Password setting method, password unlocking method, electronic device and storage medium

Abstract

Provided in the embodiments of the present disclosure are a password setting method, a password unlocking method, an electronic device and a storage medium. The method comprises: acquiring input first password information; generating one or more associated password images on the basis of the first password information; receiving a selection operation for the one or more associated password images; and extracting features of a selected target password image and storing the features.

Description

Password setting method, unlocking method, electronic device and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202311192078.3 filed with the China Patent Office on September 14, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to, but is not limited to, the field of cryptography. Background Art

[0004] The industry already has relevant cryptographic technologies, such as digital verification, face verification, fingerprint verification, etc.

[0005] The industry has also conducted research on dynamic passwords. For example, a password is saved in a preset terminal (such as a token, U-shield, etc.). The password can change randomly to achieve a dynamic password to enhance confidentiality.

[0006] Summary of the Invention

[0007] Embodiments of the present disclosure provide a password setting method, an unlocking method, an electronic device, and a storage medium.

[0008] In a first aspect, an embodiment of the present disclosure provides a password setting method, which may include: obtaining input first password information; generating one or more associated password images based on the first password information; receiving a selection operation for the one or more associated password images; and extracting features of the selected target password image for saving.

[0009] In a second aspect, an embodiment of the present disclosure provides a password unlocking method, which may include: providing an unlocking interface; the unlocking interface includes one or more unlocking methods; obtaining an unlocking image according to the selected target unlocking method; detecting whether the unlocking image matches a pre-stored target password image; the target password image is one or more associated password images generated based on a preset first password information; unlocking or returning an unlocking failure message based on the detection result.

[0010] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: one or more processors; a memory on which one or more programs are stored, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the password setting method and / or the password unlocking method; and one or more input / output I / O interfaces connected between the processor and the memory, and configured to implement information interaction between the processor and the memory.

[0011] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the password setting method and / or password unlocking method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In the accompanying drawings of the embodiments of the present disclosure:

[0013] FIG1 is a flow chart of a password setting method provided by an embodiment of the present disclosure;

[0014] Figure 2 is a schematic diagram of the diffusion model principle;

[0015] FIG3 is a flow chart of a password unlocking method provided by an embodiment of the present disclosure;

[0016] FIG4 is a flow chart of a password setting method according to an embodiment of the present disclosure;

[0017] FIG5 is a flow chart of an embodiment of a password unlocking method provided by an embodiment of the present disclosure;

[0018] FIG6 is a block diagram of an electronic device according to an embodiment of the present disclosure;

[0019] FIG7 is a block diagram of the composition of a computer-readable storage medium provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] To enable those skilled in the art to better understand the technical solutions of the present disclosure, the password setting method, unlocking method, electronic device, and storage medium provided by the embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0021] The present disclosure will be described more fully hereinafter with reference to the accompanying drawings, but the illustrated embodiments may be embodied in different forms, and the present disclosure should not be construed as limited to the embodiments set forth below. Rather, these embodiments are provided so that the present disclosure will be thorough and complete and will fully understand the scope of the present disclosure to those skilled in the art.

[0022] The accompanying drawings of the embodiments of the present disclosure are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the detailed embodiments, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. The above and other features and advantages will become more apparent to those skilled in the art by describing the detailed embodiments with reference to the accompanying drawings.

[0023] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0024] The terms used in this disclosure are only used to describe specific embodiments and are not intended to limit the disclosure. As used in this disclosure, the term "and / or" includes any and all combinations of one or more related enumerated items. As used in this disclosure, the singular forms "a" and "the" are also intended to include plural forms, unless the context clearly indicates otherwise. As used in this disclosure, the terms "comprising" and "made of" specify the presence of the features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof.

[0025] Unless otherwise defined, all terms (including technical and scientific terms) used in this disclosure have the same meanings as those commonly understood by those skilled in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly defined in this disclosure.

[0026] The industry already has relevant password technologies, such as digital verification, facial recognition, and fingerprint verification. However, digital verification methods are prone to users forgetting passwords, especially long and complex ones. Facial and fingerprint verification methods are also prone to being unlocked by similar faces or fingerprints, making them less secure.

[0027] The industry has also conducted research on dynamic passwords. For example, a password is saved in a preset terminal (such as a token, U shield, etc.), and the password changes periodically. However, the terminal usually needs to be purchased, has a time limit, and generally needs to be carried around, which is inconvenient to use.

[0028] The disclosed embodiment proposes a new password setting and unlocking solution, which can generate a password image (which can include but is not limited to images and videos) through the password information entered by the user (for example, which can include but is not limited to text information, audio information, operation information, terminal status information, etc.). Since users may have their own styles and preferences when setting image passwords, and even include commonly used code words, the disclosed embodiment visualizes these styles, preferences and code words of users, which can further deepen the user's memory.

[0029] In addition, the user inputs diversified and personalized one-dimensional information, which is different from the password composed of characters (such as numbers, letters, special symbols, etc.). The meaning expressed by audio information and text information is ever-changing. The password image is just the concretization and stylization of these one-dimensional information. Different input information will obtain different pictures, so the security is not weaker than some existing character passwords.

[0030] Compared to related technologies, the disclosed embodiments utilize images as passwords, ensuring security while being faster, more convenient, more efficient, more diverse, and more scenario-specific (it can be images of any scene). Furthermore, it's easier to remember, preventing passwords from being forgotten. As an exploration of AIGC (AI Generated Content) applications, all models used in the disclosed embodiments are pre-trained models. Converting audio / text information to images will become a key research and application focus in the field of machine vision across various industries.

[0031] The password setting method and password unlocking method of the embodiments of the present disclosure can be executed by any electronic device that requires encryption and unlocking, such as a terminal device or a server. The terminal device may include, but is not limited to, an in-vehicle device, a user equipment (UE), a mobile device, a computing device, a wearable device, and the like, including, but not limited to, a cellular phone, a cordless phone, a personal digital assistant (PDA), a portable computer, and the like. The password setting method and password unlocking method can be implemented by a processor calling computer-readable program instructions stored in a memory, or can be implemented by a server.

[0032] The following is a detailed introduction to the embodiments of the present disclosure.

[0033] The present disclosure provides a password setting method, as shown in FIG1 , which may include steps S11 to S14:

[0034] S11, obtaining the input first password information;

[0035] S12. generating one or more associated password images according to the first password information;

[0036] S13. Receive a selection operation for one or more associated password images;

[0037] S14. Extract the features of the selected target password image and save it.

[0038] In an embodiment of the present disclosure, obtaining the input first password information may include: providing at least one password setting interaction method; obtaining the first password information according to a target password setting interaction method selected from the at least one password setting interaction method; and / or providing at least one application scenario; determining a target application scenario selected from the at least one application scenario; and providing a corresponding password setting interaction method according to the target application scenario, so as to obtain the first password information through the provided password setting interaction method.

[0039] In an embodiment of the present disclosure, when a user needs to generate a password, a preset password setting button can be triggered. When the terminal detects that the password setting button is triggered, it can provide one or more password setting interaction methods, for example, including but not limited to providing a text input interface, turning on an audio input device, turning on an operation detection device (for example, including but not limited to a gesture detection device), turning on a terminal status detection device, etc., wherein, when one password setting interaction method is provided, the user can be prompted by voice or text to enter the first password information based on the provided password setting interaction method (for example, please enter the password content through text / voice); when multiple password setting interaction methods are provided, the user can be reminded to select a target password setting interaction method from the multiple password setting interaction methods, and enter the first password information based on the selected target password setting interaction method.

[0040] In the embodiment of the present disclosure, this embodiment provides users with multiple options, improves user experience, and increases the flexibility of password setting.

[0041] In an embodiment of the present disclosure, when a user needs to generate a password, a preset password setting button can be triggered. Upon detecting that the password setting button has been triggered, the terminal may provide a variety of application scenarios for the user to select. For example, the application scenarios may include, but are not limited to, home scenarios, work scenarios, private scenarios, public scenarios, navigation scenarios, and driving scenarios. The user can select the corresponding application scenario based on the scenario they are in, and the terminal will provide a corresponding password setting interaction method based on the selected application scenario. For example, in a private scenario, any password setting interaction method that can collect the first password information may be provided, such as a text input interface, activating an audio input device, or activating a gesture collection device. In a public scenario, to prevent password information leakage, only a text input interface and activating a gesture collection device may be provided. In a driving scenario, considering that the user may not be able to enter text, an audio input device or a gesture detection device may be activated. Based on the different password setting interaction methods provided for different application scenarios, the user can further select a password setting interaction method, either directly entering the first password information according to one of the provided password setting interaction methods, or selecting one of the provided password setting interaction methods to enter the first password information.

[0042] In an embodiment of the present disclosure, if the user does not manually select an application scenario within a preset time period (e.g., 5 seconds) when providing multiple application scenarios, it can be determined that the user is inconvenient to manually select an application scenario, and an audio input device or a gesture detection device can be automatically activated for the user to enable the user to enter the first password information through audio or gesture. Before the user enters the password information through gesture, the terminal can be pre-trained so that the terminal recognizes the semantics corresponding to each gesture.

[0043] In the embodiment of the present disclosure, the embodiment scheme collects the first password information according to different application scenarios, making the interaction between the terminal and the user more humane and further improving the user experience.

[0044] In an embodiment of the present disclosure, a user can input text information and / or audio information that the user is familiar with, interested in, or easy to remember in a provided password setting interaction mode (for example, a text input interface, an audio input device, or both). For example, the first password information of "a girl under a cherry blossom tree in the second dimension" in text or audio form can be input, and the embodiment of the present disclosure can obtain the first password information and generate one or more password images that match the content of the password information based on the first password information, for example, a girl with a second dimension style standing under a cherry blossom tree; for another example, the first password information of "a cute puppy with a mecha style" in text or audio form can be input, and the embodiment of the present disclosure can obtain the first password information and generate one or more password images that match the content of the first password information based on the first password information, for example, a mechanical dog with a metallic texture.

[0045] In the disclosed embodiment, when multiple password images are generated, they are associated with each other. The images may differ in color, pose, clothing, and other aspects. The user can select at least one image as a target password image based on their needs or preferences. If the user is unable to select the image they need or prefer from the generated password images, they can regenerate multiple different password images and reselect until a satisfactory target password image is obtained.

[0046] In the embodiment of the present disclosure, the user can use different first password information (audio information, text information, operation information, terminal status information) as input carriers anytime and anywhere to generate different password images, which reflects the convenience, diversification, and multi-scenario advantages of the embodiment of the present disclosure, and the embodiment is more humane, making the password generation process more entertaining and enhancing the user experience. Compared with the password composed of characters, the password image can deepen the user's memory and impression of the password and effectively extend the user's password memory time. In addition, since the first password information can be ever-changing, the password image generated according to the first password information is also ever-changing and will not be easily cracked. Therefore, the password scheme of the embodiment of the present disclosure can ensure security, and the password of the embodiment of the present disclosure has no time limit, can be used all the time or changed at any time according to user needs, and does not require a carrier, avoiding the inconvenience caused by the need for users to carry it with them.

[0047] In the embodiment of the present disclosure, the password image may include but is not limited to: a password picture and / or a password video.

[0048] In the embodiment of the present disclosure, the password image may include but is not limited to: color image, black and white image, one-dimensional image, multi-dimensional image, etc., and there is no limitation on the detailed color, size, shape, presentation method, content, etc. of the password image.

[0049] In the disclosed embodiment, the password video may include but is not limited to: dynamic avatars, dynamic expressions, film and television clips, recorded videos, etc. There is no restriction on the detailed color, size, video style, presentation method, content, etc. of the password video.

[0050] In the disclosed embodiment, the generated password image can be used as wallpaper, avatar, etc., so as to remind the user of the password information and the content of the password image in real time to avoid forgetting, and one image can be used for multiple purposes.

[0051] In an embodiment of the present disclosure, one or more associated password images are generated based on first password information, including: inputting the first password information into a preset image generation model, and generating the password image by the image generation model; wherein the image generation model is obtained by pre-training a preset deep learning network using image text as training data.

[0052] In the disclosed embodiments, the image generation model may include, but is not limited to, an image generation model and a video generation model. The image generation model may be a currently existing generative model, with a generative model capable of generating images being used as the image generation model and a generative model capable of generating videos being used as the video generation model. The detailed structure of the deep learning network of the image generation model is not limited herein.

[0053] In an embodiment of the present disclosure, when the password image includes a password image, the image generation model includes an image generation model; generating one or more associated password images according to the first password information includes: inputting the first password information into a preset image generation model, and generating the password image through the image generation model; the image generation model includes: a trained feature extraction model, a diffusion model and a super-resolution model.

[0054] In an embodiment of the present disclosure, generating a password image through an image generation model may include: obtaining first feature information of first password information through a feature extraction model; generating a first initial image based on the first feature information through a diffusion model; and processing the resolution of the first initial image through a super-resolution model to obtain a password image.

[0055] In the embodiment of the present disclosure, the input of the feature extraction model serves as the input of the image generation model, the output of the feature extraction model is connected to the input of the diffusion model, the output of the diffusion model is connected to the input of the super-resolution model, and the output of the super-resolution model serves as the output of the image generation model.

[0056] In the embodiment of the present disclosure, the feature extraction model, diffusion model and super-resolution model can all adopt currently existing models and be pre-trained according to the requirements of the embodiment of the present disclosure.

[0057] In the disclosed embodiment, the feature extraction model is used to understand the content of the input text or audio, and convert the content into specific features to obtain feature information (for example, first feature information can be obtained based on the first password information).

[0058] In the embodiment of the present disclosure, the first feature information may be a three-dimensional feature matrix, such as a matrix with dimensions of (1, 77, 768), for example:

[0059] [[[0.25,0.34,...,0.35],[0.25,0.34,...,0.35],[0.25,0.34,...,0.35],[0.25,0.34,...,0.35]...[0.25,0.34,...,0.35]]].

[0060] In the embodiment of the present disclosure, the diffusion model (Diffusion_model) can generate an image according to the first feature information extracted by the feature extraction model. The image can be called a first initial image.

[0061] In the disclosed embodiment, as shown in Figure 2, the basic principle of the diffusion model is to continuously add noise to an original image (origin_image) in the forward process until a noise image (noise_image) is generated. The noise image (noise_image) is then continuously de-noised in the reverse process to restore the original image (origin_image). The reverse de-noising process requires learning (i.e., training) to predict the distribution of noise removed at each stage.

[0062] In an embodiment of the present disclosure, the deep learning network includes: a first deep learning network, the image-text pairs include image-text pairs; and the diffusion model is obtained by pre-training the first deep learning network using the image-text pairs as training data.

[0063] In the embodiment of the present disclosure, pre-training the diffusion model may include:

[0064] Obtain training data; training data includes: image-text pairs;

[0065] The training data is input into the first deep learning network, and the first deep learning network adds noise to the first original image (origin_image1) in the image-text pair to obtain a noisy image, and fuses the noisy image with the text in the image-text pair to obtain a first fused noisy image. The first fused noisy image is reversely denoised to obtain a second original image (origin_image2. During the training phase, origin_image2 and origin_image1 are not necessarily exactly the same). The loss is calculated based on the second original image. When the calculated loss value meets the preset requirements, the parameters of the first deep learning network are saved to obtain a trained diffusion model. When the calculated loss value does not meet the preset requirements, the parameters of the first deep learning network are adjusted and the first deep learning network is retrained.

[0066] In the disclosed embodiment, during the training process of the first deep learning network, origin_image1 is first noise-added to obtain a noise image noise_image. During the reverse noise elimination process, the noise image noise_image and the text text corresponding to the image in the image-text pair are fused into a new noise image. The noise in the new noise image is then reversely eliminated to restore origin_image1. The noise added in the forward pass is known noise, while the noise eliminated in the reverse pass is unknown noise. One or more training sessions are required to obtain noise distribution information for each reverse noise elimination stage. The noise distribution information for each reverse noise elimination stage is adjusted during each training session. After the training is completed, the noise distribution information for each reverse noise elimination stage during the last training session is saved, thereby obtaining a trained diffusion model.

[0067] In the embodiment of the present disclosure, according to the trained diffusion model and based on the saved noise distribution information, when processing the first feature information output by the feature extraction model, a password image matching the first feature information can be generated based on the noise distribution information and the first feature information.

[0068] In an embodiment of the present disclosure, a first initial image is generated based on the first feature information through a diffusion model, including: fusing the input first feature information with a pre-stored noise image to generate a second fused noise image; and reversely eliminating noise from the second fused noise image based on pre-stored noise distribution information to obtain the initial image.

[0069] In the disclosed embodiment, when using a trained diffusion model to generate the first initial image, only the second half of the diffusion model, namely the inverse denoising process, is required. The first feature information output by the feature extraction model can be fused with a pre-existing noise image to generate the aforementioned second fused noise image. This second fused noise image is then continuously denoised through the inverse diffusion process to generate a physically low-resolution image, image_low, which is the aforementioned first initial image.

[0070] In the disclosed embodiment, according to the password generation principle and the password unlocking principle, some information used in password generation is consistent with some information used in unlocking, and the noise image used in generating the password image during the password generation process and the noise image noise_image used in unlocking (i.e., the pre-stored noise image mentioned above) are consistent, thereby ensuring that the image generated each time for the same password information is the same.

[0071] In the embodiment of the present disclosure, the super-resolution model (Vae_model) can process the input low-resolution image and output a high-resolution image.

[0072] In the embodiment of the present disclosure, after the first initial image is input into the super-resolution model, a cipher image with high resolution can be obtained.

[0073] In the embodiment of the present disclosure, high resolution may refer to a resolution greater than or equal to a preset first resolution threshold, and low resolution may refer to a resolution less than or equal to a preset second resolution threshold, wherein the first resolution threshold is greater than the second resolution threshold.

[0074] In an embodiment of the present disclosure, when the password image includes a password video, the image generation model may include a video generation model; generating one or more associated password images based on the password information includes: inputting the password information into a preset video generation model, and generating the password video through the video generation model.

[0075] In the embodiment of the present disclosure, the video generation model can adopt an existing already trained generative model with the function of generating video based on text and / or audio. The detailed structure of the second deep learning network included in the video generation model is not limited here.

[0076] In the embodiment of the present disclosure, the video generation model may adopt but is not limited to: an artificial intelligence system model Make-A-Video, which can generate a short video based on a given text prompt.

[0077] In the embodiment of the present disclosure, the generated password image can be stored separately as a password, and unlocked only by the password image when the password is unlocked, or it can be stored together with the input first password information to form a password, so that the password image and the first password information can be used together to unlock the password when the password is unlocked, thereby enhancing the password strength.

[0078] In an embodiment of the present disclosure, when the target password image includes multiple associated password images, the features of the selected target password image are extracted and saved, including: extracting the features of the multiple associated password images separately and saving them, and saving the first selection order of the multiple associated password images to obtain a cascade password.

[0079] In the disclosed embodiment, users can also generate multiple password images as a cascade password as needed to enhance the strength of the password and effectively reduce the probability of password cracking. The multiple password images in the cascade password have a preset arrangement order (for example, the first selection order of multiple related password images when the user selects the target password image). This arrangement order is also saved as the password content. When the user decodes the cascade password, the arrangement order of the decoding images required to be entered is the same as the above arrangement order.

[0080] The present disclosure also provides a password unlocking method, as shown in FIG3 , which may include steps S21 to S24:

[0081] S21. Providing an unlocking interface; the unlocking interface includes one or more unlocking methods;

[0082] S22, acquiring an unlocking image according to the selected target unlocking method;

[0083] S23, detecting whether the unlocking image matches a pre-stored target password image; the target password image is one or more associated password images generated based on the preset first password information;

[0084] S24. Unlock or return unlock failure information based on the detection result.

[0085] In the disclosed embodiment, the unlocking image is one or more images captured to determine whether they are password images, used for unlocking. The unlocking image can be obtained based on the second password information provided by the user when unlocking, or can be selected by the user from multiple pre-provided images. The method for obtaining the unlocking image is not limited herein and can be determined based on the unlocking method selected by the user.

[0086] In the embodiment of the present disclosure, the unlocking image may include but is not limited to: an unlocking picture and / or an unlocking video.

[0087] In the embodiment of the present disclosure, the unlock image may include but is not limited to: color image, black and white image, one-dimensional image, multi-dimensional image, etc. There is no limitation on the detailed color, size, shape, presentation method, content, etc. of the unlock image.

[0088] In the disclosed embodiment, the unlocking video may include but is not limited to: dynamic avatars, dynamic expressions, film and television clips, recorded videos, etc. There is no restriction on the detailed color, size, video style, presentation method, content, etc. of the unlocking video.

[0089] In the disclosed embodiment, password unlocking can be performed based on the input second password information and the target password image, or based solely on the target password image. However, since the user may misremember or forget the password information during unlocking, the password information may not necessarily be the correct first password information. To distinguish it from the correct first password information entered during password generation, the password information entered by the user during unlocking is recorded as the second password information.

[0090] In the disclosed embodiments, the user can set one or more unlocking methods when setting a password, and set corresponding unlocking method selection controls for different unlocking methods. When the user needs to unlock, the unlocking method selection controls are provided on the unlocking interface, allowing the user to select different unlocking methods. Alternatively, any one of the multiple unlocking methods can be used by default when setting a password.

[0091] In the disclosed embodiment, the terminal can obtain the unlock image required for the user to unlock the device based on the unlock method selected by the user (i.e., the unlock method selection control triggered). The unlock methods in the disclosed embodiment can include the two unlock methods described above (a first unlock method: unlocking based on the second password information and the password image, and a second unlock method: unlocking based solely on the password image). The difference between the two unlock methods lies primarily in the method for obtaining the unlock image. After determining the unlock image, both methods determine whether the unlock image is the password image, i.e., whether the unlock image is consistent with a pre-stored password image. The following details the methods for obtaining the unlock image for each of the two unlock methods.

[0092] Method 1:

[0093] In an embodiment of the present disclosure, when the target unlocking method is the first unlocking method, obtaining an unlocking image according to the target unlocking method may include: obtaining input second password information; the second password information may include text information and / or audio information; and generating at least one unlocking image according to the second password information.

[0094] In the embodiment of the present disclosure, the second password information may be input into a preset image generation model, and the image generation model may generate at least one unlocking image.

[0095] In the embodiment of the present disclosure, in the first unlocking mode, the user is required to provide password information when unlocking. Therefore, a preset unlocking interaction device may be provided at this time so that the user can input password information through the unlocking interaction device.

[0096] In the embodiment of the present disclosure, one or more images can be generated again according to the aforementioned image generation model based on the input second password information. At this time, since the input second password information is not necessarily correct, the generated image is not necessarily the password image. The one or more images generated at this time can be recorded as unlocking images.

[0097] In the disclosed embodiment, when the unlock image includes an unlock image, the image generation model includes an image generation model; the image generation model includes: a trained feature extraction model, a diffusion model, and a super-resolution model. In the disclosed embodiment, when the unlock image includes an unlock video, the image generation model includes a video generation model.

[0098] Method 2:

[0099] In an embodiment of the present disclosure, when the target unlocking method is the second unlocking method, obtaining an unlocking image according to the target unlocking method may include: providing multiple mixed images to be selected and the number of images to be selected; obtaining an image that matches the number of images selected from the multiple mixed images as an unlocking image; wherein the multiple mixed images are obtained based on the password image and the preset interference image.

[0100] In the embodiment of the present disclosure, an interference image library can be set up. The number of interference images in the interference image library is not limited. For example, the interference image library can be 100 in number. The interference image and the password image are both configured with a specific identifier. Each time the user opens the unlocking interface (or unlocking interactive interface) and needs to unlock, the system can randomly select one or more interference images and unlockable password images and put them together in random order to form multiple mixed images, which are displayed on the unlocking interface for the user to select.

[0101] In the embodiment of the present disclosure, the interference image may be automatically generated, or may be generated in advance based on input text and / or audio information, or may be captured from certain set images. There is no limitation on the method of obtaining the interference image.

[0102] In the embodiment of the present disclosure, after the user selects any one or more images from the mixed images in the unlocking interface, these images can be used as unlocking images.

[0103] In an embodiment of the present disclosure, detecting whether an unlock image matches a pre-stored target password image includes: detecting whether the identifier of each unlock image in at least one unlock image is the identifier of the target password image; when the identifier of each unlock image is the identifier of the target password image, confirming that the unlock image matches the target password image; or, when the identifier of any one or more unlock images is not the identifier of the target password image, confirming that the unlock image does not match the target password image.

[0104] In the embodiment of the present disclosure, after the user selects the unlock image, the identifiers of these unlock images can be retrieved according to the triggered status of these unlock images, and the identifiers of these unlock images can be checked one by one to see whether they match the identifiers of the target password image; if the identifier of each unlock image can match the target password image with the same identifier, it can be confirmed that the unlock image and the target password image match; if the identifier of any one or more unlock images cannot match the target password image with the same identifier, it is confirmed that the unlock image and the target password image do not match.

[0105] In the embodiment of the present disclosure, when the password to be unlocked is a cascade password, detecting whether the unlocking image matches the pre-stored target password image may further include:

[0106] Before detecting whether the identifier of each unlocking image in the at least one unlocking image is the identifier of the target password image, detecting whether a second selection order of the selected multiple unlocking images is the same as a first selection order of the pre-stored multiple target password images; if the second selection order is the same as the first selection order, entering a process of detecting whether the identifier of each unlocking image in the at least one unlocking image is the identifier of the target password image; if the second selection order is not the same as the first selection order, determining that the unlocking image does not match the target password image;

[0107] or,

[0108] When the identifier of each unlocking image is the identifier of the target password image, it is detected whether the second selection order of the selected multiple unlocking images is the same as the first selection order of the pre-stored multiple target password images; when the second selection order is the same as the first selection order, it is confirmed that the unlocking image matches the target password image; when the second selection order is different from the first selection order, it is confirmed that the unlocking image does not match the target password image.

[0109] In the disclosed embodiment, for a cascaded password, when checking whether the unlock image matches the target password image, it is also necessary to check the second selection order of the multiple unlock images obtained. This second selection order can refer to the order in which the user selects the unlock image from the multiple mixed images provided by the terminal. For example, if the selected unlock images are identified as 1, 2, and 3, respectively, and the user first selects the unlock image identified as 2, then the unlock image identified as 3, and finally the unlock image identified as 1, then the second selection order is 2 3 1. This second selection order can also refer to the artificial arrangement order obtained by the user after selecting multiple unlock images from the multiple mixed images. For example, for the three unlock images identified as 1, 2, and 3, after selecting these images, the user can sort these three unlock images according to the memory of the arrangement order of the password images, for example, 3 2 1, and the second selection order is 3 2 1. This second selection order can be compared with the pre-stored first arrangement order of the target password images to further determine whether the unlock image matches the target password image.

[0110] In the embodiment of the present disclosure, the above-mentioned scheme of comparing the second selection order of the decoded image with the second selection order of the target password image can be performed before detecting whether the identification of each unlocking image in at least one unlocking image is the identification of the target password image, or after detecting that the identification of each unlocking image is the identification of the target password image. Here, the detailed implementation location of the comparison scheme of the second selection order with the first selection order is not limited.

[0111] In the embodiment of the present disclosure, after obtaining the unlock image based on the above two unlocking methods, it is further possible to detect whether the unlock image matches the password image based on the similarity between the unlock image and the target password image.

[0112] In an embodiment of the present disclosure, detecting whether an unlocking image matches a pre-stored target password image may include: detecting the similarity between at least one unlocking image and at least one target password image; confirming that the unlocking image matches the target password image when the similarity between each unlocking image and the target password image is greater than or equal to a preset similarity threshold; or confirming that the unlocking image does not match the target password image when the similarity between any one or more unlocking images and the target password image is less than the similarity threshold.

[0113] In the embodiment of the present disclosure, when the unlocking image is the unlocking image and the password image is the password image, the unlocking is performed. To determine whether an unlocking image and a target password image match, it is possible to directly determine whether the similarity between the unlocking image and the target password image meets a first preset requirement. If the first preset requirement is met, the unlocking image and the target password image match; if the first preset requirement is not met, the unlocking image and the target password image do not match. The similarity between the unlocking image and the target password image can be calculated based on the color cumulative histogram feature.

[0114] In an embodiment of the present disclosure, calculating the similarity between the unlock image and the target password image based on the color cumulative histogram feature may include:

[0115] Calculating a first color cumulative histogram feature of the unlock image and a second color cumulative histogram feature of the target password image within a preset pixel level range respectively;

[0116] Calculating the difference between the first color cumulative histogram feature and the second color cumulative histogram feature corresponding to each pixel level within the pixel level range;

[0117] Calculate the sum of the difference values ​​calculated for each pixel level;

[0118] The sum of the differences is divided by the number of all pixel levels to obtain an average difference, which is used as the similarity between the unlock image and the target password image.

[0119] In the embodiment of the present disclosure, for example, to determine whether the unlock image img_match and the target password image img_refs are consistent, the color cumulative histogram features embed_match (i.e., the first color cumulative histogram feature mentioned above) and embed_refs (i.e., the second color cumulative histogram feature mentioned above) of the unlock image img_match and the target password image img_refs can be calculated respectively:

[0120] embed_match(X i )=∑ j≤i h_match(X j );

[0121] embed_refs(X i )=∑ j≤i h_refs(X j );

[0122] Where x represents any x-th image, x is a positive integer, i represents the pixel level, i is 0 and a positive integer, ranging from 0 to 255; h_match(X j ) and h_refs(X j) represent the number of pixels in the B (blue), G (green), and R (red) channels of the unlock image img_match and the target password image img_refs that are smaller than pixel j;

[0123] Then the similarity

[0124] In the embodiment of the present disclosure, when the unlocking image is the unlocking video and the target password image is the password video, determining whether an unlocking video and a target password video match can also directly determine whether the similarity between the unlocking video and the target password video meets the second preset requirement. If the second preset requirement is met, the unlocking video and the target password video match; if the second preset requirement is not met, the unlocking video and the target password video do not match; based on the color cumulative histogram feature, the similarity between at least one frame of unlocking image in the unlocking video and the target password image in the target password video corresponding to the time of the frame of unlocking image can be calculated, and the duration of the unlocking video and the target password video can be compared to see whether they are the same.

[0125] In the embodiment of the present disclosure, if the duration of the unlocking video and the target password video are different, the unlocking video and the target password video must not match. If the duration of the unlocking video and the target password video is the same, it is possible to further determine whether the unlocking video and the target password video match based on the color cumulative histogram features, or to determine whether the unlocking video and the target password video match based only on the color cumulative histogram features. There is no limitation on the judgment scheme for whether the unlocking video and the target password video match.

[0126] In the disclosed embodiment, password unlocking can be performed based on the matching detection result between the unlocking image and the target password image, wherein, if the unlocking image matches the target password image, unlocking is performed, and if the unlocking image does not match the target password image, unlocking failure information is returned.

[0127] Based on the above-mentioned solutions of the embodiments of the present disclosure, exemplary embodiments of password generation and unlocking are given below.

[0128] First Exemplary Embodiment

[0129] As shown in FIG4 , the password setting method of the embodiment of the present disclosure includes steps S31 to S37:

[0130] S31. Open the password setting interactive interface.

[0131] S32. Obtain the text “A girl under a cherry blossom tree in the second dimension” input on the password setting interactive interface.

[0132] S33. Input the text “a girl under a cherry blossom tree in the second dimension” into an image generation model, and generate at least one image containing a girl under a cherry blossom tree according to the text “a girl under a cherry blossom tree in the second dimension” through the image generation model.

[0133] S34. The generated image is provided to the user for selection, and the user is asked whether he is satisfied with the generated image. If he is satisfied, the selected image is saved and the process proceeds to step S35 or S37. If he is not satisfied, the process returns to step S33.

[0134] S35. Providing an unlocking mode selection interface to the user, for the user to select a first unlocking mode or a second unlocking mode included in the unlocking mode selection interface;

[0135] The first unlocking method is used to unlock based on both the password information and the password image, and the second unlocking method is used to unlock based only on the password image.

[0136] S36. According to the first unlocking method selected by the user, the text "Girl under the cherry blossom tree in the second dimension" and the image are saved as a password; or, according to the second unlocking method selected by the user, the image is saved as a password, and the process ends.

[0137] S37. The first unlocking method is adopted by default, and the text "Girl under the Second Dimension Cherry Blossom Tree" and the image are saved as the password; or the second unlocking method is adopted by default, and the image is saved as the password, and the process ends.

[0138] Second Exemplary Embodiment

[0139] As shown in FIG5 , the password unlocking method of the embodiment of the present disclosure includes steps S41 to S48:

[0140] S41. Open the unlocking interface and provide a first unlocking method and a second unlocking method.

[0141] The first unlocking method corresponds to the first unlocking image acquisition method, and the second unlocking method corresponds to the second unlocking image acquisition method.

[0142] S42: Determine the unlocking mode selected by the user. If the user selects the first unlocking mode, proceed to step S43; if the user selects the second unlocking mode, proceed to step S45.

[0143] S43. Obtain the input second password information “a girl under a cherry blossom tree in the second dimension”, input “a girl under a cherry blossom tree in the second dimension” into an image generation model, and generate at least one unlocking image by the image generation model.

[0144] S44 , detecting whether the unlock image and the target password image match based on the similarity between the unlock image and the target password image, and proceeding to step S48 after obtaining the detection result.

[0145] S45. Select multiple interference images and mix them with the target password image to obtain a mixed image, which is displayed on the unlocking interface for user selection.

[0146] S46: Obtain at least one image selected by the user from the multiple mixed images as an unlocking image.

[0147] S47 , detecting whether the unlock image and the target password image match based on the identifiers of the unlock image and the target password image, and proceeding to step S48 after obtaining the detection result.

[0148] S48. If the unlock image matches the target password image, unlocking is performed. If the unlock image does not match the target password image, unlock failure information is returned.

[0149] An embodiment of the present disclosure also provides an electronic device 100, as shown in Figure 6, the electronic device 100 may include: one or more processors 101; a memory 102, on which one or more programs are stored, when the one or more programs are executed by the one or more processors, the one or more processors implement the password setting method and / or the password unlocking method; one or more input / output I / O interfaces 103, connected between the processor 101 and the memory 102, and configured to implement information interaction between the processor 101 and the memory 102.

[0150] Among them, the processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read-write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus), etc.

[0151] In some embodiments, the processor 101 , the memory 102 , and the I / O interface 103 are connected to each other via a bus 104 , and further connected to other components of the computing device.

[0152] The embodiment of the present disclosure further provides a computer-readable storage medium 200, as shown in FIG7 , on which a computer program is stored, and when the computer program is executed by a processor, the password setting method and / or the password unlocking method are implemented.

[0153] Those skilled in the art will appreciate that all or some of the steps, systems, and functional modules / units in the apparatus disclosed above may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0154] In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation.

[0155] Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit (CPU), a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As is well known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH) or other disk storage; compact disc (CD-ROM), digital versatile disc (DVD) or other optical disc storage; magnetic cassettes, tapes, disk storage or other magnetic storage; any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0156] The present disclosure has disclosed example embodiments, and although specific terms are employed, they are used and should be interpreted only in a general illustrative sense and not for purposes of limitation. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly indicated, features, characteristics, and / or elements described in conjunction with a particular embodiment may be used alone or in combination with features, characteristics, and / or elements described in conjunction with other embodiments. Therefore, it will be understood by those skilled in the art that various changes in form and detail may be made without departing from the scope of the present disclosure as set forth in the appended claims.

Claims

1. A password setting method, comprising: Obtain the first password information entered; generating one or more associated password images according to the first password information; receiving a selection operation for the one or more associated cryptographic images; Extract the features of the selected target password image and save it.

2. The password setting method according to claim 1, wherein: The step of obtaining the input first password information includes: Providing at least one password setting interaction mode; acquiring the first password information according to a target password setting interaction mode selected from the at least one password setting interaction mode; and / or, Provide at least one application scenario; determine a target application scenario selected from the at least one application scenario; provide a corresponding password setting interaction method according to the target application scenario, so as to obtain the first password information through the provided password setting interaction method.

3. The password setting method according to claim 1, wherein: In the case where the password image includes a password picture, generating one or more associated password images according to the first password information includes: The first password information is input into a preset image generation model, and the features of the first password information are extracted by the image generation model to generate the password image.

4. The password setting method according to any one of claims 1 to 3, wherein: In the case where the target password image includes a plurality of associated password images, the extracting and saving the features of the selected target password image includes: The features of the multiple associated password images are extracted and saved respectively, and the first selection order of the multiple associated password images is saved to obtain a cascade password.

5. A password unlocking method, comprising: Provide unlocking interface; The unlocking interface includes one or more unlocking modes; Acquire the unlocking image according to the selected target unlocking method; Detecting whether the unlocking image matches a pre-stored target password image; the target password image is one or more associated password images generated according to the preset first password information; Unlock or return unlock failure information based on the detection result.

6. The password unlocking method according to claim 5, wherein: When the target unlocking method is the first unlocking method, acquiring the unlocking image according to the selected target unlocking method includes: Obtaining the input second password information; At least one unlocking image is generated according to the second password information.

7. The password unlocking method according to claim 5, wherein: When the target unlocking method is the second unlocking method, acquiring the unlocking image according to the selected target unlocking method includes: providing a plurality of mixed images to be selected and the number of images to be selected; Acquire an image selected from the plurality of mixed images and matching the number of images as the unlocking image; The multiple mixed images are obtained based on the password image and the preset interference image.

8. The password unlocking method according to claim 7, wherein: The detecting whether the unlocking image matches the pre-stored target password image includes: Detecting whether the identification of each of the unlocking images in at least one of the unlocking images is the identification of the target password image; In the case where the identification of each of the unlocking images is the identification of the target password image, confirming that the unlocking image matches the target password image; or, In the event that the identification of any one or more of the unlocking images is not the identification of the target password image, it is confirmed that the unlocking image does not match the target password image.

9. The password unlocking method according to claim 8, wherein: In the case where the password to be unlocked is a cascade password, the detecting whether the unlocking image matches the pre-stored target password image further includes: Before detecting whether the identification of each of the unlocking images in at least one of the unlocking images is the identification of the target password image, detecting whether a second selection order of the selected multiple unlocking images is the same as a first selection order of the pre-stored multiple target password images; if the second selection order is the same as the first selection order, entering a process of detecting whether the identification of each of the unlocking images in at least one of the unlocking images is the identification of the target password image; if the second selection order is different from the first selection order, determining that the unlocking image does not match the target password image; or, In the case where the identification of each of the unlocking images is the identification of the target password image, it is detected whether the second selection order of the selected multiple unlocking images is the same as the first selection order of the pre-stored multiple target password images; in the case where the second selection order is the same as the first selection order, it is confirmed that the unlocking image matches the target password image; in the case where the second selection order is different from the first selection order, it is confirmed that the unlocking image does not match the target password image.

10. The password unlocking method according to any one of claims 5 to 7, wherein: The detecting whether the unlocking image matches the pre-stored target password image includes: detecting a similarity between at least one of the unlocking images and at least one of the target password images; In the case where the similarity between each of the unlocking images and the target password image is greater than or equal to a preset similarity threshold, confirming that the unlocking image matches the target password image; When the similarity between any one or more of the unlocking images and the target password image is less than the similarity threshold, it is confirmed that the unlocking image does not match the target password image.

11. An electronic device, comprising: one or more processors; A memory having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the password setting method described in any one of claims 1 to 4, or the password unlocking method described in any one of claims 5 to 10; One or more input / output I / O interfaces are connected between the processor and the memory and are configured to implement information interaction between the processor and the memory.

12. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the password setting method described in any one of claims 1 to 4 or the password unlocking method described in any one of claims 5 to 10 is implemented.

Images