Digital human anti-counterfeiting method and device and electronic equipment

Abstract

The invention provides an anti-counterfeiting method and device for a digital human and electronic equipment, and relates to the technical field of data processing, in particular to the technical field of artificial intelligence, virtual reality and the like, and the method comprises the steps that a calling request is received, the calling request comprises an access token of a client side, and identity verification is carried out on the client side based on the access token; in response to passing of the identity verification, sending a target digital person to the client, each frame of content corresponding to the target digital person carrying an invisible watermark; receiving digital human interaction information sent by the client, and extracting encryption behavior characteristics of a target digital human from the digital human interaction information; and performing anti-counterfeiting verification on the target digital person based on the encryption behavior characteristics and the invisible watermark, thereby performing anti-counterfeiting verification on the digital person based on the encryption behavior characteristics and the invisible watermark, effectively solving the anti-counterfeiting problem of the digital person, enhancing the anti-counterfeiting effect of the digital person, and ensuring safe and stable use of the digital person.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, specifically to the fields of artificial intelligence and augmented reality, and in particular to an anti-counterfeiting method, device and electronic device for digital humans. Background Art

[0002] With the development of technologies such as virtual reality and metaverse, digital humans have been widely used in many fields. However, the image, behavior, voice and other contents of digital humans can be easily copied, tampered with or used without authorization. However, the anti-counterfeiting methods of digital humans in related technologies cannot effectively solve the anti-counterfeiting problem of digital humans. Summary of the invention

[0003] The present disclosure provides a digital human anti-counterfeiting method, device, electronic device, storage medium and computer program product.

[0004] According to the first aspect of the present disclosure, a digital human anti-counterfeiting method is proposed, comprising: receiving a call request, the call request including an access token of a client, and authenticating the client based on the access token; in response to passing the identity authentication, sending a target digital human to the client, each frame of content corresponding to the target digital human carrying an invisible watermark; receiving digital human interaction information sent by the client, and extracting encrypted behavior features of the target digital human from the digital human interaction information; and performing anti-counterfeiting verification on the target digital human based on the encrypted behavior features and the invisible watermark.

[0005] According to the second aspect of the present disclosure, a digital human anti-counterfeiting method is proposed, comprising: sending a call request to a server, the call request including an access token of a client, the access token being used to authenticate the client; receiving and displaying a target digital human sent by the server, each frame of the target digital human carrying an invisible watermark; obtaining input information, and extracting a first behavioral feature of the target digital human from the target digital human; generating an encrypted behavioral feature based on the first behavioral feature, generating digital human interaction information based on the encrypted behavioral feature and the input information, and sending the digital human interaction information to the server.

[0006] According to the third aspect of the present disclosure, a digital human anti-counterfeiting device is proposed, comprising: an identity authentication module, used to receive a call request, the call request includes an access token of a client, and authenticate the client based on the access token; a sending module, used to send a target digital human to the client in response to passing the identity authentication, and each frame of content corresponding to the target digital human carries an invisible watermark; a feature extraction module, used to receive digital human interaction information sent by the client, and extract the encrypted behavior features of the target digital human from the digital human interaction information; a verification module, used to perform anti-counterfeiting verification on the target digital human based on the encrypted behavior features and the invisible watermark.

[0007] According to a fourth aspect of the present disclosure, a digital human anti-counterfeiting device is proposed, comprising: a first sending module, which sends a call request to a server, the call request including an access token of a client, and the access token is used to authenticate the client; a receiving module, which is used to receive and display a target digital human sent by the server, and each frame of the target digital human carries an invisible watermark; an acquisition module, which is used to acquire input information and extract a first behavioral feature of the target digital human from the target digital human; a second sending module, which is used to generate an encrypted behavioral feature based on the first behavioral feature, and generate digital human interaction information based on the encrypted behavioral feature and the input information, and send the digital human interaction information to the server.

[0008] According to the fifth aspect of the present disclosure, an electronic device is proposed, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the anti-counterfeiting method of digital humans proposed in the first or second aspect above.

[0009] According to a sixth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is proposed, wherein the computer instructions are used to enable the computer to execute the anti-counterfeiting method of digital human proposed in the first aspect or the second aspect above.

[0010] According to a seventh aspect of the present disclosure, a computer program product is proposed, including a computer program, which, when executed by a processor, implements the anti-counterfeiting method for digital humans proposed in the first aspect or the second aspect.

[0011] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0013] Figure 1 A schematic diagram of the process of the anti-counterfeiting method of a digital human according to an embodiment of the present disclosure;

[0014] Figure 2 A schematic diagram of a flow chart of an anti-counterfeiting method for a digital human according to another embodiment of the present disclosure;

[0015] Figure 3 A schematic diagram of a flow chart of an anti-counterfeiting method for a digital human according to another embodiment of the present disclosure;

[0016] Figure 4 A schematic diagram of the structure of an anti-counterfeiting device for a digital human according to an embodiment of the present disclosure;

[0017] Figure 5 A schematic diagram of the structure of an anti-counterfeiting device for a digital human according to an embodiment of the present disclosure;

[0018] Figure 6 A schematic block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0020] Data processing is the collection, storage, retrieval, processing, transformation and transmission of data. Data is a form of expression of facts, concepts or instructions, which can be processed by manual or automated devices. After being interpreted and given a certain meaning, data becomes information.

[0021] Artificial Intelligence (AI) is an important driving force for a new round of scientific and technological revolution and industrial transformation. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0022] Augmented Reality (AR) technology integrates the virtual environment generated by the computer with the real environment around the user by means of optoelectronic display technology, interactive technology, multiple sensor technologies, computer graphics and multimedia technology, so that the user can be convinced from the sensory effect that the virtual environment is a part of the real environment around him. Augmented reality has the new characteristics of combining virtual and real, real-time interaction, and three-dimensional registration.

[0023] Figure 1 FIG. 1 is a flow chart of a digital human anti-counterfeiting method according to an embodiment of the present disclosure. Figure 1 As shown, the method includes:

[0024] S101, receiving a call request including an access token of a client, and authenticating the client based on the access token.

[0025] It should be noted that the execution subject of the anti-counterfeiting method of the digital human in the embodiment of the present disclosure may be a hardware device with data information processing capabilities and / or the necessary software required to drive the hardware device to work. Optionally, the execution subject may include a workstation, a server, a computer, a user terminal and other intelligent devices. Among them, the user terminal includes but is not limited to a mobile phone, a computer, an intelligent voice interaction device, an intelligent home appliance, a vehicle-mounted terminal, etc.

[0026] It should be noted that the client obtains the first identity authentication information corresponding to the client and the second identity authentication information of the target digital person, generates an access token Token based on multiple identity authentication information, and generates a call request based on the access token.

[0027] In the embodiment of the present disclosure, after the client generates a call request, it sends the call request to the server. Accordingly, the server receives the call request and parses the call request to obtain the access token of the client included in the call request.

[0028] In the embodiment of the present disclosure, after obtaining the access token, multiple identity authentication information corresponding to the client can be obtained based on the access token. The multiple identity authentication information includes first identity authentication information corresponding to the client and second identity authentication information corresponding to the target digital person. The multiple identity authentication information are verified separately, and in response to passing the multiple identity authentications, it is determined that the client has passed the identity authentication.

[0029] S102, in response to passing the identity authentication, sending the target digital person to the client, each frame of content corresponding to the target digital person carries an invisible watermark.

[0030] Among them, Digital Human refers to a digital character image close to the human image created using digital technology. Digital Human can be applied to multiple fields such as games, film and television, live broadcasts, and virtual social networking.

[0031] It should be noted that after the client passes the identity authentication, it means that the client has the legal authority to use the target digital person, can add an invisible watermark to each frame of content corresponding to the target digital person, and send the target digital person to the client.

[0032] It should be noted that in related technologies, static watermarks are often added to digital humans. However, digital humans are often dynamic. Existing static watermarks can only be applied to single-frame content of digital humans and cannot cover dynamic interactive scenes of digital humans. They can be easily bypassed by screen recording and other methods.

[0033] In the disclosed embodiment, the timestamp of each frame of the target digital human's content, the upload device identifier and the creator identifier of the target digital human can be obtained, and an invisible watermark corresponding to each frame of the content can be generated based on the timestamp, upload device identifier and creator identifier of each frame of the content, and the invisible watermark can be added to each frame of the content and the texture of the digital human model.

[0034] It should be noted that for dynamic interactive scenarios of the target digital human, such as the display and interaction scenarios of the target digital human, by adding an invisible watermark to each frame of the target digital human content and the texture of the digital human model, it can be updated as the target digital human's movements change, that is, the invisible watermark is a dynamic watermark, and each frame of the target digital human content contains the corresponding invisible watermark information, such as timestamp, upload device ID and creator ID, to ensure that it cannot be bypassed even through video recording.

[0035] S103, receiving digital human interaction information sent by the client, and extracting encrypted behavior features of the target digital human from the digital human interaction information.

[0036] It should be noted that when digital humans interact, in order to ensure that each action of the target digital human is legally authorized, the digital human interaction information sent by the client can be received, and the encrypted behavior features of the target digital human can be extracted from the digital human interaction information.

[0037] Optionally, after the digital human interaction information is acquired, the encrypted behavior features associated with the target digital human may be extracted from the digital human interaction information according to the identification information of the target digital human.

[0038] Among them, the encrypted behavioral characteristics of the target digital person include but are not limited to the target digital person's action characteristics, facial characteristics, and conversational voice characteristics.

[0039] S104, based on the encrypted behavior characteristics and invisible watermark, the target digital person is verified for anti-counterfeiting.

[0040] In the disclosed embodiment, after the encrypted behavior features and invisible watermarks are acquired, anti-counterfeiting verification can be performed on the target digital person based on the encrypted behavior features and invisible watermarks.

[0041] Optionally, the encrypted behavior feature can be decrypted to obtain the first behavior feature, the second behavior feature corresponding to the target digital person can be obtained from the feature database, and the first behavior feature and the second behavior feature can be feature matched. Based on the feature matching result and the invisible watermark, it is determined whether the target digital person has passed the anti-counterfeiting verification.

[0042] For example, in response to at least one of the following conditions being met: the behavioral characteristics of the target digital person are not matched successfully and the digital person's interactive information does not carry an invisible watermark, it is determined that the target digital person has failed the anti-counterfeiting verification; in response to all of the following conditions being met: the behavioral characteristics of the target digital person are matched successfully and the digital person's interactive information carries an invisible watermark, it is determined that the target digital person has passed the anti-counterfeiting verification.

[0043] In the embodiment of the present disclosure, after determining that the target digital person has not passed the anti-counterfeiting verification, indication information related to the call request may be sent to the client, where the indication information is used to indicate that the target digital person has not passed the anti-counterfeiting verification.

[0044] The anti-counterfeiting method for digital humans proposed in the present disclosure receives a call request, the call request includes an access token of a client, and authenticates the client based on the access token. In response to successful authentication, a target digital human is sent to the client, and each frame of content corresponding to the target digital human carries an invisible watermark. The digital human interaction information sent by the client is received, and the encrypted behavior features of the target digital human are extracted from the digital human interaction information. The target digital human is verified for anti-counterfeiting based on the encrypted behavior features and the invisible watermark. Therefore, the present disclosure performs anti-counterfeiting verification on the digital human based on the encrypted behavior features and the invisible watermark, which effectively solves the anti-counterfeiting problem of the digital human, enhances the anti-counterfeiting effect of the digital human, and ensures the safe and stable use of the digital human.

[0045] Figure 2 It is a flowchart of the anti-counterfeiting method of digital human according to the second embodiment of the present disclosure.

[0046] like Figure 2 As shown, in Figure 1 Based on the illustrated embodiment, the pattern generating method of the embodiment of the present disclosure may specifically include the following steps:

[0047] S201, receiving a call request, where the call request includes an access token of a client.

[0048] For the relevant contents of step S201, please refer to the above embodiment, which will not be described again here.

[0049] In the above embodiment, step S101 “authenticating the client based on the access token” may specifically include the following steps S202 and S203 .

[0050] S202, obtaining multiple identity authentication information corresponding to the client according to the access token, wherein the multiple identity authentication information includes first identity association information corresponding to the client and second identity association information corresponding to the target digital person.

[0051] In the embodiment of the present disclosure, after obtaining the access token, the access token can be parsed to obtain various identity authentication information corresponding to the client.

[0052] The first identity-related information includes, but is not limited to, device identification information corresponding to the client, account information, and authorization information corresponding to the account information.

[0053] Among them, the second identity-related information includes but is not limited to the identity information of the developer corresponding to the digital person, the platform application programming interface (Application Programming Interface, referred to as API) information and the authorized device information.

[0054] S203, verifying the multiple identity authentication information respectively, and in response to passing the multiple identity authentications, determining that the client passes the identity authentication.

[0055] In the embodiment of the present disclosure, the first identity-associated information corresponding to the client and the second identity-associated information corresponding to the target digital person can be verified. In response to the first identity-associated information passing the verification and the second identity-associated information passing the verification, it is determined that the client has passed the identity authentication.

[0056] S204, in response to passing the identity authentication, sending the target digital person to the client, each frame of content corresponding to the target digital person carries an invisible watermark.

[0057] S205, receiving the digital human interaction information sent by the client, and extracting the encrypted behavior features of the target digital human from the digital human interaction information.

[0058] For the relevant contents of steps S204 and S205, please refer to the above embodiments, which will not be described again here.

[0059] The step S104 in the above embodiment, “performing anti-counterfeiting verification on the target digital person based on the encrypted behavior characteristics and the invisible watermark”, may specifically include the following steps S206 and S208.

[0060] S206, decrypt the encrypted behavior feature to obtain a first behavior feature.

[0061] In the disclosed embodiment, after the encrypted behavior feature is acquired, the encrypted behavior feature may be decrypted by a decryption algorithm to obtain the first behavior feature.

[0062] S207, obtaining a second behavior feature corresponding to the target digital human from a feature database, and performing feature matching on the first behavior feature and the second behavior feature.

[0063] In the disclosed embodiment, a feature database may be generated in advance to obtain the second behavior feature corresponding to the target digital human from the feature database, and perform feature matching on the first behavior feature and the second behavior feature.

[0064] Optionally, a full number of candidate digital persons may be obtained, and the second behavioral characteristics of the candidate digital persons may be extracted, wherein the target digital person is one of the full number of candidate digital persons, a behavioral characteristic set of the candidate digital persons is generated based on the second behavioral characteristics, and a characteristic database is generated based on the behavioral characteristic set of the candidate digital persons.

[0065] In an embodiment of the present disclosure, a target behavior feature set corresponding to the target digital person can be obtained from a feature database based on the identification information of the target digital person, and matching is performed based on the first behavior feature and the second behavior feature in the target behavior feature set. In response to a matching degree between the first behavior feature and at least one second behavior feature in the target behavior feature set being greater than a set value, it is determined that the behavior features of the target digital person are successfully matched. In response to a matching degree between the first behavior feature and each second behavior feature in the target behavior feature set being less than or equal to a set value, it is determined that the behavior features of the target digital person are not successfully matched.

[0066] It should be noted that the present disclosure does not limit the setting of the set value. For example, the set value may be 95%, or for another example, the set value may be 98%.

[0067] In the disclosed embodiment, the frame number associated with the first behavior feature can be determined based on the frame number associated with the digital human interaction information, and the second behavior feature associated with the frame number can be obtained from the target behavior feature set. The first behavior feature is matched with the second behavior feature associated with the frame number. In response to the matching degree between the first behavior feature and the second behavior feature associated with the frame number being greater than a set value, it is determined that the behavior features of the target digital human are successfully matched. In response to the matching degree between the first behavior feature and the second behavior feature associated with the frame number being less than or equal to the set value, it is determined that the behavior features of the target digital human are not successfully matched.

[0068] The frame number associated with the first behavior feature may be the frame number of the current frame, or the frame number of the first N frames before the current frame.

[0069] For example, when the set value is 98% and the frame number associated with the first behavior feature X1 is the Mth frame of the current frame, the second behavior feature X2 associated with the Mth frame is obtained from the target behavior feature set, in response to the matching degree between the first behavior feature X1 and the second behavior feature X2 being 99%, in this case, the matching degree between the first behavior feature X1 and the second behavior feature X2 is greater than the set value of 98%, which means that the behavior feature match of the target digital person is determined to be successful.

[0070] For example, when the set value is 98% and the frame number associated with the first behavior feature X1 is the Mth frame of the current frame, the second behavior feature X2 associated with the Mth frame is obtained from the target behavior feature set, in response to the matching degree between the first behavior feature X1 and the second behavior feature X2 being 90%, in this case, the matching degree between the first behavior feature X1 and the second behavior feature X2 is less than the set value of 98%, which means that it is determined that the behavior features of the target digital person have not been matched successfully.

[0071] S208, in response to at least one of the following conditions being met: the behavior characteristics of the target digital person are not matched successfully and the digital person interaction information does not carry an invisible watermark, determining that the target digital person has failed the anti-counterfeiting verification.

[0072] It should be noted that when the digital human interaction information does not carry at least one item of the invisible watermark, in this case, the target digital human fails the invisible watermark verification. When the digital human interaction information carries all items of the invisible watermark, in this case, the target digital human passes the invisible watermark verification.

[0073] It should be noted that, in response to the successful matching of the behavioral characteristics of the target digital person and all items in the invisible watermark carried by the digital person's interactive information, it is determined that the target digital person has passed the anti-counterfeiting verification.

[0074] It should be noted that the copyright, creation, update (e.g. modification) and use of each digital person are recorded and stored on the blockchain through blockchain technology, forming an unalterable copyright chain.

[0075] In the disclosed embodiment, during the use of the target digital person, the storage location of the target digital person on the blockchain can be determined based on the identification information of the target digital person, and the blockchain can be accessed based on the storage location to obtain the record information corresponding to the target digital person. Based on the record information, the copyright of the target digital person can be verified to ensure that each use of the target digital person is legally authorized.

[0076] Optionally, the associated information of the target digital person may be stored in the blockchain to generate record information of the target digital person, the associated information including at least one of copyright information, creation information, usage information and update information.

[0077] In an embodiment of the present disclosure, in response to failure of copyright verification, indication information related to the call request is sent to the client, and the indication information is used to indicate that the target digital person has not passed the copyright verification; in response to passing the copyright verification, indication information related to the call request can be sent to the client, and the indication information is used to indicate that the target digital person has passed the copyright verification.

[0078] In summary, the anti-counterfeiting method for digital human proposed in the present disclosure receives a call request, the call request includes an access token of a client, obtains multiple identity authentication information corresponding to the client according to the access token, the multiple identity authentication information includes first identity association information corresponding to the client and second identity association information corresponding to a target digital human, verifies the multiple identity authentication information respectively, determines that the client passes the identity authentication in response to passing the multiple identity authentications, sends the target digital human to the client in response to passing the identity authentication, and each frame of content corresponding to the target digital human carries an invisible watermark, sends the target digital human to the client in response to passing the identity authentication, and each frame of content corresponding to the target digital human carries an invisible watermark, decrypts the encrypted behavior feature to obtain the first behavior feature, and obtains the first behavior feature from A second behavior feature corresponding to the target digital person is obtained from the feature database, and feature matching is performed on the first behavior feature and the second behavior feature. In response to at least one of the following conditions being met: the behavior feature of the target digital person is not successfully matched and the digital person's interactive information does not carry an invisible watermark, it is determined that the target digital person has not passed the anti-counterfeiting verification, and copyright verification is performed on the target digital person based on the record information corresponding to the target digital person. Thus, the present disclosure effectively solves the anti-counterfeiting problem of digital persons through multiple verification methods. When the target digital person is used on multiple platforms, cross-platform synchronous anti-counterfeiting verification of the target digital person can be achieved, preventing the target digital person from being used or tampered with on unauthorized platforms, thereby enhancing the anti-counterfeiting effect of the digital person and ensuring the authenticity, uniqueness and copyright ownership of the content of the target digital person.

[0079] Figure 3 FIG. 1 is a flow chart of a digital human anti-counterfeiting method according to an embodiment of the present disclosure. Figure 3 As shown, the method includes:

[0080] S301, sending a call request to the server, where the call request includes an access token of the client, and the access token is used to authenticate the client.

[0081] It should be noted that the execution subject of the anti-counterfeiting method of the digital human in the embodiment of the present disclosure may be a hardware device with data information processing capabilities and / or the necessary software required to drive the hardware device to work. Optionally, the execution subject may include a workstation, a server, a computer, a user terminal and other intelligent devices. Among them, the user terminal includes but is not limited to a mobile phone, a computer, an intelligent voice interaction device, an intelligent home appliance, a vehicle-mounted terminal, etc.

[0082] In the embodiment of the present disclosure, the first identity authentication information corresponding to the client and the second identity authentication information of the target digital person can be obtained, an access token can be generated based on multiple identity authentication information, and a call request can be generated based on the access token.

[0083] In an embodiment of the present disclosure, after a call request is generated, the call request may be sent to a server, the call request including an access token of the client, and the server may authenticate the client based on the access token.

[0084] It should be noted that when a digital person is created and published, it will be bound to the first identity authentication information corresponding to the client and the second identity authentication information of the target digital person. Each time the digital person is used, an access token Token is generated based on the first identity authentication information and the second identity authentication information of the target digital person to ensure that only clients with legal authority can use the digital person.

[0085] The first identity authentication information includes but is not limited to device identification information corresponding to the client, account information, and authorization information corresponding to the account information.

[0086] Among them, the second identity authentication information includes but is not limited to the identity information of the developer corresponding to the target digital person, platform application programming interface API information and authorized device information.

[0087] It should be noted that the target digital person can be used simultaneously on multiple different platforms, such as live broadcast platforms, game platforms and virtual social platforms. By obtaining the platform API information corresponding to the target digital person, the server can connect with the platform API information and perform anti-counterfeiting verification on the digital person synchronously across platforms.

[0088] S302, receiving the target digital human sent by the server and displaying it, wherein each frame of the target digital human carries an invisible watermark.

[0089] In an embodiment of the present disclosure, after the server receives a call request, which includes the access token of the client, and authenticates the client based on the access token, in response to the client passing the identity authentication, the server sends a target digital human to the client. Accordingly, the client can receive the target digital human sent by the server for display.

[0090] S303, obtaining input information, and extracting the first behavior feature of the target digital human from the target digital human.

[0091] It should be noted that the target digital human is driven by input information to achieve interaction with the target digital human, so as to extract the first behavioral feature of the target digital human from the target digital human.

[0092] It should be noted that the present disclosure does not limit the form of input information. For example, the input information can be in various forms such as text and voice.

[0093] It should be noted that the present disclosure does not limit the extraction of the first behavioral feature of the target digital human from the target digital human, and it can be selected according to actual conditions.

[0094] Optionally, a pre-trained behavior feature extraction model may be obtained, and based on the pre-trained behavior feature extraction model, a first behavior feature of the target digital human may be extracted from the target digital human.

[0095] In the implementation of the present disclosure, the content frame of the target digital human associated with the digital human interaction information can be obtained, and the first behavior feature can be extracted from the content frame, the frame number of the content frame can be determined, and the frame number of the content frame can be associated with the first behavior feature.

[0096] S304: Generate an encrypted behavior feature according to the first behavior feature, generate digital human interaction information according to the encrypted behavior feature and the input information, and send the digital human interaction information to the server.

[0097] It should be noted that after the first behavior feature is obtained, the first behavior feature may be encrypted using an encryption algorithm to generate an encrypted behavior feature.

[0098] In the disclosed embodiment, at least one of the usage information and update information of the target digital person can be stored in the blockchain to update the record information of the target digital person stored on the blockchain, and based on the identification information of the target digital person, the storage location of the target digital person on the blockchain can be determined, and the blockchain can be accessed based on the storage location to obtain the record information of the target digital person.

[0099] In an embodiment of the present disclosure, the server sends indication information of the call request, and correspondingly, the client receives indication information of the server sending and the call request, wherein the indication information is used to indicate that the target digital person has not passed the copyright verification performed by the server based on the record information of the target digital person on the blockchain.

[0100] The anti-counterfeiting method for digital humans proposed in the present disclosure sends a call request to a server, the call request includes an access token of a client, the access token is used to authenticate the client, receives and displays a target digital human sent by the client, each frame of the target digital human carries a hidden watermark, obtains input information, extracts a first behavior feature of the target digital human from the target digital human, generates an encrypted behavior feature based on the first behavior feature, generates digital human interaction information based on the encrypted behavior feature and the input information, and sends the digital human interaction information to the server. Therefore, the present disclosure sends the digital human interaction information to the server, and the server can extract the encrypted behavior feature of the target digital human from the digital human interaction information, and perform anti-counterfeiting verification on the target digital human based on the encrypted behavior feature and the invisible watermark, thereby effectively solving the anti-counterfeiting problem of digital humans, enhancing the anti-counterfeiting effect of digital humans, ensuring the legal use of digital humans, and realizing the uniqueness and copyright ownership of digital humans without additional verification operations, thereby ensuring the safe and stable use of digital humans.

[0101] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0102] According to an embodiment of the present disclosure, the present disclosure also provides an anti-counterfeiting device for a digital human, which is used to implement the anti-counterfeiting method for a digital human.

[0103] Figure 4 4 is a block diagram of a digital human anti-counterfeiting device according to an embodiment of the present disclosure.

[0104] like Figure 4 As shown, the anti-counterfeiting device 400 of a digital human includes: an identity authentication module 401, a sending module 402, a feature extraction module 403 and a verification module 404.

[0105] The identity authentication module 401 is used to receive a call request, the call request includes an access token of a client, and authenticate the client based on the access token;

[0106] A sending module 402, configured to send a target digital person to the client in response to passing the identity authentication, wherein each frame of content corresponding to the target digital person carries an invisible watermark;

[0107] The feature extraction module 403 is used to receive the digital human interaction information sent by the client, and extract the encrypted behavior features of the target digital human from the digital human interaction information;

[0108] The verification module 404 is used to perform anti-counterfeiting verification on the target digital person based on the encryption behavior characteristics and the invisible watermark.

[0109] In one embodiment of the present disclosure, the verification module 404 is used to: decrypt the encrypted behavior feature to obtain a first behavior feature; obtain a second behavior feature corresponding to the target digital person from a feature database, and perform feature matching on the first behavior feature and the second behavior feature; in response to the fact that the behavior feature of the target digital person is not successfully matched and the digital person interaction information does not carry at least one of the invisible watermarks, determine that the target digital person has not passed the anti-counterfeiting verification.

[0110] In one embodiment of the present disclosure, before obtaining the second behavior feature corresponding to the target digital person from the feature database and performing feature matching on the first behavior feature and the second behavior feature, the device 400 is used to: obtain a full number of candidate digital persons, and extract the second behavior feature of the candidate digital persons, wherein the target digital person is one of the full number of candidate digital persons; generate a behavior feature set of the candidate digital person based on the second behavior feature; and generate the feature database based on the behavior feature set of the candidate digital person.

[0111] In one embodiment of the present disclosure, the verification module 404 is used to: obtain a target behavior feature set corresponding to the target digital person from the feature database based on the identification information of the target digital person; match the first behavior feature with a second behavior feature in the target behavior feature set; in response to a matching degree between the first behavior feature and at least one second behavior feature in the target behavior feature set being greater than a set value, determine that the behavior feature of the target digital person is successfully matched; in response to a matching degree between the first behavior feature and each second behavior feature in the target behavior feature set being less than or equal to the set value, determine that the behavior feature of the target digital person is not successfully matched.

[0112] In one embodiment of the present disclosure, the verification module 404 is used to: determine the frame number associated with the first behavior feature based on the frame number associated with the digital human interaction information; obtain the second behavior feature associated with the frame number from the target behavior feature set; match the first behavior feature with the second behavior feature associated with the frame number; in response to the matching degree between the first behavior feature and the second behavior feature associated with the frame number being greater than a set value, determine that the behavior feature of the target digital human is successfully matched; in response to the matching degree between the first behavior feature and the second behavior feature associated with the frame number being less than or equal to the set value, determine that the behavior feature of the target digital human is not successfully matched.

[0113] In one embodiment of the present disclosure, before sending the target digital human to the client, the device 400 is used to: obtain the timestamp of each frame content of the target digital human, the upload device identifier and the creator identifier of the target digital human; generate an invisible watermark corresponding to each frame content according to the timestamp, the upload device identifier and the creator identifier of each frame content, and add the hidden watermark to each frame content and the texture of the digital human model.

[0114] In one embodiment of the present disclosure, the identity authentication module 401 is used to: obtain multiple identity authentication information corresponding to the client based on the access token, and the multiple identity authentication information includes first identity association information corresponding to the client and second identity association information corresponding to the target digital person; verify the multiple identity authentication information respectively, and in response to passing the multiple identity authentications, determine that the client has passed the identity authentication.

[0115] In one embodiment of the present disclosure, the device 400 is used to: determine the storage location of the target digital person on the blockchain based on the identification information of the target digital person; access the blockchain based on the storage location to obtain the record information corresponding to the target digital person, and perform copyright verification on the target digital person based on the record information.

[0116] In one embodiment of the present disclosure, the device 400 is used to: determine the storage location of the target digital person on the blockchain based on the identification information of the target digital person; access the blockchain based on the storage location to obtain the record information corresponding to the target digital person, and perform copyright verification on the target digital person based on the record information.

[0117] In one embodiment of the present disclosure, the device 400 is used to: store the associated information of the target digital person in the blockchain to generate record information of the target digital person, and the associated information includes at least one of copyright information, creation information, usage information and update information.

[0118] The anti-counterfeiting device for digital humans proposed in the present disclosure receives a call request, which includes an access token of a client, and authenticates the client based on the access token. In response to successful authentication, the device sends a target digital human to the client, and each frame of content corresponding to the target digital human carries an invisible watermark. The device receives digital human interaction information sent by the client, and extracts encrypted behavior features of the target digital human from the digital human interaction information. The device performs anti-counterfeiting verification on the target digital human based on the encrypted behavior features and the invisible watermark. Therefore, the present disclosure performs anti-counterfeiting verification on the digital human based on the encrypted behavior features and the invisible watermark, which effectively solves the anti-counterfeiting problem of the digital human, enhances the anti-counterfeiting effect of the digital human, and ensures the safe and stable use of the digital human.

[0119] According to an embodiment of the present disclosure, the present disclosure also provides an anti-counterfeiting device for a digital human, which is used to implement the anti-counterfeiting method for a digital human.

[0120] Figure 5 4 is a block diagram of a digital human anti-counterfeiting device according to an embodiment of the present disclosure.

[0121] like Figure 5 As shown, the anti-counterfeiting device 500 of a digital human includes: a first sending module 501 , a receiving module 502 , an acquiring module 503 and a second sending module 504 .

[0122] A first sending module 501 sends a call request to a server, wherein the call request includes an access token of a client, and the access token is used to authenticate the identity of the client;

[0123] A receiving module 502 is used to receive and display the target digital human sent by the server, wherein each frame of the target digital human carries a hidden watermark;

[0124] An acquisition module 503 is used to acquire input information and extract a first behavior feature of the target digital human from the target digital human;

[0125] The second sending module 504 is used to generate an encrypted behavior feature according to the first behavior feature, generate digital human interaction information according to the encrypted behavior feature and the input information, and send the digital human interaction information to the server.

[0126] In one embodiment of the present disclosure, the device 500 is used to: obtain a content frame in the target digital human associated with the digital human interaction information, and extract the first behavior feature from the content frame; determine the frame number of the content frame, and associate the frame number of the content frame with the first behavior feature.

[0127] In one embodiment of the present disclosure, the first sending module is used to: obtain the first identity association information corresponding to the client and the second identity association information of the target digital person; generate the access token based on the multiple identity authentication information, and generate the call request based on the access token.

[0128] In one embodiment of the present disclosure, the device 500 is used to: store at least one of the usage information and update information of the target digital person in the blockchain to update the record information of the target digital person stored on the blockchain.

[0129] In one embodiment of the present disclosure, the device 500 is used to: determine the storage location of the target digital person on the blockchain based on the identification information of the target digital person; access the blockchain based on the storage location to obtain the record information of the target digital person.

[0130] In one embodiment of the present disclosure, the device 500 is used to: receive indication information sent by the server in conjunction with the call request, wherein the indication information is used to indicate that the target digital person has not passed the copyright verification performed by the server based on the record information of the target digital person on the blockchain.

[0131] The anti-counterfeiting device for digital humans proposed in the present disclosure receives a call request, which includes an access token of a client, and authenticates the client based on the access token. In response to successful authentication, the device sends a target digital human to the client, and each frame of content corresponding to the target digital human carries an invisible watermark. The device receives digital human interaction information sent by the client, and extracts encrypted behavior features of the target digital human from the digital human interaction information. The device performs anti-counterfeiting verification on the target digital human based on the encrypted behavior features and the invisible watermark. Therefore, the present disclosure performs anti-counterfeiting verification on the digital human based on the encrypted behavior features and the invisible watermark, which effectively solves the anti-counterfeiting problem of the digital human, enhances the anti-counterfeiting effect of the digital human, and ensures the safe and stable use of the digital human.

[0132] According to an embodiment of the present disclosure, the present disclosure also proposes an electronic device, a readable storage medium, and a computer program product.

[0133] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0134] like Figure 6As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0135] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 606, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0136] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the anti-counterfeiting method of a digital person. For example, in some embodiments, the anti-counterfeiting method of a digital person may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the anti-counterfeiting method of a digital person described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the anti-counterfeiting method of a digital person by any other appropriate means (e.g., by means of firmware).

[0137] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be presented to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0139] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] To propose interactions with a user account, the systems and techniques described herein may be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user account; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user account can propose input to the computer. Other types of devices may also be used to propose interactions with the user account; for example, feedback proposed to the user account may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user account may be received in any form (including acoustic input, voice input, or tactile input).

[0141] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user account computer with a graphical user account interface or a web browser through which a user account can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0142] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0143] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, including a computer program, wherein when the computer program is executed by a processor, the steps of the anti-counterfeiting method of the digital human described in the above embodiment of the present disclosure are implemented.

[0144] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0145] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A digital human anti-counterfeiting method, wherein: The method comprises: receiving a call request, the call request including an access token of a client, and authenticating the client based on the access token; In response to passing the identity authentication, sending the target digital person to the client, each frame of content corresponding to the target digital person carries an invisible watermark; Receiving digital human interaction information sent by the client, and extracting the encrypted behavior features of the target digital human from the digital human interaction information; Based on the encryption behavior characteristics and the invisible watermark, anti-counterfeiting verification is performed on the target digital person.

2. The method according to claim 1, wherein: The anti-counterfeiting verification of the target digital person based on the encryption behavior characteristics and the invisible watermark includes: Decrypting the encrypted behavior feature to obtain a first behavior feature; Acquire a second behavior feature corresponding to the target digital human from a feature database, and perform feature matching on the first behavior feature and the second behavior feature; In response to at least one of the following conditions being met: the behavioral characteristics of the target digital person are not matched successfully and the digital person interaction information does not carry the invisible watermark, it is determined that the target digital person has failed the anti-counterfeiting verification.

3. The method according to claim 2, wherein: Before acquiring the second behavior feature corresponding to the target digital human from the feature database and performing feature matching on the first behavior feature and the second behavior feature, the method further includes: Acquire a full number of candidate digital persons, and extract a second behavior feature of the candidate digital persons, wherein the target digital person is one of the full number of candidate digital persons; Generating a set of behavioral features of the candidate digital human based on the second behavioral feature; The feature database is generated according to the behavioral feature set of the candidate digital human.

4. The method according to claim 3, wherein: The acquiring the second behavior feature corresponding to the target digital human from the feature database and performing feature matching on the first behavior feature and the second behavior feature includes: According to the identification information of the target digital person, a target behavior feature set corresponding to the target digital person is acquired from the feature database; Matching the first behavior feature with a second behavior feature in the target behavior feature set; In response to the matching degree between the first behavior feature and at least one second behavior feature in the target behavior feature set being greater than a set value, determining that the behavior feature of the target digital person is successfully matched; In response to the matching degree between the first behavior feature and each second behavior feature in the target behavior feature set being less than or equal to the set value, it is determined that the behavior feature of the target digital human is not matched successfully.

5. The method according to claim 4, wherein: The matching based on the first behavior feature with a second behavior feature in the target behavior feature set further includes: Determining the frame number associated with the first behavior feature according to the frame number associated with the digital human interaction information; Acquire a second behavior feature associated with the frame number from the target behavior feature set; Matching the first behavior feature with a second behavior feature associated with the frame number; In response to the matching degree between the first behavior feature and the second behavior feature associated with the frame number being greater than a set value, determining that the behavior feature of the target digital human is matched successfully; In response to the matching degree between the first behavior feature and the second behavior feature associated with the frame number being less than or equal to the set value, it is determined that the behavior feature of the target digital human is not matched successfully.

6. The method according to any one of claims 1 to 5, wherein: Before sending the target digital human to the client, the method further includes: Obtaining the timestamp of each frame of the target digital person's content, the upload device identifier and the creator identifier of the target digital person; According to the timestamp of each frame content, the uploading device identifier and the creator identifier, an invisible watermark corresponding to each frame content is generated, and the invisible watermark is added to the texture of each frame content and the digital human model.

7. The method according to any one of claims 1 to 5, wherein: The authenticating the client based on the access token comprises: According to the access token, obtaining multiple identity authentication information corresponding to the client, the multiple identity authentication information including first identity association information corresponding to the client and second identity association information corresponding to the target digital person; The multiple identity authentication information is verified respectively, and in response to passing the multiple identity authentications, it is determined that the client passes the identity authentication.

8. The method according to any one of claims 1 to 5, wherein: The method further comprises: Based on the identification information of the target digital person, determine the storage location of the target digital person on the blockchain; The blockchain is accessed based on the storage location to obtain the record information corresponding to the target digital person, and the copyright of the target digital person is verified based on the record information.

9. The method according to claim 8, wherein: The method further comprises: In response to the copyright verification failing, sending indication information related to the call request to the client, the indication information being used to indicate that the target digital human has failed the copyright verification.

10. The method according to claim 8, wherein: The method further comprises: The associated information of the target digital person is stored in the blockchain to generate record information of the target digital person, wherein the associated information includes at least one of copyright information, creation information, usage information and update information.

11. A digital human anti-counterfeiting method, wherein: The method comprises: Sending a call request to a server, wherein the call request includes an access token of the client, and the access token is used to authenticate the client; receiving and displaying the target digital human sent by the server, wherein each frame of the target digital human carries an invisible watermark; Acquire input information, and extract a first behavior feature of the target digital human from the target digital human; An encrypted behavior feature is generated according to the first behavior feature, digital human interaction information is generated according to the encrypted behavior feature and the input information, and the digital human interaction information is sent to the server.

12. The method according to claim 11, wherein: The method further comprises: Acquire a content frame in the target digital human associated with the digital human interaction information, and extract the first behavior feature from the content frame; The frame number of the content frame is determined, and the frame number of the content frame is associated with the first behavior feature.

13. The method according to claim 11, wherein: The sending of a call request to the server comprises: Acquire the first identity association information corresponding to the client and the second identity association information of the target digital person; Based on the multiple identity authentication information, the access token is generated, and the call request is generated based on the access token.

14. The method according to any one of claims 11 to 13, wherein: The method further comprises: At least one of the usage information and update information of the target digital person is stored in the blockchain to update the record information of the target digital person stored on the blockchain.

15. The method according to claim 14, wherein: The method further comprises: Based on the identification information of the target digital person, determine the storage location of the target digital person on the blockchain; The blockchain is accessed based on the storage location to obtain the record information of the target digital person.

16. The method according to any one of claims 11 to 13, wherein: The method further comprises: Receive indication information sent by the server in conjunction with the call request, wherein the indication information is used to indicate that the target digital person has not passed the copyright verification performed by the server based on the record information of the target digital person on the blockchain.

17. An anti-counterfeiting device for a digital human, comprising: An identity authentication module, configured to receive a call request, the call request including an access token of a client, and authenticate the client based on the access token; A sending module, configured to send a target digital person to the client in response to passing the identity authentication, wherein each frame of content corresponding to the target digital person carries an invisible watermark; A feature extraction module, used for receiving the digital human interaction information sent by the client, and extracting the encrypted behavior features of the target digital human from the digital human interaction information; A verification module is used to perform anti-counterfeiting verification on the target digital person based on the encryption behavior characteristics and the invisible watermark.

18. The device according to claim 17, wherein: The verification module is used to: Decrypting the encrypted behavior feature to obtain a first behavior feature; Acquire a second behavior feature corresponding to the target digital human from a feature database, and perform feature matching on the first behavior feature and the second behavior feature; In response to at least one of the following conditions being met: the behavioral characteristics of the target digital person are not matched successfully and the digital person interaction information does not carry the invisible watermark, it is determined that the target digital person has failed the anti-counterfeiting verification.

19. The device according to claim 18, wherein: Before acquiring the second behavior feature corresponding to the target digital person from the feature database and performing feature matching on the first behavior feature and the second behavior feature, the device is used to: Acquire a full number of candidate digital persons, and extract a second behavior feature of the candidate digital persons, wherein the target digital person is one of the full number of candidate digital persons; Generating a set of behavioral features of the candidate digital human based on the second behavioral feature; The feature database is generated according to the behavioral feature set of the candidate digital human.

20. The device according to claim 19, wherein The verification module is used to: According to the identification information of the target digital person, a target behavior feature set corresponding to the target digital person is acquired from the feature database; Matching the first behavior feature with a second behavior feature in the target behavior feature set; In response to the matching degree between the first behavior feature and at least one second behavior feature in the target behavior feature set being greater than a set value, determining that the behavior feature of the target digital person is successfully matched; In response to the matching degree between the first behavior feature and each second behavior feature in the target behavior feature set being less than or equal to the set value, it is determined that the behavior feature of the target digital human is not matched successfully.

21. The device according to claim 19, wherein The verification module is used to: Determining the frame number associated with the first behavior feature according to the frame number associated with the digital human interaction information; Acquire a second behavior feature associated with the frame number from the target behavior feature set; Matching the first behavior feature with a second behavior feature associated with the frame number; In response to the matching degree between the first behavior feature and the second behavior feature associated with the frame number being greater than a set value, determining that the behavior feature of the target digital human is matched successfully; In response to the matching degree between the first behavior feature and the second behavior feature associated with the frame number being less than or equal to the set value, it is determined that the behavior feature of the target digital human is not matched successfully.

22. The device according to any one of claims 17 to 21, wherein: Before sending the target digital person to the client, the device is used to: Obtaining the timestamp of each frame of the target digital person's content, the upload device identifier and the creator identifier of the target digital person; According to the timestamp of each frame content, the uploading device identifier and the creator identifier, an invisible watermark corresponding to each frame content is generated, and the invisible watermark is added to the texture of each frame content and the digital human model.

23. The device according to any one of claims 17 to 21, wherein: The identity authentication module is used to: According to the access token, obtaining multiple identity authentication information corresponding to the client, the multiple identity authentication information including first identity association information corresponding to the client and second identity association information corresponding to the target digital person; The multiple identity authentication information is verified respectively, and in response to passing the multiple identity authentications, it is determined that the client passes the identity authentication.

24. The device according to claims 17-21, wherein: The device is also used for: Based on the identification information of the target digital person, determine the storage location of the target digital person on the blockchain; The blockchain is accessed based on the storage location to obtain the record information corresponding to the target digital person, and the copyright of the target digital person is verified based on the record information.

25. The device according to claim 24, wherein: The device is also used for: In response to the copyright verification failing, sending indication information related to the call request to the client, the indication information being used to indicate that the target digital human has failed the copyright verification.

26. The device according to claim 24, wherein: The device is also used for: The associated information of the target digital person is stored in the blockchain to generate record information of the target digital person, wherein the associated information includes at least one of copyright information, creation information, usage information and update information.

27. A digital human anti-counterfeiting device, used for: A first sending module sends a call request to a server, wherein the call request includes an access token of a client, and the access token is used to authenticate the identity of the client; A receiving module, used for receiving and displaying the target digital human sent by the server, wherein each frame of the target digital human carries an invisible watermark; An acquisition module, used for acquiring input information and extracting a first behavior feature of the target digital human from the target digital human; The second sending module is used to generate an encrypted behavior feature according to the first behavior feature, generate digital human interaction information according to the encrypted behavior feature and the input information, and send the digital human interaction information to the server.

28. The device according to claim 27, wherein The device is used for: Acquire a content frame in the target digital human associated with the digital human interaction information, and extract the first behavior feature from the content frame; The frame number of the content frame is determined, and the frame number of the content frame is associated with the first behavior feature.

29. The device according to claim 27, wherein: The first sending module is used for: Acquire the first identity association information corresponding to the client and the second identity association information of the target digital person; Based on the multiple identity authentication information, the access token is generated, and the call request is generated based on the access token.

30. The training device according to claims 27-29, wherein: The device is used for: At least one of the usage information and update information of the target digital person is stored in the blockchain to update the record information of the target digital person stored on the blockchain.

31. The training device according to claim 30, wherein: The device is used for: Based on the identification information of the target digital person, determine the storage location of the target digital person on the blockchain; The blockchain is accessed based on the storage location to obtain the record information of the target digital person.

32. The training device according to claims 27-29, wherein: The device is used for: Receive indication information sent by the server together with the call request, wherein the indication information is used to indicate that the target digital person has not passed the copyright verification performed by the server based on the record information of the target digital person on the blockchain.

33. An electronic device, characterized in that: including a processor and a memory; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the method according to any one of claims 1-10 or claims 11-16.

34. 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 10 or claims 11 to 16 is implemented.

35. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1-10 or claims 11-16.

Images