Digital civil air defense tampering method and device based on block chain

Abstract

The invention discloses a digital civil defense tampering method based on a block chain, and the method comprises the steps: determining first information of a digital person in response to a digital person playing request, the first information comprising at least one of a digital person identity label, a digital person generation algorithm, an appearance image feature, a sound tone and creator information; comparing the first information stored in the block chain with the first information of the digital person requesting to play, and determining a variable of the first information; in response to the variable, enabling or prohibiting the digital human from playing the job; and transmitting the first information of the digital person requested to be played to the block chain. The invention also discloses a device and a system for realizing the method. The scheme of the invention improves the controllability of digital human propagation, and has the advantages of digital human defense tampering and traceability.

Description

Technical Field

[0001] The present application relates to a field, and in particular to a blockchain-based digital human tamper-proof method, device and system. Background Art

[0002] With the rapid development of artificial intelligence technology, digital human technology has made a qualitative leap, showing the characteristics of lower technical threshold, faster generation speed, better generation effect, and lower generation cost, and has been widely used in various fields. The image, voice, algorithm and other information of digital humans may be used and copied without authorization, and even the characteristics of digital humans may be tampered with, resulting in network fraud, infringement of intellectual property rights, production and dissemination of bad information, etc. At present, in order to prevent digital humans from being tampered with, watermark technology is often used for marking. Although watermark technology can mark the source of digital humans, the watermark itself can also be counterfeited, and it cannot solve the problem of theft, tampering and abuse of digital humans from the root.

[0003] How to prevent illegal tampering of digital people during the transmission process is a technical problem to be solved by this application. Summary of the invention

[0004] In order to solve the problem of lack of technical means to reliably identify or suppress tampering of digital humans during the dissemination process, the present application proposes a blockchain-based digital human anti-tampering method and device, which determines the first information of the digital human, generates the second information through hash operation, encrypts the first information to generate the third information, and saves it to the blockchain, so as to realize the tamper-proof of the digital human information.

[0005] In a first aspect, the embodiment of the present application provides a digital person anti-tampering method based on blockchain, including:

[0006] In response to a digital human playback request, determining first information of the digital human, the first information including at least one of a digital human identity identifier, a digital human generation algorithm, appearance features, voice timbre, and creator information;

[0007] Comparing the first information stored in the blockchain with the first information of the digital person requested to be played, and determining the variables of the first information;

[0008] In response to the variable, enabling or disabling the digital human to play the job;

[0009] The first information of the digital person requesting to be played is transmitted to the blockchain.

[0010] This application also provides a digital person anti-tampering method based on blockchain, which is applied to the server, including:

[0011] In response to a digital human playback request, obtaining first information of the digital human from the blockchain; determining the first information of the digital human, the first information including at least one of a digital human identity identifier, a digital human generation algorithm, appearance features, voice timbre, and creator information;

[0012] Comparing multiple first information stored in the blockchain to determine variables of the first information;

[0013] In response to the variable, the digital human playing operation is enabled or disabled.

[0014] This application also provides a digital person anti-tampering method based on blockchain, which is applied to the client, including:

[0015] Determining first information of the digital human, the first information including at least one of a digital human identity identifier, a digital human generation algorithm, appearance features, voice timbre, and creator information;

[0016] Generate, send or receive a digital human playback request, and transmit the first information to the blockchain;

[0017] Generate or receive a digital human playback instruction, where the digital human playback instruction is a response to a variable between the first information stored multiple times in the blockchain;

[0018] In response to the digital human playback instruction, the digital human playback operation is enabled or disabled.

[0019] In any embodiment of the first aspect of the present application, preferably, comparing the first information stored in the blockchain with the first information of the digital person requested to be played, and determining the variables of the first information, comprises:

[0020] After decrypting the third information pointed to by the second index identifier, the decrypted first information is obtained;

[0021] By comparing the second information pointed to by the first index identifier with the summary generated by hashing the decrypted first information, it is determined that the stored first information has not been tampered with; and / or, by comparing the first information of the digital person requested to be played with the decrypted first information, the variables of the first information are determined.

[0022] In any embodiment of the first aspect of the present application, preferably, transmitting the first information of the digital person requested to be played to the blockchain includes:

[0023] The first information of the digital person requested to be played is subjected to a hash operation to generate the second information of the digital person, and the first information is encrypted to generate the third information;

[0024] The second information and the third information are saved to the blockchain according to the specified smart contract, and a first index identifier and a second index identifier fed back by the blockchain are obtained, which are used to indicate the storage locations of the second information and the third information respectively.

[0025] In any embodiment of the first aspect of the present application, preferably, comparing a plurality of first information stored in the blockchain to determine a variable of the first information includes:

[0026] Obtaining the first index identifier and / or the second index identifier of the digital person, and decrypting the third information pointed to by the second index identifier to obtain the decrypted first information;

[0027] By comparing the second information pointed to by the first index identifier and the summary generated by hashing the decrypted first information, it is determined that the stored first information of the digital person has not been tampered with; or, by comparing the decrypted first information, the variables of the first information are determined, and the client that caused the change in the first information is traced back.

[0028] In any embodiment of the first aspect of the present application, preferably, in response to the variable, enabling or disabling the digital human playing operation includes:

[0029] It is determined whether the variable is compliant according to the rule base, and whether the digital human playback operation is enabled or prohibited.

[0030] In any one of the embodiments of the first aspect of the present application, preferably, it also includes: configuring a smart contract for a rule base, identifying whether the variable is compliant according to the rule base, and determining an instruction to enable or prohibit the digital human from playing the operation.

[0031] In a second aspect, an embodiment of the present application further provides a digital person tamper-proof device based on blockchain, which is used to implement the method described in any one of the embodiments of the first aspect, including: a determination module, a comparison module, and a decision module;

[0032] The determination module is used to determine the first information of the digital human in response to the digital human playback request, wherein the first information includes at least one of the digital human identity, the digital human generation algorithm, the appearance characteristics, the voice timbre and the creator information;

[0033] The comparison module is used to compare the multiple first information of the digital human and determine the variables of the first information;

[0034] The decision module is used to enable or disable the digital human playing operation in response to the variable.

[0035] In one embodiment of the present application, the blockchain-based digital human anti-tampering device also includes a storage module; the storage module is used to transmit the first information of the digital human to be played to the blockchain, and / or to obtain the stored second information and third information from the blockchain, and further, to obtain the first information by decrypting the third information.

[0036] In one embodiment of the present application, the blockchain-based digital human anti-tampering device further includes: a sending module, a receiving module and an execution module;

[0037] The sending module is used to send a digital human play request or a digital human play instruction, wherein the request includes a digital human video and / or a picture;

[0038] The receiving module is used to receive a digital human playback request or a digital human playback instruction;

[0039] The execution module is used to enable or disable the digital human playing operation in response to the digital human playing instruction.

[0040] In one embodiment of the present application, the blockchain-based digital human anti-tampering device further includes: a generation module;

[0041] The generating module is also used to generate a digital human playing request and / or a digital human playing instruction.

[0042] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method described in any embodiment provided in the present application is implemented.

[0043] In a fourth aspect, an embodiment of the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any embodiment provided in the present application is implemented.

[0044] In a fifth aspect, an embodiment of the present application also proposes a digital person tamper-proof system based on blockchain, which is used to implement the method described in any embodiment of the present application, and the system includes at least 1 client and / or at least 1 server.

[0045] The client is used to determine the first information of the digital human; generate, send or receive a digital human playback request, and transmit the first information to the blockchain; generate or receive a digital human playback instruction, which is a response to the variable between the first information stored multiple times in the blockchain; and enable or disable the digital human playback operation in response to the digital human playback instruction;

[0046] The server is used to respond to a digital human playback request and obtain the first information of the digital human from the blockchain; compare multiple first information stored in the blockchain to determine variables of the first information; and enable or disable the digital human playback operation in response to the variables.

[0047] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the present application first determines the first information of the digital person in the request, compares it with the first information of the corresponding digital person stored in the blockchain, determines the variables of the first information, and then determines whether to enable or prohibit the digital person's playback operation according to the variables. Through the method described in the embodiments of the present application, it is ensured that during the transmission and playback of the digital person, it can be determined whether the digital person can be played according to the changes in the first information, which improves the controllability of the digital person's playback, and at the same time, it is ensured that the stored first information has the advantages of anti-tampering and traceability. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0049] Figure 1 A flowchart of a digital person anti-tampering method based on blockchain provided in an embodiment of the present application;

[0050] Figure 2 A digital human first information processing block diagram provided in an embodiment of the present application;

[0051] Figure 3 A first information hash operation processing block diagram provided in an embodiment of the present application;

[0052] Figure 4 A blockchain storage processing block diagram provided for an embodiment of the present application;

[0053] Figure 5 This is a flow chart of an embodiment of the method of the present application embodiment used in a client;

[0054] Figure 6 A digital person anti-tampering processing block diagram based on blockchain provided in an embodiment of the present application;

[0055] Figure 7 This is a flow chart of an embodiment of the method of the embodiment of the present application used for a server;

[0056] Figure 8 A digital person anti-tampering system based on blockchain provided in an embodiment of the present application;

[0057] Fig. 9 A schematic diagram of a digital person anti-tampering device based on blockchain is provided for an embodiment of the present application;

[0058] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0060] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0061] Figure 1 A flowchart of a digital person anti-tampering method based on blockchain provided in an embodiment of the present application includes steps 110 to 140:

[0062] Step 110: In response to the digital human playback request, determine the first information of the digital human, wherein the first information includes at least one of the digital human identity identifier, digital human generation algorithm, appearance features, voice timbre, and creator information.

[0063] Digital human is a digital character image close to human image created by digital technology. It is the product of the integration of information science and life science. It uses information science methods to virtually simulate the human body's form and function at different levels.

[0064] After the digital person is created, the first information of the digital person can be further determined.

[0065] In one embodiment, Figure 2 As shown, a block diagram of a digital human first information processing provided by an embodiment of the present application is provided, wherein the first information includes at least one of a digital human identity identifier, a digital human generation algorithm, appearance features, voice timbre, and creator information, and the first information may come from the same data source or multiple different data sources. Optimally, the first information includes a digital human identity identifier, a digital human generation algorithm, appearance features, voice timbre, and creator information.

[0066] The digital person identity is used to uniquely identify the identity of the digital person. In the digital person identity, the universally unique identifier UUID (Universally Unique Identifier) ​​can be used as a reference to IETF RFC4122 to standardize, and the nationality field can also be added to form the digital person identity.

[0067] Digital human identity can be obtained by applying from the digital identity authorization system.

[0068] In one embodiment, the digital human generation algorithm includes one or more of GeneFace, Wav2Lip, Sadtalker, Blendshape, generative adversarial network, variational autoencoder and skinned multi-person linear model.

[0069] Specifically, GeneFace is a deep learning-driven facial feature detection and recognition framework.

[0070] Wav2Lip is a deep learning-based lip-syncing technology that can convert audio signals into corresponding lip-syncing animations. Wav2Lip is a deep learning model whose core idea is to directly convert audio waveforms into facial animations. The model is designed based on a generative adversarial network (GAN) and consists of two main parts: a generator and a discriminator. The task of the generator is to generate realistic facial animations based on the input audio waveform, while the goal of the discriminator is to distinguish the generated animations from real facial animations.

[0071] Sadtalker is a plug-in based on the Stable Diffusion framework that can combine people's photos and voice files to generate digital people with realistic expressions and voices.

[0072] Blendshape is a technique of deforming a single mesh to achieve many predefined shapes and combinations between any number.

[0073] Generative Adversarial Networks (GAN) is a deep learning architecture that trains two neural networks to compete with each other to generate more realistic new data from a given training dataset.

[0074] Variational Autoencoder (VAE) is a generative algorithm whose structure includes an encoder and a decoder. Its encoding distribution is regularized during training to ensure that it has good properties in its latent space, allowing us to generate some new data.

[0075] Skinned Multi-Person Linear Mode (SMPL) is a skinned, vertex-based 3D human model that can accurately represent different shapes and poses of the human body, and can extract algorithm fingerprints for different algorithms.

[0076] In one embodiment, different digital humans are determined using one or more algorithms including GeneFace, Wav2Lip, Sadtalker, Blendshape, generative adversarial network, variational autoencoder, and skinned multi-person linear model.

[0077] Determine the digital human generation algorithm, which can be obtained through the digital human configuration file.

[0078] Preferably, the digital human generation algorithm is determined by analyzing the digital human's facial features.

[0079] In one embodiment, determining the appearance features includes: using an active shape model (ASM) and an active appearance model (AAM) to detect the eyes, nose and mouth of the digital person, using a convolutional neural network model and a recurrent neural network model to extract facial feature information, and using an image segmentation algorithm to segment the digital person from the background.

[0080] Active Shape Model (ASM) is to abstract the target object through the shape model. It uses the local texture model to perform local search around the feature points, and uses the global statistical model to constrain the shape composed of the feature point set. The two are iterated repeatedly and finally converge to the optimal shape. The processing process includes: selecting a set of training samples of face images, using shape vectors (composed of the coordinates of all feature points) to describe the shape of the face, first aligning the samples in the training set to make the shapes as similar as possible; then using the principal component analysis method to statistically model the aligned shape vectors; finally, matching specific objects is achieved through the search of key points.

[0081] The Active Appearance Model (AAM) algorithm is an improvement on the ASM. It not only uses shape constraints, but also adds texture features of the entire facial area. AAM is mainly divided into two stages: model building stage and model search and matching stage. The model building stage includes building shape models and texture models for training samples respectively, and then combining the two models to form an AAM model.

[0082] In one embodiment, determining the timbre of a sound includes: describing the sound and timbre by analyzing the time domain and frequency domain characteristics of the sound, such as frequency, amplitude, duration, zero-crossing rate, etc.; converting the sound signal to the frequency domain, and describing the frequency components and timbre characteristics of the sound through information such as frequency band distribution, peak value, valley value, and bandwidth in the spectrum diagram.

[0083] In one embodiment, the creator information is determined, including: the digital human creator's signature, the software company's signature, and the software usage account registration information.

[0084] Creator information can be determined via a text file.

[0085] In one embodiment, the first information further includes transaction information and / or usage information.

[0086] Transaction information refers to the transaction information that is generated by the digital human creator and then traded to other users (such as advertisers, organizational publicity departments, etc.) through the market. The transaction information determined in this transaction process includes: transaction time, transaction price, transaction content, transaction agreement and other information.

[0087] Usage information refers to the use of digital humans in the fields of publicity, news broadcasting, advertising, etc. after they are generated. This includes information such as usage scenarios, published content, and target audiences. Specifically, for example, a digital human of a fire protection propagandist is generated and applied to school classrooms to explain fire protection knowledge and skills to students.

[0088] Transaction information and usage information can be determined via text files.

[0089] Step 120: Compare the first information of the digital human stored in the blockchain with the first information of the digital human requested to be played, and determine the variables of the first information.

[0090] Preferably, the first index identifier and the second index identifier are obtained, for example, by retrieving the first index identifier and the second index identifier of the digital human stored in the blockchain, or the first index identifier and the second index identifier carried in the digital human playback request.

[0091] The "first information stored in the blockchain" mentioned in this application can be the first information in original form or in encrypted form. For the convenience of expression, this application refers to the encrypted first information as the third information.

[0092] Preferably, second information is stored on the blockchain, and the second information is generated by hashing the first information.

[0093] Decrypting the third information pointed to by the second index identifier to obtain the decrypted first information;

[0094] By comparing the second information pointed to by the first index identifier and the digest generated by hashing the decrypted first information, it can be determined whether the stored first information of the digital person has been tampered with.

[0095] When the first information stored in the blockchain is not tampered with, the variables of the first information of the digital person requested to be played can be determined by comparing the first information of the digital person requested to be played with the first information decrypted from the blockchain.

[0096] The first information of the digital person stored includes at least one of: the digital person's identity, the digital person's generation algorithm, the appearance characteristics, the voice timbre and the creator's information. It should be noted that in the process of the digital person's circulation, the first information of the digital person (in original or encrypted form) is stored in the blockchain, and the first information is stored in the blockchain again in response to the playback instruction (such as step 140 below). Therefore, when the downstream digital person user plays the digital person, the first information of the digital person stored in the blockchain by the upstream digital person user can be read from the blockchain to confirm that the played digital person is the "same" digital person as the upstream digital person. The "same" means that the first information of the digital person is the same, or the change of the first information of the digital person is within the range allowed by the set rules.

[0097] Step 130: In response to the variable, enable or disable the digital human playing operation.

[0098] Preferably, whether the variable is compliant is identified according to the rule base, and whether the digital human playback operation is enabled or disabled is determined.

[0099] For example, in one embodiment, the variable in the first information indicates that the timbre or semantics of the digital human voice has changed, indicating that the digital human requested to be played has changed in timbre or semantics compared with the digital human previously existing on the blockchain, and a decision to enable or prohibit the digital human playback operation can be made according to the set rules.

[0100] For another example, in one embodiment, the variable in the first information indicates that the image feature of the digital human has changed, indicating that a new player has changed the video of the digital human, and the enabling or disabling of the digital human playback operation is determined according to the degree of change of the image feature set in the rule library.

[0101] For another example, in one embodiment, the variable in the first information indicates that the application scenario in the usage information of the digital human has changed. For example, the digital human in the news media work scenario is transferred to the entertainment media work scenario. According to the scope of application of the application scenario set in the rule library, it is determined whether to enable or prohibit the digital human playback operation.

[0102] For another example, in one embodiment, the variable in the first information indicates that the algorithm for generating the digital human has changed, indicating that the new player has rewritten the program for generating the digital human. Based on the digital human algorithm change rules set in the rule library, it is determined whether to enable or disable the digital human playback operation.

[0103] Furthermore, the content of the rule base is configured, and the smart contract is triggered to identify whether the variable is compliant according to the rule base, and determine the instructions for enabling or prohibiting the digital human from playing the operation.

[0104] Step 140: transmit the first information of the digital person requested to be played to the blockchain.

[0105] Preferably, the first information of the digital person requested to be played is subjected to a hash operation to generate the second information of the digital person, and the first information is encrypted to generate the third information;

[0106] The second information and the third information are saved to the blockchain according to the specified smart contract, and a first index identifier and a second index identifier fed back by the blockchain are obtained, which are used to indicate the storage locations of the second information and the third information respectively.

[0107] In an embodiment of the present application, the first information of the digital person is subjected to a hash operation to generate the second information of the digital person, including: using an SM3 cryptographic hash algorithm, a secure hash algorithm, or a message digest algorithm to convert the first information into the second information.

[0108] The SM3 cryptographic hash algorithm is a Chinese commercial cryptographic hash algorithm standard announced by the China National Cryptography Administration in 2010. The algorithm was released as a cryptographic industry standard (GM / T 0004-2012) in 2012 and a national cryptographic hash algorithm standard (GB / T 32905-2016) in 2016. It is now widely used in important economic fields such as finance, transportation, and the State Grid. SM3 is suitable for digital signatures and verification in commercial cryptographic applications, achieving similar effects to the SHA-256 algorithm.

[0109] The Secure Hash Algorithm (SHA) was developed by the National Security Agency (NSA) of the United States for digital signatures and blockchain. In the fields of computer science and information security, SHA-256 (Secure Hash Algorithm 256-bit) is a popular and commonly used cryptographic hash function. SHA-256 generates a unique, fixed-length 256-bit (32-byte) hash value.

[0110] Secure Hash Algorithm (SHA) is a cryptographic hash function designed by the National Security Agency (NSA) and published by the National Institute of Standards and Technology (NIST). The SHA algorithm generates a fixed-length hash value, commonly known as a message digest, which is used to verify the integrity and authenticity of data. The output length of the SHA algorithm can be 160 bits, 224 bits, 256 bits, 384 bits, or 512 bits, depending on the algorithm version. SHA algorithms include SHA-1, SHA-2 (including SHA-224, SHA-256, SHA-384, SHA-512, etc.), SHA-3 (based on the Keccak algorithm), etc.

[0111] Commonly used message digest algorithms include MD5.

[0112] The core processing of the above-mentioned SM3 cryptographic hash algorithm, secure hash algorithm or message digest algorithm is hash operation. After hash operation, the first information is converted into the second information of the digital person. The first information cannot be reversely derived from the second information.

[0113] In one embodiment, Figure 3 The figure shows a first information hash operation processing block diagram provided in an embodiment of the present application.

[0114] In step 110, the first information of the digital person is determined, including: the digital person's identity, the digital person generation algorithm, the appearance characteristics, the voice timbre and the creator information, as well as the transaction information and the usage information. These are collectively referred to as the feature values ​​of the first information. These feature values ​​are processed according to the set rules, such as adding the ASCII code values, or by sequential concatenation, or combined operations (such as multiplying the specified feature values ​​and shifting the product, etc.), and then the processing results are processed by the selected hash algorithm to obtain the hash value, which is the second information of the present application. Specific hash algorithms include: using the SM3 cryptographic hash algorithm, the secure hash algorithm or the message digest algorithm.

[0115] In one embodiment, a symmetric encryption algorithm is used to encrypt the first information to generate the third information. An asymmetric encryption algorithm may also be used to encrypt the first information using a public key to generate the third information.

[0116] In one embodiment, the second information and the third information are appropriately encoded and processed to meet the data format requirements of the blockchain, and then the second information and the third information are saved to the blockchain by calling the smart contract method. The blockchain feeds back an index identifier indicating the storage location of the second information and the third information, and the user can use the index identifier to access the second information and the third information saved on the blockchain.

[0117] The index identifier indicating the storage location of the second information and the third information may be the same index identifier or two different index identifiers, such as a first index identifier and a second index identifier.

[0118] Specifically, Figure 4 The figure shows a blockchain storage processing block diagram provided by an embodiment of the present application.

[0119] In one embodiment, the second information (i.e., hash value) is obtained in step 140, and is sent to the smart contract module for processing after encoding. The smart contract module includes: receiving data function, processing data function, storing data function, authority allocation function, identity authentication function, and authority checking function. After processing by these functions, it is determined that the second information is saved to the designated node of the blockchain. The third information can also be stored in the blockchain in the same way.

[0120] By setting the data receiving function, data processing function, data storage function, permission allocation function, identity authentication function and permission checking function in the smart contract module, the terms of the smart contract can be adjusted to change the location, storage method and frequency of the second information and the third information stored in the blockchain, the permission to access the data, etc.

[0121] Preferably, a consortium chain may be used to store the second information and the third information.

[0122] In the embodiment of the present application, preferably, before determining the first information of the digital human, a software and hardware configuration is constructed to generate the digital human and determine the identity of the digital human.

[0123] The present application first determines the first information of the digital person in the playback request, compares it with the first information of the corresponding digital person stored in the blockchain, determines the variables of the first information, and then determines whether to enable or disable the digital person playback operation according to the variables. Through the method described in the embodiment of the present application, it is ensured that during the transmission and playback of the digital person, it can be determined whether to play according to the change of the first information, which improves the controllability of the digital person playback, and at the same time, ensures that the stored first information has the advantages of anti-tampering and traceability.

[0124] In one embodiment, the methods of steps 110, 120, 130 and 140 are applied to the client, the second information and the third information are saved to the blockchain, and the first index identifier and the second index identifier for indicating the storage locations of the second information and the third information fed back by the blockchain are obtained.

[0125] Figure 5 This is a flowchart of an embodiment of the method of the present application for a client. The present application provides a digital person anti-tampering method based on blockchain, which is applied to a client and includes the following steps 510 to 540:

[0126] Step 510: determine the first information of the digital human, the first information including at least one of the digital human identity, digital human generation algorithm, appearance features, voice timbre and creator information; preferably, the first information also includes usage information or transaction information.

[0127] The client may be a creation user, a use user or an audit user of a digital person.

[0128] For example, the first client is the creator of the digital human. The first client can determine the digital human identity, digital human generation algorithm, appearance features, voice timbre and creator information, and can also set transaction information or usage information. For example, the digital human assets of public figures or historical celebrities are generated by a specific digital human generation algorithm, marked by specific appearance features and voice timbre features, and publish specific conversation content (usage information) in a set application scenario. They are produced by a designated creator and delivered to a designated user for use (transaction information).

[0129] For another example, the second client is a user of the digital human and obtains the digital human for playback in a specific application scenario. The second client can determine the digital human identity, digital human generation algorithm, appearance features, voice timbre and creator information according to the method of step 110 above, and can also obtain transaction information or usage information.

[0130] For another example, the third client is an audit user of the digital person. The third client can obtain the digital person and determine the first information by detecting the digital person; the third client can also obtain the first information from the first client and / or the second client.

[0131] Step 520: Generate, send or receive a digital human playback request, and transmit the first information to the blockchain.

[0132] The digital human playback request may come from the digital human's creation user, user user or audit user. That is to say, the first client, the second client and the third client may generate, send or receive a digital human playback request. For example: the first client generates a digital human playback request and sends it to the second client, and the first client transmits the first information to the blockchain. For another example, the second client generates a digital human playback request and sends it to the first client, the third client or the server, and transmits the first information to the blockchain. For another example, the second client receives a digital human playback request from the first client or the third client, and transmits the first information to the blockchain.

[0133] In one embodiment, the first information of the digital person requesting to play is transmitted to the blockchain, including:

[0134] The first information of the digital person requested to be played is subjected to a hash operation to generate the second information of the digital person, and the first information is encrypted to generate the third information;

[0135] The second information and the third information are saved to the blockchain according to the specified smart contract, and a first index identifier and a second index identifier fed back by the blockchain are obtained, which are used to indicate the storage locations of the second information and the third information respectively.

[0136] It should be noted that, in the process of digital human circulation, multiple clients transmit the first information to the blockchain, the first information carries a timestamp, and the first information contains user information or address information corresponding to the client.

[0137] Specifically, the first information is transmitted to the blockchain, as described in steps 610 to 640 of the embodiment.

[0138] Step 530: Generate or receive a digital human playback instruction, where the digital human playback instruction is a response to a variable between the first information stored multiple times in the blockchain.

[0139] It should be noted that the digital human playback instruction can be generated by the client of the creation user, the use user, and the audit user, or can come from the server.

[0140] For example, the first client, the second client or the third client generates a digital human playback instruction by itself;

[0141] For another example, the first client receives a digital human playback instruction from the second client, the third client or the server;

[0142] For another example, the second client receives a digital human playback instruction from the first client, the third client or the server;

[0143] For another example, the third client receives a digital human playback instruction from the first client, the second client or the server.

[0144] The digital human playback instruction is a response to the variables between the first information stored multiple times in the blockchain, and the client or server that generates the digital human playback instruction compares the first information stored in the blockchain with the first information of the digital human requested to be played, and determines the variables of the first information. Specifically, it includes:

[0145] After decrypting the third information pointed to by the second index identifier, the decrypted first information is obtained;

[0146] By comparing the second information pointed to by the first index identifier with the summary generated by hashing the decrypted first information, it is determined that the stored first information has not been tampered with; and / or, by comparing the first information of the digital person requested to be played with the decrypted first information, the variables of the first information are determined.

[0147] The digital human playback instruction is a response to a variable between the first information stored multiple times in the blockchain. Alternatively, the client or server that generates the digital human playback instruction compares multiple first information stored in the blockchain to determine the variable of the first information, including:

[0148] Obtaining the first index identifier and / or the second index identifier of the digital person, and decrypting the third information pointed to by the second index identifier to obtain the decrypted first information;

[0149] By comparing the second information pointed to by the first index identifier and the summary generated by hashing the decrypted first information, it is determined that the stored first information of the digital person has not been tampered with; or, by comparing the decrypted first information, the variables of the first information are determined, and the client that caused the change in the first information is traced back to be determined.

[0150] Furthermore, it is determined whether the variable is compliant according to the rule base, and whether the digital human playback operation is enabled or disabled, thereby generating a digital human playback instruction, which includes instruction information for enabling or disabling the digital human playback operation.

[0151] Step 540: In response to the digital human playback instruction, enable or disable the digital human playback operation.

[0152] The digital human playback instruction comes from a local client or other client, or a server. In response to the digital human playback instruction, the local client enables or disables the digital human playback operation according to the instruction information for enabling or disabling the digital human playback operation contained therein.

[0153] Figure 6 A digital person anti-tampering processing block diagram based on blockchain provided in the embodiment of the present application includes steps 610 to 640:

[0154] Step 610: The user generates a digital human through a digital human creation platform, which includes a digital human software and hardware platform.

[0155] Some application platform providers include Tencent, Douyin, Kuaishou, Alibaba, SenseTime, etc.

[0156] Step 620: determine the first information of the digital human, the first information including at least one of the digital human identity, the digital human generation algorithm, the appearance characteristics, the voice timbre and the creator information.

[0157] Furthermore, the first information also includes transaction information and / or usage information.

[0158] Step 630: The first information of the digital person is subjected to a hash operation to generate the second information of the digital person, and the first information is encrypted to generate the third information.

[0159] Step 640: Save the second information and the third information to the blockchain according to the specified smart contract, and obtain the index identifier fed back by the blockchain for indicating the storage location of the second information and the third information.

[0160] In one embodiment, the methods of steps 110, 120, 130 and 140 are applied to the server to obtain the second information and the third information from the blockchain and / or other clients, or to obtain the first index identifier and the second index identifier fed back by the blockchain or other clients for indicating the storage locations of the second information and the third information.

[0161] Figure 7 This is a flowchart of an embodiment of the method of the present application embodiment used on the server. The present application also provides a digital person anti-tampering method based on blockchain, which is applied to the server and includes the following steps 710 to 730:

[0162] Step 710: In response to the digital human playback request, obtain the first information of the digital human from the blockchain. Determine the first information of the digital human, the first information includes at least one of the digital human identity, the digital human generation algorithm, the appearance characteristics, the voice timbre and the creator information.

[0163] It can be understood that during the circulation of the digital human, the first information of the digital human (in original or encrypted form) is stored in the blockchain, and the first information is stored in the blockchain again in response to the playback instruction. The blockchain stores the first information that is uploaded multiple times. Preferably, multiple clients in the circulation of the digital human transmit the first information to the blockchain, the first information carries a timestamp, and the first information contains the user information or address information corresponding to the client.

[0164] Step 720: Compare multiple first information stored in the blockchain to determine variables of the first information.

[0165] In one embodiment of the present application, comparing multiple first information stored in the blockchain to determine variables of the first information includes:

[0166] Obtaining the first index identifier and / or the second index identifier of the digital person, and decrypting the third information pointed to by the second index identifier to obtain the decrypted first information;

[0167] By comparing the second information pointed to by the first index identifier and the summary generated by hashing the decrypted first information, it is determined that the stored first information of the digital person has not been tampered with; and / or, by comparing the decrypted first information, the variables of the first information are determined, and the client that caused the change in the first information is traced back.

[0168] Step 730: In response to the variable, enable or disable the digital human playing operation.

[0169] It is determined whether the variable is compliant according to the rule base, and whether the digital human playback operation is enabled or prohibited.

[0170] For example, in one embodiment, the variable of the first information indicates that the creator information of the digital human has changed, and according to the rules of the rule base regarding the change of creator information, the digital human playback operation is enabled or prohibited.

[0171] For example, in one embodiment, the variable of the first information indicates that the transaction information of the digital human has changed, and according to the rules of the rule base regarding the permitted transactions of the digital human, it is determined whether to enable or prohibit the digital human playback operation.

[0172] Preferably, it also includes: configuring the content of the rule library through the client or server, configuring the smart contract, and when executing the smart contract, identifying whether the variable is compliant according to the rule library, and determining an instruction to enable or prohibit the digital human from playing the operation.

[0173] The server generates instruction information for enabling or disabling the digital human playback operation, and then generates a digital human playback instruction including the instruction information.

[0174] The digital human playback instruction is sent to the client that changes the first information based on the tracing of the first instruction information stored in the blockchain.

[0175] Figure 8 A blockchain-based digital human anti-tampering system provided for an embodiment of the present application includes: a client and a blockchain network. The blockchain network is called a server 84 relative to the client and may also include multiple computer nodes.

[0176] A blockchain-based digital person tamper-proof system according to an embodiment of the present application is used to implement the method described in any one of the embodiments of the present application. The system includes at least one client and / or at least one server.

[0177] The client is used to determine the first information of the digital human; generate, send or receive a digital human playback request, and transmit the first information to the blockchain; generate or receive a digital human playback instruction, which is a response to the variable between the first information stored multiple times in the blockchain; and enable or disable the digital human playback operation in response to the digital human playback instruction;

[0178] The server is used to respond to a digital human playback request and obtain the first information of the digital human from the blockchain; compare multiple first information stored in the blockchain to determine variables of the first information; and enable or disable the digital human playback operation in response to the variables.

[0179] Specifically, after generating a digital human, the creator determines the first information of the digital human through the first client 81, the first information including at least one of the digital human identity identifier, digital human generation algorithm, appearance image characteristics, voice timbre and creator information; generates the second information of the digital human through a hash operation, and encrypts the first information to generate the third information; saves the second information and the third information to the blockchain network according to the specified smart contract, and obtains the index identifier fed back by the blockchain for indicating the storage location of the second information and the third information.

[0180] Furthermore, the creator may attach an index identifier for indicating the storage location of the second information and / or third information to the digital person, or may store the index identifier in a storage network (such as a cloud data center, network disk, etc.) accessed via a Uniform Resource Identifier (URI), and attach the URI to the digital person to access the second information and / or third information of the digital person.

[0181] After creating a digital human, the creative user can generate, send or receive a digital human playback request through the first client; and can also generate, send or receive a digital human playback instruction.

[0182] When using the digital human, the user of the digital human determines the first information of the digital human through the second client 82, the first information including at least one of the digital human identity identifier, the digital human generation algorithm, the appearance image characteristics, the voice timbre and the creator information; the first information of the digital human is subjected to a hash operation to generate the second information of the digital human, and the first information is encrypted to generate the third information; the second information and the third information are saved to the blockchain network according to the specified smart contract, and the index identifier for indicating the storage location of the second information and the third information fed back by the blockchain is obtained.

[0183] After obtaining the digital human, the user can generate, send or receive a digital human playback request, or generate or receive a digital human playback instruction through the second client.

[0184] The user of the digital human can request a playback operation, which in one embodiment includes: the second client sends a digital human playback request, wherein the request includes a digital human video and / or picture; receives a digital human playback instruction; and in response to the digital human playback instruction, enables or disables the digital human playback operation.

[0185] The user of the digital human can receive the digital human playback request and perform the playback operation. In one embodiment, the second client receives the digital human playback request and responds.

[0186] The user of the digital human can generate a digital human playback instruction to prohibit or enable the digital human playback operation. In one embodiment, when the second client can access the blockchain, the first information is compared, the variables of the first information are determined, and the digital human playback operation is enabled or prohibited according to the variables of the first information.

[0187] The user of the digital human can receive a digital human playback instruction from a creation user, an audit user or a blockchain network, enabling or disabling the digital human playback operation. In some embodiments, the second client receives a digital human playback instruction from the first client, the third client 83 or the server, enabling or disabling the digital human playback operation. At this time, the first client, the third client or the server can compare the first information, determine the variables of the first information, and generate a digital human playback instruction, including instruction information for enabling or disabling the playback of the digital human.

[0188] It can be understood that the digital human play request, that is, the digital human play instruction, can come from the local, other clients, or the server.

[0189] For example, a digital human playback request comes from any client, and the server responds to the playback request. In one embodiment, the process includes:

[0190] In response to a digital human playback request, determining first information of the digital human in the request

[0191] Compare the first information of the digital person stored in the blockchain with the first information of the digital person in the request to determine the variables of the first information; or compare the first information of the digital person stored multiple times in the blockchain to determine the variables of the first information.

[0192] In response to the variable, a digital human playback instruction is generated to enable or disable the digital human playback operation.

[0193] Preferably, the content of the rule base is configured and the smart contract is triggered to identify whether the variable is compliant according to the rule base and determine the instructions for enabling or disabling the digital human playback operation.

[0194] The configuration of the rule base can come from the local client, other clients or the server. For example, the local rule base of the first client or the second client is configured by the third client; or the rule base of the server is configured by the third client. The digital human playback instruction can come from the local client, other clients or the server.

[0195] It can be understood that when the rule base is configured in the local client, the client can identify whether the variable is compliant through the rule base and generate a digital human playback instruction.

[0196] It can be understood that when the rule base is configured on the server side, it is possible to identify whether the variables are compliant according to the rule base and generate digital human playback instructions by executing smart contracts.

[0197] The audit user checks whether there is tampering: through the third client 83, the second information and the third information stored corresponding to the specified index identifier are retrieved, the third information is decrypted, and the decrypted first information is obtained. By comparing the second information retrieved from the blockchain and the digest generated by the hash operation of the decrypted first information, it is determined whether the two are consistent. If the two are consistent, it means that the relevant information has not been tampered; otherwise, tampering has occurred.

[0198] Furthermore, the third client responds to the digital human playback request and determines the first information of the digital human in the request; compares the first information of the digital human stored in the blockchain with the first information of the digital human in the request and determines the variables of the first information; or compares the first information of the digital human stored multiple times in the blockchain and determines the variables of the first information.

[0199] In response to the variable, a digital human playback instruction is generated to enable or disable the digital human playback operation.

[0200] The digital human tamper-proof system composed of the client and blockchain network of this application can record the information of the digital human during the dissemination and use process, and retrieve the saved second information and third information through index identifiers. Furthermore, the first information uploaded to the chain by multiple clients can be traced, and the client that causes the first information to change can be supervised according to preset rules.

[0201] Fig. 9 A schematic diagram of a digital human anti-tampering device based on blockchain is provided for an embodiment of the present application. The device is used to implement any of the aforementioned methods of the present application, including: a determination module 910, a comparison module 920 and a decision module 930.

[0202] The determination module 910 is used to determine the first information of the digital human in response to the digital human playback request, wherein the first information includes at least one of the digital human identity, the digital human generation algorithm, the appearance characteristics, the voice timbre and the creator information;

[0203] The comparison module 920 is used to compare multiple first information of the digital human and determine the variables of the first information; the multiple first information comes from the blockchain and / or the client that wants to play the digital human.

[0204] The decision module 930 is used to enable or disable the digital human playing operation in response to the variable.

[0205] In one embodiment of the present application, the blockchain-based digital human tamper-proof device further includes a storage module 940;

[0206] The storage module 940 is used to transmit the first information of the digital person to be played to the blockchain, and / or to obtain the stored second information and third information from the blockchain, and further, to obtain the first information by decrypting the third information.

[0207] In one embodiment, the digital human generation algorithm executed in the determination module 910 includes one or more of GeneFace, Wav2Lip, Sadtalker, Blendshape, generative adversarial network, variational autoencoder and skinned multi-person linear model.

[0208] In one embodiment, the determination module 910 is also used to determine the appearance features, including: using the active shape model and the active appearance model to detect the eyes, nose and mouth of the digital human, using the convolutional neural network model and the recurrent neural network model to extract facial feature information, and using the image segmentation algorithm to segment the digital human from the background.

[0209] In one embodiment, the first information in the determination module 910 further includes transaction information and / or usage information.

[0210] In the aforementioned embodiment, the comparison module 920 is further used for:

[0211] Obtaining the first index identifier and the second index identifier of the digital person from the client, or retrieving the first index identifier and the second index identifier of the digital person stored in the blockchain, decrypting the third information pointed to by the second index identifier, and obtaining the decrypted first information;

[0212] By comparing the second information pointed to by the first index identifier with the digest generated by the hash operation of the decrypted first information, determining that the stored first information of the digital person has not been tampered with;

[0213] In the aforementioned embodiment, the comparison module 920 is further used for:

[0214] The first information of the digital human to be played is compared with the decrypted first information to determine the variables of the first information of the digital human in the request.

[0215] In the aforementioned embodiment, the storage module 940 is further used for:

[0216] The first information of the digital person in the request is subjected to a hash operation to generate the second information of the digital person, and the first information is encrypted to generate the third information;

[0217] The second information and the third information are saved to the blockchain according to the specified smart contract, and a first index identifier and a second index identifier fed back by the blockchain are obtained, which are used to indicate the storage locations of the second information and the third information respectively.

[0218] In the aforementioned embodiment, a digital human generation module is also included, which is used to: before determining the first information of the digital human, construct a software and hardware configuration for generating a digital human and determining the identity of the digital human.

[0219] In one embodiment, the determination module 910, the comparison module 920, the decision module 930 and / or the storage module 940 are configured to the client;

[0220] In another embodiment, the determination module 910, the comparison module 920, the decision module 930 and / or the storage module 940 are configured at the server.

[0221] In one embodiment, the sending module, the receiving module and / or the execution module are configured to the client, wherein:

[0222] The sending module is used to send a digital human playback request or a digital human playback instruction, wherein the request includes a digital human identifier and / or a digital human video and / or picture, and the instruction includes instruction information for enabling or disabling digital human playback;

[0223] The receiving module is used to receive a digital human playback request or a digital human playback instruction;

[0224] The execution module is used to enable or disable the digital human playback operation in response to the digital human playback instruction. In one embodiment of the present application, the blockchain-based digital human anti-tampering device further includes: a generation module;

[0225] The generating module is also used to generate a digital human playing request and / or a digital human playing instruction.

[0226] In an embodiment of the present application, the generation module is configured on any client or server.

[0227] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may 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.

[0228] Therefore, the present application also proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the first aspect of the present application is implemented.

[0229] Furthermore, in order to generate the device described in the embodiment of the second aspect of this application, the present application also proposes an electronic device (or computing device), comprising a processor and a memory storing program instructions, wherein the processor is configured to implement the method described in the embodiment of the first aspect of this application when running the program instructions.

[0230] Fig.10 The electronic device 1000 shown in the figure is only an example and should not bring any limitation to the functions and application scope of the embodiment of the present application.

[0231] It includes: one or more processors 1020; a storage device 1010, used to store one or more programs. When the one or more programs are run by the one or more processors 1020, the one or more processors 1020 implement the blockchain-based digital human tamper-proof method provided in the embodiments of the present application, and the method includes at least one step described in each embodiment of the present application.

[0232] The number of processors 1020 in the electronic device may be one or more. Fig.10 A processor 1020 is taken as an example; the processor 1020, storage device 1010, input device 1030 and output device 1040 in the electronic device can be connected via a bus or other methods, and the figure takes the connection via bus 1050 as an example.

[0233] The storage device 1010, as a computer-readable storage medium, can be used to store software programs, computer executable programs, and module units, such as program instructions corresponding to the digital person anti-tampering method based on blockchain in the embodiment of the present application. The storage device 1010 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to the use of the terminal, etc. In addition, the storage device 1010 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the storage device 1010 may further include a memory remotely arranged relative to the processor 1020, and these remote memories may be connected via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0234] It can be understood that the processor 1020 of this embodiment includes at least one module among the determination module 910, comparison module 920, decision module 930, storage module 940, generation module, sending module, receiving module and execution module of the embodiment of the present application, which is used to implement at least one part of the functions of the above-mentioned embodiment and can be an entity composed of one or more components. The specific functions of each module will not be repeated here.

[0235] The input device 1030 may be used to receive input numbers, character information or voice information, and to generate key signal inputs related to user settings and function control of the electronic device.

[0236] The output device 1040 may include electronic devices such as a display screen and a speaker.

[0237] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0238] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A digital person anti-tampering method based on blockchain, characterized in that: include: In response to a digital human playback request, determining first information of the digital human, the first information including at least one of a digital human identity identifier, a digital human generation algorithm, appearance features, voice timbre, and creator information; Comparing the first information stored in the blockchain with the first information of the digital person requested to be played, and determining the variables of the first information; In response to the variable, enabling or disabling the digital human to play the job; The first information of the digital person requesting to be played is transmitted to the blockchain.

2. According to the blockchain-based digital human tamper-proof method of claim 1, it is characterized in that: Compare the first information stored in the blockchain with the first information of the digital person requested to be played, and determine the variables of the first information, including: After decrypting the third information pointed to by the second index identifier, the decrypted first information is obtained; By comparing the second information pointed to by the first index identifier with the summary generated by hashing the decrypted first information, it is determined that the stored first information has not been tampered with; and / or, by comparing the first information of the digital person requested to be played with the decrypted first information, the variables of the first information are determined.

3. According to the blockchain-based digital human tamper-proof method of claim 1, it is characterized in that: The first information of the digital person requested to be played is transmitted to the blockchain, including: The first information of the digital person requested to be played is subjected to a hash operation to generate the second information of the digital person, and the first information is encrypted to generate the third information; The second information and the third information are saved to the blockchain according to the specified smart contract, and a first index identifier and a second index identifier fed back by the blockchain are obtained, which are used to indicate the storage locations of the second information and the third information respectively.

4. A digital person anti-tampering method based on blockchain, applied to the server, characterized in that: include: In response to a digital human playback request, obtaining first information of the digital human from the blockchain; Determining first information of the digital human, the first information including at least one of a digital human identity identifier, a digital human generation algorithm, appearance features, voice timbre, and creator information; Comparing multiple first information stored in the blockchain to determine variables of the first information; In response to the variable, the digital human playing operation is enabled or disabled.

5. According to claim 4, a digital person anti-tampering method based on blockchain is applied to the server, characterized in that: Comparing a plurality of first information stored in the blockchain to determine variables of the first information includes: Obtaining the first index identifier and / or the second index identifier of the digital person, and decrypting the third information pointed to by the second index identifier to obtain the decrypted first information; By comparing the second information pointed to by the first index identifier and the summary generated by hashing the decrypted first information, it is determined that the stored first information of the digital person has not been tampered with; or, by comparing the decrypted first information, the variables of the first information are determined, and the client that caused the change in the first information is traced back.

6. A digital person anti-tampering method based on blockchain, applied to the client, characterized in that: include: Determining first information of the digital human, the first information including at least one of a digital human identity identifier, a digital human generation algorithm, appearance features, voice timbre, and creator information; Generate, send or receive a digital human playback request, and transmit the first information to the blockchain; Generate or receive a digital human playback instruction, where the digital human playback instruction is a response to a variable between the first information stored multiple times in the blockchain; In response to the digital human playback instruction, the digital human playback operation is enabled or disabled.

7. A blockchain-based digital person tamper-proof method according to any one of claims 1 to 6, characterized in that: In response to the variable, enabling or disabling the digital human playing operation includes: It is determined whether the variable is compliant according to the rule base, and whether the digital human playback operation is enabled or prohibited.

8. A blockchain-based digital person tamper-proof method according to any one of claims 1 to 6, characterized in that: The smart contract is configured for the rule base, and the rule base is used to identify whether the variable is compliant, and determine the instructions for enabling or prohibiting the digital human from playing the operation.

9. A digital person anti-tampering device based on blockchain, used to implement the method described in any one of claims 1 to 8, characterized in that: include: Determination module, comparison module, decision module and storage module; The determination module is used to determine the first information of the digital human in response to the digital human playback request, wherein the first information includes at least one of the digital human identity, the digital human generation algorithm, the appearance characteristics, the voice timbre and the creator information; The comparison module is used to compare the multiple first information of the digital human and determine the variables of the first information; The decision module is used to enable or disable the digital human playing operation in response to the variable.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

11. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

12. A digital person anti-tampering system based on blockchain, used to implement the method described in any one of claims 1 to 8, characterized in that: Includes at least 1 client and / or at least 1 server, The client is used to determine the first information of the digital human; generate, send or receive a digital human playback request, and transmit the first information to the blockchain; Generate or receive a digital human playback instruction, where the digital human playback instruction is a response to a variable between the first information stored multiple times in the blockchain; In response to the digital human playback instruction, enabling or disabling the digital human playback operation; The server is used to obtain the first information of the digital human from the blockchain in response to the digital human playback request; compare multiple first information stored in the blockchain to determine the variables of the first information; In response to the variable, the digital human playing operation is enabled or disabled.

Images