Verification code set generation method, apparatus and device, and computer program product

Abstract

The invention discloses a verification code set generation method, device and equipment and a computer program product, and relates to the technical field of data processing, the verification code set generation method comprises the steps that a target video is acquired, and the target video is generated based on a text material, a picture material and a video generation model; extracting a plurality of target scene frames in the target video, and determining a scene frame display sequence, a scene frame switching rule and verification code prompt information corresponding to each target scene frame; and based on the scene frame display sequence corresponding to each target scene frame, a scene frame switching rule and verification code prompt information, performing association combination on each target scene frame to generate a first verification code set. According to the method, the verification code cracking difficulty is improved by generating the verification code set with relevance, the authenticity and accuracy of user verification are effectively improved, and the verification safety is enhanced.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a verification code set generation method, device, equipment and computer program product. Background Art

[0002] At present, whether the current login behavior is a real user behavior is usually determined by verifying a static verification code image. However, the image in the verification code has no correlation with the interference information. For example, some websites use distorted letters and numbers as static verification codes, and add noise or blurred lines to the background as interference. Although this method increases the difficulty of visual recognition to a certain extent, it does not substantially increase the complexity of generating and recognizing the verification code. Attackers can use automated image recognition technology to train models through machine learning algorithms to identify these distorted characters, thereby cracking the verification code, making the verification code difficult to crack and less secure. Summary of the invention

[0003] The main purpose of this application is to provide a verification code set generation method, device, equipment and computer program product, aiming to improve the difficulty of cracking the verification code and the security.

[0004] To achieve the above purpose, the present application proposes a method for generating a verification code set, the method comprising:

[0005] Acquire a target video, wherein the target video is generated based on text material, picture material and a video generation model;

[0006] Extracting a plurality of target scene frames in the target video, and determining a scene frame display order, a scene frame switching rule and a verification code prompt information corresponding to each of the target scene frames;

[0007] Based on the scene frame display order, scene frame switching rules and verification code prompt information corresponding to each of the target scene frames, the target scene frames are associated and combined to generate a first verification code set.

[0008] In one embodiment, the acquiring of the target video, wherein the target video is generated based on text material, picture material and a video generation model, includes:

[0009] Get text materials and picture materials;

[0010] Extracting semantic information from the picture material to obtain picture content text, and determining the text type of the text material;

[0011] The target video is generated based on the picture content text, the text type and the video generation model.

[0012] In one embodiment, generating the target video based on the picture content text, the text type, and the video generation model includes:

[0013] If the text type is a numerical type, the text material is split into a number of numerical values;

[0014] Based on the values, determining an entity quantity adjustment value, an entity action adjustment value, and an entity type quantity change value corresponding to the image content text;

[0015] Based on the preset intermediate frame generation rules, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

[0016] In one embodiment, based on the preset intermediate frame generation rule, the picture content text, the entity quantity adjustment value, the entity action adjustment value, and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model, including:

[0017] Outputting an initial scene frame corresponding to the picture content text through the video generation model, and outputting an ending scene frame corresponding to the entity quantity adjustment value, the entity action adjustment value, and the entity type quantity change value through the video generation model;

[0018] Outputting, through the video generation model, a plurality of intermediate scene frames corresponding to the preset intermediate frame generation rule, the initial scene frame and the end scene frame;

[0019] Each of the intermediate scene frames is associated and combined with the initial scene frame and the ending scene frame to generate the target video.

[0020] In one embodiment, generating the target video based on the picture content text, the text type, and the video generation model includes:

[0021] If the text type is non-numeric, all factors of the length value of the text content in the text material are determined;

[0022] Based on the factors, determining an entity quantity adjustment value, an entity action adjustment value, and an entity type quantity change value corresponding to the image content text;

[0023] Based on the preset intermediate frame generation rules, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

[0024] In one embodiment, extracting a plurality of target scene frames in the target video and determining a scene frame display order, a scene frame switching rule and a verification code prompt information corresponding to each of the target scene frames includes:

[0025] Extracting a plurality of target scene frames from the target video based on a preset scene frame extraction rule;

[0026] Obtaining the appearance time relationship and entity association relationship of each target scene frame in the target video;

[0027] Based on the appearance time relationship and the entity association relationship, the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each of the target scene frames are determined.

[0028] In one embodiment, after associating and combining the target scene frames based on the scene frame display order, scene frame switching rule and verification code prompt information corresponding to the target scene frames to generate the first verification code set, the method further includes:

[0029] Receive a verification code acquisition request sent by a user verification terminal;

[0030] A second verification code set is extracted from a preset verification code database, and the second verification code set is returned to the user verification terminal, the user verification terminal obtains the target user's operation behavior for the second verification code set, and determines whether the target user passes the verification based on the operation behavior and the second verification code set.

[0031] In addition, to achieve the above purpose, the present application also proposes a verification code set generation device, the verification code set generation device comprising:

[0032] A video acquisition module, used to acquire a target video, wherein the target video is generated based on text material, picture material and a video generation model;

[0033] An information extraction module, used to extract a plurality of target scene frames in the target video, and determine a scene frame display order, a scene frame switching rule and a verification code prompt information corresponding to each of the target scene frames;

[0034] The set generation module is used to associate and combine the target scene frames based on the scene frame display order, scene frame switching rules and verification code prompt information corresponding to the target scene frames to generate a first verification code set.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a verification code set generation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the verification code set generation method described above.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the verification code set generation method described above are implemented.

[0037] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the verification code set generation method described above are implemented.

[0038] The present application provides a verification code set generation method, apparatus, device and computer program product. The verification code set generation method obtains a target video, wherein the target video is generated based on text material, picture material and a video generation model, and then extracts several target scene frames in the target video, and determines the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each target scene frame, thereby associating and combining each target scene frame based on the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each target scene frame, and generating a first verification code set, thereby increasing the difficulty of cracking the verification code by generating a verification code set with association, effectively improving the authenticity and accuracy of user verification, and enhancing verification security. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 One of the implementation example diagrams of the currently popular verification code generation method provided for the verification code set generation method of this application;

[0042] Figure 2The second example diagram of the implementation of the verification code set generation method provided by the present application regarding the currently popular verification code generation method;

[0043] Figure 3 Figure 3 of the implementation example of the currently popular verification code generation method provided for the verification code set generation method of this application;

[0044] Figure 4 Figure 4 of the implementation example of the currently popular verification code generation method provided for the verification code set generation method of this application;

[0045] Figure 5 A flowchart of the first embodiment of the verification code generation method of the present application is provided;

[0046] Figure 6 One of the implementation example diagrams of the verification code matching method provided for the verification code set generation method of this application;

[0047] Figure 7 The second example diagram of the implementation of the verification code matching method provided for the verification code set generation method of this application;

[0048] Figure 8 Figure 3 of the implementation example of the verification code matching method provided for the verification code set generation method of this application;

[0049] Fig. 9 This is a schematic diagram of the module structure of the verification code set generation device according to an embodiment of the present application;

[0050] Fig.10 This is a schematic diagram of the device structure of the hardware operating environment involved in the verification code set generation method in the embodiment of the present application.

[0051] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] The main solution of the embodiment of the present invention is: obtaining a target video, wherein the target video is generated based on text material, picture material and video generation model; extracting several target scene frames in the target video, and determining the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each of the target scene frames; based on the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each of the target scene frames, associating and combining each of the target scene frames to generate a first verification code set. Obtaining text material and picture material; extracting semantic information from the picture material to obtain picture content text, and determining the text type of the text material; generating the target video based on the picture content text, the text type and the video generation model. If the text type is a numerical type, the text material is split into several numerical values; based on each of the numerical values, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value corresponding to the picture content text are determined; based on the preset intermediate frame generation rule, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model. The video generation model outputs an initial scene frame corresponding to the image content text, and the video generation model outputs an ending scene frame corresponding to the entity quantity adjustment value, the entity action adjustment value, and the entity type quantity change value; the video generation model outputs a number of intermediate scene frames corresponding to the preset intermediate frame generation rule, the initial scene frame, and the ending scene frame; each of the intermediate scene frames is associated and combined with the initial scene frame and the ending scene frame to generate the target video. If the text type is non-numeric, all factors of the text content length value in the text material are determined; based on each of the factors, the entity quantity adjustment value, the entity action adjustment value, and the entity type quantity change value corresponding to the image content text are determined; based on the preset intermediate frame generation rule, the image content text, the entity quantity adjustment value, the entity action adjustment value, and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model. Based on preset scene frame extraction rules, several target scene frames in the target video are extracted; the appearance time relationship and entity association relationship of each target scene frame in the target video are obtained; based on the appearance time relationship and the entity association relationship, the scene frame display order, scene frame switching rules and verification code prompt information corresponding to each target scene frame are determined.Receive a verification code acquisition request sent by a user verification terminal; extract a set of second verification code sets from a preset verification code database, and return the second verification code set to the user verification terminal, the user verification terminal obtains the target user's operation behavior for the second verification code set, and based on the operation behavior and the second verification code set, determines whether the target user has passed the verification. Thus, the problem of increasing the difficulty of cracking the verification code is solved, and the authenticity and accuracy of user verification are effectively improved, and the verification security is enhanced. Based on the solution of the present invention, starting from the problem that there is a verification code that is used for user verification by a generation method that does not substantially increase the generation complexity and recognition difficulty of the verification code, resulting in a low difficulty in cracking the verification code, a verification code set generation method is designed, and the effectiveness of the verification code set generation method of the present invention is verified when generating the verification code set. Finally, the difficulty of cracking and the safety of use of the verification code set generated by the method of the present invention are significantly improved.

[0055] With the rapid development of Internet technology, information and network security are increasingly valued by users and service providers. At the same time, there have been many criminals who use computers to brute force user accounts to obtain sensitive information, property, etc. of users. In order to prevent related behaviors, Internet service providers use picture verification codes. When users log in, they need to first identify the valid content of the picture verification code, and then manually enter the verification code to determine whether the login behavior is real user behavior. The currently popular verification code generation methods are: one is to simply generate a picture containing verification information and add interference information to the picture. The user obtains the valid content in the picture through visual recognition and then enters it; the other is to generate a sliding verification code. The user drags a specific icon in the picture to a specified position through mouse operation to verify the user's behavior.

[0056] Specifically, please refer to Figure 1 , Figure 2 , Figure 3 as well as Figure 4 ,in, Figure 1 as well as Figure 4 The font is directly generated on the background image, or the font and the background are converted and synthesized by simple algorithms. When matching rules, this type of verification code still mainly uses the text content in the image as the matching basis. The image in the verification code only interferes with the characters in the verification code. Figure 2 and Figure 3 It adds user behavior interaction to the image verification code. When the verification code rules are matched, it actually matches the first and fourth images. Figure 1 Similarly, the rule matching is performed based on the picture obtained after the user slides.

[0057] Based on the above content, it can be seen that the implementation of the picture verification code has the following technical problems:

[0058] (1) The fusion method of the background image and the characters is single, and the characters in the verification code have no correlation with the background image, which makes it easy to be cracked and identified. The difficulty of cracking the verification code and its security are low;

[0059] (2) Although user behavior interaction is added during the image verification code verification process, the image verification code obtained after the user performs a specific operation is still used to implement rule matching. The user behavior interaction operation does not substantially increase the complexity of image verification code generation and the difficulty of recognition.

[0060] Therefore, the present application provides a solution to obtain a target video, wherein the target video is generated based on text material, picture material and a video generation model, and then extracting several target scene frames in the target video, and determining the scene frame display order, scene frame switching rules and verification code prompt information corresponding to each of the target scene frames, thereby associating and combining each of the target scene frames based on the scene frame display order, scene frame switching rules and verification code prompt information corresponding to each of the target scene frames, and generating a first verification code set to complete dynamic authentication of user verification, thereby improving the fusion degree of characters and background images in the generated verification code image, and enriching the fusion method of the verification code image characters and images, avoiding the defect of being easily recognized by machines caused by simple superposition in traditional methods, and at the same time improving the static verification code display method in traditional methods, and realizing dynamic verification code display through a determined combination of multiple verification code images (i.e., a verification code set), and enriching the verification code matching method, improving the security of the verification code and the complexity of operation, thereby effectively improving the difficulty of cracking the verification code.

[0061] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a big data service platform, a verification code set generation system, etc. The following takes the verification code set generation system as an example to illustrate this embodiment and the following embodiments.

[0062] Based on this, the present application embodiment provides a verification code set generation method, referring to Figure 5 , Figure 5 A flowchart of the first embodiment of the verification code set generation method of the present application is provided.

[0063] In this embodiment, the verification code set generation method includes steps S11 to S13:

[0064] Step S11, obtaining a target video, wherein the target video is generated based on text material, picture material and a video generation model;

[0065] It should be noted that the target video contains scenes and elements used to generate a verification code set, which is the core part of the dynamic authentication process.

[0066] It should be further explained that the text material refers to the text content in the video used to generate the verification code, such as the letters, numbers or Chinese characters in the verification code. The text material can be randomly generated or selected according to specific rules, such as selected from the material library according to specific rules, and there is no limitation here. The picture material refers to the background picture used to generate the verification code video or the image elements contained in the video. The picture material can be a static background image or a dynamic image sequence, and there is no limitation here. It can be understood that the text material and the picture material are only the original materials for the verification code generation, which are different from the scene picture corresponding to the verification code finally generated. The scene picture corresponding to the verification code finally generated can realize the implicit semantic display of the text material and the picture material.

[0067] Furthermore, the video generation model is an algorithm or system for generating a target video, which can generate a video containing specific scenes and actions based on the provided text material and image material in combination with the prompt word text.

[0068] Specifically, text material and picture material are obtained, and then semantic information is extracted from the picture material to obtain picture content text, and the text type of the text material is determined, so as to generate the target video based on the picture content text, the text type and the video generation model.

[0069] Step S12, extracting a plurality of target scene frames in the target video, and determining a scene frame display order, a scene frame switching rule and a verification code prompt information corresponding to each of the target scene frames;

[0070] It should be noted that the target scene frame refers to a specific frame or image extracted from the target video for generating a verification code, and the target scene frame contains key visual information for verifying the user's identity. In addition, the scene frame display order refers to the display order of the target scene frame in the verification code video. The scene frame display order is pre-set according to the video content and verification logic, and is used to guide the user to perform verification in a specific order.

[0071] It should be further explained that the scene frame switching rule refers to the rule for controlling when the scene frame switches, such as automatically switching after a specific time, or triggering the switch after the user completes a certain operation (such as clicking, sliding, etc.), etc., to ensure the dynamic and interactive nature of the verification code. In addition, the verification code prompt information refers to instructions or prompts provided to the user on how to complete the verification code verification, which are used to help the user understand the operations they need to perform, including operation instructions, example descriptions, error prompts, etc., to help the user correctly complete the verification process, such as "click all pictures containing cats".

[0072] Specifically, based on preset scene frame extraction rules, several target scene frames in the target video are extracted, and then the appearance time relationship and entity association relationship of each target scene frame in the target video are obtained, so as to determine the scene frame display order, scene frame switching rules and verification code prompt information corresponding to each target scene frame based on the appearance time relationship and the entity association relationship.

[0073] Step S13, based on the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each of the target scene frames, the target scene frames are associated and combined to generate a first verification code set.

[0074] It should be noted that the first verification code set refers to a set of verification codes generated according to the target scene frame, scene frame display order, scene frame switching rules and verification code prompt information. The first verification code set contains all visual and logical elements for user verification, which are used to complete login or other authentication processes.

[0075] Specifically, based on the scene frame display order, scene frame switching rules and verification code prompt information corresponding to each of the target scene frames, the target scene frames are associated and combined to generate a first verification code set. In one embodiment, the obtained multiple target scene frames are generated and stored according to the scene frame display order, scene frame switching rules and verification code prompt information, wherein the generated verification code set includes the target scene frame, the display time of each target scene frame, the switching rules of each target scene frame, etc., and the verification code matching method is stored at the same time, and a set of verification code sets corresponds to a verification code matching method.

[0076] For example, the target scene frames are arranged in a predetermined scene frame display order, such as scene frame A is displayed first, then scene frame B, and so on. Then, scene frame switching rules are defined for each target scene frame, such as automatically switching to the next target scene frame after a target scene frame is displayed, such as displaying scene frame A for 5 seconds and scene frame B for 3 seconds, or triggering switching after the user completes a certain operation (such as a mouse click).

[0077] Furthermore, corresponding prompt information is prepared for the verification code set based on the verification code prompt information to guide the user on how to operate according to the displayed scene frame, such as "click on the newly appeared object in each scene", thereby generating a verification code set including scene frames, display time, switching rules and prompt information, and storing it in a preset verification code set database.

[0078] Furthermore, according to the verification code type of the current verification code set, a matching method is specified for the verification code set, such as whether the object selected by the user is a newly appeared object, and the matching method is associated with the verification code set and stored. In this way, when the user encounters this verification code during the login process, the system can determine whether the user's identity is legal based on the user's operation and the pre-set matching method.

[0079] This embodiment obtains a target video, wherein the target video is generated based on text material, picture material and a video generation model, and then extracts several target scene frames in the target video, and determines the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each of the target scene frames, thereby associating and combining each of the target scene frames based on the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each of the target scene frames, and generating a first verification code set, thereby increasing the difficulty of cracking the verification code by generating a verification code set with association, and effectively improving the authenticity and accuracy of user verification, and enhancing the verification security. In addition, generating a verification code set with image-text association can also improve the fusion degree of characters and background images in the generated verification code image, and enrich the fusion method of characters and images in the verification code image, avoiding the defect of being easily recognized by machines caused by simple superposition in the traditional verification code generation method, and realizing dynamic verification code display through the combination of multiple verification code images determined, thereby enriching the verification code matching method, improving the security of the verification code and the complexity of operation, and further increasing the difficulty of cracking the verification code.

[0080] In a feasible implementation manner, the acquiring of the target video, wherein the target video is generated based on text material, picture material and a video generation model, includes:

[0081] Step S21, obtaining text material and picture material;

[0082] Specifically, the text material and the picture material may be obtained according to user settings, or may be randomly extracted from a material library to obtain the text material and the picture material. There is no limitation here, and the settings may be made according to actual conditions.

[0083] Step S22, extracting semantic information from the picture material to obtain picture content text, and determining the text type of the text material;

[0084] It should be noted that the image content text refers to text information extracted from the image material, including entity information, entity action information and text content description, etc., so as to realize the description of the scenes, objects, actions, etc. in the picture. For example, the text content description in the image content text is "birds are flying in the blue sky, and children are running happily among the flowers"; the entity information in the image content text is "birds, children, flowers, blue sky"; the entity action information in the image content text is "birds are flying, children are running", which helps the video generation model understand the context of the image material and generate related video content accordingly.

[0085] It should be further explained that the entity information refers to specific objects or people that can be identified in the picture or video scene. For example, in a picture of a park, the entity information may include "bench", "tree", "children", etc.; the entity action information refers to the action or state of the entity in the video or picture, which is used to describe what the entity is doing or what state it is in. For example, if there is a person in the picture, the entity action information may be "running" or "sitting"; the text content description is a more detailed description that provides additional contextual information about the picture or video scene, wherein the text content description can be a narration of the scene, such as "children playing in the park", or a more specific emotional description, such as "the lake is sparkling at sunset", so as to guide the video generation model to create a scene that matches the description, enhance the richness and expressiveness of the video content, and then the above information together constitutes the input of the video generation model, so that the model can create video content that contains specific entities and actions and conforms to specific text descriptions.

[0086] Furthermore, the text type refers to the classification or attribute of the text material, such as whether the text is numerical or non-numerical text.

[0087] Specifically, semantic information is extracted from the picture material to obtain a picture content text, which may be a content description or a sentiment description of the picture material, etc., wherein semantic information can be extracted from the picture material through picture semantic extraction, which is not limited here.

[0088] Furthermore, the text type of the text material is determined, such as by reading the content of the text material and performing content recognition thereon, thereby determining the text type of the text material.

[0089] Step S23, generating the target video based on the picture content text, the text type and the video generation model.

[0090] Specifically, if the text type is a numerical type, the text material is split into several numerical values, and then based on each of the numerical values, the entity quantity adjustment value, entity action adjustment value and entity type quantity change value corresponding to the picture content text are determined, so that based on the preset intermediate frame generation rules, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

[0091] In addition, if the text type is non-numeric, all factors of the text content length value in the text material are determined, and then based on each of the factors, the entity quantity adjustment value, entity action adjustment value and entity type quantity change value corresponding to the image content text are determined, so that based on the preset intermediate frame generation rules, the image content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

[0092] This embodiment obtains text material and picture material, and then extracts semantic information from the picture material to obtain picture content text, and determines the text type of the text material, so as to generate the target video based on the picture content text, the text type and the video generation model, thereby ensuring that the generated video content is closely related to the picture material and the text material, improving the coherence and logic of the video content, and thus enhancing the content relevance, and at the same time can realize customized video content to meet the specific needs of different users or scenarios, allowing flexible adjustment and optimization during the video generation process to adapt to different business needs and technical changes, and the dynamic generation of video content makes prediction and automatic cracking more difficult, thereby effectively improving the security of user verification.

[0093] In a feasible implementation manner, the generating the target video based on the picture content text, the text type and the video generation model includes:

[0094] Step S31, if the text type is a numerical type, split the text material into a plurality of numerical values;

[0095] It should be noted that the numerical type refers to the type of data that can be quantified contained in the text material, that is, the numbers or values ​​in the text. The value refers to the specific numerical content in the text material, which can be an integer, decimal or any form that can express quantity, and there is no limitation here.

[0096] Specifically, if the text type is a numerical type, the numerical value included in the text material is split according to the digits to obtain multiple single-digit numerical values. For example, if the text material is "524", it can be split into "5", "2" and "4".

[0097] Step S32, determining the entity quantity adjustment value, entity action adjustment value and entity type quantity change value corresponding to the image content text based on the respective values;

[0098] It should be noted that the entity quantity adjustment value refers to adjusting the quantity of a certain entity (such as a person, animal, object, etc.) in the video according to the numerical value in the text. For example, "5" in the text may mean that there should be 5 specific entities in the video. The entity action adjustment value refers to adjusting the action or behavior of the entity in the video according to the numerical value. For example, if the entity action is related to speed or frequency, then this numerical value can be used to adjust the speed or frequency of the entity action.

[0099] It should be further explained that the entity type quantity change value refers to adjusting the quantity of different types of entities in the video according to the numerical value in the text. For example, the numerical value may indicate that a certain type of entity should be increased or decreased in the video, such as "adding 2 different types of birds."

[0100] Specifically, based on each of the numerical values, determine the entity quantity adjustment value, entity action adjustment value and entity type quantity change value corresponding to the picture content text. Continuing with the above example, the split numerical values ​​are used as the entity quantity adjustment value (e.g., the number adjustment value of birds is 5), the entity action adjustment value (e.g., the flight speed adjustment value is 2) and the entity type quantity change value (e.g., adding 4 entity butterflies).

[0101] In addition, the numerical values ​​in the text material can also be split according to the number of entity types included in the picture material, and then the entity quantity adjustment value, entity action adjustment value and entity type quantity change value are determined based on the numerical values ​​obtained after the split. You can also select any object from the entity information, entity action and entity type for adjustment, and there is no restriction here.

[0102] Step S33, based on the preset intermediate frame generation rules, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

[0103] It should be noted that the preset intermediate frame generation rule refers to a series of predefined rules or algorithms for creating intermediate frames during the video generation process, thereby determining how to generate a series of coherent intermediate frames based on the initial frame and the end frame to form a complete video sequence. The intermediate frame generation rule can be set based on factors such as time, action changes, scene transitions, etc., and is not limited here.

[0104] Specifically, the video generation model outputs an initial scene frame corresponding to the picture content text, and the video generation model outputs an ending scene frame corresponding to the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value, and then the video generation model outputs a number of intermediate scene frames corresponding to the preset intermediate frame generation rule, the initial scene frame and the ending scene frame, so that each of the intermediate scene frames is associated and combined with the initial scene frame and the ending scene frame to generate the target video.

[0105] In this embodiment, if the text type is a numerical type, the text material is split into several numerical values, and then based on each of the numerical values, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value corresponding to the picture content text are determined, so that based on the preset intermediate frame generation rule, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model, and then by combining the numerical value in the text material with the picture content text, the entity quantity, action and type in the video can be dynamically adjusted, so that the video content is richer and more varied, the personalization and customization of the video content are improved, the complexity and security of the video content are further improved, and automated attacks and cracking become more difficult, thereby improving the security of applications such as video verification codes, and at the same time, by presetting the intermediate frame generation rule, the logical and visual coherence of the video content is ensured, making the video more natural and smooth, and by directly converting the numerical value in the text material into the adjustment parameter of the video content, the video generation process is simplified, the video generation efficiency is improved, and the video content is allowed to be quickly adjusted and optimized, thereby enhancing the scalability of the video content.

[0106] In a feasible implementation manner, based on the preset intermediate frame generation rule, the picture content text, the entity quantity adjustment value, the entity action adjustment value, and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model, including:

[0107] Step S41, outputting an initial scene frame corresponding to the picture content text through the video generation model, and outputting an ending scene frame corresponding to the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value through the video generation model;

[0108] It should be noted that the initial scene frame refers to the first frame at the beginning of the video, which sets the background and environment for the entire video, and usually contains the starting state of the video story or scene. The ending scene frame refers to the last frame at the end of the video, which marks the end of the video story or scene, and usually shows the final state of the video content, which can be the completion of an action or the result of an event. For example, in a verification code video, the ending scene frame can be a scene that shows the final result or the completion of an action, such as all objects that need to be identified have appeared or a specific action has been completed.

[0109] Specifically, the entity quantity adjustment value, entity action adjustment value, entity type quantity change value and text content description are encoded into a feature vector through an encoder, and the initial scene frame of the video is first obtained based on the text content description, entity information and entity action information. At the same time, the ending scene frame of the video is obtained based on the entity quantity adjustment value, entity action adjustment value, entity type quantity change value and text content description.

[0110] Step S42, outputting a plurality of intermediate scene frames corresponding to the preset intermediate frame generation rule, the initial scene frame and the end scene frame through the video generation model;

[0111] It should be noted that the intermediate scene frames refer to all frames between the initial scene frame and the final scene frame, which are used to show the transition and change from the initial state to the final state. They are the main part of the video content and include the development and change of the story or scene. In the verification code video, the intermediate scene frames may contain a series of dynamic changes, such as the appearance of new objects, the change of object position or the transformation of the background, thereby increasing the complexity and security of the verification process.

[0112] Specifically, according to the preset prompt text, such as "please generate a video based on text material A and picture material B", the video generation model outputs a number of intermediate scene frames corresponding to the preset intermediate frame generation rule, the initial scene frame and the end scene frame, and based on the preset intermediate frame generation rule, multiple intermediate scene frames are obtained in sequence. The preset intermediate frame generation rule can be: the quantity adjustment value of entity information, the entity action adjustment value, and the entity type quantity change value are respectively increased by the minimum value, and the set value is increased in sequence to obtain multiple intermediate scene frames. In one embodiment, the input text material "43822" and the text content description "birds are flying in the blue sky, and children are running happily in the flowers", in the target video to be processed generated by this step, the first scene frame can be 4 birds flying in the blue sky, followed by the second scene frame of 3 children running from a distance, the third scene frame of 8 birds flying in the sky, the fourth scene frame of two flowers blooming in the flowers, and the fifth scene frame of 2 butterflies flying in the flowers.

[0113] Step S43: Associating and combining each of the intermediate scene frames with the initial scene frame and the end scene frame to generate the target video.

[0114] In this embodiment, the video generation model outputs an initial scene frame corresponding to the picture content text, and the video generation model outputs an ending scene frame corresponding to the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value, and then the video generation model outputs a plurality of intermediate scene frames corresponding to the preset intermediate frame generation rule, the initial scene frame and the ending scene frame, so as to associate and combine each of the intermediate scene frames with the initial scene frame and the ending scene frame to generate the target video, and then by defining the initial scene frame and the ending scene frame, the video content can construct a clear narrative line, The video is not just a pile of static images, but a dynamic display with a story. The preset intermediate frame generation rules ensure that the transition from the initial frame to the end frame is natural and smooth, avoiding abrupt changes in the video content, thereby improving the overall viewing experience of the target video, allowing users to think and interact along the narrative line of the video while watching the video. For example, in the verification code application, users need to respond according to the video content, thereby improving the user experience through user participation. In addition, the dynamically generated video content, especially videos containing multiple intermediate frames and complex actions, are more difficult for automated attacks and cracking, thereby improving the security of the verification code and the difficulty of cracking.

[0115] In a feasible implementation manner, the generating the target video based on the picture content text, the text type and the video generation model includes:

[0116] Step S51, if the text type is non-numeric, then determining all factors of the text content length value in the text material;

[0117] It should be noted that the non-numeric type refers to a text type in which the text material does not contain directly quantifiable numbers (such as integers or decimals), and is usually composed of letters, words, phrases or sentences, which convey information but do not directly indicate quantity. For example, "apple", "sunny day" or "fast running cat" are all non-numeric texts.

[0118] It should be further explained that the text content length value refers to the length of non-numeric text material, usually measured in terms of the number of characters, words or syllables. The factors refer to all positive integer factors of the text length value. For example, if the text content length value is 12 (determined based on the number of characters, words, etc.), then its factors include 1, 2, 3, 4, 6 and 12.

[0119] Step S52, determining the entity quantity adjustment value, entity action adjustment value and entity type quantity change value corresponding to the image content text based on the factors;

[0120] Specifically, based on each of the factors, the entity quantity adjustment value, entity action adjustment value and entity type quantity change value corresponding to the image content text are determined. For example, one of the values ​​is randomly selected from the factors as the entity quantity adjustment value, entity action adjustment value and entity type quantity change value, respectively.

[0121] Step S53, based on the preset intermediate frame generation rules, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

[0122] Specifically, the video generation model outputs an initial scene frame corresponding to the picture content text, and the video generation model outputs an ending scene frame corresponding to the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value, and then the video generation model outputs a number of intermediate scene frames corresponding to the preset intermediate frame generation rule, the initial scene frame and the ending scene frame, so that each of the intermediate scene frames is associated and combined with the initial scene frame and the ending scene frame to generate the target video.

[0123] In this embodiment, if the text type is non-numeric, all factors of the text content length value in the text material are determined, and then based on each of the factors, the entity quantity adjustment value, entity action adjustment value and entity type quantity change value corresponding to the picture content text are determined, and then based on the preset intermediate frame generation rule, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model, and then by combining the factors in the text material with the picture content text, the entity quantity, action and type in the video can be dynamically adjusted, so that the video content is richer and more varied, the personalization and customization of the video content are improved, the complexity and security of the video content are further improved, and automated attacks and cracking become more difficult, thereby improving the security of applications such as video verification codes, and at the same time, by presetting the intermediate frame generation rule, the logical and visual coherence of the video content is ensured, making the video more natural and smooth, and by directly converting the numerical value in the text material into the adjustment parameter of the video content, the video generation process is simplified, the video generation efficiency is improved, and the video content is allowed to be quickly adjusted and optimized, thereby enhancing the scalability of the video content.

[0124] In a feasible implementation manner, extracting a plurality of target scene frames in the target video and determining a scene frame display order, a scene frame switching rule and verification code prompt information corresponding to each of the target scene frames includes:

[0125] Step S61, extracting a plurality of target scene frames in the target video based on a preset scene frame extraction rule;

[0126] It should be noted that the preset scene frame extraction rules refer to a series of predefined standards or criteria for identifying and extracting key frames (scene frames) from the target video during the video content generation process. They can be set based on specific features of the video content, such as scene changes, the start or end of a specific action, or the appearance of a specific object, and are not limited here.

[0127] Specifically, in one embodiment, the preset scene frame extraction rule is: "Extraction rule for the initial target scene frame: the previous frame in which the background information between two consecutive frames in the target video to be processed remains unchanged is determined as the initial scene frame; other scene frames: after the initial scene frame, the number of entities in the video frame of the target video changes, and the video frames in which new entities are fully displayed or completely disappear are newly added or reduced, which are determined as other scene frames", and then according to the preset scene frame extraction rule, several target scene frames in the target video are extracted.

[0128] Step S62, obtaining the appearance time relationship and entity association relationship of each target scene frame in the target video;

[0129] It should be noted that the appearance time relationship refers to the order and time points in which each target scene frame appears in the target video, which is used to describe the timing relationship between each target scene frame in the video, including the start and end time of the target scene frame, and the time interval between each target scene frame.

[0130] It should be further explained that the entity association relationship refers to the relationship between entities (such as people, objects, etc.) appearing in each target scene frame in the target video, which can be the interaction between entities, relative position changes, or changes in entity states over time, etc., and is not limited here.

[0131] Specifically, the appearance time relationship and entity association relationship of each target scene frame in the target video are obtained. In one embodiment, the key frames in the video, i.e., the target scene frames, are identified by video analysis techniques, such as computer vision and pattern recognition, which usually involve scene change detection algorithms for identifying scene transition points in the video stream, thereby determining the start and end time of each scene frame, and then using object tracking and recognition techniques to track various entities in the video (such as people, vehicles, animals, etc.) and their actions and state changes, thereby determining the entity association relationship by analyzing the positions, actions, and relationships of these entities in each scene frame. For example, if there are two people talking in the video, the entity association relationship will include their relative positions and interactions, thereby constructing the appearance timeline of each target scene frame and the complex relationship network between entities, providing a solid data foundation for subsequent video content understanding and dynamic authentication.

[0132] Step S63, based on the appearance time relationship and the entity association relationship, determining the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each of the target scene frames.

[0133] It should be noted that the scene frame display order refers to the order in which the target scene frames are arranged when they are finally displayed to the user, which is used to ensure the logic and coherence of the video content. In addition, the scene frame switching rule refers to the rule for controlling how to transition between target scene frames, which defines when and how to switch from one scene frame to another, and can be set based on time, user interaction or other trigger conditions, which are not limited here.

[0134] It should be further explained that the verification code prompt information refers to guidance information provided to users to help them understand how to complete the verification process based on the video content, which may include operating instructions, details that need attention, expected user behaviors, etc., and is not limited here.

[0135] Specifically, the appearance time relationship of each target scene frame is analyzed to determine the scene frame display order corresponding to each target scene frame, wherein the scene frame display order can be set in ascending order or descending order according to the appearance time relationship, and then the dynamic changes in the video are understood according to the entity association relationship, and scene frame switching rules are formulated accordingly. For example, when an entity's action is completed, switch to the next scene frame containing a new action or a new entity.

[0136] Furthermore, based on the content and switching rules of the target scene frame, verification code prompt information is designed to guide users on how to perform verification operations based on the entities and actions in the target scene frame, such as "click all scenes containing running people", to ensure that users can correctly interact with the video content and complete the authentication process, thereby integrating the logic and interactivity of the video content into the design of the verification code, thereby improving the security of authentication and user experience.

[0137] In one embodiment, when making a video verification code about a kitten chasing a butterfly, we first determine the display order of each target scene frame: first, the picture of the kitten sitting still on a park bench, followed by the scene of the butterfly flying into the picture, and finally the action of the kitten starting to chase the butterfly. The scene frame switching rule is: the static picture of the kitten automatically switches to the scene where the butterfly appears after 5 seconds of display. After the user clicks the butterfly, the video immediately switches to the picture of the kitten chasing. The prompt information of the verification code is: "Please wait and observe the kitten's actions", "The butterfly appears, click the butterfly", and "The kitten starts chasing, prepare to click the chasing action", so as to guide the user to operate at the appropriate time and complete the verification process.

[0138] This embodiment extracts several target scene frames in the target video based on preset scene frame extraction rules, and then obtains the appearance time relationship and entity association relationship of each target scene frame in the target video, thereby determining the scene frame display order, scene frame switching rules and verification code prompt information corresponding to each target scene frame based on the appearance time relationship and the entity association relationship, and then automatically extracts scene frames through preset rules to reduce manual intervention, thereby improving the efficiency and speed of video processing, while ensuring the logic and coherence of video content, making the transition between video scene frames more natural and reasonable, and improving the security of video verification codes by precisely controlling the display and switching of scene frames, preventing automated attacks and cheating. In addition, through carefully designed switching rules and prompt information, the interactivity of video content can be increased, and user participation can be improved, thereby enhancing the security, personalization and interactivity of video content as a whole, and having high adaptability and controllability.

[0139] In a feasible implementation manner, after associating and combining the target scene frames based on the scene frame display order, scene frame switching rule and verification code prompt information corresponding to the target scene frames to generate the first verification code set, the method further includes:

[0140] Step S71, receiving a verification code acquisition request sent by a user verification terminal;

[0141] It should be noted that the user verification terminal refers to a device or platform with which the user directly interacts, which is used to input information, receive verification codes and perform verification operations. It can be a personal computer, smart phone, tablet computer or any other device that can access the network and execute identity authentication procedures, without any limitation here.

[0142] It should be further explained that the verification code acquisition request refers to a request initiated by the user verification terminal, requiring the server or verification system to provide a set of verification codes so that the user can complete the identity authentication process, which is usually triggered when the user logs in, registers or performs sensitive operations.

[0143] Step S72, extract a set of second verification code sets from a preset verification code database, and return the second verification code set to the user verification terminal, the user verification terminal obtains the target user's operation behavior for the second verification code set, and determines whether the target user passes the verification based on the operation behavior and the second verification code set.

[0144] It should be noted that the preset verification code database refers to a database storing a large number of pre-generated verification code sets, which is used to verify the identity of the user and ensure that the operation is performed by a legitimate user. The second verification code set refers to a specific set of verification codes extracted from the preset verification code database. The target user refers to an individual user whose identity needs to be verified by a verification code, and the target user can be anyone who attempts to log in to an account, conduct a transaction, or access protected content.

[0145] It should be further explained that the operation behavior refers to all actions performed by the target user on the user verification terminal, including entering a verification code, clicking an image, dragging a slider, etc. These actions are used to verify the identity of the user. The operation behavior may also include information such as the time, speed and accuracy of the user's response to the verification code, thereby determining whether the user has passed the verification through multi-dimensional analysis.

[0146] Specifically, in one embodiment, a set of second verification code sets in a preset verification code database is randomly extracted, and the second verification code set is returned to the user verification terminal, so that the user verification terminal displays the verification code image and prompt information according to the display order, switching rules and prompt information corresponding to the second verification code set.

[0147] Furthermore, after the user verification terminal determines that the second verification code set in the verification page satisfies the switching rules, the response page displays an updated verification code image, wherein the switching rules may be that the current verification code state is continuously displayed to meet a time threshold and no input, sliding or clicking operation is detected in a designated area in the terminal page, or that the current verification code state is continuously displayed to not reach a time threshold and input, sliding or clicking operation is detected in the user's verification code operation area in the terminal page.

[0148] Furthermore, each time the verification code state is switched, the user verification terminal collects operation event data (ie, operation behavior) of the designated operation area in the verification page before switching the verification code state and submits it for verification.

[0149] Regarding the step of obtaining, by the user verification terminal, the operation behavior of the target user for the second verification code set, and judging whether the target user has passed the verification based on the operation behavior and the second verification code set, the implementation method that the user verification terminal needs to perform is as follows:

[0150] Specifically, a verification code matching method corresponding to the second verification code set is obtained, and a matching verification is performed on the obtained operation behavior according to the verification code matching method, wherein the verification code matching method includes: verification through letters, numbers, mathematical calculations, Chinese characters and even pictures in the picture input by the user, as well as the operation rules of the mouse and keyboard during the input process, for example, the verification code matching method is "matching whether the verification code numbers input by the user are consistent with the number of objects appearing in sequence in the verification code picture", or "the user slides the slider to the specified position of each scene picture in the verification code picture within a specified time", or "matching whether the object selected by the user is a new object that appears relative to the previous verification code picture", and the matching method to be used can be selected according to the actual application and the type of the second verification code set.

[0151] In one embodiment, the following three verification code matching methods based on the target scene frame are proposed.

[0152] The first verification code matching method: matching whether the object selected by the user is a new object relative to the previous verification code image. Accordingly, the determined verification code prompt information is "Please click on the new objects in the image in sequence."

[0153] Specifically, each target scene frame is displayed according to the set display time length and the corresponding scene frame additional information (such as scene frame display order, scene frame switching rules and verification code prompt information, etc.). For example, when the number of entities in the verification code picture of the next frame in the scene frame with adjacent time association relationship is less than the number of entities in the verification code picture of the previous frame, combined with the verification code prompt information, the display order is determined to be displayed in reverse order according to the time relationship; when the number of entities in the verification code picture of the next frame in the scene frame with adjacent time association relationship is greater than the number of entities in the verification code picture of the previous frame, combined with the verification code prompt information, the display order is determined to be displayed in forward order according to the time relationship.

[0154] For example, see Figure 6 , Figure 6 The verification code image on the left only includes the "sun" object, and the "duck" object appears in the verification code image on the right. For this, the target user needs to click on the multiple states of the verification code image in turn to select the newly appeared object. Among them, the scene frame switching rule can be to switch to a new scene image after each scene image is displayed for a set time, or to switch to a new scene image after the user completes the set operation event in the previous scene image.

[0155] The second verification code matching method: the user slides the slider to the specified position of each scene picture in the verification code picture within a specified time, and accordingly, the determined verification code prompt information is "slide the slider in the x direction".

[0156] Specifically, move the newly appearing objects in each picture to the specified position within the set time of the scene picture display. Figure 7 , Figure 7 The verification code picture on the left only includes the "deer" object, and the slider needs to be slid to move the object to the square position within the display setting time. In the verification code picture on the right, a "duck" object has newly appeared in the verification code picture in the picture display area. It is necessary to continue to slide the slider to the right to move it to a new square position within the display setting time based on the slider position corresponding to the previous verification code state. Among them, the scene frame switching rule can be to switch to a new scene picture after each scene picture is displayed for a set time, or to switch to a new scene picture after the user completes the set operation event in the previous scene picture.

[0157] The third verification code matching method: matching the verification code number entered by the user with the number of objects appearing sequentially in the verification code image to see if they are consistent.

[0158] Specifically, please refer to Figure 8 , Figure 8 There is no verification code prompt information. Figure 8The verification code image on the left includes the "43" object, that is, you need to enter the number represented in the image within the set time of the verification code image display. The "82" object has appeared in the verification code image on the right. You need to continue to enter the "82" digital object that appears in the new verification code image based on the input number corresponding to the previous verification code state to complete the verification.

[0159] Finally, the obtained operation behavior is matched and verified according to the verification code matching method. If the verification fails, the login verification is terminated; if the verification passes, the verification code status and the operation events in the page are continuously monitored.

[0160] This embodiment receives a verification code acquisition request sent by a user verification terminal, and then extracts a set of second verification code sets in a preset verification code database, and returns the second verification code set to the user verification terminal, so that the user verification terminal obtains the target user's operation behavior for the second verification code set, and based on the operation behavior and the second verification code set, determines whether the target user has passed the verification, and then reduces the risk of the verification code being cracked in advance by dynamically extracting the verification code set from the database, thereby improving the security of the verification process, improving the response speed, and enhancing the anti-attack capability, improving the reliability of the system, and at the same time, through the analysis of the user's operation behavior, more accurately judges the user's identity and reduces misjudgment.

[0161] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0162] This application also provides a verification code set generation device, please refer to Fig. 9 , the verification code set generating device comprises:

[0163] A video acquisition module 91 is used to acquire a target video, wherein the target video is generated based on text material, picture material and a video generation model;

[0164] An information extraction module 92 is used to extract a plurality of target scene frames in the target video, and determine a scene frame display order, a scene frame switching rule and a verification code prompt information corresponding to each of the target scene frames;

[0165] The set generation module 93 is used to associate and combine the target scene frames based on the scene frame display order, scene frame switching rules and verification code prompt information corresponding to the target scene frames to generate a first verification code set.

[0166] The verification code set generating device is also used for:

[0167] Get text materials and picture materials;

[0168] Extracting semantic information from the picture material to obtain picture content text, and determining the text type of the text material;

[0169] The target video is generated based on the picture content text, the text type and the video generation model.

[0170] The verification code set generating device is also used for:

[0171] If the text type is a numerical type, the text material is split into a number of numerical values;

[0172] Based on the values, determining an entity quantity adjustment value, an entity action adjustment value, and an entity type quantity change value corresponding to the image content text;

[0173] Based on the preset intermediate frame generation rules, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

[0174] The verification code set generating device is also used for:

[0175] Outputting an initial scene frame corresponding to the picture content text through the video generation model, and outputting an ending scene frame corresponding to the entity quantity adjustment value, the entity action adjustment value, and the entity type quantity change value through the video generation model;

[0176] Outputting, through the video generation model, a plurality of intermediate scene frames corresponding to the preset intermediate frame generation rule, the initial scene frame and the end scene frame;

[0177] Each of the intermediate scene frames is associated and combined with the initial scene frame and the ending scene frame to generate the target video.

[0178] The verification code set generating device is also used for:

[0179] If the text type is non-numeric, all factors of the length value of the text content in the text material are determined;

[0180] Based on the factors, determining an entity quantity adjustment value, an entity action adjustment value, and an entity type quantity change value corresponding to the image content text;

[0181] Based on the preset intermediate frame generation rules, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

[0182] The verification code set generating device is also used for:

[0183] Extracting a plurality of target scene frames from the target video based on a preset scene frame extraction rule;

[0184] Obtaining the appearance time relationship and entity association relationship of each target scene frame in the target video;

[0185] Based on the appearance time relationship and the entity association relationship, the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each of the target scene frames are determined.

[0186] The verification code set generating device is also used for:

[0187] Receive a verification code acquisition request sent by a user verification terminal;

[0188] extracting a set of second verification codes from a preset verification code database, and returning the second verification code set to the user verification terminal,

[0189] The user verification terminal obtains the target user's operation behavior for the second verification code set, and determines whether the target user passes the verification based on the operation behavior and the second verification code set.

[0190] The verification code set generation device provided by the present application adopts the verification code set generation method in the above embodiment, which can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the verification code set generation device provided by the present application are the same as the beneficial effects of the verification code set generation method provided by the above embodiment, and other technical features in the verification code set generation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0191] The present application provides a verification code set generation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the verification code set generation method in the above-mentioned embodiment one.

[0192] Reference below Fig.10, which shows a schematic diagram of the structure of a verification code set generation device suitable for implementing the embodiment of the present application. The verification code set generation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.10 The verification code set generating device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0193] like Fig.10 As shown, the verification code set generating device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the verification code set generating device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the verification code set generation device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a verification code set generation device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0194] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0195] The verification code set generation device provided by the present application adopts the verification code set generation method in the above embodiment, which can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the verification code set generation device provided by the present application are the same as the beneficial effects of the verification code set generation method provided by the above embodiment, and other technical features in the verification code set generation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0196] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0197] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0198] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the verification code set generation method in the above-mentioned embodiment.

[0199] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0200] The computer-readable storage medium may be included in the verification code set generation device; or may exist independently without being assembled into the verification code set generation device.

[0201] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the verification code set generation device, the verification code set generation device:

[0202] Acquire a target video, wherein the target video is generated based on text material, picture material and a video generation model;

[0203] Extracting a plurality of target scene frames in the target video, and determining a scene frame display order, a scene frame switching rule and a verification code prompt information corresponding to each of the target scene frames;

[0204] Based on the scene frame display order, scene frame switching rules and verification code prompt information corresponding to each of the target scene frames, the target scene frames are associated and combined to generate a first verification code set.

[0205] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0206] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0207] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0208] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned verification code set generation method, and can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the verification code set generation method provided in the above-mentioned embodiment, and will not be repeated here.

[0209] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the verification code set generation method as described above when the computer program is executed by a processor.

[0210] The computer program product provided in this application can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the verification code set generation method provided in the above embodiment, which will not be repeated here.

[0211] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A verification code set generation method, characterized in that: include: Acquire a target video, wherein the target video is generated based on text material, picture material and a video generation model; Extracting a plurality of target scene frames in the target video, and determining a scene frame display order, a scene frame switching rule and a verification code prompt information corresponding to each of the target scene frames; Based on the scene frame display order, scene frame switching rules and verification code prompt information corresponding to each of the target scene frames, the target scene frames are associated and combined to generate a first verification code set.

2. The verification code set generation method according to claim 1, characterized in that: The obtaining of the target video, wherein the target video is generated based on text material, picture material and a video generation model, includes: Get text materials and picture materials; Extracting semantic information from the picture material to obtain picture content text, and determining the text type of the text material; The target video is generated based on the picture content text, the text type and the video generation model.

3. The verification code set generation method according to claim 2, characterized in that: The generating the target video based on the picture content text, the text type and the video generation model includes: If the text type is a numerical type, the text material is split into a number of numerical values; Based on the values, determining an entity quantity adjustment value, an entity action adjustment value, and an entity type quantity change value corresponding to the image content text; Based on the preset intermediate frame generation rules, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

4. The verification code set generation method according to claim 3, characterized in that: The method of inputting the picture content text, the entity quantity adjustment value, the entity action adjustment value, and the entity type quantity change value into the video generation model based on the preset intermediate frame generation rule to obtain the target video output by the video generation model includes: Outputting an initial scene frame corresponding to the picture content text through the video generation model, and outputting an ending scene frame corresponding to the entity quantity adjustment value, the entity action adjustment value, and the entity type quantity change value through the video generation model; Outputting, through the video generation model, a plurality of intermediate scene frames corresponding to the preset intermediate frame generation rule, the initial scene frame and the end scene frame; Each of the intermediate scene frames is associated and combined with the initial scene frame and the ending scene frame to generate the target video.

5. The verification code set generation method according to claim 2, characterized in that: The generating the target video based on the picture content text, the text type and the video generation model includes: If the text type is non-numeric, all factors of the length value of the text content in the text material are determined; Based on the factors, determining an entity quantity adjustment value, an entity action adjustment value, and an entity type quantity change value corresponding to the image content text; Based on the preset intermediate frame generation rules, the picture content text, the entity quantity adjustment value, the entity action adjustment value and the entity type quantity change value are input into the video generation model to obtain the target video output by the video generation model.

6. The verification code set generation method according to claim 1, characterized in that: The step of extracting a plurality of target scene frames from the target video and determining a scene frame display order, a scene frame switching rule and verification code prompt information corresponding to each of the target scene frames includes: Extracting a plurality of target scene frames from the target video based on a preset scene frame extraction rule; Obtaining the appearance time relationship and entity association relationship of each target scene frame in the target video; Based on the appearance time relationship and the entity association relationship, the scene frame display order, scene frame switching rule and verification code prompt information corresponding to each of the target scene frames are determined.

7. The verification code set generation method according to claim 1, characterized in that: After associating and combining the target scene frames based on the scene frame display order, scene frame switching rule and verification code prompt information corresponding to the target scene frames to generate the first verification code set, the method further includes: Receive a verification code acquisition request sent by a user verification terminal; A second verification code set is extracted from a preset verification code database, and the second verification code set is returned to the user verification terminal, the user verification terminal obtains the target user's operation behavior for the second verification code set, and determines whether the target user passes the verification based on the operation behavior and the second verification code set.

8. A verification code set generating device, characterized in that: include: A video acquisition module, used to acquire a target video, wherein the target video is generated based on text material, picture material and a video generation model; An information extraction module, used to extract a plurality of target scene frames in the target video, and determine a scene frame display order, a scene frame switching rule and a verification code prompt information corresponding to each of the target scene frames; The set generation module is used to associate and combine the target scene frames based on the scene frame display order, scene frame switching rules and verification code prompt information corresponding to the target scene frames to generate a first verification code set.

9. A verification code set generating device, characterized in that: The verification code set generation device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the verification code set generation method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the verification code set generation method according to any one of claims 1 to 7 are implemented.

Images