Digital artwork intelligent copyright protection and authorization management system and method

Abstract

The invention provides an intelligent copyright protection and authorization management method for digital artworks, and aims to overcome the defects of a traditional copyright protection method in the aspects of real-time monitoring and dynamic management. According to the method, fine behavior data of a user are recorded in real time, the data are grouped, cleaned and encrypted, the behavior intention of the user is analyzed by utilizing a machine learning algorithm, and corresponding authorization operation is automatically executed in combination with a preset strategy rule engine. The system can accurately identify high-risk behaviors and carry out encryption protection on high-risk data, so that the security of the data is ensured. Meanwhile, based on deep analysis of user behaviors, the system can flexibly adjust an authorization scheme, and the accuracy and response speed of copyright protection are improved. Through innovative data processing and behavior intention analysis technologies, the copyright protection and authorization management efficiency of the digital artwork is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of management systems, and in particular, to an intelligent copyright protection and authorization management system for digital artworks. Background Art

[0002] With the rapid development of information technology and the Internet, digital artworks, as an important part of the cultural and creative industries, have witnessed a significant expansion in their creation, dissemination, and trading scale. However, the easy replicability and easy transmissibility of digital artworks have also brought severe challenges to copyright protection. Traditional copyright protection methods mainly rely on means such as digital watermarking, encryption technology, and copyright registration to prevent unauthorized copying and dissemination. However, with the progress of technology, hacker attacks and copyright infringement behaviors have become increasingly complex and concealed, and traditional methods have shown obvious deficiencies in real-time monitoring and dynamic management. In addition, most existing authorization management systems are based on static rules, lacking in-depth analysis of user behavior and real-time response capabilities, and it is difficult to achieve precise copyright protection and authorization management. In recent years, with the application of big data and machine learning technologies, researchers have begun to explore improving the intelligent level of copyright protection by analyzing users' subtle behavior data. However, existing research mainly focuses on simple analysis of behavior data and fails to fully combine data grouping, cleaning, and encryption processing, resulting in significant deficiencies in the security and accuracy of the system.

[0003] When dealing with the copyright protection and authorization management of digital artworks, the existing technologies mainly face the following deficiencies: First, there is a lack of real-time recording and in-depth analysis of users' subtle interaction behaviors, and the actual usage intentions of users cannot be accurately identified, resulting in inaccurate implementation of authorization policies; Second, during the data processing process, the grouping, cleaning, and encryption of behavior data lack systematic and secure guarantees, easily leading to risks of data leakage and abuse; Third, most existing authorization management systems rely on preset static rules, unable to dynamically respond to changes in user behavior, lacking flexibility and adaptability, and it is difficult to meet the complex and changing copyright protection requirements. Summary of the Invention

[0004] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title. However, such simplifications or omissions shall not be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention provides an intelligent copyright protection and authorization management method for digital artworks, including the following technical steps:

[0006] Real-time record the subtle behavior data formed by interaction behaviors, and at the same time perform grouping, cleaning, and encryption processing on the subtle behavior data;

[0007] Extract features from the encrypted high-risk grouped data and normal grouped data respectively, and automatically analyze the behavior intention results through machine learning algorithms;

[0008] According to the behavior intention results of the user, check against the preset policy rule engine, and select an authorization plan in the policy library to perform an operation.

[0009] As a preferred technical solution of a digital art intelligent copyright protection and authorization management method, the fine-grained behavior data includes mouse movement trajectory, number of local magnifications, residence time in a specific area, frequency of invoking the keyboard screenshot shortcut key, and browser focus switching.

[0010] As a preferred technical solution of a digital art intelligent copyright protection and authorization management method, the specific steps of grouping the fine-grained behavior data include:

[0011] Group the fine-grained behavior data recorded in real time within a fixed time window, and uniformly classify all the fine-grained behavior data within this time window into the same basic group;

[0012] Divide the data in the basic group into multiple subgroups according to the behavior type, and perform dynamic grouping by combining behavior intention recognition and focus status. Compare the behavior characteristics in the dynamic grouping with the set behavior threshold, and mark the dynamic grouping as a high-risk group or a normal group.

[0013] As a preferred technical solution of a digital art intelligent copyright protection and authorization management method, the specific steps of encrypting the fine-grained behavior data include:

[0014] Perform encryption processing on the high-risk group, dynamically allocate and regularly rotate the encryption key through a key management system, store the encrypted data in slices in a distributed storage system, also encrypt and protect the index information, and adopt the TLS1.3 security protocol during data transmission.

[0015] As a preferred technical solution of a digital art intelligent copyright protection and authorization management method, the specific steps of respectively extracting features from the decrypted high-risk grouped data and normal grouped data and automatically analyzing the behavior intention results include the following:

[0016] Extract key behavior characteristics from the decrypted high-risk grouped data and normal grouped data, and construct a complete behavior feature vector. The key behavior characteristics include mouse trajectory density, number of local magnifications, proportion of residence time in a specific area, screenshot frequency, and focus switching frequency;

[0017] Normalize the extracted features, screen out highly correlated features through principal component analysis, and statistically enhance the time series of behavioral features through a sliding window;

[0018] Based on machine learning algorithms, analyze the behavioral intentions of the constructed feature vectors, use a random forest model for non-linear classification, and combine LSTM to capture the characteristics of time series, classifying user behavioral intentions into three categories: in-depth appreciation, general browsing, or potential infringement.

[0019] As a preferred technical solution of an intelligent copyright protection and authorization management method for digital artworks,

[0020] Input the behavioral intention result into a preset policy rule engine. The policy rule engine contains a structured rule library, and each rule consists of a behavioral intention category, a policy priority, and a corresponding authorization plan;

[0021] The policy rule engine matches according to the input behavioral intention in the order of rule priorities, and selects the authorization plan that best matches the current behavioral intention.

[0022] On the other hand, the present invention provides an intelligent copyright protection and authorization management system for digital artworks, including:

[0023] A data recording and processing module, configured to record in real time the subtle behavioral data formed by interaction behaviors, and at the same time perform grouping, cleaning, and encryption processing on the subtle behavioral data;

[0024] A feature extraction and behavioral intention analysis module, configured to extract features from the encrypted subtle behavioral data and automatically analyze the behavioral intention result through machine learning algorithms;

[0025] An authorization management and execution module, configured to select an authorization plan from a policy library for execution operations according to the user's behavioral intention result in contrast to a preset policy rule engine.

[0026] The present invention provides an intelligent copyright protection and authorization management system and method for digital artworks. By combining the user's subtle behavioral data and machine learning algorithms, it can achieve real-time and accurate copyright protection and authorization management. Through dynamic grouping and encryption processing, the system can effectively improve data security and prevent data leakage and abuse. At the same time, based on user behavioral intention analysis, the system can flexibly select the most suitable authorization plan to achieve in-depth analysis and real-time response to user behaviors. This system not only improves the efficiency and security of copyright protection, but also provides a more intelligent management means for the creation, dissemination, and trading of digital artworks. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings. Among them:

[0028] Figure 1 It is the overall flowchart of the passenger comprehensive service method based on an integrated transportation hub according to an embodiment of the present invention; Specific embodiments

[0029] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific embodiments of the present invention in detail with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0031] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that mutually excludes other embodiments.

[0032] Embodiment 1

[0033] Refer to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a method for intelligent copyright protection and authorization management of digital artworks, including the following technical steps:

[0034] S100. Record the minute behavior data formed by the interaction behavior in real time, and at the same time perform grouping, cleaning, and encryption processing on the minute behavior data; wherein, the minute behavior data includes the mouse movement trajectory M(i), the local magnification times Z(i), the residence time T(i) in a specific area, the keyboard screenshot shortcut key call frequency K(i), and the browser focus switching F(i);

[0035] Further, the minute behavior data recorded in real time is grouped within a fixed time window, and all the minute behavior data within this time window is uniformly classified into the same basic group;

[0036] Specifically, the mathematical expression of the basic group is:

[0037] G(i) = {M(i), Z(i), T(i), K(i), F(i)}

[0038] where G(i) is the basic group data set of the i-th time window; M(i) is the mouse movement trajectory data set of the i-th time window; Z(i) is the data set of the number of local magnification operations in the i-th time window; G(i) is the data set of the residence time in a specific area within the k-th time window W k ; T(i) is the data set of the frequency of invoking the keyboard screenshot shortcut key in the i-th time window; F(i) is the behavior data set of the browser focus switching in the i-th time window.

[0039] Furthermore, the data within the basic group is divided into multiple subgroups according to the behavior type, and dynamic grouping is performed by combining behavior intention recognition and focus status. The behavior characteristics in the dynamic grouping are compared with the set behavior threshold, and the dynamic grouping is marked as a high-risk group or an ordinary group;

[0040] Specifically, the elements in G(i) are divided to obtain the corresponding subgroups

[0041]

[0042] where Type(x) is the defined type mapping function, and m represents the corresponding behavior type;

[0043] The dynamic grouping formula can be expressed as:

[0044]

[0045] where Ψ(·) represents a dynamic grouping function, Intention(Wi) represents the recognition result of the user operation behavior intention within the i-th time window Wi, and FocusStatus(Wi) represents the focus status information within the i-th time window.

[0046] To evaluate the risk level of the dynamic grouping , a risk scoring function is introduced:

[0047]

[0048] where represents the set of behavior types included in this dynamic grouping, ωm represents the weights assigned to m types of behaviors, represents the calculation of the comprehensive evaluation function of "behavior intention" and "focus state information" related to state W i related to the "behavior intention" and "focus state information".

[0049] By setting a security threshold Θ to distinguish high-risk behaviors from normal behaviors:

[0050]

[0051] When the risk scoring function exceeds or equals this threshold, mark this dynamic grouping as a "high-risk grouping", otherwise mark it as a "normal grouping".

[0052] It should be noted that by subdividing the basic grouping into multiple subgroups according to the behavior type, data redundancy can be effectively reduced, ensuring that the behavior data of each subgroup has a high degree of correlation. In this way, the system can better capture the characteristics of each detailed behavior, such as abnormalities in the mouse trajectory or frequent screenshot behaviors. Secondly, combining behavior intention recognition and focus state for dynamic grouping further improves the depth and accuracy of behavior analysis. By identifying the user's actual operation intention (such as whether it is a sensitive information interception behavior) and focus state (such as whether it is in the active window), the data grouping can be dynamically adjusted to avoid misjudgment or missed judgment. Finally, by comparing with the set behavior threshold and features, potential high-risk behaviors can be effectively identified. For example, frequent screenshot behaviors and long-term stays in specific areas may indicate abnormal or malicious behaviors when the focus state is active. Through the combination of this series of mechanisms, the system can monitor, analyze and accurately classify high-risk and normal behaviors in real time, thus providing more reliable data support for security protection and risk control.

[0053] Furthermore, perform encryption processing on the high-risk grouping, dynamically allocate and regularly rotate the encryption key through the key management system, store the encrypted data in shards in the distributed storage system, also encrypt and protect the index information, and use the TLS1.3 security protocol during data transmission.

[0054] Specifically, the encryption process for the high-risk grouping can be expressed as:

[0055]

[0056] Among them, C high represents the encrypted high-risk grouping data, represents the kth high-risk group within the ith time window, K high represents the encryption key;

[0057] It should be noted that encrypting high-risk groups while not encrypting ordinary groups can optimize system performance and resource utilization while ensuring security. By encrypting high-risk data, even if this data is illegally obtained, it cannot be easily decrypted, thereby effectively preventing data leakage and abuse, and reducing potential security risks and legal liabilities. For the data of ordinary groups, due to its lower sensitivity, encryption operations can be reduced, thereby improving the system processing speed and resource utilization efficiency. This hierarchical encryption strategy can ensure that high-risk data is protected as necessary, while avoiding the computational overhead brought by unnecessary encryption of low-risk data, thereby improving the overall system operation efficiency and response speed. Combining with a key management system to dynamically allocate and regularly rotate encryption keys can significantly enhance data security and management efficiency. Through the dynamic allocation and rotation of keys, the potential risks brought by using the same key for a long time are avoided, ensuring the continuous security of the encryption process. At the same time, storing the encrypted data in fragments in a distributed storage system not only improves data redundancy and availability, but also enhances the fault tolerance of the system. Even if a certain node is attacked, other nodes can still ensure data integrity and accessibility. In addition, encrypting and protecting index information prevents attackers from inferring or leaking the location or structure of encrypted data by accessing index information, further enhancing data privacy. Finally, adopting the TLS1.3 security protocol during data transmission ensures the confidentiality and integrity of data during transmission, preventing man-in-the-middle attacks and data leakage. This series of measures effectively improves the data security protection level, ensures the protection of sensitive information, and also improves the system's availability, reliability, and compliance.

[0058] S200. Respectively extract features from the decrypted high-risk group data and ordinary group data, and automatically analyze the behavior intention results through machine learning algorithms;

[0059] Furthermore, the specific steps of respectively extracting features from the decrypted high-risk group data and ordinary group data and automatically analyzing the behavior intention results include the following:

[0060] Extract key behavior features from the decrypted high-risk group data and ordinary group data, and construct a complete behavior feature vector. The key behavior features include mouse trajectory density, local magnification times, specific area residence time ratio, screenshot frequency, and focus switching frequency;

[0061] The behavior feature vector can be expressed as: X i =[D M ,Z total ,R T ,F K ,F focus ​

[0062] Among them, D M is the mouse trajectory density, representing the activity density of the user in each area on the screen; Z total is the number of local magnifications, indicating whether the user frequently magnifies certain areas; R T is the proportion of the stay time in a specific area, representing the proportion of the stay time of the user in the sensitive area to the total time; FK is the screenshot frequency, representing the screenshot operation frequency of the user; F focus is the focus switching frequency, indicating whether the user frequently switches tasks or windows.

[0063] The mouse trajectory density DM is expressed as:

[0064] Among them, Q is the number of grid areas; M(i) j represents the mouse trajectory data of the j-th grid area in the i-th time window; Density(M(i) j ) is the mouse trajectory density in the j-th grid area;

[0065] The number of local magnifications Z total is expressed as:

[0066] Among them, Z total represents the number of local magnifications in all time windows, and Z(i) represents the number of local magnifications in the i-th time window;

[0067] The proportion of the stay time in a specific area R T is expressed as:

[0068]

[0069] Among them, R T represents the stay time of the i-th time window in the specific area, and T total is the total stay time in this time period;

[0070] The screenshot frequency F K is expressed as:

[0071]

[0072] Among them, n is the number of screenshots, and T total is the total time interval.

[0073] Normalize the extracted features, screen out highly correlated features through principal component analysis, and perform statistical enhancement on the time series of behavioral features through a sliding window;

[0074] Based on machine learning algorithms, conduct behavioral intention analysis on the constructed feature vectors, use a random forest model for non-linear classification, and combine LSTM to capture time series characteristics, classifying user behavioral intentions into three categories: deep appreciation, normal browsing, or potential infringement.

[0075] It should be noted that by decrypting the high-risk grouped data and then extracting the key behavioral characteristics in the high-risk group and the normal group, we can effectively construct behavioral feature vectors, including mouse trajectory density, number of local magnifications, proportion of residence time in specific areas, screenshot frequency, and focus switching frequency. These features provide a basis for the detailed analysis of user behavior. Through feature normalization and principal component analysis (PCA), we can effectively reduce the dimensions, screen out highly correlated features, thereby improving the efficiency and accuracy of subsequent classification. Further, by using the sliding window enhancement method to statistically process time series features, the model's ability to capture time-dependent relationships is enhanced. Combining the random forest model for non-linear classification and processing time series data through LSTM, we can accurately classify user behavioral intentions into deep appreciation, normal browsing, or potential infringement. This process can not only effectively identify the normal behavior patterns of users but also timely detect potential high-risk behaviors, providing strong support for security monitoring and user behavior analysis. Therefore, by combining these technical means, the understanding of user behavior can be greatly enhanced, the accuracy of risk prediction can be improved, and data support can be provided for formulating better security protection strategies.

[0076] S300. According to the result of the user's behavioral intention, compare it with the preset policy rule engine, and select an authorization plan in the policy library for execution operations.

[0077] Furthermore, input the result of the behavioral intention into the preset policy rule engine. The policy rule engine includes a structured rule library, and each rule consists of a behavioral intention category, a policy priority, and a corresponding authorization plan;

[0078] The policy rule engine matches according to the priority order of the rules based on the input behavioral intention, and selects the authorization plan that best matches the current behavioral intention.

[0079] Embodiment 2

[0080] In addition, this embodiment also provides a passenger integrated service system based on an integrated transportation hub, including:

[0081] A passenger behavior data collection and preprocessing module, configured to collect passenger behavior data in real time and preprocess and standardize the passenger behavior data;

[0082] The convolutional neural network analysis module is configured to analyze historical passenger behavior data and current passenger behavior data through a convolutional neural network model to obtain the future fuzzy demand of the comprehensive transportation hub service area.

[0083] The multi-modal real-time resource scheduling is configured to automatically adjust the passenger seat allocation and the opening of safety channels in the comprehensive transportation hub service area through a multi-modal real-time resource scheduling model.

[0084] The monitoring and optimization module is configured to monitor in real time the passenger seat allocation and the opening of safety channels in the current comprehensive transportation hub service area, and further optimize the passenger seat allocation and the opening of safety channels in different service areas in combination with the passenger flow situation.

[0085] The computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0086] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the flue gas extraction type monitoring and preprocessing method proposed in the above embodiment.

[0087] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0088] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript, etc.

[0089] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0090] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0091] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0092] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0093] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to cover these changes and modifications.

Claims

1. A method for intelligent copyright protection and authorization management of digital artworks, characterized in that, It includes the following technical steps: Record the subtle behavior data formed by interaction behaviors in real time, and at the same time group, clean, and encrypt the subtle behavior data; Extract features from the encrypted high-risk grouped data and normal grouped data respectively, and automatically analyze the behavior intention results through machine learning algorithms; According to the behavior intention results of the user, compare with the preset policy rule engine, and select an authorization scheme from the policy library to perform an operation.

2. The digital art intelligent copyright protection and authorization management method according to claim 1, wherein The subtle behavior data includes mouse movement trajectory, local magnification times, residence time in a specific area, keyboard screenshot shortcut key call frequency, and browser focus switching.

3. The digital art intelligent copyright protection and authorization management method according to claim 1, wherein The specific steps for grouping the subtle behavior data include: Group the real-time recorded subtle behavior data within a fixed time window, and uniformly classify all the subtle behavior data within this time window into the same basic group; Divide the data in the basic group into multiple subgroups according to the behavior type, and perform dynamic grouping by combining behavior intention recognition and focus status. Compare the behavior characteristics in the dynamic group with the set behavior threshold, and mark the dynamic group as a high-risk group or a normal group.

4. The digital art intelligent copyright protection and authorization management method according to claim 3, characterized in that, The specific steps for encrypting the subtle behavior data include: Perform encryption processing on the high-risk group, dynamically allocate and regularly rotate the encryption key through a key management system, store the encrypted data in slices in a distributed storage system, also encrypt and protect the index information, and use the TLS1.3 security protocol during data transmission.

5. The digital art intelligent copyright protection and authorization management method according to claim 4, characterized in that The specific steps for extracting features from the decrypted high-risk grouped data and normal grouped data respectively and automatically analyzing the behavior intention results through machine learning algorithms include the following: Extract key behavior features from the decrypted high-risk grouped data and normal grouped data to construct a complete behavior feature vector. The key behavior features include mouse trajectory density, local magnification times, specific area residence time ratio, screenshot frequency, and focus switching frequency; Normalize the extracted features, screen out highly correlated features through principal component analysis, and perform statistical enhancement on the time series of behavior features through a sliding window; Based on machine learning algorithms, perform behavior intention analysis on the constructed feature vector, use a random forest model for non-linear classification, and combine LSTM to capture the time series characteristics, and classify the user behavior intention into three categories: in-depth appreciation, normal browsing, or potential infringement.

6. The intelligent copyright protection and authorization management method for digital artworks according to claim 1, wherein Input the behavior intention result into a preset policy rule engine. The policy rule engine includes a structured rule library, and each rule consists of a behavior intention category, a policy priority, and a corresponding authorization scheme; The policy rule engine matches according to the input behavior intention in the order of rule priorities, and selects the authorization scheme that best matches the current behavior intention.

7. A digital art intelligent copyright protection and authorization management system, based on the digital art intelligent copyright protection and authorization management method according to any one of claims 1 to 6, characterized in that, It includes: A data recording and processing module, configured to record the subtle behavior data formed by interaction behaviors in real time, and at the same time group, clean, and encrypt the subtle behavior data; The feature extraction and behavior intention analysis module is configured to extract features from the encrypted subtle behavior data and automatically analyze the behavior intention result through machine learning algorithms; The authorization management and execution module is configured to select an authorization scheme from the policy library for execution operations according to the user's behavior intention result and in contrast to the preset policy rule engine.

Images