Verification code verification method

Abstract

The invention discloses a check code verification method, belongs to the technical field of information security, and is used for improving verification code verification security and user experience. The method comprises the steps of generating a first verification code according to a first virtual image under the condition that the first virtual image preset by a user exists; under the condition that the first virtual image does not exist, generating a second virtual image, and generating a second verification code according to the second virtual image and the first use scene; and performing verification through the first verification code or the second verification code.

Description

Technical Field

[0001] The present invention relates to the field of information security, and specifically relates to a verification code verification method. Background Art

[0002] Since the registration threshold for Internet applications is low, it is easy for a large number of machine scripts to simulate user operations, squeezing platform resources and posing security risks. To avoid this problem, many Internet applications use random graphic verification codes to verify the real identity of the operator.

[0003] Common types of graphic verification codes include sliding puzzles, text selection, word order selection, font recognition, spatial reasoning, etc. However, current graphic verification codes are mostly in the form of two-dimensional images, and generally come from public graphic material libraries, which cannot meet the user's needs for fun and personalized display. Summary of the invention

[0004] The embodiment of the present application provides a verification code verification method, which can solve the problem that the user's needs for fun and personalized display cannot be met.

[0005] In a first aspect, an embodiment of the present application provides a verification code verification method, the method comprising: in the presence of a first virtual image pre-set by a user, generating a first verification code based on the first virtual image; in the absence of the first virtual image, generating a second virtual image, and generating a second verification code based on the second virtual image and a first usage scenario; and verifying through the first verification code or the second verification code.

[0006] In a second aspect, an embodiment of the present application provides a verification code verification device, which includes: a first generation module, used to generate a first verification code based on a first virtual image pre-set by a user; a second generation module, used to generate a second virtual image in the absence of the first virtual image, and generate a second verification code based on the second virtual image and a first usage scenario; a verification module, used to verify through the first verification code or the second verification code.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0008] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0009] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, which, when executed by a computer, cause the computer to perform the steps of the method described in the first aspect.

[0010] In an embodiment of the present application, by generating a first verification code based on a first virtual image pre-set by a user when there is one; generating a second virtual image when the first virtual image does not exist, and generating a second verification code based on the second virtual image and the first usage scenario; and verifying through the first verification code or the second verification code, the security of the verification code verification and the user experience can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flowchart of a verification code verification method provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of a verification code verification device provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] 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 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.

[0013] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0014] The following is a detailed description of a verification code verification method provided in an embodiment of the present application through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0015] Figure 1A verification code verification method provided by an embodiment of the present application is shown, and the method can be executed by an electronic device, and the electronic device may include: a server and / or a terminal device. In other words, the method can be executed by software or hardware installed in the electronic device, and the method includes the following steps: Step 102: In the case where there is a first virtual image preset by the user, a first verification code is generated according to the first virtual image.

[0016] In an embodiment of the present application, the method for generating a verification code can be determined according to the scenario in which the verification code is verified. In the case of a first virtual image pre-set by the user, a first verification code needs to be generated according to the first virtual image. The current usage scenario is when the user is watching a live football match. At this time, the scene content of the usage scenario (such as football, events, time, etc.) has an impact on the user portrait originally constructed by the server. If the current usage scenario is when the user just starts the terminal, since there is no usage information at the time of startup, at this time, the scene content of the usage scenario has no impact on the user portrait originally constructed by the server.

[0017] Specifically, the usage scenarios may include: user login, withdrawal, voting, logout and unbinding, etc. Among them, the user login scenario can also be subdivided into: login verification before watching videos, login verification when browsing web pages, and login verification before playing online games, etc.

[0018] In one implementation, in the presence of a first virtual image pre-set by the user, generating a first verification code based on the first virtual image includes: acquiring multiple target features from a feature set corresponding to the user, wherein the feature set includes: user's IP address features, time features, user level features, user interest features, and usage scenario features; generating the first verification code based on the multiple target features and the first virtual image.

[0019] Specifically, a feature set may be obtained first, and the feature set may include a first virtual image preset by the user, the user's IP address, and user big data tag information. Among them, the user big data tag information may include user level features, user interest features, etc. It may also include time features recorded by the system and usage scenario features of usage scenarios. Multiple target features may be obtained from the above feature set, for example, 2-3 target features may be randomly obtained from the above feature set. Among them, if the IP address feature and the time feature can be read, they may be set as required target features.

[0020] As an example, if the user's IP address characteristics (such as Guangzhou), time characteristics (such as the evening of September 1), user level characteristics (such as V2), user interest characteristics (such as football, cars), and usage scenario characteristics (such as the Football World Cup, live broadcast platform live broadcast, TV series, etc.) are successfully found, the IP address characteristics, time characteristics, user identity level, and usage scenario characteristics are selected and recorded.

[0021] After obtaining a plurality of target features, a first verification code may be generated according to the plurality of target features and the first virtual image.

[0022] In one implementation, generating the first verification code based on the scene feature elements and the first virtual image includes: generating a first verification image based on the multiple target features and the first virtual image; obtaining an error feature and a third virtual image that do not correspond to the user; generating a plurality of second verification images based on the multiple target features, the first virtual image, the error feature and / or the third virtual image, the second verification image including the error feature and / or the third virtual image; generating the first verification code based on the first verification image and the plurality of the second verification images.

[0023] Specifically, multiple target features and the first virtual image can be integrated to extract the first virtual image and related scene feature elements to generate a first verification image. For example, if the user IP address feature, time feature (such as the night of September 1), user identity level feature (such as V2), and usage scene feature (such as a football match) are selected, a first verification image can be generated, the background of which is the moon at night, the background building has a landmark building corresponding to the IP address feature, there are yellow fallen leaves on the ground, the upper right corner of the picture shows the V2 level, the middle is the front of the user's first virtual image, and there is a football next to the first virtual image.

[0024] It is possible to obtain an erroneous feature that does not correspond to the user, confuse the erroneous feature with the target feature, and randomly extract a third virtual image that is not the user and is stored in the system. According to the multiple target features, the first virtual image, the erroneous feature and / or the third virtual image, a plurality of erroneous second verification images are generated, and the plurality of second verification images include erroneous features and / or third virtual images. For example, assuming that the user IP address feature, the time feature (such as the evening of September 1), the user identity level feature (such as V2), and the usage scenario feature (such as a football match) are selected. Then, it is possible to randomly generate three second verification images with incorrect virtual images, one second verification image with a correct virtual image but an incorrect IP address feature, and one second verification image with a correct virtual image and IP address feature but an incorrect time feature. The user level feature (V2) is displayed in the upper right corner of all images.

[0025] Second verification Figure 1(Incorrect avatar, incorrect IP address characteristics, incorrect time characteristics, correct usage scenario characteristics); Error Figure 2 (Incorrect avatar, correct IP address characteristics, incorrect time characteristics, correct usage scenario characteristics); Error Figure 3 (Incorrect virtual image, incorrect IP address feature, correct time feature, correct usage scenario feature); Error Figure 4 (Correct virtual image, correct IP address feature, incorrect time feature, incorrect usage scenario feature); Error Figure 5 (Correct virtual image, incorrect IP address feature, correct time feature, incorrect usage scenario feature). The number of second verification images generated can be set according to actual needs. Usually, the number of second verification images is 5. The selection process is random for inconsistent items (just determine if the features of the 6 images are not completely consistent). The features of the error items are randomly extracted by the system, and only 1 unified error feature is extracted for the error items. In this way, a total of 6 verification images are formed, for example: First verification image 0 (correct avatar features, correct IP address features, autumn evening, football).

[0026] Second verification Figure 1 (Incorrect avatar characteristics, incorrect IP address characteristics, summer noon, football).

[0027] Second verification Figure 2 (Incorrect avatar characteristics, correct IP address characteristics, summer noon, football).

[0028] Second verification Figure 3 (Incorrect avatar characteristics, incorrect IP address characteristics, summer noon, football).

[0029] The second verification diagram is Figure 4 (the characteristics of the virtual image are correct, the characteristics of the IP address are correct, it is noon in summer, and the game console).

[0030] Second verification Figure 5 (correct avatar features, incorrect IP address features, autumn evening, game console).

[0031] In one implementation, generating the first verification code according to the first verification diagram and the plurality of second verification diagrams includes: generating a multi-faceted cube according to the first verification diagram and the plurality of second verification diagrams, wherein the first verification diagram and the plurality of second verification diagrams are faces of the multi-faceted cube; and using the multi-faceted cube as the first verification code.

[0032] Specifically, a multi-faceted cube can be generated based on the first verification image and multiple second verification images, for example, a 6-faced cube is generated, wherein the order of the images of the faces of the 6-faced cube is random and the placement angles are random, and the obtained multi-faceted cube is used as the first verification code.

[0033] Step 104: In the absence of the first virtual image, a second virtual image is generated, and a second verification code is generated according to the second virtual image and the first usage scenario.

[0034] Specifically, in the absence of the first virtual image, a second virtual image may be generated, and a second verification code may be generated according to the second virtual image and the first usage scenario.

[0035] In one implementation, generating a second verification code based on the second virtual image and the usage scenario includes: generating a virtual animation based on the first usage scenario and the second virtual image; controlling the second virtual image to generate a first human posture in the virtual animation; and using the animation playback time, animation playback screen, and the first human posture of the first human posture in the virtual animation as the second verification code.

[0036] Specifically, the scene content of the first usage scenario of the verification code can be determined first, and a virtual animation including a second virtual image can be generated based on the scene content, wherein the background content of the virtual animation is the same as the scene content of the first usage scenario. The second virtual image is controlled to randomly generate a specific first human body posture in the virtual animation, and the first human body posture can be a 3D human body posture. The animation playback time, animation playback screen, and first human body posture of the specific first human body posture generated by the second virtual image are used as the second verification code.

[0037] Step 106: Verify using the first verification code or the second verification code.

[0038] Specifically, after obtaining the first verification code or the second verification code according to the usage scenario of the verification code, verification can be performed using the first verification code or the second verification code.

[0039] The verification code verification method provided in the embodiment of the present application generates a first verification code according to a first virtual image preset by a user in the presence of the first virtual image; generates a second virtual image in the absence of the first virtual image, and generates a second verification code according to the second virtual image and the first usage scenario; the verification is performed by the first verification code or the second verification code, so that the security of the verification code can be improved. Traditional verification codes with combinations of numbers and letters are often vulnerable to brute force or machine-generated attacks, and the use of virtual character images to generate verification codes can increase the complexity and difficulty of the verification code and improve the security of the system; it can enhance the user experience: by using virtual character images to generate verification codes, a more attractive and interesting user interface can be created. When users perform verification operations, they will feel more interesting and interactive, thereby improving the overall user experience. Prevent automated robot attacks: The verification code generated by the virtual character image can prevent automated robot attacks through image recognition, human-machine recognition and other technologies, thereby protecting the system from threats such as malware, spam and robot attacks, and ensuring access by normal users.

[0040] In one implementation, the verification using the first verification code or the second verification code includes: displaying the first verification code to a user; and determining that the verification is successful when the user operates the first verification code to move the target verification code in the first verification code to a predetermined position.

[0041] When verifying the first verification code, the generated multi-faceted cube with picture information can be randomly displayed to the user, and then the user is required to face the verification picture that best suits his or her situation to himself or herself. Specifically, the user can press and hold to rotate and drag the multi-faceted cube. Sometimes the picture will be upside down, and the user needs to press and hold with two fingers to rotate the cube. When the user is sure that the move is complete, click the OK button in the lower right corner to make a judgment. When the target verification code in the first verification code is moved to the predetermined position, it is determined that the verification is successful. Using virtual characters to generate verification codes can increase the complexity and difficulty of the verification codes, improve the security of the system, and users will feel more interesting and interactive when performing verification operations, thereby improving the overall user experience.

[0042] In one implementation, the verification using the first verification code or the second verification code includes: showing a plurality of second usage scenarios and a plurality of third virtual images to the user; playing the virtual animation when the second usage scenario and the third virtual image selected by the user are the same as the first usage scenario and the second virtual image of the virtual animation; acquiring an animation picture including the second human body posture while monitoring a second human body posture generated by the second virtual image in the virtual animation controlled by the user; and performing verification based on the animation picture.

[0043] Specifically, when verifying through the second verification code, multiple second usage scenarios and multiple third virtual images can be displayed to the user. When the second usage scenario and the third virtual image selected by the user are the same as the first usage scenario and the second virtual image of the virtual animation, the virtual animation is played, and when the virtual animation is played, the user is prompted to control the virtual image to generate a 3D human body posture at any time. The user can choose to control the virtual character image to generate a 3D human body posture at the target playback time and the target playback screen according to the playback time and playback screen of the virtual animation. After monitoring that the user controls the virtual character image to generate a 3D human body posture, an animation screen containing a 3D human body posture can be obtained. When monitoring that the user controls the second virtual image in the virtual animation to generate a second human body posture, an animation screen containing the second human body posture is obtained; and verification is performed according to the animation screen. In this way, using a virtual character image to generate a verification code can increase the complexity and difficulty of the verification code, improve the security of the system, and enhance the user experience: by using a virtual character image to generate a verification code, a more attractive and interesting user interface can be created. When the user performs the verification operation, it will feel more interesting and interactive, thereby improving the overall user experience.

[0044] In one implementation, when it is determined that the second human body posture in the animation picture is the same as the first human body posture, before determining that the verification is successful, it also includes: inputting the animation picture into a target model, and judging whether the second human body posture is the same as the first human body posture through the target model.

[0045] Specifically, the animation picture is input into the target model, which may be a virtual character posture estimation network model, to identify whether the second human body posture generated by the virtual character is the same as the first human body posture of the virtual character in the verification code.

[0046] In one implementation, the target model includes a ResNet-based feature extractor, a bidirectional convolutional LSTM (BiConvLSTM) layer, an HPE backbone network, and a triangulation module.

[0047] Specifically, the avatar pose estimation network model includes a ResNet-based feature extractor, a bidirectional convolutional LSTM (BiConvLSTM) layer, an HPE backbone network, and a triangulation module. The initial part of ResNet34 is used as a feature extractor, which is then succeeded by a BiConvLSTM layer containing skip connections.

[0048] Among them, BiConvLSTM represents a bidirectional variant of ConvLSTM, combining convolutional structures in both input-to-state and state-to-state transitions. Subsequently, the HPE backbone network consists of three hourglass-like CNN blocks, each of which produces a series of edge heat maps to reconstruct the coordinates of human joints in 3D space. All intermediate outputs of these three modules are used to calculate the loss using the true heat map, while the last two modules can be regarded as refinement networks. The feature extractor and backbone network architecture are developed based on the model proposed in.

[0049] In the embodiment of the present application, the animation picture is first represented as Xt, and U-Net is ; Correspondingly, the animation picture is input into the virtual character posture estimation network model, which can be expressed as:

[0050] in, represents the animation content at timestamp t, and Represents the animation content at this time in history. Confidence score and , expressed as and in:

[0051] Secondly, after receiving the input animation picture, the virtual character posture estimation network model can extract the feature information of the animation picture based on the feature extractor, and generate the element map of the virtual character image based on the feature information in the following manner:

[0052] in, Represents a feature extractor. A graph of elements representing an avatar image.

[0053] Afterwards, based on the feature map of the avatar image, a joint heat map is generated as follows :

[0054] Afterwards, three heat maps are generated for each joint of the avatar as follows to describe its 3D position on the xy, xz, and yz planes.

[0055]

[0056] in, represents the estimate of the xy-plane heatmap for a specific joint j at time t; represents the estimate of the xz-plane heatmap for a specific joint j at time t; Represents a preset parameter-finding function; Represents the 3D coordinates of a specific joint j of the avatar at time t.

[0057] In order to ensure the accuracy of the virtual character image posture estimation network model, the virtual character image posture estimation network model can also be iteratively updated according to the following method.

[0058]

[0059] Finally, according to the 3D positions of the joints of the 3D human body posture generated by the virtual character image and the positions of the joints of the virtual character image contained in the verification code, it is determined whether the 3D human body posture generated by the virtual character image is the same as the posture of the virtual character image in the verification code. Specifically, if they are the same, the verification is considered successful; otherwise, the verification fails.

[0060] It should be noted that the verification code verification method provided in the embodiment of the present application can be executed by a verification code verification device, or a control module in the verification code verification device for executing the verification code verification method. In the embodiment of the present application, the verification code verification device provided in the embodiment of the present application is illustrated by taking the verification code verification device executing the verification code verification method as an example.

[0061] Figure 2 Schematic diagram of the structure of the verification code verification device according to the embodiment of the present application. Figure 2 As shown, the verification code verification device 200 includes: a first generation module 210, a second generation module 220 and a verification module 230.

[0062] The first generation module 210 is used to generate a first verification code according to a first virtual image pre-set by a user when there is the first virtual image; the second generation module 220 is used to generate a second virtual image in the absence of the first virtual image, and generate a second verification code according to the second virtual image and the first usage scenario; the verification module 230 is used to perform verification through the first verification code or the second verification code.

[0063] In one implementation, the first generation module 210 is used to obtain multiple target features from a feature set corresponding to the user, wherein the feature set includes: user IP address features, time features, user level features, user interest features, and usage scenario features; and generate the first verification code based on the multiple target features and the first virtual image.

[0064] In one implementation, the first generation module 210 is used to generate a first verification image based on the multiple target features and the first virtual image; obtain an error feature and a third virtual image that do not correspond to the user; generate a plurality of second verification images based on the multiple target features, the first virtual image, the error feature and / or the third virtual image, the second verification image including the error feature and / or the third virtual image; generate the first verification code based on the first verification image and the plurality of the second verification images.

[0065] In one implementation, the second generation module 220 is used to generate a virtual animation according to the first usage scenario and the second virtual image; control the second virtual image to generate a first human posture in the virtual animation; and use the animation playback time, animation playback screen and the first human posture of the first human posture in the virtual animation as the second verification code.

[0066] In one implementation, the verification module 230 is used to display the first verification code to the user; when the user operates the first verification code and moves the target verification code in the first verification code to a predetermined position, it is determined that the verification is successful.

[0067] In one implementation, the verification module 230 is used to display multiple second usage scenarios and multiple third virtual images to the user; play the virtual animation when the second usage scenario and the third virtual image selected by the user are the same as the first usage scenario and the second virtual image of the virtual animation; obtain an animation picture including the second human body posture while monitoring the second human body posture generated by the second virtual image in the virtual animation controlled by the user; and perform verification based on the animation picture.

[0068] In one implementation, the verification module 230 is used to determine that the verification is successful if it is determined that the second human body posture in the animation picture is the same as the first human body posture.

[0069] In one implementation, the verification module 230 is used to input the animation picture into a target model, and determine whether the second human body posture is the same as the first human body posture through the target model.

[0070] In one implementation, the target model includes a ResNet-based feature extractor, a bidirectional convolutional LSTM (BiConvLSTM) layer, an HPE backbone network, and a triangulation module.

[0071] In one implementation, the first generating module 210 is used to generate a multi-faceted cube according to the first verification diagram and multiple second verification diagrams, wherein the first verification diagram and multiple second verification diagrams are faces of the multi-faceted cube; and use the multi-faceted cube as the first verification code.

[0072] The verification code verification device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0073] The verification code verification device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0074] The verification code verification device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0075] like Figure 3 As shown, an embodiment of the present application further provides an electronic device 300, including a processor 301 and a memory 302, wherein the memory 302 stores a program or instruction that can be executed on the processor 301, and the program or instruction is implemented when executed by the processor 301: in the case of a first virtual image pre-set by a user, a first verification code is generated according to the first virtual image; in the case of the absence of the first virtual image, a second virtual image is generated, and a second verification code is generated according to the second virtual image and the first usage scenario; and verification is performed through the first verification code or the second verification code.

[0076] In one implementation, multiple target features are obtained from a feature set corresponding to the user, wherein the feature set includes: user's IP address features, time features, user level features, user interest features, and usage scenario features; and the first verification code is generated based on the multiple target features and the first virtual image.

[0077] In one implementation, based on the multiple target features and the first virtual image, a first verification image is generated to obtain an error feature and a third virtual image that do not correspond to the user; based on the multiple target features, the first virtual image, the error feature and / or the third virtual image, a plurality of second verification images are generated, the second verification image including the error feature and / or the third virtual image; based on the first verification image and the plurality of the second verification images, the first verification code is generated.

[0078] In one implementation, a virtual animation is generated based on the first usage scenario and the second virtual image; the second virtual image is controlled to generate a first human posture in the virtual animation; and the animation playback time, animation playback screen and the first human posture of the first human posture in the virtual animation are used as the second verification code.

[0079] In one implementation, the first verification code is displayed to the user; when the user operates the first verification code and moves the target verification code in the first verification code to a predetermined position, it is determined that the verification is successful.

[0080] In one implementation, multiple second usage scenarios and multiple third virtual images are displayed to the user; when the second usage scenario and the third virtual image selected by the user are the same as the first usage scenario and the second virtual image of the virtual animation, the virtual animation is played; while monitoring the second human body posture generated by the second virtual image in the virtual animation controlled by the user, an animation picture including the second human body posture is obtained; and verification is performed based on the animation picture.

[0081] In one implementation, when it is determined that the second human body posture in the animation picture is the same as the first human body posture, it is determined that the verification is successful.

[0082] In one implementation, when it is determined that the second human body posture in the animation picture is the same as the first human body posture, before determining that the verification is successful, the animation picture is input into a target model, and whether the second human body posture is the same as the first human body posture is determined by the target model.

[0083] In one implementation, the target model includes a ResNet-based feature extractor, a bidirectional convolutional LSTM (BiConvLSTM) layer, an HPE backbone network, and a triangulation module.

[0084] In one implementation, a multi-faceted cube is generated according to the first verification graph and the plurality of the second verification graphs, wherein the first verification graph and the plurality of the second verification graphs are faces of the multi-faceted cube; and the multi-faceted cube is used as the first verification code.

[0085] The specific execution steps can refer to the various steps of the above-mentioned verification code verification method embodiment, and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0086] It should be noted that the electronic devices in the embodiments of the present application include: servers, terminals, or other devices except terminals.

[0087] The above electronic device structure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, the input unit may include a graphics processing unit (GPU) and a microphone, and the display unit may be configured with a display panel in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit includes a touch panel and at least one of other input devices. The touch panel is also called a touch screen. Other input devices may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0088] The memory can be used to store software programs and various data. The memory may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory may include a volatile memory or a non-volatile memory, or the memory may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DRRAM).

[0089] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to the operating system, user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor.

[0090] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned verification code verification method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0091] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as ROM, RAM, magnetic disk or optical disk.

[0092] The embodiment of the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the various processes of the above-mentioned verification code verification method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0093] It should be noted that, in this article, the term "comprises", "includes" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0094] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0095] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A verification code verification method, characterized in that: include: In the case where there is a first virtual image preset by the user, generating a first verification code according to the first virtual image; In the absence of the first virtual image, generating a second virtual image, and generating a second verification code according to the second virtual image and the first usage scenario; Verification is performed using the first verification code or the second verification code.

2. The method according to claim 1, characterized in that The step of generating a first verification code according to the first virtual image in a case where there is a first virtual image preset by the user includes: Acquire multiple target features from a feature set corresponding to the user, wherein the feature set includes: a user's IP address feature, a time feature, a user level feature, a user interest feature, and a usage scenario feature; The first verification code is generated according to the multiple target features and the first virtual image.

3. The method according to claim 2, characterized in that The step of generating the first verification code according to the scene feature element and the first virtual image includes: generating a first verification image according to the plurality of target features and the first virtual image; Acquiring erroneous features and a third avatar that do not correspond to the user; generating a plurality of second verification images according to the plurality of target features, the first virtual image, the error features and / or the third virtual image, wherein the second verification images include the error features and / or the third virtual image; The first verification code is generated according to the first verification graph and a plurality of the second verification graphs.

4. The method according to claim 1, characterized in that The generating a second verification code according to the second virtual image and the first usage scenario includes: generating a virtual animation according to the first usage scenario and the second virtual image; controlling the second virtual image to generate a first human posture in the virtual animation; The animation playing time, the animation playing screen and the first human posture of the first human posture in the virtual animation are used as the second verification code.

5. The method according to claim 3, characterized in that: The verifying by using the first verification code or the second verification code includes: Displaying the first verification code to the user; When the user operates the first verification code to move the target verification code in the first verification code to a predetermined position, it is determined that the verification is successful.

6. The method according to claim 4, characterized in that The verifying by using the first verification code or the second verification code includes: presenting a plurality of second usage scenarios and a plurality of third virtual images to the user; When the second usage scenario and the third virtual image selected by the user are the same as the first usage scenario and the second virtual image of the virtual animation, playing the virtual animation; Under the condition of monitoring a second human body posture generated by a second virtual image in the virtual animation controlled by a user, acquiring an animation picture including the second human body posture; Verification is performed according to the animation picture.

7. The method according to claim 6, characterized in that The checking according to the animation picture includes: When it is determined that the second human body posture in the animation picture is the same as the first human body posture, it is determined that the verification is successful.

8. The method according to claim 7, characterized in that In the case where it is determined that the second human body posture in the animation picture is the same as the first human body posture, before determining that the verification is successful, the method further includes: The animation picture is input into a target model, and whether the second human body posture is the same as the first human body posture is determined by the target model.

9. The method according to claim 8, characterized in that The target model includes a ResNet-based feature extractor, a bidirectional convolutional LSTM (BiConvLSTM) layer, an HPE backbone network, and a triangulation module.

10. The method according to claim 1, characterized in that The step of generating the first verification code according to the first verification graph and the plurality of the second verification graphs includes: Generate a multi-faceted cube according to the first verification graph and the plurality of the second verification graphs, wherein the first verification graph and the plurality of the second verification graphs are faces of the multi-faceted cube; The multi-faceted cube is used as the first verification code.

Images