Digital music copyright risk identification and protection system based on deep learning and block chain

Abstract

The invention relates to the technical field of digital music copyright protection, and provides a digital music copyright risk identification and protection system based on deep learning and a block chain. Comprising a data collection module, a GAN-based musical work copyright identification feature recognition and identification module, a digital musical work copyright infringement risk control decision planning module, a block chain-based music copyright infringement event evidence obtaining and recording module and an online copyright retrieval platform. According to the system, an innovative and efficient copyright protection mechanism is provided for the digital music industry, the copyright invasion risk can be effectively reduced, the copyright management efficiency is improved, meanwhile, more perfect and safer copyright guarantee is provided for music creators, platforms and other related parties, and healthy and orderly development of the digital music industry is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of digital music copyright protection, and particularly to a digital music copyright risk identification and protection system based on deep learning and blockchain. Background Art

[0002] With the rapid development of digital music, the dissemination and sharing of music works have become more convenient, but at the same time, it has also brought a series of copyright problems. In the current digital music environment, the phenomenon of copyright infringement is becoming increasingly serious, causing huge economic losses to music creators and copyright owners.

[0003] Traditional music copyright protection methods have many limitations. For example, the manual copyright identification method is inefficient, and its accuracy is difficult to guarantee, unable to meet the copyright management needs of a large number of digital music works. Moreover, traditional copyright management systems have deficiencies in information security and transparency, and are prone to copyright information being tampered with or lost, making it difficult to resolve copyright disputes.

[0004] In addition, for the dissemination and use of digital music works, there is a lack of effective real-time monitoring means, making it difficult to timely discover and warn of potential copyright infringement behaviors. In terms of copyright risk assessment and decision-making, there is also a lack of comprehensive and accurate analysis tools, resulting in copyright owners often being unable to take timely and effective countermeasures when facing infringement problems.

[0005] With the continuous expansion of the digital music market, the need for music copyright protection has become increasingly urgent. How to use advanced technical means to improve the efficiency and accuracy of music copyright protection, strengthen the security and transparency of copyright information, and achieve comprehensive and real-time monitoring and management of digital music copyright has become an urgent problem to be solved in the current digital music industry. Summary of the Invention

[0006] To overcome the defects of the prior art, the purpose of the present invention is to provide a digital music copyright risk identification and protection system based on deep learning and blockchain.

[0007] To achieve the above object, the technical solution of the present invention is realized as follows: A digital music copyright risk identification and protection system based on deep learning and blockchain, comprising: A data collection module, used to collect data related to music works, and the data includes but is not limited to audio data, metadata of music works, and information related to copyright, providing a data basis for the identification and authentication of music work copyright identification features based on GAN (Generative Adversarial Network); A music work copyright identification feature recognition and authentication module based on GAN, comprising: The intelligent comparison unit is configured to use GAN technology to extract and compare the features of the collected music work data. Through the adversarial training of the generator and the discriminator, it can accurately identify the copyright features in the music work and perform intelligent comparison with the known copyright works; The risk prediction unit, based on the intelligent comparison results, uses deep learning algorithms to predict the possible copyright infringement risks of music works. Among them, the deep learning algorithm uses the CNN - RNN learning model combined with meta - heuristic algorithms for risk prediction; The digital music work copyright infringement risk control decision - making and planning module includes: The copyright intelligent monitoring system is used to monitor the dissemination and use of music works in the network environment in real - time. Combining blockchain technology, it marks and tracks the copyright - related information. Through the blockchain risk assessment mechanism, it quantifies and classifies the copyright infringement risks; The decision - making optimization unit, according to the risk assessment results of the copyright intelligent monitoring system, uses predefined rules and algorithms to optimize the decision - making and generate strategies to deal with copyright infringement risks; The blockchain - based music copyright infringement event evidence collection and recording module includes: The encryption and authorization management unit uses the encryption technology of the blockchain to encrypt the copyright information of music works to ensure the security and integrity of the copyright information. At the same time, it manages the authorization of the behaviors of accessing and operating the copyright information; The unit for preventing unauthorized copying and distribution, through the distributed ledger feature of the blockchain, records the dissemination path and usage of music works, prevents unauthorized copying and distribution behaviors, and can accurately record the information related to the event as evidence when a copyright infringement event occurs; The copyright information database is used to store the copyright information, feature information of music works, and the historical records of copyright identification and risk assessment, providing data support for the entire system; The real - time monitoring and early warning system is connected to the copyright intelligent monitoring system. When it monitors that the copyright infringement risk of a music work reaches the preset threshold, it sends out early warning information, which can be pushed to relevant interested parties, such as copyright owners, music platforms, etc.; The online copyright retrieval platform includes: The feature information extraction unit is used to extract feature information from the music work to be detected; The known copyright library comparison unit compares the extracted feature information with the known copyright library in the copyright information database; The infringement risk judgment unit judges whether there is an infringement risk for the music work to be detected according to the comparison results; The decision - making support unit provides decision - making support information for copyright owners or relevant management parties according to the results of the infringement risk judgment unit, assisting them to take corresponding measures to deal with copyright risks.

[0008] Preferably, the data collected by the data collection module further includes the creation background information, author information, and first release platform information of the music work, so as to improve the accuracy of copyright identification.

[0009] Preferably, the intelligent comparison unit in the GAN-based music work copyright identification feature recognition and identification module, the comparison process includes but is not limited to audio waveform comparison, melody feature comparison, rhythm feature comparison, and harmony feature comparison.

[0010] Preferably, in the CNN-RNN learning model of the risk prediction unit, CNN (Convolutional Neural Network) is used to extract local features of the music work, RNN (Recurrent Neural Network) is used to process the temporal features of the music work, and the meta-heuristic algorithm is used to optimize the parameters of the model to improve the accuracy of risk prediction.

[0011] Preferably, in the decision optimization unit of the digital music work copyright infringement risk control decision-making and planning module, the factors considered in the decision optimization process include the level of copyright infringement risk, the commercial value of the music work, the scope of dissemination of the infringement act, and the historical infringement records of the infringing party.

[0012] Preferably, in the encryption and authorization management unit of the blockchain-based music copyright infringement event evidence collection and recording module, the asymmetric encryption algorithm is used to encrypt the copyright information, and the digital signature technology is used to verify the authorization information.

[0013] Preferably, the warning information of the real-time monitoring and warning system includes the type of copyright infringement risk, the relevant information of the infringing work, the estimated possible losses, and the recommended countermeasures.

[0014] Preferably, the known copyright library comparison unit of the online copyright retrieval platform uses the hash algorithm to quickly compare the feature information to improve the comparison efficiency.

[0015] Preferably, the system further includes a user interaction interface for the copyright owner, music platform administrator, and other relevant users to interact with the system, including inputting query information, viewing copyright identification results, receiving warning information, and setting system parameters.

[0016] The beneficial effects of the present invention are reflected in: Through the combination of deep learning and blockchain technology, this system innovatively proposes a multi-level and all-round digital music copyright risk identification and protection solution. First of all, the application of deep learning technology, especially generative adversarial networks (GAN) and CNN - RNN models, makes the copyright identification and risk prediction of music works more accurate and intelligent. Secondly, the introduction of blockchain technology ensures the security, transparency and immutability of copyright information, providing a powerful protection means and legal basis for copyright holders.

[0017] Compared with traditional copyright protection means, this system can not only automatically identify and evaluate the copyright risks of music works, but also monitor copyright dynamics in real time and give risk warnings, greatly improving the efficiency and accuracy of copyright management. The decentralized feature of blockchain also makes the processing of copyright information more open, fair and transparent, providing a more trustworthy environment for all parties in the music industry chain.

[0018] In addition, functions such as an online copyright retrieval platform, a real-time monitoring and warning system, and a decision-making optimization module enable copyright owners and relevant management agencies to quickly respond to potential copyright infringement risks and avoid the spread and deterioration of copyright disputes.

[0019] In short, this system provides an innovative and efficient copyright protection mechanism for the digital music industry, which can effectively reduce the risk of copyright infringement, improve the efficiency of copyright management, and at the same time provide more perfect and secure copyright protection for music creators, platforms and other relevant parties, promoting the healthy and orderly development of the digital music industry. Brief Description of the Drawings

[0020] In the drawings: Figure 1 is the system operation flow chart of the present invention. Detailed Description of the Preferred Embodiment

[0021] The present invention will be further described in detail below in conjunction with the drawings and embodiments. Obviously, the described embodiments are only a part of the embodiments of the invention, rather than all of the embodiments. Without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the invention without creative efforts shall fall within the scope of protection of the invention.

[0022] Please refer to the attached drawings of the specification Figure 1 , the present invention provides a digital music copyright risk identification and protection system based on deep learning and blockchain: I. System Composition This system includes the following main modules: Data collection module: Responsible for collecting data related to music works, such as audio data, metadata, copyright-related information of music works, as well as the creation background information, author information, and first release platform information of music works, etc., providing a data basis for the identification and recognition of copyright features of music works based on GAN.

[0023] Module for identifying and recognizing copyright features of music works based on GAN: Intelligent comparison unit: Utilize GAN technology to extract and compare features from the collected music work data. The specific comparison process includes audio waveform comparison, melody feature comparison, rhythm feature comparison, and harmony feature comparison, etc. Through the adversarial training of the generator and discriminator, accurately identify the copyright features in music works and conduct intelligent comparison with known copyright works.

[0024] Risk prediction unit: Based on the intelligent comparison results, use the CNN - RNN learning model combined with metaheuristic algorithms for risk prediction. Among them, CNN is used to extract local features of music works, RNN is used to process the temporal features of music works, and metaheuristic algorithms are used to optimize the parameters of the model to improve the accuracy of risk prediction.

[0025] Module for decision-making and planning of risk control for digital music work copyright infringement: Copyright intelligent monitoring system: Real-time monitor the dissemination and use of music works in the network environment, and combine blockchain technology to mark and track copyright-related information. Through the blockchain risk assessment mechanism, quantify and classify the copyright infringement risks.

[0026] Decision optimization unit: According to the risk assessment results of the copyright intelligent monitoring system, considering factors such as the level of copyright infringement risk, the commercial value of music works, the dissemination scope of infringement acts, and the historical infringement records of the infringing party, etc., use predefined rules and algorithms for decision optimization to generate strategies for dealing with copyright infringement risks.

[0027] Module for evidence collection and recording of music copyright infringement events based on blockchain: Encryption and authorization management unit: Use asymmetric encryption algorithms to encrypt the copyright information of music works, and use digital signature technology to verify authorization information. At the same time, conduct authorization management for behaviors accessing and operating copyright information to ensure the security and integrity of copyright information.

[0028] Unit for preventing unauthorized copying and distribution: Through the distributed ledger feature of blockchain, record the dissemination path and usage of music works to prevent unauthorized copying and distribution behaviors. When a copyright infringement event occurs, be able to accurately record event-related information as evidence for taking legal action.

[0029] Copyright Information Database: It is used to store the copyright information, feature information of music works, and the historical records of copyright identification and risk assessment, providing data support for the entire system.

[0030] Real-time Monitoring and Early Warning System: It is connected to the Copyright Intelligent Monitoring System. When the copyright infringement risk of a music work reaches the preset threshold, it issues early warning information. The early warning information includes the type of copyright infringement risk, relevant information of the infringing work, estimated possible losses, and recommended countermeasures, and can be pushed to relevant interested parties, such as copyright owners, music platforms, etc.

[0031] Online Copyright Search Platform: Feature Information Extraction Unit: It extracts feature information from the music works to be detected.

[0032] Known Copyright Library Comparison Unit: It uses the hash algorithm to quickly compare the extracted feature information with the known copyright library in the copyright information database.

[0033] Infringement Risk Judgment Unit: It judges whether there is an infringement risk for the music works to be detected according to the comparison result.

[0034] Decision Support Unit: According to the result of the Infringement Risk Judgment Unit, it provides decision support information for copyright owners or relevant management parties to assist them in taking corresponding measures to deal with copyright risks.

[0035] User Interaction Interface: It is used for copyright owners, music platform administrators, and other relevant users to interact with the system, including inputting query information, viewing copyright identification results, receiving early warning information, and setting system parameters, etc.

[0036] II. System Operation Process Data Collection: The data collection module collects relevant data of music works, including audio data, metadata, copyright information, creation background information, author information, first release platform information, etc.

[0037] Copyright Identification Feature Recognition and Identification: The intelligent comparison unit uses GAN technology to extract and compare the features of the collected music work data, and makes an intelligent comparison with known copyright works.

[0038] The risk prediction unit, based on the intelligent comparison result, uses the CNN - RNN learning model combined with the meta - heuristic algorithm to predict the possible copyright infringement risks of music works.

[0039] Copyright Infringement Risk Control Decision Planning: The copyright intelligent monitoring system monitors the dissemination and use of music works in the network environment in real time, marks and tracks copyright-related information in combination with blockchain technology, and quantifies and grades the copyright infringement risks through the blockchain risk assessment mechanism.

[0040] Based on the risk assessment results of the copyright intelligent monitoring system, the decision-making optimization unit considers various factors for decision-making optimization and generates strategies to deal with copyright infringement risks.

[0041] Copyright infringement event evidence collection record: The encryption and authorization management unit uses an asymmetric encryption algorithm to encrypt the copyright information of music works, uses digital signature technology to verify authorization information, and conducts authorization management on the behaviors of accessing and operating copyright information.

[0042] The unit for preventing unauthorized copying and distribution records the dissemination path and usage of music works through the distributed ledger feature of the blockchain, preventing unauthorized copying and distribution behaviors. When a copyright infringement event occurs, it accurately records the information related to the event as evidence for collection.

[0043] The copyright information database stores the copyright information, feature information of music works, and historical records of copyright identification and risk assessment.

[0044] Real-time monitoring and early warning: The real-time monitoring and early warning system is connected to the copyright intelligent monitoring system. When the copyright infringement risk of a music work is detected to reach the preset threshold, it sends out early warning information and pushes it to the relevant rights holders.

[0045] Online copyright retrieval: The feature information extraction unit extracts feature information from the music work to be detected.

[0046] The known copyright library comparison unit uses the hash algorithm to quickly compare the extracted feature information with the known copyright library in the copyright information database.

[0047] The infringement risk judgment unit judges whether there is an infringement risk for the music work to be detected based on the comparison results.

[0048] The decision support unit provides decision support information for copyright owners or relevant management parties based on the results of the infringement risk judgment unit.

[0049] User interaction: Users interact with the system through the user interaction interface, input query information, view copyright identification results, receive early warning information, and set system parameters, etc.

[0050] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0051] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

[0052] In addition, it should be understood that although this specification is described according to embodiments, not every embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A digital music copyright risk identification and protection system based on deep learning and blockchain, characterized by: include: A data collection module is used to collect data related to music works, including but not limited to audio data, metadata and copyright-related information of music works, so as to provide a data basis for feature recognition and identification of copyright identification of music works based on GAN (Generative Adversarial Network); The GAN-based music copyright identification feature recognition module includes: An intelligent comparison unit, configured to use GAN technology to extract features and compare the collected music work data, accurately identify copyright features in the music work through adversarial training of the generator and the discriminator, and perform intelligent comparison with known copyrighted works; The risk prediction unit uses a deep learning algorithm to predict the copyright infringement risks of music works based on the intelligent comparison results. The deep learning algorithm uses a CNN-RNN learning model combined with a meta-heuristic algorithm to predict risks. The digital music copyright infringement risk control decision-making planning module includes: The copyright intelligent monitoring system is used to monitor the dissemination and use of music works in the network environment in real time, mark and track copyright-related information in combination with blockchain technology, and quantify and grade copyright infringement risks through the blockchain risk assessment mechanism; The decision optimization unit uses predefined rules and algorithms to optimize decisions based on the risk assessment results of the copyright intelligent monitoring system and generates strategies to deal with copyright infringement risks; The blockchain-based music copyright infringement incident evidence collection and recording module includes: The encryption and authorization management unit uses blockchain encryption technology to encrypt the copyright information of music works to ensure the security and integrity of copyright information, and at the same time authorizes the access and operation of copyright information; Prevent unauthorized copying and distribution units. Through the distributed ledger characteristics of blockchain, the dissemination path and usage of music works are recorded to prevent unauthorized copying and distribution. When copyright infringement occurs, relevant information of the incident can be accurately recorded as a basis for evidence collection; Copyright information database, which is used to store copyright information, feature information, and historical records of copyright identification and risk assessment of musical works, providing data support for the entire system; The real-time monitoring and early warning system is connected to the copyright intelligent monitoring system. When the copyright infringement risk of a music work reaches a preset threshold, an early warning message is issued, which can be pushed to relevant stakeholders, such as copyright owners, music platforms, etc. Online copyright search platform, including: A feature information extraction unit, used to extract feature information from the music piece to be detected; A known copyright library comparison unit compares the extracted feature information with a known copyright library in a copyright information database; The infringement risk judging unit judges whether the music work to be tested has infringement risk according to the comparison result; The decision support unit provides decision support information to copyright owners or relevant management parties based on the results of the infringement risk judgment unit, and assists them in taking appropriate measures to deal with copyright risks.

2. According to claim 1, the digital music copyright risk identification and protection system based on deep learning and blockchain is characterized in that: The data collected by the data collection module also includes the creation background information, author information and first release platform information of the music work to improve the accuracy of copyright identification.

3. According to claim 1, the digital music copyright risk identification and protection system based on deep learning and blockchain is characterized in that: The intelligent comparison unit in the GAN-based music work copyright identification feature recognition module includes, but is not limited to, audio waveform comparison, melody feature comparison, rhythm feature comparison, and harmony feature comparison.

4. According to claim 1, the digital music copyright risk identification and protection system based on deep learning and blockchain is characterized in that: The CNN - RNN learning model in the risk prediction unit, wherein CNN (convolutional neural network) is used to extract local features of music works, RNN (recurrent neural network) is used to process the temporal features of music works, and the meta-heuristic algorithm is used to optimize the parameters of the model to improve the accuracy of risk prediction.

5. According to claim 1, the digital music copyright risk identification and protection system based on deep learning and blockchain is characterized in that: The decision optimization unit in the digital music copyright infringement risk control decision planning module considers factors such as the level of copyright infringement risk, the commercial value of the music work, the scope of the infringement behavior, and the historical infringement record of the infringer in its decision optimization process.

6. According to claim 1, the digital music copyright risk identification and protection system based on deep learning and blockchain is characterized in that: The encryption and authorization management unit in the blockchain-based music copyright infringement incident evidence collection and recording module uses an asymmetric encryption algorithm to encrypt copyright information and uses digital signature technology to verify authorization information.

7. According to claim 1, the digital music copyright risk identification and protection system based on deep learning and blockchain is characterized in that: The warning information of the real-time monitoring and early warning system includes the type of copyright infringement risk, relevant information of the infringing works, the estimated loss that may be caused, and the recommended response measures.

8. The digital music copyright risk identification and protection system based on deep learning and blockchain according to claim 1 is characterized in that: The known copyright database comparison unit of the online copyright search platform adopts a hash algorithm to quickly compare feature information, thereby improving comparison efficiency.

9. The digital music copyright risk identification and protection system based on deep learning and blockchain according to claim 1 is characterized in that: The system also includes a user interaction interface for copyright owners, music platform administrators and other relevant users to interact with the system, including inputting query information, viewing copyright identification results, receiving warning information and setting system parameters.

Images