Man-machine identification verification method and device and storage medium

Abstract

The embodiment of the invention provides a man-machine identification verification method and device and a storage medium, the method and device are applied to a public management platform, the public management platform is provided with a front-end interaction interface and a gallery, and the method comprises the following steps: in response to an identity verification operation of a user, triggering a first man-machine identification verification operation, obtaining a verification pattern corresponding to the first man-machine identification verification operation from the image library, displaying the verification pattern and a user interaction area in the front-end interaction interface, generating first user prompt information for drawing the verification pattern in the user interaction area, and sending the first user prompt information to the server; the drawing behavior data of the user for drawing the verification pattern in the user interaction area according to the first user prompt information is received, and the first verification result of the first man-machine identification verification operation is generated according to the drawing behavior data, so that man-machine identification is performed through the drawing behavior of the user to complete verification, the misjudgment rate of verification is reduced, and the verification efficiency is improved. And the verification security is improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing and behavior analysis, and in particular to a verification method, device and storage medium for human-machine identification. Background Art

[0002] CAPTCHA is a technology that automatically distinguishes whether a user is a human or a machine. It was first proposed by Louis von Ahn and others at Carnegie Mellon University in 2000 to prevent automated programs from abusing Internet resources, such as registering fake accounts and sending spam. With the development of the Internet, CAPTCHA technology has also evolved, from the initial simple character recognition CAPTCHA to the current image CAPTCHA and behavior CAPTCHA, in order to cope with increasingly complex automated attack technologies.

[0003] As artificial intelligence technology becomes more and more popular, it is increasingly difficult to defend against verification codes. Machine learning and deep learning technologies are used to train image recognition models to automatically identify and crack image verification codes. For example, image preprocessing technologies such as denoising and dedistortion can be used to restore the original characters in the verification code and improve recognition accuracy. Artificial intelligence can also be used to simulate human behaviors such as mouse movement and clicking. Summary of the invention

[0004] In view of the above problems, a human-machine identification verification method, device and storage medium are proposed to overcome the above problems or at least partially solve the above problems, including:

[0005] A human-machine identification verification method is applied to a public management platform, wherein the public management platform is provided with a front-end interactive interface and a gallery, and the method comprises:

[0006] In response to the user's identity verification operation, triggering a first human-machine identification verification operation;

[0007] Acquire a verification pattern corresponding to the first human-machine identification verification operation from the gallery;

[0008] In the front-end interactive interface, displaying the verification pattern and the user interaction area, and generating first user prompt information for drawing the verification pattern in the user interaction area;

[0009] receiving drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information;

[0010] A first verification result of the first human-machine identification verification operation is generated according to the drawing behavior data.

[0011] Optionally, the drawing behavior data includes any one or more of the following:

[0012] Starting point information, path information, speed information, pause information and drawing patterns.

[0013] Optionally, generating a first verification result of the first human-machine identification verification operation according to the drawing behavior data includes:

[0014] Verifying whether the verification pattern is similar to the drawing pattern in the drawing behavior data, and obtaining a first verification result;

[0015] A first verification result of the first human-machine identification verification operation is generated according to the first verification result.

[0016] Optionally, generating a first verification result of the first human-machine identification verification operation according to the first verification result includes:

[0017] When the first verification result is similar, performing human trajectory analysis on the drawing behavior data to obtain a first analysis result;

[0018] Analyzing the scale offset of the drawn pattern to obtain a second analysis result;

[0019] A first verification result of the first human-machine identification verification operation is generated according to the first analysis result and the second analysis result.

[0020] Optionally, generating a first verification result of the first human-machine identification verification operation according to the first verification result includes:

[0021] In the case where the first verification result is not similar, the first verification result is determined to be failed, and the first human-machine recognition verification operation is triggered again.

[0022] Optionally, it also includes:

[0023] When it is detected that the first human-machine identification verification operation is triggered multiple times or the first verification result is unrecognizable, triggering a second human-machine identification verification operation;

[0024] Generate second user prompt information for acquiring image data of the user's surrounding environment;

[0025] receiving surrounding environment image data photographed by the user in response to the second user prompt information, and determining target image data from the surrounding environment image data;

[0026] Generate, based on the target image data, an augmented reality interaction scene displayed on the front-end interaction interface, and prompt information for a third user interacting in the augmented reality interaction scene;

[0027] Receiving interaction operation data of the user in the augmented reality interaction scene in response to the third user prompt information;

[0028] A second verification result of the second human-machine identification verification operation is determined according to the interactive operation data.

[0029] Optionally, the augmented reality interaction scene is one of a game interaction scene and a mobile interaction scene;

[0030] The game interaction scene is an augmented reality game that interacts with the user;

[0031] The mobile interaction scene is an augmented reality scene that interacts with the user, and the augmented reality scene is generated according to surrounding environment image data corresponding to the target image data.

[0032] Optionally, determining a second verification result of the second human-machine identification verification operation according to the interactive operation data includes:

[0033] Scoring the interactive operation data to obtain an interactive operation score;

[0034] Verifying the interactive operation score by using a preset first threshold and a second threshold to obtain a second verification result;

[0035] According to the second verification result, a second verification result of the second human-machine identification verification operation is determined.

[0036] Optionally, the first threshold is greater than a second threshold, and determining a second verification result of the second human-machine identification verification operation according to the second verification result includes:

[0037] When the interactive operation score is greater than the first threshold, determining that the second verification result is passed;

[0038] If the interactive operation score is less than the second threshold, determining the second verification result as failure;

[0039] When the interaction operation score is less than the first threshold and greater than the second threshold, it is determined that the second verification result cannot be recognized, and the first human-machine recognition verification operation is triggered.

[0040] A verification device for human-machine identification is applied to a public management platform, wherein the public management platform is provided with a front-end interactive interface and a gallery, and the device comprises:

[0041] A verification operation triggering module, used to trigger a first human-machine recognition verification operation in response to a user's identity verification operation;

[0042] A verification pattern acquisition module, used to acquire the verification pattern corresponding to the first human-machine identification verification operation from the gallery;

[0043] A verification pattern display module, used to display the verification pattern and the user interaction area in the front-end interaction interface, and generate first user prompt information for drawing the verification pattern in the user interaction area;

[0044] A drawing behavior data receiving module, configured to receive drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information;

[0045] The verification result generating module is used to generate a first verification result of the first human-machine identification verification operation according to the drawing behavior data.

[0046] An electronic device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the human-machine identification verification method as described above when executed by the processor.

[0047] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the human-machine identification verification method as described above is implemented.

[0048] The embodiments of the present invention have the following advantages:

[0049] In an embodiment of the present invention, a first human-machine identification verification operation is triggered in response to the user's identity authentication operation, a verification pattern corresponding to the first human-machine identification verification operation is obtained from the gallery, the verification pattern and the user interaction area are displayed in the front-end interactive interface, a first user prompt information for drawing the verification pattern in the user interaction area is generated, and drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information is received. According to the drawing behavior data, a first verification result of the first human-machine identification verification operation is generated, and human-machine identification is realized through the user's drawing behavior to complete the verification, thereby reducing the misjudgment rate of the verification, improving the security of the verification, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0051] Figure 1It is a flowchart of the steps of a human-machine identification verification method provided by some embodiments of the present invention;

[0052] Figure 2 is a flowchart of a verification method for distinguishing between humans and machines provided by some embodiments of the present invention;

[0053] Figure 3 is a schematic diagram of the architecture of another human-machine identification verification system provided by some embodiments of the present invention;

[0054] Figure 4 It is a structural block diagram of a human-machine identification verification device provided by some embodiments of the present invention. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Reference Figure 1 , shows a flowchart of a method for verifying human-machine identification provided by some embodiments of the present invention. The method can be applied to a public management platform, and the public management platform can be provided with a front-end interactive interface and a gallery required by the method, and specifically can include the following steps:

[0057] Step 101, in response to a user's identity verification operation, trigger a first human-machine recognition verification operation.

[0058] On the public management platform, the user's identity authentication operation may be a human operation or a machine operation.

[0059] Therefore, when a user logs in or registers on the public management platform, he can trigger the first human-machine identification verification operation after entering his account number and password, so as to first verify the behavior category of this identity authentication operation, and verify whether this login or registration is a human operation or a machine operation. After the verification result is passed, the identity verification is performed. Specifically, the first human-machine identification verification operation can be a one-stroke verification, which is a type of verification code service.

[0060] Step 102: Acquire a verification pattern corresponding to the first human-machine identification verification operation from the gallery.

[0061] After the user triggers the one-stroke verification, the verification pattern corresponding to the first human-machine identification verification operation can be obtained from the gallery. Specifically, the verification pattern corresponding to this one-stroke verification can be obtained from the gallery of the public management platform, and the verification pattern can be a pattern that the user can complete with one stroke.

[0062] In practical applications, some pictures in the gallery can be obtained from pictures on the Internet and judged, and qualified pictures are saved in the database corresponding to the gallery.

[0063] In some embodiments of the present invention, the first human-machine identification verification operation includes a single mode and a multiple mode, and obtaining a verification pattern corresponding to the first human-machine identification verification operation from the gallery includes:

[0064] When the first human-machine identification verification is in a single-time mode, obtaining a verification pattern corresponding to the first human-machine identification verification operation from the gallery;

[0065] In the case where the first human-machine identification verification is in a multiple-time mode, a plurality of verification patterns corresponding to the first human-machine identification verification operation are obtained from the gallery.

[0066] There are two modes to choose from for one-stroke verification: single-shot mode and multiple-shot mode.

[0067] Specifically, the single-shot mode only requires one determination, so when the one-shot verification is in the single-shot mode, a verification pattern corresponding to the one-shot verification can be obtained from the gallery.

[0068] The multiple-time mode may require multiple determinations, so when the one-stroke verification is in multiple-time mode, multiple verification patterns corresponding to the one-stroke verification can be obtained from the gallery, but the maximum number of determinations can be 3. It should be noted that the mode selection method for one-stroke verification is not specifically limited in the present invention.

[0069] Step 103: display the verification pattern and the user interaction area in the front-end interaction interface, and generate first user prompt information for drawing the verification pattern in the user interaction area.

[0070] In the front-end interactive interface of the public management platform, a verification pattern and a user interaction area corresponding to the one-stroke verification are displayed, and a first user prompt information can be generated to prompt the user to draw a verification pattern corresponding to the one-stroke verification in the user interaction area.

[0071] Step 104 : receiving drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information.

[0072] During the drawing process of the user, the front end where the front end interaction interface is located can receive the drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information. Specifically, the front end can collect the drawing trajectory of the user drawing the verification pattern.

[0073] It should be noted that if the mode of one-stroke verification is a multiple-time mode, the front end can collect the drawing behavior data of the user when drawing each verification pattern in sequence.

[0074] In some embodiments of the present invention, the drawing behavior data includes any one or more of the following:

[0075] Starting point information, path information, speed information, pause information and drawing patterns.

[0076] In one-stroke verification, the drawing behavior data may include starting point information, path information, speed information, pause information, and drawing pattern, and may also include information such as the ratio and offset of the drawing pattern and the verification pattern.

[0077] Step 105: Generate a first verification result of the first human-machine identification verification operation according to the drawing behavior data.

[0078] After collecting the user's drawing behavior data, the drawing behavior data can be verified and analyzed to generate a first verification result of the first human-machine identification verification operation. Specifically, the first verification result can be one of pass, fail, and unrecognizable.

[0079] In some embodiments of the present invention, generating a first verification result of the first human-machine identification verification operation according to the drawing behavior data includes:

[0080] Sub-step 11, verifying whether the verification pattern is similar to the drawing pattern in the drawing behavior data, and obtaining a first verification result.

[0081] A verification operation may be performed on the drawing pattern in the drawing behavior data to verify whether the verification pattern and the drawing pattern are similar, and obtain a first verification result. Specifically, the drawing pattern may be recognized by OCR (Optical Character Recognition) to verify whether the verification pattern and the drawing pattern are similar. The first verification result may be similar or dissimilar. Similarity may be considered as the drawing pattern and the verification pattern being relatively consistent, and dissimilarity may be considered as a drawing error.

[0082] Sub-step 12: generating a first verification result of the first human-machine identification verification operation according to the first verification result.

[0083] After the first verification result is obtained, a first verification result of the first human-machine identification verification operation may be generated according to the first verification result.

[0084] In one embodiment of the present invention, generating a first verification result of the first human-machine identification verification operation according to the first verification result includes:

[0085] Sub-step 21 : when the first verification result is similar, performing human trajectory analysis on the drawing behavior data to obtain a first analysis result.

[0086] When the first verification result is similar, that is, it is considered that the drawing pattern and the verification pattern are relatively consistent, the drawing trajectory in the drawing behavior data can be further analyzed through the trained analysis model to analyze whether the one-stroke pattern (that is, the drawing pattern) is a human operation behavior. The drawing trajectory can include starting point, path, speed, pause and other information to obtain a first analysis result.

[0087] It should be noted that this step can be considered as analyzing whether the drawing trajectory is drawn by humans or by machines.

[0088] Sub-step 22, analyzing the scale offset of the drawn pattern to obtain a second analysis result.

[0089] While analyzing the drawing trajectory, the scale offset of the drawing pattern in the drawing behavior data can also be analyzed to obtain a second analysis result. Specifically, the user's drawing pattern can be analyzed by CV (Computer Vision) to analyze the offset scale of the drawing pattern to obtain a second analysis result.

[0090] Sub-step 23: generating a first verification result of the first human-machine identification verification operation according to the first analysis result and the second analysis result.

[0091] After waiting for the first analysis result and the second analysis result, a first verification result of the first human-machine identification verification operation can be generated according to the first analysis result and the second analysis result. The result of the first verification may be one of failure, passing or unrecognizable.

[0092] In some embodiments of the present invention, generating a first verification result of the first human-machine identification verification operation according to the first verification result includes:

[0093] In the case where the first verification result is not similar, the first verification result is determined to be failed, and the first human-machine recognition verification operation is triggered again.

[0094] When the first verification result is not similar, that is, the drawn pattern and the verification pattern are inconsistent, it can be directly determined that the drawing pattern is drawn incorrectly, so that the first verification result can be determined as failed, and the first human-machine recognition verification operation is ended, and a new first human-machine recognition verification operation is triggered again.

[0095] In some embodiments of the present invention, the method further comprises:

[0096] Sub-step 31, triggering a second human-machine identification verification operation when it is detected that the first human-machine identification verification operation is triggered multiple times or the first verification result is unrecognizable.

[0097] During the verification process, if the first verification result is unrecognizable, that is, it is unclear whether it is a human operation or a machine operation, or if the first human-machine recognition verification operation is triggered multiple times due to an error in drawing a pattern, that is, the same IP (Internet Protocol) address triggers the verification code service multiple times, a second human-machine recognition verification operation can be triggered. The second human-machine recognition verification operation can be an AR (Augmented Reality) object movement scheme verification.

[0098] Sub-step 32: generating second user prompt information for acquiring the image data of the user's surrounding environment.

[0099] After the second human-machine identification verification operation is triggered, the user may be prompted through a second user prompt message to scan the surrounding environment through the camera of the mobile device where the public management platform is located.

[0100] Sub-step 33: receiving surrounding environment image data photographed by the user in response to the second user prompt information, and determining target image data from the surrounding environment image data.

[0101] The server (i.e., the backend) corresponding to the public management platform can receive the surrounding environment (i.e., the surrounding environment image data) photographed by the user in response to the second user prompt information, that is, the user uploads the surrounding environment image data to the server, and can identify the space through the AR application and select an area suitable for display, that is, determine the target image data.

[0102] Sub-step 34, generating an augmented reality interaction scene displayed on the front-end interaction interface and third user prompt information for interacting in the augmented reality interaction scene based on the target image data.

[0103] The backend can generate an augmented reality interaction scene, i.e., an AR interaction scene, and third-party user prompt information on how to operate in the augmented reality interaction scene based on the target image data, and display them on the front-end interaction interface.

[0104] Sub-step 35: receiving the user's interactive operation data in the augmented reality interaction scene in response to the third user prompt information.

[0105] The user performs operations in the augmented reality interaction scene, and the backend can receive the user's interactive operation data in the augmented reality interaction scene in response to the third user prompt information.

[0106] Sub-step 36, determining a second verification result of the second human-machine identification verification operation according to the interactive operation data.

[0107] After acquiring the interactive operation data, the backend can analyze and judge the interactive operation data according to the preset specified rules, so as to determine the second verification result of the second human-machine identification verification operation. The second verification result can be one of pass, fail and unrecognizable.

[0108] In some embodiments of the present invention, the augmented reality interaction scene is one of a game interaction scene and a mobile interaction scene;

[0109] The game interaction scene is an augmented reality game that interacts with the user;

[0110] The mobile interaction scene is an augmented reality scene that interacts with the user, and the augmented reality scene is generated according to surrounding environment image data corresponding to the target image data.

[0111] The augmented reality interaction scene, that is, the AR interaction scene can be one of a game interaction scene and a mobile interaction scene, that is, an interactive scene and a mobile scene.

[0112] If the determined AR application recognizes the space and selects an area suitable for display, i.e., the target image data, and the corresponding content is too monotonous, the backend provides an interactive scene (i.e., a game interaction scene), which can be an augmented reality game (i.e., an AR game) that interacts with the user.

[0113] The AR game interaction scene can have two games, one is a goal-scoring game, which generates a goal frame and allows users to kick (push) the ball into it, and the other is a tennis game, which requires users to hit the flying tennis ball back.

[0114] If the content corresponding to the target image data is relatively complex, the backend generates an AR real scene based on the surrounding environment image data corresponding to the target image data, identifies the objects therein, and generates a mobile scene (i.e., a mobile interactive scene) that can interact with the user. The user can interact by moving objects in the mobile scene.

[0115] For example, according to the third user prompt information, the user can move the cup in the mobile interaction scene from one place to another to complete the interaction.

[0116] In some embodiments of the present invention, determining a second verification result of the second human-machine identification verification operation according to the interactive operation data includes:

[0117] Sub-step 41 is used to score the interactive operation data to obtain an interactive operation score.

[0118] The backend can analyze and judge the interactive operation data according to the preset specified rules to score the interactive operation data and obtain the score of the interactive operation data of the user's augmented reality interactive scene, that is, the interactive operation score. Specifically, the user's trajectory, speed, pause and other behavioral characteristics during the movement of the AR object can be analyzed and then scored.

[0119] Sub-step 42 is used to verify the interactive operation score using a preset first threshold and a second threshold to obtain a second verification result.

[0120] After obtaining the interactive operation score, the interactive operation score can be verified by a preset first threshold and a second threshold to obtain a second verification result. The first threshold can be a human behavior threshold, and the second threshold can be a machine behavior threshold.

[0121] Sub-step 43 is used to determine a second verification result of the second human-machine identification verification operation according to the second verification result.

[0122] After the second verification result is obtained, a second verification result of the second human-machine identification verification operation may be determined based on the second verification result.

[0123] In some embodiments of the present invention, the first threshold is greater than the second threshold, that is, the human behavior threshold is greater than the machine behavior threshold, and determining the second verification result of the second human-machine identification verification operation according to the second verification result includes:

[0124] When the interactive operation score is greater than the first threshold, the second verification result is determined to be passed.

[0125] That is, when the interactive operation score is greater than the human behavior threshold, the second verification result is determined to be passed, that is, it is determined that the interactive operation data is obtained through human operation behavior.

[0126] When the interactive operation score is less than the second threshold, the second verification result is determined to be failed.

[0127] That is, when the interactive operation score is less than the machine behavior threshold, the second verification result is determined to be failed, that is, it is determined that the interactive operation data is obtained through machine operation behavior.

[0128] When the interaction operation score is less than the first threshold and greater than the second threshold, it is determined that the second verification result cannot be recognized, and the first human-machine recognition verification operation is triggered.

[0129] That is, when the interactive operation score is less than the human behavior threshold and greater than the machine behavior threshold, the second verification result is determined to be unrecognizable, that is, further recognition is required, thus triggering an additional first human-machine recognition verification operation.

[0130] The present invention can more accurately identify and distinguish the operation behaviors of humans and machines, reduce the misjudgment rate, and increase the difficulty for attackers to simulate human operations by deeply analyzing the user's operation behaviors (i.e., drawing behavior data or interactive operation data), such as the dragging trajectory in AR interaction and the path drawn in one-stroke verification. Behavior analysis also increases the difficulty for attackers to simulate human operations.

[0131] In summary, the present invention combines AR object movement verification with one-stroke verification to provide a multi-level verification mechanism. One-stroke verification is used for routine verification, while AR object movement verification is enabled in specific circumstances (such as the same IP triggering the verification code multiple times in a short period of time) to further improve security. Moreover, the two verification methods can be intelligently switched according to user behavior and verification history to balance security and user experience. By combining complex tile movement and one-stroke verification, multi-level security protection is achieved, which greatly improves the ability to resist automated script attacks, intelligently switches verification methods, and provides corresponding protection measures for different threat scenarios, thereby improving overall security while avoiding excessive operational burden on users. In addition, attackers need to crack multiple verification methods at the same time, which significantly increases the difficulty of cracking.

[0132] Moreover, by giving priority to one-stroke verification, the reliance on AR object movement verification, which requires higher computing resources, is reduced, effectively reducing resource consumption and improving operating efficiency. Lightweight model design and resource optimization enable support for higher concurrency, adapt to large-scale user access scenarios, and ensure stability and response speed.

[0133] In some embodiments of the present invention, before executing the first human-machine recognition verification operation shown, a judgment can be made based on the account entered by the user. For accounts that are always identified as human, when logging in a new time, a verification image that has not been trained by an analysis model can be used for a one-stroke verification, allowing the user to draw.

[0134] It should be noted that some of the images in the gallery are used for training the aforementioned analysis model, and some of the images have not been trained with the analysis model. These images that have not been trained with the analysis model may be newly acquired from the Internet.

[0135] For such accounts that are always considered to be human, when they log in again, they can use a verification image that has not been trained by the analysis model for one-stroke verification, let the user draw, and collect and store the corresponding drawing behavior data, and select 70% of them for data training of the analysis model. Similarly, for accounts that are always considered to be machines, they are also drawn using untrained data to obtain the machine's drawing behavior data, and 70% of them are also selected for data training of the analysis model.

[0136] This not only prevents attackers (i.e. machine users) from relying on pre-trained analysis models to crack the system, significantly improving defense effectiveness, but also allows the verification difficulty to be adaptively adjusted based on user behavior and performance, ensuring that verification is user-friendly and easy to pass for real users, while increasing the difficulty of verification for suspicious users, thereby enhancing defense effectiveness.

[0137] In addition, after the collected drawing behavior data reaches a certain stage, the data training service is started. The drawing behavior data can be preprocessed and reprocessed first, and then trained through the adversarial network.

[0138] This enables continuous optimization of methods and model updates through real-time mapping of behavioral data collection and online learning to adapt to new attack methods, maintain long-term verification effects and high recognition rates, and dynamic model updates to quickly respond to emerging automated attack technologies, making it difficult for automated attack tools to effectively simulate real user operations.

[0139] As an example, in actual applications, when a user posts a comment on a public management platform, a one-stroke verification can be performed. And if the same IP posts multiple comments in a short period of time, it can automatically switch to AR object movement verification.

[0140] As an example, when a user calls AI resources on a public management platform, a stroke verification is performed, and when the user calls too many resources, an AR object movement verification is performed.

[0141] In an embodiment of the present invention, a first human-machine identification verification operation is triggered in response to the user's identity authentication operation, a verification pattern corresponding to the first human-machine identification verification operation is obtained from the gallery, the verification pattern and the user interaction area are displayed in the front-end interactive interface, a first user prompt information for drawing the verification pattern in the user interaction area is generated, and drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information is received. According to the drawing behavior data, a first verification result of the first human-machine identification verification operation is generated, and human-machine identification is realized through the user's drawing behavior to complete the verification, thereby reducing the misjudgment rate of the verification, improving the security of the verification, and improving the user experience.

[0142] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0143] Reference Figure 2 , shows a schematic diagram of the structure of a human-machine identification verification device provided by some embodiments of the present invention, in order to enable those skilled in the art to better understand the above steps, the following is combined with the attached Figure 2 The embodiments of the present invention are described exemplarily, but it should be understood that the embodiments of the present invention are not limited thereto.

[0144] 1. Call the verification code service (i.e. trigger the first human-machine recognition verification operation);

[0145] 2. Start one-stroke verification (i.e. the first human-machine recognition verification operation);

[0146] 3. After obtaining the user's drawing behavior data, first perform pattern detection (i.e., determine whether it is similar to the verification pattern). If the drawing is wrong, that is, the first verification result fails, then return to step 2 (i.e., trigger the first human-machine recognition verification operation again);

[0147] 4. If the drawing is correct, that is, similar to the verification pattern, human detection is performed (i.e., determining whether the drawing behavior data is human operation behavior or machine operation behavior);

[0148] 5. Perform human detection (i.e., analyze the drawing behavior data to obtain a first detection result). If it is a human operation behavior, the verification code is allowed to pass, i.e., the first verification result is passed, and then the process ends; if it is a machine operation behavior, the verification code is prohibited to pass, i.e., the first verification result is failed, and then the process ends; if the detection result is uncertain, i.e., the first verification result is unrecognizable, then execute step 6;

[0149] 6. Perform AR object movement verification (i.e. trigger the second human-machine identification verification operation and perform the second human-machine identification verification operation);

[0150] 7. Analyze and detect user behavior (i.e., analyze based on interactive operation data);

[0151] 8. Perform human detection (i.e., obtain a first detection result based on the results of interactive operation data analysis). If it is a human operation behavior, the verification code is allowed to pass, i.e., the second verification result is passed, and then the process ends; if it is a machine operation behavior, the verification code is prohibited to pass, i.e., the second verification result is failed, and then the process ends.

[0152] In practical applications, the method of the present invention may be a verification system applied to a public management platform. The schematic diagram of the verification system architecture is as follows: Figure 3 As shown, the verification system may specifically include:

[0153] 1. Front-end service

[0154] It includes a verification code component, namely a first human-machine identification verification operation and a second human-machine identification verification operation.

[0155] A new training data acquisition script is a script for acquiring drawing behavior data when the first human-machine recognition verification operation uses an image that has not been trained with an analysis model as a verification pattern.

[0156] 2. Backend services

[0157] Tile motion detection script, that is, the interactive operation data analysis script used in AR object motion verification.

[0158] The training data is stored, that is, when the first human-machine recognition verification operation uses an image that has not been trained with an analysis model as a verification pattern, the drawing behavior data is stored.

[0159] IP address detection can be used to detect that the same IP address triggers the first human-machine identification verification operation multiple times.

[0160] One-stroke transfer means transferring the drawing behavior data to the analysis model for analysis.

[0161] The verification code is switched, i.e., the second human-machine identification verification operation is triggered, and the second human-machine identification verification operation is performed.

[0162] 3. Model layer

[0163] Data standardization is to standardize the aforementioned stored drawing behavior data or the real-time drawing behavior data to be analyzed, that is, preprocessing.

[0164] One-stroke recognition, including image similarity detection, trajectory analysis detection, and scale offset detection.

[0165] Data content expansion, that is, after the stored or collected drawing behavior data reaches a certain stage, the data training service is started, including image analysis, user data analysis, and GAN (Generative Adversarial Network) adversarial generation.

[0166] 4. Data Layer

[0167] MySQL (My Structured Query Language, an open source relational database management system) and Redis (Remote Dictionary Server, an open source in-memory data storage system) can be considered as databases for storing data, including image galleries.

[0168] Reference Figure 4 , shows a schematic diagram of the structure of a human-machine identification verification device provided by some embodiments of the present invention, the device can be applied to a public management platform, the public management platform can be provided with a front-end interactive interface and a gallery, and specifically can include the following modules:

[0169] The verification operation triggering module 401 is used to trigger a first human-machine recognition verification operation in response to a user's identity verification operation;

[0170] A verification pattern acquisition module 402, configured to acquire a verification pattern corresponding to the first human-machine identification verification operation from the gallery;

[0171] A verification pattern display module 403, configured to display the verification pattern and the user interaction area in the front-end interaction interface, and generate first user prompt information for drawing the verification pattern in the user interaction area;

[0172] A drawing behavior data receiving module 404 is used to receive drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information;

[0173] The verification result generating module 405 is used to generate a first verification result of the first human-machine identification verification operation according to the drawing behavior data.

[0174] In one embodiment of the present invention, the drawing behavior data includes any one or more of the following:

[0175] Starting point information, path information, speed information, pause information and drawing patterns.

[0176] In one embodiment of the present invention, the verification result generation module 405 includes:

[0177] A first verification result acquisition module is used to verify whether the verification pattern is similar to the drawing pattern in the drawing behavior data, and obtain a first verification result;

[0178] The first verification result generating submodule is used to generate a first verification result of the first human-machine identification verification operation according to the first verification result.

[0179] In one embodiment of the present invention, the first verification result generating submodule includes:

[0180] A first analysis result obtaining unit, configured to perform human trajectory analysis on the drawing behavior data to obtain a first analysis result when the first verification result is similar;

[0181] A second analysis result obtaining unit, configured to analyze the scale offset of the drawing pattern to obtain a second analysis result;

[0182] The first verification result obtaining unit is used to generate a first verification result of the first human-machine identification verification operation according to the first analysis result and the second analysis result.

[0183] In one embodiment of the present invention, generating a first verification result of the first human-machine identification verification operation according to the first verification result includes:

[0184] The first human-machine identification verification operation triggering unit is used to determine the first verification result as failed when the first verification result is not similar, and to trigger the first human-machine identification verification operation again.

[0185] In one embodiment of the present invention, it further includes:

[0186] A second human-machine identification and verification operation module is used to trigger a second human-machine identification and verification operation when it is detected that the first human-machine identification and verification operation is triggered multiple times or the first verification result is unrecognizable;

[0187] A second user prompt information generating module, used to generate second user prompt information for acquiring the image data of the user's surrounding environment;

[0188] a target image data determining module, configured to receive the surrounding environment image data photographed by the user in response to the second user prompt information, and determine the target image data from the surrounding environment image data;

[0189] An augmented reality interaction scene generation module, used to generate an augmented reality interaction scene displayed on the front-end interaction interface and third user prompt information for interacting in the augmented reality interaction scene according to the target image data;

[0190] An interactive operation data receiving module, used to receive the interactive operation data of the user in the augmented reality interactive scene in response to the third user prompt information;

[0191] The second verification result determination module is used to determine a second verification result of the second human-machine identification verification operation according to the interactive operation data.

[0192] In one embodiment of the present invention, the augmented reality interaction scene is one of a game interaction scene and a mobile interaction scene;

[0193] The game interaction scene is an augmented reality game that interacts with the user;

[0194] The mobile interaction scene is an augmented reality scene that interacts with the user, and the augmented reality scene is generated according to surrounding environment image data corresponding to the target image data.

[0195] In one embodiment of the present invention, the second verification result determination module includes:

[0196] A scoring submodule, used for scoring the interactive operation data to obtain an interactive operation score;

[0197] A second verification result obtaining submodule, used to verify the interactive operation score by using a preset first threshold and a second threshold to obtain a second verification result;

[0198] The second verification result determination submodule is used to determine the second verification result of the second human-machine identification verification operation according to the second verification result.

[0199] In one embodiment of the present invention, the first threshold is greater than the second threshold, and the second verification result determination submodule includes:

[0200] A passing unit, configured to determine that the second verification result is passed if the interaction operation score is greater than the first threshold;

[0201] A failure unit, configured to determine that the second verification result is a failure if the interaction operation score is less than the second threshold;

[0202] An unrecognizable unit is used to determine that the second verification result is unrecognizable and trigger the first human-machine recognition verification operation when the interaction operation score is less than the first threshold and greater than the second threshold.

[0203] In an embodiment of the present invention, a first human-machine identification verification operation is triggered in response to the user's identity authentication operation, a verification pattern corresponding to the first human-machine identification verification operation is obtained from the gallery, the verification pattern and the user interaction area are displayed in the front-end interaction interface, a first user prompt information for drawing the verification pattern in the user interaction area is generated, and drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information is received. According to the drawing behavior data, a first verification result of the first human-machine identification verification operation is generated, and human-machine identification is realized through the user's drawing behavior to complete the verification, thereby reducing the misjudgment rate of the verification, improving the security of the verification, and improving the user experience.

[0204] Some embodiments of the present invention further provide an electronic device, comprising a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the above method is implemented when the computer program is executed by the processor.

[0205] Some embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, and the computer program implements the above method when executed by a processor.

[0206] Some embodiments of the present invention further provide a computer program product, including a computer program, which implements the above method when executed by a processor.

[0207] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0208] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0209] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0210] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0211] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0212] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0213] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0214] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0215] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including 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 terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the above elements.

[0216] The above is a detailed introduction to the verification method, device and storage medium for human-machine identification. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A human-machine identification verification method, characterized in that: Applied to a public management platform, the public management platform is provided with a front-end interactive interface and a gallery, the method comprises: In response to the user's identity verification operation, triggering a first human-machine identification verification operation; Acquire a verification pattern corresponding to the first human-machine identification verification operation from the gallery; In the front-end interactive interface, displaying the verification pattern and the user interaction area, and generating first user prompt information for drawing the verification pattern in the user interaction area; receiving drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information; A first verification result of the first human-machine identification verification operation is generated according to the drawing behavior data.

2. The method according to claim 1, characterized in that The drawing behavior data includes any one or more of the following: Starting point information, path information, speed information, pause information and drawing patterns.

3. The method according to claim 2, characterized in that The step of generating a first verification result of the first human-machine identification verification operation according to the drawing behavior data includes: Verifying whether the verification pattern is similar to the drawing pattern in the drawing behavior data, and obtaining a first verification result; A first verification result of the first human-machine identification verification operation is generated according to the first verification result.

4. The method according to claim 3, characterized in that The step of generating a first verification result of the first human-machine identification verification operation according to the first verification result includes: When the first verification result is similar, performing human trajectory analysis on the drawing behavior data to obtain a first analysis result; Analyzing the scale offset of the drawn pattern to obtain a second analysis result; A first verification result of the first human-machine identification verification operation is generated according to the first analysis result and the second analysis result.

5. The method according to claim 3, characterized in that: The step of generating a first verification result of the first human-machine identification verification operation according to the first verification result includes: In the case where the first verification result is not similar, the first verification result is determined to be failed, and the first human-machine recognition verification operation is triggered again.

6. The method according to claim 5, characterized in that Also includes: When it is detected that the first human-machine identification verification operation is triggered multiple times or the first verification result is unrecognizable, triggering a second human-machine identification verification operation; Generate second user prompt information for acquiring image data of the user's surrounding environment; receiving surrounding environment image data photographed by the user in response to the second user prompt information, and determining target image data from the surrounding environment image data; Generate, based on the target image data, an augmented reality interaction scene displayed on the front-end interaction interface, and prompt information for a third user interacting in the augmented reality interaction scene; Receiving interaction operation data of the user in the augmented reality interaction scene in response to the third user prompt information; A second verification result of the second human-machine identification verification operation is determined according to the interactive operation data.

7. The method according to claim 6, characterized in that The augmented reality interaction scene is one of a game interaction scene and a mobile interaction scene; The game interaction scene is an augmented reality game that interacts with the user; The mobile interaction scene is an augmented reality scene that interacts with the user, and the augmented reality scene is generated according to surrounding environment image data corresponding to the target image data.

8. The method according to claim 6, characterized in that The determining, according to the interactive operation data, a second verification result of the second human-machine identification verification operation includes: Scoring the interactive operation data to obtain an interactive operation score; Verifying the interactive operation score by using a preset first threshold and a second threshold to obtain a second verification result; According to the second verification result, a second verification result of the second human-machine identification verification operation is determined.

9. The method according to claim 8, characterized in that The first threshold is greater than the second threshold, and determining the second verification result of the second human-machine identification verification operation according to the second verification result includes: When the interactive operation score is greater than the first threshold, determining that the second verification result is passed; If the interactive operation score is less than the second threshold, determining the second verification result as failure; When the interaction operation score is less than the first threshold and greater than the second threshold, it is determined that the second verification result cannot be recognized, and the first human-machine recognition verification operation is triggered.

10. A verification device for human-machine identification, characterized in that: Applied to a public management platform, the public management platform includes a front-end interactive interface and a gallery, and the device includes: A verification operation triggering module, used to trigger a first human-machine recognition verification operation in response to a user's identity verification operation; A verification pattern acquisition module, used to acquire the verification pattern corresponding to the first human-machine identification verification operation from the gallery; A verification pattern display module, used to display the verification pattern and the user interaction area in the front-end interaction interface, and generate first user prompt information for drawing the verification pattern in the user interaction area; A drawing behavior data receiving module, configured to receive drawing behavior data of the user drawing the verification pattern in the user interaction area in response to the first user prompt information; The verification result generating module is used to generate a first verification result of the first human-machine identification verification operation according to the drawing behavior data.

11. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the human-machine identification verification method according to any one of claims 1 to 9 is implemented.

12. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the human-machine identification verification method according to any one of claims 1 to 9 is implemented.

Images