally, the extracted IoT card features are normalized to have the same scale and range. Normalization methods include mean normalization and Z-score normalization.

[0052] S203: Input the IoT card features into the trained risk level identification model, so that the trained risk level identification model performs the following steps.

[0053] Specifically, step S203 includes S2031-S2034:

[0054] S2031: Perform matrix rank reduction processing on the IoT card features to obtain low-dimensional IoT card features.

[0055] Specifically, the IoT card features are mapped from the four-dimensional space to the two-dimensional space to obtain low-dimensional IoT card features.

[0056] In this embodiment, in the first linear layer of the trained risk level identification model, the high-dimensional four-dimensional tensor s=[d1, d2, d3, d4] is converted into a two-dimensional tensor t=[d1, d2] through matrix rank reduction, which means that the high-dimensional feature space is compressed, reducing the number and complexity of features.

[0057] S2032: Calculate the risk score of each IoT card number according to the low-dimensional IoT card features and the customer ID and account ID corresponding to each IoT card number.

[0058] Optionally, there are 5 risk scores: 4, 3, 2, 1 and 0.

[0059] In this embodiment, the risk score of the IoT card number is calculated under the customer and account dimensions based on the low-dimensional IoT card features.

[0060] S2033: Identify the risk level of each IoT card number based on the risk score of each IoT card number.

[0061] In this embodiment, one risk score corresponds to one risk level, and scores of 4, 3, 2, 1, and 0 correspond to mobile phone use, segmented track, phone change, phone-card separation, and high-frequency calls, respectively.

[0062] Among them, use on mobile phones: IoT cards are designed for IoT devices and are not allowed to be used on mobile phones; segmented tracks: signal interruption or instability, resulting in IoT devices not being able to work properly; changing devices: IoT cards are usually bound to specific devices, and changing devices may cause device authentication problems, affecting the normal connection and use of devices; machine-card separation: IoT devices usually need to be inserted with IoT cards to work properly. If the machine-card is separated, the device may not work properly; high-frequency calls: IoT cards are generally not used for voice calls. If high-frequency calls occur, it may be that the IoT card is abused or stolen.

[0063] S2034: Output multiple IoT card numbers and the risk level of each IoT card number in descending order of risk level according to the risk level of each IoT card number.

[0064] In this embodiment, the higher the score, the higher the risk level. According to the risk level, the IoT card number with a high risk level is output first, as well as the risk level of the IoT card number.

[0065] Optionally, the risk level of the IoT card number is output to the security monitoring platform for early warning and for shutdown and processing by relevant personnel.

[0066] In summary, the trained risk level identification model is used to perform matrix rank reduction on IoT card features to obtain low-dimensional IoT card features; IoT card numbers under customers and accounts often have a certain correlation, and the risk score of each IoT card number is calculated according to the customer ID and account ID corresponding to each IoT card number. Through low-dimensional IoT card features, the amount of features involved in the calculation is reduced, and the risk level of the IoT card number is identified in the customer and account dimensions, which reduces the time for calculating the risk score, thereby improving the efficiency of identifying the risk level of the IoT card number.

[0067] Based on the above embodiment, in this embodiment, the training process of the risk level identification model is introduced, which is detailed as follows:

[0068] S301: Collect historical IoT card data, where the historical IoT card data includes multiple IoT card numbers.

[0069] In this embodiment, under the spark framework, historical IoT card data is collected from multiple IoT terminals, which are real-time streaming data and offline data, including but not limited to real-time streaming call list data, real-time streaming location data and offline attribute data.

[0070] S302: Label the risk levels of IoT card numbers with risks in historical IoT card data, use the historical IoT card data corresponding to the IoT card numbers with labeled risk levels as positive samples, and use the historical IoT card data corresponding to the IoT card numbers without labeled risk levels as negative samples.

[0071] In this embodiment, the IoT card numbers with risks in the historical IoT card data are labeled with 5 levels of labels (label=4, 3, 2, 1, 0), corresponding to mobile phone use, segment track, phone change, machine card separation and high-frequency calls respectively. The labeled IoT card data is saved to HDFS. The sample format is as follows:

[0072]

[0073] In this embodiment, in order to balance the sample data set, the oversampling method is used to perform SMOTE (Synthetic Minority Over-sampling Technique) oversampling on the minority class samples. SMOTE oversampling synthesizes new minority class samples to increase the number of minority class samples, thereby improving the model's recognition ability for the minority class. The majority class samples are randomly downsampled to reduce the number of majority class samples to avoid the model being overly biased towards the majority class. The ratio of positive samples to negative samples is a preset ratio, which can optionally be 1:5.

[0074] S303: extracting positive sample features from the positive samples, and extracting negative sample features from the negative samples.

[0075] S304: Using a recursive feature elimination method, positive sample features and negative sample features are screened to obtain a sample training feature set.

[0076] Among them, the recursive feature elimination (RFE) method is used to eliminate redundancy between features and select the optimal features. Starting from all features, the least important features are gradually deleted until the predetermined number of features is reached or other stopping conditions are met.

[0077] Specifically, a regression model is selected, such as linear regression, ridge regression, Lasso regression, etc. Exemplarily, a model that supports L1 regularization, such as Lasso regression, is used. The process of feature screening using the RFE method is as follows: the Lasso regression model is trained using positive sample features and negative sample features. The importance of each feature is evaluated according to the model coefficient, and the least important features are eliminated. For example, one or more features are eliminated each time until a predetermined number of features is reached or other stopping conditions are met.

[0078] Optionally, add an L1 regularization term to the regression model, whose loss function is:

[0079]

[0080] Among them, the loss function consists of two parts, the loss term part:

[0081]

[0082] And the L1 regularization part:

[0083]

[0084] In the formula, n is the number of samples, is the target value of the feature of the ith sample, is the jth eigenvalue of the ith sample, is the regression coefficient. is the regularization parameter, and p is the number of positive and negative features.

[0085] In this embodiment, the regularization parameter is adjusted by cross-validation or other methods to balance the complexity and fitting ability of the regression model, thereby screening the positive sample features and the negative sample features.

[0086] S305: Inputting the sample training feature set into the risk level recognition model for iterative training to obtain a trained risk level recognition model.

[0087] Specifically, the sample training feature set is mapped from the four-dimensional space to the two-dimensional space to obtain a low-dimensional sample training feature set; the position coefficient is obtained based on the low-dimensional sample training feature set; the gradient boosting decision tree algorithm based on ranking learning is used to iteratively train the regression tree based on the low-dimensional sample training feature set and the position coefficient until the number of regression trees reaches a preset value.

[0088] In this embodiment, the formula for obtaining the position coefficient is as follows:

[0089]

[0090] In the formula, represents the position coefficient, Indicates location The low-dimensional sample training features, Indicates location Low-dimensional sample training features.

[0091] In this embodiment, the training process is:

[0092]

[0093]

[0094]

[0095]

[0096] Specifically, calculate NDCG(original), which is the original normalized discounted cumulative gain. DCG is the discounted cumulative gain, and IDCG is the ideal discounted cumulative gain. represents the absolute value of the difference between the original NDCG and the NDCG after swapping the positions of i and j; K represents the position coefficient, that is, the average value of different positions of i and j is taken as the position coefficient, which is used to assist in training a regression tree. Using the average value of two position changes can reduce the number of parameters during the regression retraining process and improve the training efficiency of the regression tree; λ is used to train a regression tree for the labels. That is, for all labels j, if label(i)>label(j), then accumulate , if label(i)<label(j), then subtract .

[0097] At each leaf node of the regression tree, the score is output through the second-order derivative of the predicted lambda. Based on this, all scores are calculated according to the training features of the low-dimensional samples, that is, α×λ, where α is the learning rate. Then, this score is used to screen the results of the IoT card numbers under the customer identification and account identification, and the benchmark NDCG of the IoT card numbers under each new customer identification and account identification is calculated. Based on this, the above training process is repeated to form a forest until the number of regression trees reaches the setting of the training parameters.

[0098] In summary, on the one hand, the sample training feature set is mapped from a four-dimensional space to a two-dimensional space, reducing the amount of features involved in the calculation; on the other hand, by taking the average value of different positions of i and j as the position coefficient to assist in training a regression tree, using the average value of two position changes can significantly reduce the number of parameters during the regression retraining process and improve the training efficiency of the regression tree; on the other hand, the second-order derivative can provide more information about the rate of change of the function. Compared with the first-order derivative, it can more accurately reflect the change trend of the model under the current parameters and improve the convergence speed of the model.

[0099] Figure 3 is a schematic structural diagram of the identification device for the risk level of IoT card numbers provided by the embodiment of the present application. As Figure 3 shown, the identification device for the risk level of IoT card numbers provided in this embodiment includes: a collection module 301, an extraction module 302, and an input module 303, where the input module 303 includes an acquisition unit 3031, a calculation unit 3032, an identification unit 3033, and an output unit 3034.

[0100] The collection module 301 is used to collect IoT card data within any time period; the IoT card data includes multiple IoT card numbers, and each IoT card number includes a customer identification and an account identification;

[0101] The extraction module 302 is used to extract IoT card features from the IoT card data;

[0102] An input module 303 is used to input the IoT card features into the trained risk level identification model, so that the trained risk level identification model performs the following steps;

[0103] Wherein, the input module 303 includes:

[0104] An acquisition unit 3031 is used to perform matrix rank reduction processing on the IoT card features to obtain low-dimensional IoT card features;

[0105] A calculation unit 3032 is used to calculate the risk score of each IoT card number according to the low-dimensional IoT card features and the customer identifier and account identifier corresponding to each IoT card number;

[0106] An identification unit 3033, used to identify the risk level of each IoT card number according to the risk score of each IoT card number;

[0107] The output unit 3034 is used to output multiple Internet of Things card numbers and the risk level of each Internet of Things card number in order from high to low risk level according to the risk level of each Internet of Things card number.

[0108] In a possible implementation, the acquisition unit 3031 is specifically used to: map the Internet of Things card features from a four-dimensional space to a two-dimensional space to obtain low-dimensional Internet of Things card features.

[0109] In a possible implementation, the device for identifying the risk level of an Internet of Things card number also includes: a training module, used to collect historical Internet of Things card data, wherein the historical Internet of Things card data includes multiple Internet of Things card numbers; marking the risk level of the Internet of Things card numbers with risks in the historical Internet of Things card data, and using the historical Internet of Things card data corresponding to the Internet of Things card numbers with marked risk levels as positive samples, and using the historical Internet of Things card data corresponding to the Internet of Things card numbers without marked risk levels as negative samples; extracting positive sample features from the positive samples, and extracting negative sample features from the negative samples; using a recursive feature elimination method to screen the positive sample features and the negative sample features to obtain a sample training feature set; inputting the sample training feature set into a risk level recognition model for iterative training to obtain a trained risk level recognition model.

[0110] In one possible implementation, the training module is also used to map the sample training feature set from the four-dimensional space to the two-dimensional space to obtain a low-dimensional sample training feature set; obtain the position coefficient based on the low-dimensional sample training feature set; and iteratively train the regression tree based on the low-dimensional sample training feature set and the position coefficient using a gradient boosting decision tree algorithm based on ranking learning until the number of regression trees reaches a preset value.

[0111] In a possible implementation, the position coefficient is obtained according to the low-dimensional sample training feature set, and the formula is:

[0112]

[0113] In the formula, represents the position coefficient, Indicates location The low-dimensional sample training features, Indicates location Low-dimensional sample training features.

[0114] The device for identifying the risk level of an Internet of Things card number provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar, and this embodiment will not be described in detail here.

[0115] Figure 4 This is a schematic diagram of the structure of the server provided in the embodiment of the present application. Figure 4 As shown, the server provided in this embodiment includes: at least one processor 401 and a memory 402. Optionally, the server also includes a communication component 403. The processor 401, the memory 402 and the communication component 403 are connected via a bus 404.

[0116] In a specific implementation process, at least one processor 401 executes the computer-executable instructions stored in the memory 402, so that at least one processor 401 executes the above method.

[0117] The specific implementation process of the processor 401 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0118] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0119] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0120] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0121] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0122] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0123] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0124] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0125] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as 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 an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0126] 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.

[0127] In addition, each functional unit in each embodiment of the present invention 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.

[0128] If the function 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 invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0129] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0130] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for identifying the risk level of an Internet of Things card number, characterized in that: Applicable to servers, including: Collecting IoT card data within any time period; wherein the IoT card data includes multiple IoT card numbers, wherein each IoT card number includes a customer identifier and an account identifier; Extracting IoT card features from the IoT card data; The IoT card features are input into the trained risk level identification model, so that the trained risk level identification model performs the following steps: Perform matrix rank reduction processing on IoT card features to obtain low-dimensional IoT card features; According to the low-dimensional IoT card features, and according to the customer identifier and the account identifier corresponding to each IoT card number, calculate the risk score of each IoT card number; Identify the risk level of each IoT card number according to the risk score of each IoT card number; According to the risk level of each Internet of Things card number, the multiple Internet of Things card numbers and the risk level of each Internet of Things card number are output in order from high to low risk levels.

2. The method according to claim 1, characterized in that The matrix rank reduction processing is performed on the IoT card features to obtain low-dimensional IoT card features, including: The IoT card features are mapped from the four-dimensional space to the two-dimensional space to obtain low-dimensional IoT card features.

3. The method according to claim 1 or 2, characterized in that: Before collecting the IoT card data within any time period, the method further includes: Collecting historical IoT card data, wherein the historical IoT card data includes multiple IoT card numbers; The risk level of the IoT card numbers with risks in the historical IoT card data is marked, and the historical IoT card data corresponding to the IoT card numbers with marked risk levels are used as positive samples, and the historical IoT card data corresponding to the IoT card numbers without marked risk levels are used as negative samples; Extracting positive sample features from the positive samples, and extracting negative sample features from the negative samples; Using a recursive feature elimination method, the positive sample features and the negative sample features are screened to obtain a sample training feature set; The sample training feature set is input into the risk level identification model for iterative training to obtain a trained risk level identification model.

4. The method according to claim 3, characterized in that: The step of inputting the sample training feature set into the risk level identification model for iterative training to obtain a trained risk level identification model includes: Mapping the sample training feature set from the four-dimensional space to the two-dimensional space to obtain a low-dimensional sample training feature set; Train the feature set based on low-dimensional samples to obtain position coefficients; The gradient boosting decision tree algorithm based on sorting learning trains the regression tree iteratively according to the low-dimensional sample training feature set and combines the position coefficients until the number of regression trees reaches a preset value.

5. The method according to claim 4, characterized in that The formula for obtaining the position coefficient based on the low-dimensional sample training feature set is: In the formula, represents the position coefficient, Indicates location The low-dimensional sample training features, Indicates location Low-dimensional sample training features.

6. A device for identifying the risk level of an Internet of Things card number, characterized in that: Applicable to servers, including: A collection module, used to collect IoT card data within any time period; wherein the IoT card data includes multiple IoT card numbers, wherein each IoT card number includes a customer identifier and an account identifier; An extraction module, used to extract IoT card features from the IoT card data; An input module, used to input the IoT card features into a trained risk level identification model, so that the trained risk level identification model performs the following steps; Wherein, the input module includes: An acquisition unit, used for performing matrix rank reduction processing on the IoT card features to obtain low-dimensional IoT card features; A calculation unit, configured to calculate a risk score of each Internet of Things card number according to the low-dimensional Internet of Things card feature and the customer identifier and the account identifier corresponding to each Internet of Things card number; an identification unit, configured to identify a risk level of each Internet of Things card number according to a risk score of each Internet of Things card number; The output unit is used to output the multiple Internet of Things card numbers and the risk level of each Internet of Things card number according to the risk level of each Internet of Things card number in order from high to low risk levels.

7. The device according to claim 6, characterized in that The acquisition unit is used to map the IoT card features from a four-dimensional space to a two-dimensional space to obtain low-dimensional IoT card features.

8. A server, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 5 when being executed by a processor.

Images