Simulator detection method, system, storage medium and electronic device

Abstract

The present application discloses a simulator detection method, system, storage medium and electronic device, which acquire a device image, which is collected by a mobile terminal, and input the device image into a pre-trained deep classification model for recognition to obtain a model recognition image. When the model recognition image meets the preset conditions, it is determined that the mobile terminal corresponding to the model recognition image is a simulator, and the simulator is intercepted. Through the above scheme, even if the simulator modifies the configuration file to change the information including the central processing unit, MAC address, etc. to simulate a real mobile device, the scheme can distinguish the simulator from the real mobile device through the deep classification model recognition image, reduce the detection difficulty of the simulator detection method, and improve the recall rate of the simulator. In addition, when the deep classification model recognizes the data features of the simulator imaging, the data features of the simulator imaging are updated to the deep classification model, so that the deep classification model has good scalability.

Description

Technical Field

[0001] The present application relates to the field of simulator technology, and more specifically, to a simulator detection method, system, storage medium and electronic device. Background Art

[0002] With the development of mobile Internet and Internet finance, more and more information systems use mobile phones, tablets and other mobile devices as user terminals. Users can use mobile phones, tablets and other mobile devices to perform face recognition, face payment and other operations. During face recognition, face payment and other operations, running financial software on simulators may pose risks, such as using simulators for false identity authentication, hacker attacks, order swiping, account theft, password modification and other high-risk behaviors. Therefore, it is particularly important to detect whether mobile applications are installed on simulators.

[0003] An emulator is a software that runs on a computer. It can simulate the running of Android and iOS systems. Various mobile software can be installed and used on the emulator. Even if the user does not have a mobile device, he can use the emulator to simulate the use of mobile software on the computer.

[0004] Existing simulator detection methods are mainly based on the detection of the software running environment to determine whether it is a simulator environment, including terminal system logo information, hardware information (CPU, network card, battery, etc.), installed software on the mobile phone, mobile phone communication records, mobile phone storage files, etc. These device information and characteristics are used to distinguish between normal mobile terminal devices and simulators.

[0005] However, some simulators can modify configuration files to change information including the central processing unit, mobile phone brand, memory, battery, MAC address, etc. to simulate normal mobile terminal devices, thereby increasing the detection difficulty of such simulator detection methods and reducing the recall rate of the simulator. Summary of the invention

[0006] In view of this, the present application discloses a simulator detection method, system, storage medium and electronic device, aiming to reduce the detection difficulty of the simulator detection method and improve the recall rate of the simulator. In addition, when the deep classification model recognizes the data features of the simulator imaging, the data features of the simulator imaging are updated to the deep classification model, so that the deep classification model has good scalability.

[0007] In order to achieve the above purpose, the disclosed technical solution is as follows:

[0008] The first aspect of the present application discloses a simulator detection method, the method comprising:

[0009] Acquire a device image, where the device image is acquired by a mobile terminal;

[0010] Inputting the device image into a pre-trained deep classification model for recognition to obtain a model recognition image;

[0011] When the model recognition image meets the preset conditions, it is determined that the mobile terminal corresponding to the model recognition image is a simulator, and an interception operation is performed on the simulator.

[0012] Preferably, it also includes:

[0013] Get device information;

[0014] When the device information contains camera permission information, determining that the mobile terminal is in a preset state; the preset state is used to indicate that the camera function of the mobile terminal is in an available state;

[0015] When the camera permission information does not exist in the device information, it is determined that the mobile terminal is not in a preset state.

[0016] Preferably, it also includes:

[0017] When the mobile terminal is not in the preset state, it is determined that the mobile terminal is a simulator, and an interception operation is performed on the simulator.

[0018] Preferably, when the model recognition image meets a preset condition, it is determined that the mobile terminal corresponding to the model recognition image is a simulator, and an interception operation is performed on the simulator;

[0019] Obtaining image features of the model recognition image;

[0020] When the image feature of the model recognition image is consistent with the first preset image feature, determining that the model recognition image is a simulator virtual image;

[0021] It is determined that the mobile terminal corresponding to the simulator virtual image is a simulator, and an interception operation is performed on the simulator.

[0022] Preferably, the training process of the deep classification model includes:

[0023] Obtaining various images collected by different types of simulators;

[0024] A deep classification model is trained based on the respective images.

[0025] Preferably, the training of the depth classification model according to each of the images comprises:

[0026] Comparing the image features corresponding to each of the images with a second preset image feature to obtain a plurality of image difference features; the second preset image feature is used to characterize the image features corresponding to the image captured by the camera device;

[0027] Generate a script based on the multiple image difference features and preset data to obtain simulator virtual images corresponding to the different types of simulators;

[0028] The deep classification model is trained by using the simulator virtual images corresponding to the different types of simulators.

[0029] Preferably, it also includes:

[0030] When the image feature of the model recognition image is inconsistent with the image feature of the first preset image, it is determined that the model recognition image is a camera image.

[0031] A second aspect of the present application discloses a simulator detection system, the system comprising:

[0032] A first acquisition unit is used to acquire a device image, where the device image is acquired by a mobile terminal;

[0033] A recognition unit, inputting the device image into a pre-trained deep classification model for recognition to obtain a model recognition image;

[0034] The first interception unit is used to determine that the mobile terminal corresponding to the model recognition image is a simulator when the model recognition image meets a preset condition, and perform an interception operation on the simulator.

[0035] A third aspect of the present application discloses a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the simulator detection method as described in any one of the first aspects.

[0036] The fourth aspect of the present application discloses an electronic device, comprising a memory and one or more instructions, wherein the one or more instructions are stored in the memory and are configured to be executed by one or more processors to perform the simulator detection method as described in any one of the first aspects.

[0037] It can be known from the above technical scheme that the present application discloses a simulator detection method, system, storage medium and electronic device, which obtains a device image, which is collected by a mobile terminal, and inputs the device image into a pre-trained deep classification model for recognition to obtain a model recognition image. When the model recognition image meets the preset conditions, it is determined that the mobile terminal corresponding to the model recognition image is a simulator, and the simulator is intercepted. Through the above scheme, even if the simulator modifies the configuration file to change the information including the central processing unit, MAC address, etc. to simulate a real mobile device, this scheme can distinguish the simulator from the real mobile device through the model recognition image, reduce the detection difficulty of the simulator detection method, and improve the recall rate of the simulator. In addition, when the deep classification model recognizes the data features of the simulator imaging, the data features of the simulator imaging are updated to the deep classification model, so that the deep classification model has good scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0039] Figure 1 A flowchart of a simulator detection method disclosed in an embodiment of the present application;

[0040] Figure 2 A schematic diagram of the structure of the simulator disclosed in the embodiment of the present application;

[0041] Figure 3 A flowchart of the training process of the deep classification model disclosed in the embodiment of the present application;

[0042] Figure 4 A flowchart of determining that a mobile terminal corresponding to a model recognition image is a simulator and performing an interception operation on the simulator when a model recognition image is consistent with a preset image disclosed in an embodiment of the present application;

[0043] Figure 5 A schematic diagram of the structure of a simulator detection system disclosed in an embodiment of the present application;

[0044] Figure 6 A schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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 are within the scope of protection of this application.

[0046] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0047] From the background technology, it can be known that in the prior art, some simulators can modify the configuration files to change the information including the central processing unit, mobile phone brand, memory, battery, physical address (Media Access Control, MAC) to simulate a normal mobile terminal device, thereby increasing the detection difficulty of such simulator detection methods and reducing the recall rate of the simulator.

[0048] In order to solve the above problems, the embodiments of the present application disclose a simulator detection method, system, storage medium and electronic device, which can reduce the detection difficulty of the simulator detection method and improve the recall rate of the simulator. The specific implementation method is described in the following embodiments.

[0049] refer to Figure 1 FIG. 1 is a flow chart of a simulator detection method disclosed in an embodiment of the present application. The simulator detection method is applied to a server and mainly includes the following steps:

[0050] S101: Acquire a device image, where the device image is acquired by a mobile terminal.

[0051] In S101, a mobile application (Application, APP) runs on the mobile terminal, the mobile terminal calls the device information through the mobile application and takes a photo to obtain a device image, and the server obtains the device image sent by the mobile terminal.

[0052] S102: Input the device image into a pre-trained deep classification model for recognition to obtain a model recognition image.

[0053] In S102, when the camera function of the mobile terminal is in an available state, the device image is input into a pre-trained deep classification model for recognition to obtain a model recognition image, and the mobile terminal is judged as a real mobile device or a simulator based on the model recognition image.

[0054] Among them, the deep classification model is based on the deep learning method and is trained using a large amount of image data to obtain the classification model.

[0055] Identify device images by using a deep classification model to determine whether the device image was taken by an emulator or a real mobile device.

[0056] The deep classification model includes but is not limited to modern neural networks, such as deep convolutional neural networks, deep fully connected neural networks, etc. Therefore, the deep classification model of this solution has a wide range of applications and strong versatility.

[0057] The training process of the deep classification model is as follows:

[0058] Obtain individual images collected by different types of simulators and train a deep classification model based on each image.

[0059] Specifically, first, various images collected by different types of simulators are obtained.

[0060] Among them, image data captured by various simulators are collected.

[0061] Secondly, the image features corresponding to each image are compared with the second preset image features to obtain a plurality of image difference features.

[0062] Among them, the image data taken by various simulators are collected, the differences between their imaging and the imaging of camera equipment are analyzed, and the image difference characteristics are obtained.

[0063] The image features of the simulator virtual image taken by the simulator and the image of the real mobile device (camera device) are different. Therefore, the image features of the image taken by the simulator are compared with the second preset image features to obtain image difference features. The image difference features include image difference pixel features, color difference features, texture difference features, etc.

[0064] The second preset image feature is an image feature corresponding to an image taken by a real mobile device. The second preset image feature is determined by a technician according to actual conditions and is not specifically limited in this application.

[0065] Then, a script is generated based on multiple image difference features and preset data to obtain simulator virtual images corresponding to different types of simulators.

[0066] The determination of the preset data generation script is set by the technical personnel according to the actual situation, and this application does not make any specific limitation.

[0067] Finally, the deep classification model is trained using simulator virtual images corresponding to different types of simulators.

[0068] Among them, by training the deep classification model, the deep classification model is enabled to distinguish the image of the camera device and the simulator virtual image, so as to achieve the purpose of detecting the simulator.

[0069] An emulator is a software that runs on a computer. It can simulate the running of Android and iOS systems. Various mobile software can be installed and used on the emulator. Even if the user does not have a mobile device, he can use the emulator to simulate the use of mobile software on the computer.

[0070] The simulators include but are not limited to Android simulators, iOS simulators, simulators installed on computers with Windows systems, simulators on computers with Linux-like systems, etc.

[0071] The structure diagram of the specific simulator is as follows Figure 2 shown.

[0072] Figure 2 In the simulator, the software is installed on the computer, which has the function of simulating the mobile phone system. Various mobile phone applications can be installed in the simulated mobile phone system.

[0073] If a new type of simulator is found, whose imaging is different from the existing simulators, it is only necessary to collect or generate a batch of simulator virtual images of the new type of simulator, add the simulator virtual images of the new type of simulator to the training set, and retrain the deep classification model to support the detection of this type of simulator. Therefore, the deep classification model of this solution has good scalability.

[0074] The change of simulator device information will not change the image features, so it has good ability to prevent simulator device information tampering.

[0075] The simulator detection method of the present application has the characteristics of low maintenance cost, easy migration and expansion, good versatility and strong robustness.

[0076] S103: When the model recognition image meets the preset conditions, it is determined that the mobile terminal corresponding to the model recognition image is a simulator, and an interception operation is performed on the simulator.

[0077] In S103, when the image feature of the model recognition image is consistent with the first preset image feature, it is determined that the model recognition image meets the preset condition, that is, it is determined that the mobile terminal is in the simulator environment.

[0078] Specifically, when the model recognition image meets the preset conditions, the mobile terminal corresponding to the model recognition image is determined to be a simulator, and the process of intercepting the simulator is as follows:

[0079] First, the image features of the model recognition image are obtained. Then, when the image features of the model recognition image are consistent with the first preset image features, the model recognition image is determined to be a simulator virtual image. Finally, the mobile terminal corresponding to the simulator virtual image is determined to be a simulator, and an interception operation is performed on the simulator.

[0080] Among them, image features include image pixel features, color features, texture features, etc.

[0081] The first preset characteristic feature is an image feature corresponding to the image taken by the simulator. The first preset image feature is determined by the technicians according to the actual situation, and this application does not make any specific limitation.

[0082] When the image features of the model recognition image are inconsistent with the image features of the first preset image, it is determined that the model recognition image is a camera image.

[0083] The camera images are images taken by real mobile devices.

[0084] Determine that the mobile terminal is a simulator, and intercept the simulator to prevent it from performing operations such as face payment and face recognition.

[0085] In the embodiment of the present application, even if the simulator modifies the configuration file to change information including the central processing unit, MAC address, etc. to simulate a real mobile device, the present solution can distinguish the simulator from the real mobile device through the model recognition image, thereby reducing the detection difficulty of the simulator detection method and improving the recall rate of the simulator. In addition, when the deep classification model recognizes the data features of the simulator imaging, the data features of the simulator imaging are updated to the deep classification model, so that the deep classification model has good scalability.

[0086] Optionally, obtain device information and determine whether the mobile terminal is in a preset state through the device information. When camera permission information exists in the device information, determine that the mobile terminal is in the preset state. When camera permission information does not exist in the device information, determine that the mobile terminal is not in the preset state, determine that the mobile terminal is a simulator, and intercept the simulator.

[0087] Among them, the device information is the device information of the mobile terminal, and the device information includes whether the mobile terminal has camera permission information, whether the mobile terminal is in a preset state information (camera available state information), etc.

[0088] The preset state is used to indicate that the camera function of the mobile terminal is in a usable state.

[0089] Camera permission information is obtained by the user granting mobile camera permissions.

[0090] If the mobile terminal is not in the preset state, it is determined that the mobile terminal is a simulator, and the simulator is intercepted so that the simulator cannot perform operations such as face payment and face recognition.

[0091] In an embodiment of the present application, when camera permission information exists in the device information, it is determined that the mobile terminal is in a preset state; when camera permission information does not exist in the device information, it is determined that the mobile terminal is not in the preset state, and the mobile terminal is determined to be a simulator, thereby achieving the purpose of intercepting operations on the simulator.

[0092] refer to Figure 3 As shown, the training process of the deep classification model involved in the above S102 mainly includes the following steps:

[0093] S301: Acquire various images collected by different types of simulators.

[0094] S302: Compare the image features corresponding to each image with the second preset image features to obtain a plurality of image difference features.

[0095] S303: Generate a script based on multiple image difference features and preset data to obtain simulator virtual images corresponding to different types of simulators.

[0096] S304: Training the deep classification model using simulator virtual images corresponding to different types of simulators.

[0097] The execution principle of S301-S304 is consistent with the execution principle of S102 mentioned above, which can be used for reference and will not be repeated here.

[0098] In an embodiment of the present application, the image features corresponding to each acquired image are compared with the second preset image features to obtain multiple image difference features. A script is generated based on the multiple image difference features and preset data to obtain simulator virtual images corresponding to different types of simulators. The deep classification model is trained by the simulator virtual images corresponding to different types of simulators to achieve the purpose of training the deep classification model.

[0099] refer to Figure 4 As shown, the process of determining that the mobile terminal corresponding to the model recognition image is a simulator and performing an interception operation on the simulator in the above S103 when the model recognition image is consistent with the preset image mainly includes the following steps:

[0100] S401: Obtain image features of the model recognition image.

[0101] S402: When the image feature of the model recognition image is consistent with the first preset image feature, determining that the model recognition image is a simulator virtual image.

[0102] S403: Determine that the mobile terminal corresponding to the simulator virtual image is a simulator, and perform an interception operation on the simulator.

[0103] The execution principle of S401-S403 is consistent with the execution principle of S103 mentioned above, which can be referred to and will not be described again here.

[0104] In an embodiment of the present application, when the image features of the model recognition image are consistent with the first preset image features, the model recognition image is determined to be a simulator virtual image, and the mobile terminal corresponding to the simulator virtual image is determined to be a simulator, thereby achieving the purpose of intercepting the simulator.

[0105] Based on the above embodiments Figure 1 A simulator detection method is disclosed, and the embodiment of the present application also discloses a simulator detection system, such as Figure 5 As shown, the simulator detection system mainly includes a first acquisition unit 501 , an identification unit 502 and a first interception unit 503 .

[0106] The first acquisition unit 501 is used to acquire a device image, where the device image is acquired by a mobile terminal.

[0107] The recognition unit 502 is used to input the device image into a pre-trained deep classification model for recognition to obtain a model recognition image.

[0108] The first interception unit 503 is used to determine that the mobile terminal corresponding to the model recognition image is a simulator when the model recognition image meets the preset conditions, and perform an interception operation on the simulator.

[0109] Furthermore, it also includes a second acquiring unit, a first determining unit and a second determining unit.

[0110] The second acquiring unit is used to acquire device information.

[0111] The first determination unit is used to determine that the mobile terminal is in a preset state when the camera permission information exists in the device information; the preset state is used to indicate that the camera function of the mobile terminal is in an available state.

[0112] The second determining unit is used to determine that the mobile terminal is not in a preset state when the camera permission information does not exist in the device information.

[0113] Furthermore, it also includes a second interception unit.

[0114] The second interception unit is used to determine that the mobile terminal is a simulator and perform an interception operation on the simulator when the mobile terminal is not in a preset state.

[0115] Furthermore, the first interception unit 504 includes a first acquisition module, a first determination module and an interception module.

[0116] The first acquisition module is used to acquire image features of the model recognition image.

[0117] The first determination module is used to determine that the model recognition image is a simulator virtual image when the image feature of the model recognition image is consistent with the first preset image feature.

[0118] The interception module is used to determine that the mobile terminal corresponding to the simulator virtual image is a simulator and perform interception operations on the simulator.

[0119] Furthermore, the identification unit 502 of the training process of the deep classification model includes a second acquisition module, a comparison module, a third acquisition module and a training module.

[0120] The second acquisition module is used to acquire various images collected by different types of simulators.

[0121] The comparison module is used to compare the image features corresponding to each image with the second preset image features to obtain multiple image difference features.

[0122] The third acquisition module is used to generate a script based on multiple image difference features and preset data to obtain simulator virtual images corresponding to different types of simulators.

[0123] The training module is used to train the deep classification model through simulator virtual images corresponding to different types of simulators.

[0124] Furthermore, a third determining unit is also included.

[0125] The third determining unit is used to determine that the model recognition image is a camera image when the image feature of the model recognition image is inconsistent with the image feature of the first preset image.

[0126] In the embodiment of the present application, even if the simulator modifies the configuration file to change information including the central processing unit, MAC address, etc. to simulate a real mobile device, the present solution can distinguish the simulator from the real mobile device through the model recognition image, thereby reducing the detection difficulty of the simulator detection method and improving the recall rate of the simulator. In addition, when the deep classification model recognizes the data features of the simulator imaging, the data features of the simulator imaging are updated to the deep classification model, so that the deep classification model has good scalability.

[0127] An embodiment of the present application further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned simulator detection method.

[0128] The present application also provides an electronic device, whose structural diagram is as follows: Figure 6 As shown, it specifically includes a memory 601 and one or more instructions 602, wherein the one or more instructions 602 are stored in the memory 601 and are configured to be executed by one or more processors 603 to execute the one or more instructions 602 to perform the above-mentioned simulator detection method.

[0129] The specific implementation processes and derivative methods of the above-mentioned embodiments are all within the protection scope of this application.

[0130] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0131] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0132] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0133] 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 simulator detection method, characterized in that: The method comprises: Acquire a device image, where the device image is acquired by a mobile terminal; Inputting the device image into a pre-trained deep classification model for recognition to obtain a model recognition image; When the model recognition image meets the preset conditions, determining that the mobile terminal corresponding to the model recognition image is a simulator, and performing an interception operation on the simulator; Among them, the training process of the deep classification model includes: Obtaining various images acquired by different types of simulators; Training a deep classification model based on each of the images; The training of the depth classification model according to each of the images comprises: Comparing the image features corresponding to each of the images with a second preset image feature to obtain a plurality of image difference features; the second preset image feature is used to characterize the image features corresponding to the image captured by the camera device; Generate a script based on the multiple image difference features and preset data to obtain simulator virtual images corresponding to the different types of simulators; The deep classification model is trained by using the simulator virtual images corresponding to the different types of simulators.

2. The method according to claim 1, characterized in that Also includes: Get device information; When the device information contains camera permission information, determining that the mobile terminal is in a preset state; The preset state is used to indicate that the camera function of the mobile terminal is in an available state; When the camera permission information does not exist in the device information, it is determined that the mobile terminal is not in a preset state.

3. The method according to claim 2, characterized in that Also includes: When the mobile terminal is not in the preset state, it is determined that the mobile terminal is a simulator, and an interception operation is performed on the simulator.

4. The method according to claim 1, characterized in that: When the model recognition image meets the preset condition, determining that the mobile terminal corresponding to the model recognition image is a simulator, and performing an interception operation on the simulator; Obtaining image features of the model recognition image; When the image feature of the model recognition image is consistent with the first preset image feature, determining that the model recognition image is a simulator virtual image; It is determined that the mobile terminal corresponding to the simulator virtual image is a simulator, and an interception operation is performed on the simulator.

5. The method according to claim 4, characterized in that Also includes: When the image feature of the model recognition image is inconsistent with the image feature of the first preset image, it is determined that the model recognition image is a camera image.

6. A simulator detection system, characterized in that: The system comprises: A first acquisition unit is used to acquire a device image, where the device image is acquired by a mobile terminal; A recognition unit, inputting the device image into a pre-trained deep classification model for recognition to obtain a model recognition image; A first interception unit, configured to determine that the mobile terminal corresponding to the model recognition image is a simulator when the model recognition image meets a preset condition, and perform an interception operation on the simulator; Among them, the recognition unit of the training process of the deep classification model includes: A second acquisition module is used to acquire each image collected by different types of simulators; A training module, used for training a deep classification model according to each of the images; The training module is specifically used for: Comparing the image features corresponding to each of the images with a second preset image feature to obtain a plurality of image difference features; the second preset image feature is used to characterize the image features corresponding to the image captured by the camera device; Generate a script based on the multiple image difference features and preset data to obtain simulator virtual images corresponding to the different types of simulators; The deep classification model is trained by using the simulator virtual images corresponding to the different types of simulators.

7. A storage medium, characterized in that: The storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the simulator detection method according to any one of claims 1 to 5.

8. An electronic device, characterized in that: The device comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to perform the simulator detection method according to any one of claims 1 to 5.

Images