Interactive video education evaluation method and device based on AIGC technology

Generating interactive network security education videos through AIGC technology solves the problems of insufficient interaction and difficult learning effects in existing educational methods, achieves high participation and personalized learning experience, and significantly improves users' security awareness level.

CN118945429AActive Publication Date: 2024-11-12GUANBAO NETWORK SECURITY TECHNOLOGY (GUANGDONG) CO LTD

Patent Information

Application Number
CN202410542976.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-05-01
Publication Date
2024-11-12
Estimated Expiration
2044-05-01

AI Technical Summary

Technical Problem

The existing cybersecurity education methods have problems such as insufficient interaction, limited contextual experience, and difficult to last for learning effects.

Method used

An interactive video education evaluation method based on AIGC technology is adopted to find event cases through user information and network security types, generate plot videos and obtain user decision scores, and dynamically adjust content to improve security awareness.

Benefits of technology

Through highly immersive experience and instant feedback, users' learning participation and security awareness are significantly improved, personalized learning paths are provided, and the persistence of educational effects is enhanced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure BDA0004821458740000111
    Figure BDA0004821458740000111
  • Figure BDA0004821458740000121
    Figure BDA0004821458740000121
  • Figure BDA0004821458740000151
    Figure BDA0004821458740000151
Patent Text Reader

Abstract

The invention relates to the technical field of video production, and provides an interactive video education evaluation method and device based on an AIGC technology. The method comprises the following steps: searching a current network security event case in a stored network security event case set and a corresponding teaching target based on user information of a current user and a network security type to be evaluated, and generating a plot video by using an AIGC technology; obtaining a target plot selection control triggered by a current user and a decision score for triggering the target plot selection control; searching a target network security event case meeting the plot information corresponding to the plot video; taking the target network security event case as a new current network security event case, thereby generating a plot video until the watching duration of the current user reaches a preset duration; and determining a safety awareness level value of the current user based on the decision score corresponding to the story video watched by the current user. According to the method, the learning effect and participation degree of the user are improved through interactive experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of video production technology, and more specifically, to an educational assessment method and device for interactive videos based on AIGC technology. Background Art

[0002] At present, cybersecurity education and training generally adopt traditional teaching methods, such as lectures, training courses, manual reading, etc., as well as some digital means, such as online tutorials, simulation tests, animation demonstrations, etc. Although these methods have improved users' cybersecurity awareness to a certain extent, they often have problems such as insufficient interactivity, limited situational experience, and difficulty in sustaining learning effects. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide an educational assessment method and device for interactive videos based on AIGC technology, so as to solve the above-mentioned problems existing in the prior art and improve the user's learning effect and participation through interactive experience.

[0004] In a first aspect, an educational evaluation method for interactive video based on AIGC technology is provided, which is applied in a network security education system. The method may include:

[0005] Based on the user information of the current user and the network security type to be evaluated, searching for the current network security incident case and the corresponding teaching objectives in the stored network security incident case collection; the network security incident case collection includes network security incident cases of different network security types;

[0006] Based on the current cybersecurity incident case and the corresponding teaching objectives, a plot video is generated using AIGC technology; the video frame at the end of the plot video includes a plot selection control of different plots that can be triggered;

[0007] Obtaining a target plot selection control triggered by the current user and a decision score for triggering the target plot selection control; the decision score is a score used to characterize the level of safety awareness determined based on the teaching objective corresponding to the plot video and the plot direction of the target plot selection control;

[0008] Based on the plot direction corresponding to the target plot selection control, find a target network security incident case in the network security incident case collection that satisfies the plot information corresponding to the plot video;

[0009] The target network security incident case is used as a new current network security incident case, and the process returns to the step of generating a plot video based on the current network security incident case and the corresponding teaching objectives until the viewing time of the current user reaches a preset time;

[0010] Based on the corresponding relationship between different configured decision scores and different security awareness level values ​​and the decision scores corresponding to the plot videos watched by the current user, the security awareness level value of the current user is determined.

[0011] In an optional implementation, the user information includes a user identifier and user attribute information;

[0012] Searching for any network security incident case and corresponding teaching objectives in the stored network security incident case collection that meets the network security type to be evaluated and the user information, including:

[0013] Finding a network security incident case that meets the network security type to be evaluated in the stored network security incident case collection;

[0014] If the stored mapping table of user identification and security awareness level value contains the user identification and the corresponding security awareness level value, then from the found network security incident cases, select the current network security incident case that meets the security awareness level value and the corresponding teaching goal;

[0015] If the user identifier is not included in the stored mapping table of user identifiers and security awareness level values, the initial security awareness level value of the current user is determined based on the user attribute information, and any network security incident case and corresponding teaching objectives that meet the initial security awareness level value are selected from the found network security incident cases.

[0016] In an optional implementation, the plot information includes a plot summary and character information;

[0017] Based on the current cybersecurity incident cases and corresponding teaching objectives, AIGC technology is used to generate plot videos, including:

[0018] Using the trained sequence generation model, the cybersecurity incident case and the corresponding teaching objectives are processed to obtain a plot summary and character information that meets the teaching objectives;

[0019] Using a preset AIGC technology, the plot outline and the character information are combined to generate a script text of the network security incident type;

[0020] The script text is processed using a preset conditional generative adversarial network to obtain a plot video corresponding to the script text.

[0021] In an optional implementation, a preset conditional generative adversarial network is used to process the script text to obtain a plot video corresponding to the script text, including:

[0022] The generator network in the conditional generative adversarial network generates a video frame sequence according to the input script text; the video information in each video frame includes scenes, characters and actions;

[0023] The discriminator network in the conditional generative adversarial network discriminates the scenes, characters and actions in each video frame from the scenes, characters and actions in the real world respectively;

[0024] If the discrimination result satisfies a preset error condition, the video frame sequence is determined as the plot video corresponding to the script text.

[0025] In an optional implementation, determining the security awareness level value of the current user based on the configured correspondence between different decision scores and different security awareness level values ​​and the decision scores corresponding to the plot videos watched by the current user includes:

[0026] If the continuous viewing time of the current user reaches a preset viewing time threshold, obtaining a decision score corresponding to the plot video watched by the current user;

[0027] Determine the decision score of the current user by summing the decision scores of the watched plot videos;

[0028] Determine the security awareness level value corresponding to the decision score of the current user based on the corresponding relationship between different configured decision scores and different security awareness level values;

[0029] The correspondence between the user identification of the current user and the corresponding security awareness level value is stored.

[0030] In an optional implementation, based on the plot direction corresponding to the target plot selection control, different target network security incident cases that meet the plot information corresponding to the plot video in the network security incident case set are found, including:

[0031] Using the established deep learning natural language processing model, the plot direction corresponding to the target plot selection control, the plot information of the previous plot video of the current user, and the character information are analyzed to obtain a plot analysis result;

[0032] Based on the scenario analysis result, different target network security incident cases satisfying the scenario information are found in the network security incident case collection.

[0033] In an optional implementation, the method further includes:

[0034] Acquire behavior data of the current user according to the operation behavior of the target plot selection control triggered by the current user;

[0035] The behavior data is deeply analyzed to obtain learning features of the current user watching the plot video.

[0036] Based on the learning features, a learning suggestion is provided to the current user.

[0037] In a second aspect, an interactive video education evaluation device based on AIGC technology is provided, which is applied in a network security education system, and the device may include:

[0038] A search unit, configured to search for a current network security incident case and a corresponding teaching objective in a stored network security incident case collection based on user information of a current user and a network security type to be evaluated; the network security incident case collection includes network security incident cases of different network security types;

[0039] A generating unit, configured to generate a plot video based on the current cybersecurity incident case and the corresponding teaching objectives by using AIGC technology; the video frame at the end moment of the plot video includes a plot selection control of different plots that can be triggered;

[0040] An acquisition unit, used to acquire a target plot selection control triggered by the current user and a decision score for triggering the target plot selection control; the decision score is a score used to characterize a safety awareness level determined based on the teaching objective corresponding to the plot video and the plot direction of the target plot selection control;

[0041] The search unit is further configured to search for a target network security incident case in the network security incident case set that satisfies the plot information corresponding to the plot video based on the plot direction corresponding to the target plot selection control;

[0042] A triggering unit is used to use the target network security incident case as a new current network security incident case to trigger the generation unit to execute: generating a plot video based on the current network security incident case and the corresponding teaching objectives until the viewing time of the current user reaches a preset time;

[0043] The determination unit is used to determine the security awareness level value of the current user based on the corresponding relationship between different configured decision scores and different security awareness level values ​​and the decision scores corresponding to the plot videos watched by the current user.

[0044] In a third aspect, an electronic device is provided, the electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0045] Memory, used to store computer programs;

[0046] The processor is used to implement any method step described in the first aspect when executing the program stored in the memory.

[0047] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0048] The educational evaluation method of interactive video based on AIGC technology provided in the present application can search for the current network security event case and the corresponding teaching goal in the stored network security event case collection based on the user information of the current user and the network security type to be evaluated; the network security event case collection includes network security event cases of different network security types; based on the current network security event case and the corresponding teaching goal, generate a plot video using AIGC technology; the video frame at the end time of the plot video includes a plot selection control of different plots that can be triggered; obtain the target plot selection control triggered by the current user and the decision score for triggering the target plot selection control; the decision score is a score used to characterize the level of security awareness determined based on the teaching goal corresponding to the plot video and the plot direction of the target plot selection control; based on the plot direction corresponding to the target plot selection control, find the target network security event case in the network security event case collection that meets the plot information corresponding to the plot video; use the target network security event case as the new current network security event case, and return to the execution step: based on the current network security event case and the corresponding teaching goal, generate a plot video until the viewing time of the current user reaches the preset time; determine the security awareness level value of the current user based on the corresponding relationship between the configured different decision scores and the different security awareness level values ​​and the decision score corresponding to the plot video watched by the current user. This method improves users' learning outcomes and engagement through interactive experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 A flowchart of an educational assessment method for interactive video based on AIGC technology provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the structure of an interactive video education assessment device based on AIGC technology provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] The educational assessment method of interactive video based on AIGC technology provided in the embodiment of the present application can be applied in a terminal or in a communication system for communication between a server and a terminal.

[0055] If applied in a terminal, it interacts with the user through the terminal interface, and the processor in the terminal executes the method steps of the interactive video educational assessment method based on AIGC technology; if applied in a communication system in which a server and a terminal communicate, it interacts with the user through the terminal interface, and the processor in the server executes the method steps of the interactive video educational assessment method based on AIGC technology. The specific division of work steps can be determined according to actual needs, and this application is not limited here.

[0056] The server may be a physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The terminal may be a user equipment (UE) such as a mobile phone, smart phone, laptop, digital broadcast receiver, personal digital assistant (PDA), tablet computer (PAD), handheld device, vehicle-mounted device, wearable device, computing device or other processing device connected to a wireless modem, mobile station (MS), mobile terminal, etc.

[0057] The specific implementation process of the interactive video education assessment method based on AIGC technology provided in this application covers multiple key steps and technical integration to ensure that the system can effectively generate and deliver high-quality, personalized and up-to-date cybersecurity awareness education content. Before executing this application, it is necessary to set up a basic education framework and case materials, including:

[0058] For setting the basic education framework:

[0059] When designing a cybersecurity awareness education system, the first task is to create a comprehensive basic education framework. This framework is based on in-depth educational theory research and practical application results to ensure that its content is scientific and practical. Specific steps include:

[0060] 1) Division of knowledge areas: Divide the content of cybersecurity awareness education into different knowledge modules, including password security, cyber fraud prevention, data privacy protection, malware protection, cyber law and ethics, etc.

[0061] 2) Hierarchical design: The knowledge points are arranged in a step-by-step manner from elementary to advanced levels to ensure that learners of different levels can find a starting point that suits them. For example, the basic knowledge section introduces basic network security concepts and risk identification methods; the intermediate stage discusses specific security operations and strategy formulation; and the advanced stage involves enterprise-level security management and emergency response strategies.

[0062] 3) Establishment of standards and specifications: Determine the standard teaching content and learning objectives for each knowledge point based on the latest domestic and international cybersecurity standards, regulatory requirements, and best practices.

[0063] 4) Interactivity and practicality: Design interactive learning activities and simulation exercises so that students can consolidate their knowledge in practice and improve their practical operation capabilities.

[0064] To obtain case information:

[0065] In order to enhance the teaching effect, it is necessary to collect a large number of real cybersecurity incidents as a case database, that is, to build a collection of cybersecurity incident cases. The cases can be used to:

[0066] 1) Situational Reconstruction: By restoring case scenarios, students can understand the true nature of cyber threats and improve their cognitive sensitivity to potential risks.

[0067] 2) Problem Analysis: Analyze the causes, evolution and consequences of the problems in the case, guide students to think about how to prevent similar situations from happening, and learn how to deal with them.

[0068] 3) AI algorithm training and content generation: Use these case data to train AI models, so that AI can intelligently generate targeted teaching content, test questions or simulation exercises, provide personalized services to each user, and further improve the educational experience and results.

[0069] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0070] Figure 1 A flowchart of an educational evaluation method for interactive video based on AIGC technology provided in an embodiment of the present application. Figure 1 As shown, the method may include:

[0071] Step S110: based on the user information of the current user and the network security type to be evaluated, searching for the current network security incident case and the corresponding teaching objectives in the stored network security incident case collection.

[0072] The cybersecurity incident case collection includes cybersecurity incident cases of different cybersecurity types. The attribute information of cybersecurity incident cases may include the attack type, attack method, attacker, victim, impact range, response measures and security education points of the incident, and user information may include user identification and user attribute information, such as age, occupation, etc. The cybersecurity incident case collection covers core knowledge points such as various threat types (such as phishing, malware, social engineering, data leakage, etc.), protective measures, regulations and standards, and best practices.

[0073] In one example, a collection of network security incident cases can be stored in the form of a knowledge graph, wherein the nodes in the knowledge graph represent network security incident cases, and the edges represent the association relationship between two nodes (i.e., network security incident cases). It can be understood that the length of the edge can be used to represent the degree of association between the two connected nodes. For example, the longer the edge, the greater the degree of association between the two nodes, and vice versa.

[0074] Specifically, the following is a brief introduction to the knowledge graph involved in this application:

[0075] 1. Entities (Nodes)

[0076] a. Incident case: Each specific cybersecurity incident is treated as a separate node, including basic information such as its name, number, time of occurrence, and the industry or enterprise involved.

[0077] b. Attack type: such as DDoS attack, APT attack, ransomware attack, data leakage, phishing attack, supply chain attack, etc.

[0078] c. Attack methods: such as vulnerability exploits, social engineering, malware, man-in-the-middle attacks, denial of service, and other specific implementation methods.

[0079] d. Victims: include affected enterprises, organizations, individuals or systems, as well as their industry attributes, geographical locations, etc.

[0080] e. Attackers: such as known hacker groups, state-sponsored attackers, independent criminals, etc., as well as their motivations and background information.

[0081] f. Scope of impact: including quantitative indicators such as the number of affected systems, amount of data affected, economic losses, and business interruption time.

[0082] g. Response measures: such as emergency response process, patch application, system reinforcement, legal accountability and other specific response actions and results.

[0083] 2. Edges

[0084] a. Event-Attack Type: Indicates what type of attack an event belongs to.

[0085] b. Event-Attack Methods: Indicates the specific attack methods used in the event.

[0086] c. Incident-Victim: Indicates the specific entity that was attacked in the incident.

[0087] d. Incident-Attacker: refers to the perpetrator behind the incident.

[0088] e. Incident-Impact Scope: Describe the specific losses and impacts caused by the incident.

[0089] f. Event-Response Measures: Record the response strategies and results adopted in response to the event.

[0090] g. Attack Type-Related Events: Link multiple events of the same type.

[0091] h. Attack Methods-Related Incidents: Displays other incidents using the same method.

[0092] i. Victims-Related Incidents: List all cybersecurity incidents encountered by the entity.

[0093] j. Attacker-related events: Aggregates all attacks initiated by the same attacker.

[0094] 3. Structure

[0095] a. Hub-and-spoke structure: With the incident case as the central node, the relationship with attack type, attack method, victim, attacker, impact scope and response measures radiates outward.

[0096] b. Hierarchy: Organized by event level (e.g., national, industry, enterprise), attack severity (e.g., high, medium, low), or timeline (e.g., annual, quarterly).

[0097] c. Theme Groups: Cluster related incident cases based on attack methods, industry fields, geographic regions, and other factors to form theme groups, making it easier to quickly locate cases of specific types or situations.

[0098] Returning to step S110, in a specific implementation, at least one network security incident case that meets the network security type to be evaluated is found in the stored network security incident case collection;

[0099] If the stored mapping table of user identification and security awareness level value contains the user identification and the corresponding security awareness level value, then from at least one network security incident case found, select a current network security incident case and a corresponding teaching objective that meets the security awareness level value;

[0100] If the mapping table of stored user identification and security awareness level does not contain the user identification (i.e., the current user is an initial user), the initial security awareness level value of the current user is determined based on the user attribute information. For example, the initial security awareness level value of a 6-year-old student is 1, and the initial security awareness level value of a 30-year-old student is 30. The higher the security awareness level value, the stronger the security awareness level. Afterwards, any network security incident case that meets the initial security awareness level value and the corresponding teaching objectives are selected from the network security incident cases found.

[0101] Step S120: Generate a plot video using AIGC technology based on the current network security incident case and the corresponding teaching objectives.

[0102] The video frame at the end moment of the plot video may include a plot selection control of different plots that can be triggered.

[0103] In the specific implementation, a trained sequence generation model (such as Transformer) is used to process the cybersecurity incident case and the corresponding teaching objectives to obtain plot information that meets the teaching objectives, wherein the plot information may include plot outlines and character information; character information may include the number of characters, character personality traits, task image and / or occupation. Specifically, a trained sequence generation model is used, and its encoder part is responsible for understanding the content of the cybersecurity incident case, and the decoder part generates the plot line, i.e., plot information, according to the teaching objectives and the content understood by the encoder.

[0104] Among them, the Transformer model of the self-attention mechanism is trained by maximizing the likelihood estimation (MLE) for a given set of cybersecurity incident cases and the teaching target vector of the corresponding cybersecurity incident cases:

[0105]

[0106] in, This means that we want to find the maximum value of the model parameter θ so that the following expression reaches the maximum value. (c i ,t i )~D represents the mean (expected value) of all context-target pairs sampled according to data distribution D. logP θ (t i ∣c i ,G) is the model's response to the target t under given parameters θ i In the context of i and the logarithm of the conditional probability under the global variable G.

[0107] The loss function is designed to minimize the difference between the teaching content and the teaching objectives reflected in the generated plot line, while ensuring the rationality and innovation of the plot line.

[0108] Then, the preset AIGC technology is used to combine the plot synopsis and character information to generate a script text of the cybersecurity incident type; specifically, the AI ​​algorithm model trained by AIGC technology can be used based on a collection of cybersecurity incident cases to combine the plot synopsis and character information to generate a script text containing dialogue, action description, emotional expression, and triggerable plot selection points (i.e., plot turning points) of different plots. The AI ​​algorithm model can learn from a large number of video script samples, understand the script structure, character dialogue, plot turning points, theme expression and other elements, and can generate a coherent and creative script text based on the given theme, plot setting, character setting and other inputs.

[0109] In one example, the plot generation algorithm: Based on models such as reinforcement learning (RL) or variational autoencoders (VAE), the automatic planning of plot development is realized. Such algorithms can explore possible story lines and generate reasonable plot twists and endings based on the set initial conditions and target states. Character dialogue generation: Use pre-trained dialogue generation models such as BERT and DialoGPT to simulate natural dialogues between characters, ensuring that the dialogue content is consistent with the character's personality and can promote the development of the plot.

[0110] Afterwards, the script text is processed using a preset conditional generative adversarial network to obtain a plot video corresponding to the script text. Specifically, the generator network in the conditional generative adversarial network generates a video frame sequence (i.e., video) based on the input script text; the video information in each video frame may include information such as scenes, characters, and actions; the discriminator network in the conditional generative adversarial network distinguishes the scenes, characters, and actions in each video frame from the scenes, characters, and actions in the real world; if the discrimination result meets the preset error condition, the video frame sequence is determined as the plot video corresponding to the script text. If the discrimination result does not meet the preset error condition, the parameters of the generator network are adjusted to obtain a discrimination result that meets the preset error condition.

[0111] Among them, when using conditional generative adversarial networks (ConditionalGANs, cGANs), the generator `G(z,c)` accepts a random noise vector `z` and conditional information (such as text description) `c` to generate visual content, while the discriminator `D(x,c)` determines whether the input visual content `x` is real. The loss function can be composed of two parts:

[0112]

[0113] In the formula, the value function V(D,G) is expressed as:

[0114]

[0115] In this expression: represents the expected log probability that the discriminator correctly identifies the real sample and gives a high score (probability close to 1) when x is sampled from the real data distribution pdata(x). It means that when z is sampled from the prior distribution p z (z), and then mapped to the latent space by the generator G and generated samples G(z,c), the discriminator correctly judges these generated samples as non-real samples and gives the expected logarithmic probability of low scores (probability close to 0).

[0116] The process of automatically generating video scripts, images, sounds and other elements through AIGC technology involves a series of complex technology stacks and key algorithm models. The following is a detailed description of the process of generating these elements:

[0117] 1. Automatic generation of video scripts

[0118] -Script outline generation: Input information such as video type, theme, basic plot framework, etc., and the AIGC system uses the plot generation algorithm to output the outline of the script, including key nodes such as major events, character relationships, conflict climax, etc.

[0119] -Detailed script writing: Based on the outline, the NLP model fills in the details according to the standard format of video scripts (such as scene descriptions, character actions, dialogues, etc.) to generate a complete script text.

[0120] -Dialogue optimization and review: The generated character dialogues may need to be further optimized through sentiment analysis, logical consistency checking, etc. to ensure that the dialogues are consistent with both the character settings and the overall logic of the script.

[0121] 2. Screen generation:

[0122] -Scene design: Based on the script description, use the CV model to automatically generate or select appropriate background materials to build scene layouts, including indoor, outdoor, urban, natural scenery, etc.

[0123] -Character modeling and animation: Generate or select the corresponding 3D model based on the character settings, and use the action generation model to give the character actions and expressions that match the plot.

[0124] -Lighting and special effects: Use AI technology to simulate real-world lighting effects and add necessary visual effects (such as smoke, fire, magic, etc.) to enhance the expressiveness of the picture.

[0125] - Rendering output: Integrate scenes, characters, lighting, special effects and other elements, and use high-performance rendering engines to generate high-definition, realistic picture sequences.

[0126] 3. Sound Generation:

[0127] -Convert dubbing script to speech: Input the character dialogue text in the script into the speech synthesis model to generate the corresponding character's voice clips.

[0128] - Music creation: Generate background music that matches the style and rhythm of the video based on the script's emotions, scene transitions, and other information, including theme songs, interludes, transition music, etc.

[0129] -Sound effect design: Generate various sound effects that match the picture content, such as footsteps, door opening and closing sounds, fighting sounds, environmental noise, etc.

[0130] - Audio mixing and post-processing: Mix, balance, reduce noise and perform other post-processing on voice, music, sound effects and other elements to ensure the final audio quality.

[0131] In summary, the key to automatically generating video scripts, images, and sounds through AIGC technology is to integrate multiple AI algorithms and models, such as NLP, CV, deep learning speech synthesis, AI composition, etc., to work together to achieve full-link automated creation from text description to audio-visual presentation. These technologies can not only greatly improve video production efficiency, but also provide creators with unlimited creative space, pushing the video industry into a new era of intelligence.

[0132] Step S130: Obtain the target plot selection control triggered by the current user and the decision score for triggering the target plot selection control.

[0133] Among them, the decision score is a score used to characterize the level of safety awareness, which is determined based on the teaching objectives corresponding to the plot video and the plot direction of the target plot selection control.

[0134] Currently, users can watch videos through dedicated interactive platforms (such as mobile applications, web pages, VR / AR devices, etc.) and interact through touch, gestures, voice commands, etc. The platform's built-in feedback system can receive the audience's choices, pass them to the AIGC backend for content generation, and synchronize the generated content back to the front-end for display in real time.

[0135] In one example, an algorithm for obtaining a decision score for triggering a target plot selection control includes:

[0136] Using reinforcement learning algorithms, such as Q-Learning or DeepQ-Network (DQN), the user's choice at each step is used as a state transfer, and the reward function can be designed based on indicators such as user learning outcomes and satisfaction, so that the system can continuously optimize the plot direction strategy and provide users with the best personalized experience. Algorithm details:

[0137] The state space `S` contains the user's current situational state information, the action space `A` includes different plot branches that the user can choose, the reward function `R(s,a,s')` measures the user's benefit from performing action `a` from state `s` to a new state `s'`, and the policy function `π(a|s)` describes the probability of selecting action `a` in state `s`.

[0138] The goal is to minimize the negative value of the long-term cumulative discounted reward:

[0139]

[0140] The state-action value of strategy π, or the strategy value function, where: J(π) is the expected value of the long-term cumulative reward for following strategy π. R(s t , a t ,s t+1 ) means that at time step t, action a is taken t After the state s t Transfer to state s t+1 Instant rewards when you win. represents the expected computation when selecting actions according to the policy π. It is the total reward discounted by time, that is, the rewards of all future time steps are accumulated from the initial moment, and the rewards of each future moment are multiplied by the decay coefficient γ (0≤γ<1), which makes the value of future rewards gradually decrease as they are farther away from the current time step.

[0141] Step S140: based on the plot direction corresponding to the target plot selection control, find a target network security incident case in the network security incident case collection that satisfies the plot information corresponding to the plot video.

[0142] In the specific implementation, the established deep learning natural language processing model is used to analyze the plot direction corresponding to the target plot selection control, the plot information and character information of the previous plot video of the current user, and obtain the plot analysis result;

[0143] Based on the plot analysis results, different target cybersecurity incident cases that meet the plot information (plot outline and character information) are found in the cybersecurity incident case collection.

[0144] Specifically, using the bidirectional Transformer model, the probability distribution of the model output can be obtained through the softmax function. Given an input sequence x and a generated partial word sequence y1, y2, ..., y j-1 , predict the word y at the jth position in the sequence j The conditional probability of can be calculated by the following formula:

[0145] P(y j |y1,y2,...,y j-1 , x)=softmax(Wh j +b)

[0146] Among them, h j The BERT model considers the entire input sequence x and the previously generated words y1, y2, ..., y j-1 After that, the hidden state vector is generated for the jth position. W is a trainable weight matrix used to map the hidden state vector to the prediction score of each word in the vocabulary. b is a trainable bias vector that is added to the prediction score of each word.

[0147] Further, the target network security incident case is used as a new current network security incident case, and the process returns to step S120: based on the current network security incident case and the corresponding teaching objectives, a plot video is generated using AIGC technology until the current user's viewing time reaches a preset time.

[0148] Step S150: Determine the security awareness level value of the current user based on the corresponding relationship between different configured decision scores and different security awareness level values ​​and the decision scores corresponding to the plot videos watched by the current user.

[0149] In a specific implementation, if the continuous viewing time of the current user reaches a preset viewing time threshold, the decision score corresponding to the plot video watched by the current user is obtained; the decision score of the plot videos watched is summed to determine the decision score of the current user; then, based on the correspondence between different configured decision scores and different security awareness level values, the security awareness level value corresponding to the decision score of the current user is determined, and the correspondence between the user identification of the current user and the corresponding security awareness level value is stored.

[0150] For the evaluation of user decision-making behavior, a binary or multi-classification problem can be constructed, using the cross entropy loss function:

[0151]

[0152] Where L represents the average sample loss (Loss), which is usually the objective function to be minimized when training a neural network. N is the number of samples. For each sample i, y i is the actual label, which is a binary variable. In multi-classification problems, it corresponds to the one-hot encoding of a single category, with a value of 0 or 1; in binary classification problems, it directly represents the category label (for example, 0 represents the negative class and 1 represents the positive class). i is the probability of belonging to the positive class predicted by the model. For multi-classification problems, after applying the softmax function, for a certain category of the i-th sample, its corresponding p i is the predicted probability of the class. log(p i ) is when y i =1, while log(1-p i ) is when y i = 0. V is the number of categories, y ij is the label of sample i corresponding to the true category j, also using one-hot encoding, only one dimension is 1, and the others are 0, p ij is the probability that the model predicts that sample i belongs to category j, given by the softmax function. If the multi-classification of a single sample is considered, the cross entropy loss between the probability vector output by the softmax function and the corresponding true label will ensure that an effective probability distribution is learned during the model optimization process, so that the probability of the correct category is as close to 1 as possible, while the probability of other categories is as close to 0 as possible.

[0153] In some embodiments, AIGC technology can be used to monitor and analyze the decision-making behavior of users during the interaction process, provide detailed safety suggestions and objective evaluation scores in a timely manner, and dynamically adjust the training difficulty and content according to the user's learning progress and performance. Specifically, according to the operation behavior of the target plot selection control triggered by the current user, the current user's behavior data, such as selection preferences, reaction speed, problem-solving methods, etc., are obtained; the behavior data is deeply analyzed to obtain the learning characteristics of the current user watching the plot video, such as learning mode, strengths and weaknesses, interest tendencies and other characteristics. Among them, the operation behavior can include but is not limited to the user's click selection, dwell time, browsing order, strategy and time taken to solve tasks or puzzles, number of wrong attempts and other detailed information. These behavior data can reflect the user's learning habits, understanding ability and knowledge blind spots, and are the basis of personalized teaching.

[0154] Afterwards, based on the learning characteristics, learning suggestions are provided to the current user. For example, for knowledge points that the user has not yet mastered, the system will recommend corresponding intensive exercises or provide more case analysis; if it is found that the user responds slowly to a certain type of problem, the system can push targeted tutoring materials or provide clearer guidance.

[0155] That is to say, based on the results of user behavior analysis, the personalized content generation module uses AIGC technology to adaptively generate teaching content, prompt information, character dialogue and other elements that match the user's characteristics. It can customize personalized learning paths and interactive scenarios based on factors such as the user's knowledge level, interest preferences, and learning style, ensuring that each viewer can get the most suitable educational experience for themselves. For example, more detailed explanations and examples may be provided for beginners, while users with a certain foundation may focus on the drills of advanced threat identification and defense strategies.

[0156] Furthermore, when users make choices or perform operations, the system can immediately give feedback - real-time feedback (Real-time Feedback), indicating whether their decisions are appropriate, explaining the logic behind the correct answer, or providing directions for improvement. Feedback can also adjust the difficulty based on the user's specific performance to ensure that users can learn effectively at the edge of their comfort zone, neither too simple to cause boredom nor too difficult to cause frustration. Afterwards, with the continuous accumulation and analysis and update of user behavior data, the system can dynamically adjust the user's learning path to make it more in line with personal needs and development stages, realizing the transformation of education from "one size fits all" to "one person, one policy".

[0157] In some embodiments, an online learning algorithm is used to update the model parameters when new network security information appears, so that the generated video material always reflects the latest security situation and prevention strategy. Algorithm details: Online learning update mechanism: Whenever new network security threat intelligence or defense strategy data Dnew appears, the model parameters θ will be updated through online gradient descent or other online optimization algorithms:

[0158]

[0159] Among them, η is the learning rate and L is the loss function, which is used to measure how well the model fits the new data.

[0160] In some embodiments, as the cybersecurity threat situation changes and technology develops, new threat types can be obtained in real time to determine new cybersecurity incident cases, thereby updating the cybersecurity incident case collection (i.e., knowledge graph) to reflect the latest threat types, protection methods, and industry trends. The AIGC model can quickly absorb new knowledge inputs, generate video content that keeps pace with the times, and maintain the timeliness of education.

[0161] User experience optimization:

[0162] The interactive video production system has the following significant advantages over traditional cybersecurity education materials or videos in terms of improving user engagement, enhancing educational effects, and personalizing learning paths:

[0163] 1. Highly immersive experience:

[0164] Interactive videos build realistic virtual environments and role interactions, allowing users to immerse themselves in actual cyber threat scenarios, experience and respond to various cyber security incidents, and greatly enhance the sense of involvement and reality of learning. This immersive experience not only increases users' enthusiasm for participation, but also helps deepen their understanding and memory of cyber security issues.

[0165] 2. Instant feedback and reinforcement learning:

[0166] The user's decisions and actions in the video will receive immediate system feedback, whether it is positive recognition or negative consequences, which can be presented instantly, forming an efficient teaching model of "learning by doing". This instant feedback mechanism helps users quickly correct wrong ideas, consolidate correct practices, and effectively improve learning efficiency.

[0167] 3. Independent exploration and active learning:

[0168] Interactive videos allow users to advance the plot according to their own judgment and choices. This process of autonomous exploration stimulates users' willingness to learn. Users are no longer passive recipients of information, but actively participate in the story, solve problems, and avoid risks, thereby enhancing their initiative and enthusiasm in learning.

[0169] 4. Personalized learning path:

[0170] The system can dynamically adjust the plot direction, content difficulty and teaching methods based on the results of user behavior analysis to provide a personalized learning experience. Each user can obtain content that matches their knowledge level, interest preferences and learning style, avoiding the incompatibility problem caused by "one-size-fits-all" education and ensuring that the educational content is more targeted and effective.

[0171] 5. Diversified interactions and in-depth participation:

[0172] In addition to plot selection, the system also supports multimodal interaction, such as voice Q&A, simulated operation, team collaboration, etc., further enriching the user's participation. The diversified interactive methods not only meet the needs of different learning styles, but also promote in-depth thinking and practical application, which helps to cultivate users' comprehensive network security skills.

[0173] 6. Continuous updating and adaptability:

[0174] Thanks to the use of AIGC technology, interactive videos can quickly respond to the latest threat trends and technological developments in the field of cybersecurity, update educational content in real time, and maintain the timeliness and relevance of educational materials. At the same time, the system can continuously optimize teaching strategies based on the learning effect data of user groups to ensure that educational content always maintains the best educational effect.

[0175] 7. Gamification elements and incentive mechanisms:

[0176] Interactive videos often incorporate gamification elements, such as achievement systems, point rewards, and leaderboards, using the power of competition and cooperation to stimulate users' interest in learning and lasting participation. These incentive mechanisms not only increase the fun of learning, but also encourage users to actively repeat exercises and challenge more difficult tasks, thereby deepening their learning outcomes.

[0177] In summary, the interactive video production system, with its characteristics of high immersion, instant feedback, autonomous exploration, personalized paths, multi-faceted interactions, continuous updates, and gamification incentives, has significantly improved user engagement, enhanced the effectiveness of cybersecurity education, and provided a highly personalized learning experience that is difficult to match with traditional educational materials or videos.

[0178] Application scenarios:

[0179] 1. Enterprise staff training:

[0180] Scenario description: A large multinational company uses an interactive video production system for cybersecurity awareness based on AIGC technology in its annual security training program. The system automatically generates customized interactive video scripts for employees in different departments and positions, covering topics ranging from basic password management and anti-phishing emails to advanced cloud service security and supply chain risk management. Employees log in to the company's internal training platform and select video modules related to their work for study.

[0181] 2. School education:

[0182] Scenario description: A regional education bureau cooperated with us to integrate the interactive video production system into the K-12 information technology curriculum as an important part of cybersecurity education. Teachers guided students to collectively watch and participate in interactive videos in class. The video content covered common cybersecurity issues for teenagers, such as personal information protection, social network security, and cyberbullying prevention. In addition, students can also conduct independent review and extended learning through the campus learning platform after class.

[0183] 3. Publicity:

[0184] Scenario description: Cybersecurity regulatory authorities and public welfare organizations jointly organize the "National Cybersecurity Month" event. One of the core measures is to launch a series of cybersecurity micro videos produced by an interactive video production system, which are widely disseminated through social media, video websites, outdoor electronic screens and other channels. The micro videos are based on stories close to people's lives, such as online shopping traps, telecommunications fraud, and home smart device security, guiding the audience to make choices during the viewing process, affecting the direction of the plot, and ultimately revealing the correct security behavior.

[0185] 4. Cybersecurity sandbox drill

[0186] Scenario description: The operators of critical information infrastructure have carefully created a cybersecurity sandbox exercise that combines education, actual combat and entertainment elements. The activity uses an interactive video education and assessment system to build a highly simulated network environment, covering multiple architectures such as corporate intranets, cloud services and IoT devices, allowing both attackers and defenders to immerse themselves in various types of network threat responses. The defenders face the impact of DDoS attacks, keenly identify and properly handle phishing emails, and accurately detect and effectively block malware intrusions. At the event site, the realistic visual and sound effects design brings the audience into a tense and fierce actual combat scene, as if they were on a real network battlefield. The system tracks and records the attack and defense dynamics in real time, accurately evaluates the network security attack and defense skills and comprehensive strength of both parties, and gives immediate evaluation feedback, cleverly integrating serious education assessments into an interesting interactive experience.

[0187] Corresponding to the above method, the embodiment of the present application also provides an educational assessment device for interactive video based on AIGC technology, such as Figure 2 As shown, the device comprises:

[0188] A search unit 210 is used to search for a current network security incident case and a corresponding teaching objective in a stored network security incident case collection based on user information of a current user and the network security type to be evaluated; the network security incident case collection includes network security incident cases of different network security types;

[0189] A generating unit 220 is used to generate a plot video based on the current network security incident case and the corresponding teaching objectives by using AIGC technology; the video frame at the end moment of the plot video includes a plot selection control of different plots that can be triggered;

[0190] An acquisition unit 230 is used to acquire a target plot selection control triggered by the current user and a decision score for triggering the target plot selection control; the decision score is a score used to characterize a safety awareness level determined based on the teaching objective corresponding to the plot video and the plot direction of the target plot selection control;

[0191] The search unit 210 is further configured to search for a target network security incident case in the network security incident case set that satisfies the plot information corresponding to the plot video based on the plot direction corresponding to the target plot selection control;

[0192] The trigger unit 240 is used to use the target network security incident case as a new current network security incident case to trigger the generation unit to execute: based on the current network security incident case and the corresponding teaching objectives, generate a plot video until the viewing time of the current user reaches a preset time;

[0193] The determination unit 250 is used to determine the security awareness level value of the current user based on the configured correspondence between different decision scores and different security awareness level values ​​and the decision scores corresponding to the plot videos watched by the current user.

[0194] The functions of each functional unit of the interactive video educational assessment device based on AIGC technology provided in the above-mentioned embodiment of the present application can be realized through the above-mentioned method steps. Therefore, the specific working process and beneficial effects of each unit in the interactive video educational assessment device based on AIGC technology provided in the embodiment of the present application will not be repeated here.

[0195] The present application also provides an electronic device, such as Figure 3As shown, it includes a processor 310 , a communication interface 320 , a memory 330 and a communication bus 340 , wherein the processor 310 , the communication interface 320 , and the memory 330 communicate with each other via the communication bus 340 .

[0196] Memory 330, for storing computer programs;

[0197] The processor 310 is used to execute the program stored in the memory 330 to implement the following steps:

[0198] Based on the user information of the current user and the network security type to be evaluated, searching for the current network security incident case and the corresponding teaching objectives in the stored network security incident case collection; the network security incident case collection includes network security incident cases of different network security types;

[0199] Based on the current cybersecurity incident case and the corresponding teaching objectives, a plot video is generated using AIGC technology; the video frame at the end of the plot video includes a plot selection control of different plots that can be triggered;

[0200] Obtaining a target plot selection control triggered by the current user and a decision score for triggering the target plot selection control; the decision score is a score used to characterize the level of safety awareness determined based on the teaching objective corresponding to the plot video and the plot direction of the target plot selection control;

[0201] Based on the plot direction corresponding to the target plot selection control, find a target network security incident case in the network security incident case collection that satisfies the plot information corresponding to the plot video;

[0202] The target network security incident case is used as a new current network security incident case, and the process returns to the step of generating a plot video based on the current network security incident case and the corresponding teaching objectives until the viewing time of the current user reaches a preset time;

[0203] Based on the corresponding relationship between different configured decision scores and different security awareness level values ​​and the decision scores corresponding to the plot videos watched by the current user, the security awareness level value of the current user is determined.

[0204] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0205] The communication interface is used for communication between the above electronic device and other devices.

[0206] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0207] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0208] The implementation methods and beneficial effects of the components of the electronic device in the above embodiments to solve the problems can be seen in Figure 1 The various steps in the illustrated embodiment are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0209] In another embodiment provided in the present application, a computer-readable storage medium is also provided, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer executes the educational assessment method of interactive video based on AIGC technology as described in any of the above embodiments.

[0210] In another embodiment provided in the present application, a computer program product comprising instructions is also provided, which, when executed on a computer, enables the computer to execute the educational assessment method for interactive video based on AIGC technology as described in any of the above embodiments.

[0211] Those skilled in the art will appreciate that the embodiments in the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt a complete hardware embodiment, a complete software embodiment, or a form of an embodiment combining software and hardware. Moreover, the present application may adopt a form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0212] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0213] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0214] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0215] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0216] Obviously, those skilled in the art can make various changes and modifications to the embodiments in the present application without departing from the spirit and scope of the embodiments in the present application. Thus, if these modifications and variations of the embodiments in the present application fall within the scope of the claims and their equivalents in the embodiments of the present application, the embodiments of the present application are also intended to include these modifications and variations.

Claims

1. An educational evaluation method for interactive videos based on AIGC technology, It is characterized in that Applied in a network security education system, the method comprises: Based on the user information of the current user and the network security type to be evaluated, searching for the current network security incident case and the corresponding teaching objectives in the stored network security incident case collection; the network security incident case collection includes network security incident cases of different network security types; Based on the current cybersecurity incident case and the corresponding teaching objectives, a plot video is generated using AIGC technology; the video frame at the end of the plot video includes a plot selection control of different plots that can be triggered; Obtaining a target plot selection control triggered by the current user and a decision score for triggering the target plot selection control; the decision score is a score used to characterize the level of safety awareness determined based on the teaching objective corresponding to the plot video and the plot direction of the target plot selection control; Based on the plot direction corresponding to the target plot selection control, find a target network security incident case in the network security incident case collection that satisfies the plot information corresponding to the plot video; The target network security incident case is used as a new current network security incident case, and the process returns to the step of generating a plot video based on the current network security incident case and the corresponding teaching objectives until the viewing time of the current user reaches a preset time; Based on the corresponding relationship between different configured decision scores and different security awareness level values ​​and the decision scores corresponding to the plot videos watched by the current user, the security awareness level value of the current user is determined.

2. The method according to claim 1, It is characterized in that The user information includes user identification and user attribute information; Searching for any network security incident case and corresponding teaching objectives in the stored network security incident case collection that meets the network security type to be evaluated and the user information, including: Finding a network security incident case that meets the network security type to be evaluated in the stored network security incident case collection; If the stored mapping table of user identification and security awareness level value contains the user identification and the corresponding security awareness level value, then from the found network security incident cases, select the current network security incident case that meets the security awareness level value and the corresponding teaching goal; If the user identifier is not included in the stored mapping table of user identifiers and security awareness level values, the initial security awareness level value of the current user is determined based on the user attribute information, and any network security incident case and corresponding teaching objectives that meet the initial security awareness level value are selected from the found network security incident cases.

3. The method according to claim 1, It is characterized in that The plot information includes plot summary and character information; Based on the current cybersecurity incident cases and corresponding teaching objectives, AIGC technology is used to generate plot videos, including: Using the trained sequence generation model, the cybersecurity incident case and the corresponding teaching objectives are processed to obtain a plot summary and character information that meets the teaching objectives; Using a preset AIGC technology, the plot outline and the character information are combined to generate a script text of the network security incident type; The script text is processed using a preset conditional generative adversarial network to obtain a plot video corresponding to the script text.

4. The method according to claim 3, It is characterized in that The script text is processed using a preset conditional generative adversarial network to obtain a plot video corresponding to the script text, including: The generator network in the conditional generative adversarial network generates a video frame sequence according to the input script text; the video information in each video frame includes scenes, characters and actions; The discriminator network in the conditional generative adversarial network discriminates the scenes, characters and actions in each video frame from the scenes, characters and actions in the real world respectively; If the judgment result satisfies the preset error condition, the video frame sequence is determined as the plot video corresponding to the script text.

5. The method according to claim 1, It is characterized in that Determining the security awareness level value of the current user based on the corresponding relationship between different configured decision scores and different security awareness level values ​​and the decision scores corresponding to the plot videos watched by the current user includes: If the continuous viewing time of the current user reaches a preset viewing time threshold, obtaining a decision score corresponding to the plot video watched by the current user; Determine the decision score of the current user by summing the decision scores of the watched plot videos; Determine the security awareness level value corresponding to the decision score of the current user based on the corresponding relationship between different configured decision scores and different security awareness level values; The correspondence between the user identification of the current user and the corresponding security awareness level value is stored.

6. The method according to claim 3, It is characterized in that Based on the plot direction corresponding to the target plot selection control, different target network security incident cases that meet the plot information corresponding to the plot video in the network security incident case set are found, including: Using the established deep learning natural language processing model, the plot direction corresponding to the target plot selection control, the plot information of the previous plot video of the current user, and the character information are analyzed to obtain a plot analysis result; Based on the scenario analysis result, different target network security incident cases satisfying the scenario information are found in the network security incident case collection.

7. The method according to claim 1, It is characterized in that The method further comprises: Acquire behavior data of the current user according to the operation behavior of the target plot selection control triggered by the current user; Performing in-depth analysis on the behavior data to obtain learning features of the current user watching the plot video; Based on the learning features, a learning suggestion is provided to the current user.

8. An interactive video education evaluation device based on AIGC technology, applied in the network security education system, It is characterized in that The device comprises: A search unit, configured to search for a current network security incident case and a corresponding teaching objective in a stored network security incident case collection based on user information of a current user and a network security type to be evaluated; the network security incident case collection includes network security incident cases of different network security types; A generating unit, configured to generate a plot video based on the current cybersecurity incident case and the corresponding teaching objectives by using AIGC technology; the video frame at the end moment of the plot video includes a plot selection control of different plots that can be triggered; An acquisition unit, used to acquire a target plot selection control triggered by the current user and a decision score for triggering the target plot selection control; the decision score is a score used to characterize a safety awareness level determined based on the teaching objective corresponding to the plot video and the plot direction of the target plot selection control; The search unit is further configured to search for a target network security incident case in the network security incident case set that satisfies the plot information corresponding to the plot video based on the plot direction corresponding to the target plot selection control; A triggering unit is used to use the target network security incident case as a new current network security incident case to trigger the generation unit to execute: generating a plot video based on the current network security incident case and the corresponding teaching objectives until the viewing time of the current user reaches a preset time; The determination unit is used to determine the security awareness level value of the current user based on the corresponding relationship between different configured decision scores and different security awareness level values ​​and the decision scores corresponding to the plot videos watched by the current user.

9. An electronic device, It is characterized in that The electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, for implementing any of the methods described in claims 1-7 when executing a program stored in a memory.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Interactive video generation method and device

    CN108124187A

  • Interaction method and device of interactive video playing

    CN108156523A

  • Interactive video generation method and device based on artificial intelligence, equipment and medium

    CN110708595A

  • Video synthesis method, client and system

    CN112188117A

  • Plot interaction method and device and electronic equipment

    CN112957730A

Cited By

  • Telecommunication network fraud case investigation training system and method based on virtual reality

    CN120356375A

  • Teaching plan content generation method based on generative adversarial network and hierarchical teaching target analysis

    CN121071193A

  • Network security operation behavior knowledge graph construction method and device

    CN122053192A