[go: up one dir, main page]

WO2023141809A1 - Procédé de protection de confidentialité d'informations partagées basé sur le métavers et appareil associé - Google Patents

Procédé de protection de confidentialité d'informations partagées basé sur le métavers et appareil associé Download PDF

Info

Publication number
WO2023141809A1
WO2023141809A1 PCT/CN2022/073982 CN2022073982W WO2023141809A1 WO 2023141809 A1 WO2023141809 A1 WO 2023141809A1 CN 2022073982 W CN2022073982 W CN 2022073982W WO 2023141809 A1 WO2023141809 A1 WO 2023141809A1
Authority
WO
WIPO (PCT)
Prior art keywords
participants
metaverse
blockchain
information
block chain
Prior art date
Application number
PCT/CN2022/073982
Other languages
English (en)
Chinese (zh)
Inventor
王化
Original Assignee
深圳技术大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳技术大学 filed Critical 深圳技术大学
Priority to PCT/CN2022/073982 priority Critical patent/WO2023141809A1/fr
Publication of WO2023141809A1 publication Critical patent/WO2023141809A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning

Definitions

  • the present application relates to the technical field of network security, and in particular to a metaverse-based shared information privacy protection method and related devices.
  • Machine learning techniques have achieved significant success in many fields, but machine learning methods only work well under the assumption that the training data and test data are in the same feature space or have the same distribution. When the distribution changes, most statistical models need to rebuild the model using newly collected training data. In many practical applications, it is prohibitively expensive to recollect the required training data and rebuild the model. Say we have a classification task in one domain of interest, but we only have enough training data in another domain of interest, where the data for the latter may be in a different feature space or follow a different distribution, we hope to be able to transfer knowledge from the latter to help complete the task of the former.
  • the embodiment of the present application provides a shared information privacy protection method and related devices applied to the Metaverse, which can at least solve the problem in the related art that online activities based on Metaverse virtual reality application scenarios cannot guarantee the privacy information of participants in information sharing. security issues.
  • the first aspect of the embodiment of the present application provides a metaverse-based privacy protection method for shared information, which is applied to a blockchain server, including:
  • control the running node Based on the smart contract of the transaction data block chain, control the running node to obtain federated learning and training tasks based on the information data in the database model;
  • the information data is shared.
  • the second aspect of the embodiment of the present application provides a blockchain message interaction method applied to IoT devices, including:
  • the target SDK proxy node is used to send the blockchain message to the target SDK proxy node A designated area in the blockchain network described above.
  • the third aspect of the embodiment of the present application provides an electronic device, which is characterized by including a memory and a processor, wherein the processor is used to execute the first computer program or the second computer program stored in the memory, and the processor executes
  • the first computer program implements the steps in the shared information privacy protection method provided in the first aspect of the embodiment of the present application.
  • the processor executes the second computer program, it implements the blockchain provided in the second aspect of the embodiment of the present application. Steps in the message interaction method.
  • the fourth aspect of the embodiment of the present application provides a computer-readable storage medium, on which the first computer program or the second computer program is stored.
  • the first computer program is executed by the processor
  • the first aspect of the above-mentioned embodiment of the present application is realized.
  • each step in the blockchain message interaction method provided by the second aspect of the embodiment of the present application is implemented.
  • a transaction data block chain is established in online activities based on Metaverse virtual reality application scenarios; according to the transaction data area
  • the block chain constructs a database model corresponding to the characteristics of the participants in the metaverse virtual reality application scene; based on the smart contract of the transaction data block chain, the control operation node obtains the federated learning training task based on the information data in the database model ; After the running node completes the federated learning training task, share the information data.
  • the transaction data blockchain will be established in the online activities based on the metaverse virtual reality application scene, the database model will be established without leaving the local data, and the training tasks of shared machine learning will be issued in the form of smart contracts. Realize information sharing of online data while protecting the privacy of participants.
  • FIG. 1 is a schematic flow diagram of a shared information privacy protection method applied to the blockchain server side provided by the first embodiment of the present application;
  • FIG. 2 is a flow chart of issuing task management smart contract tasks of the shared information privacy protection method provided in the first embodiment of the present application;
  • FIG. 3 is a schematic flowchart of the NTL method recommended by the dual cold start provided in the first embodiment of the present application;
  • FIG. 4 is a schematic flow diagram of the Internet of Things and online data interaction provided by the first embodiment of the present application
  • FIG. 5 is a schematic flow diagram of a block chain message interaction method applied to the IoT device side provided by the first embodiment of the present application;
  • FIG. 6 is a schematic diagram of a detailed flowchart of a shared information privacy protection method provided in the second embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of an electronic device provided by a third embodiment of the present application.
  • the first embodiment of the present application provides a shared information privacy protection method, which is applied to Metaverse virtual reality application scenario, as shown in Figure 1 is a basic flow chart of the shared information privacy protection method provided in this embodiment, the shared information privacy protection method includes the following steps:
  • Step 101 Establish transaction data block chains in online activities based on metaverse virtual reality application scenarios.
  • the Metaverse is a virtual world that is linked and created using scientific and technological means, and maps and interacts with the real world.
  • the Metaverse is a virtual reality application scenario that can be connected on a large scale.
  • Cosmos is a new type of Internet application and social form that integrates a variety of new technologies. It provides immersive experience based on extended reality technology, generates a mirror image of the real world based on digital twin technology, and builds an economic system based on blockchain technology. Closely integrate the virtual world with the real world in terms of economic system, social system, and identity system, and allow each participant to perform content production and world editing.
  • a blockchain system generally consists of a data layer, a network layer, a consensus layer, an incentive layer, a contract layer, and an application layer.
  • the data layer is used to build data blocks, encrypt and sign the data, and add time stamps;
  • the network layer includes a distributed peer-to-peer network for communication and data verification between nodes;
  • the consensus layer implements various consensus algorithms;
  • the incentive layer mainly uses It is not necessary to formulate corresponding incentive mechanisms in the alliance chain and private chain, because the incentives have been confirmed outside the system;
  • the contract layer mainly encapsulates various scripts, algorithms and smart contracts, which is the basis of the programmable features of the blockchain;
  • the application layer is all kinds of applications based on the blockchain technology. Through the shared blockchain, the metaverse online social system and offline data fusion mechanism are established to ensure that the records are authoritative and credible.
  • the step of establishing the transaction data transaction data block chain in the online activities of the virtual reality application scene it also includes: Verify the transaction information; mark the corresponding time stamp for the transaction information that passes the information verification; integrate the online activities corresponding to the time stamp through the blockchain with decentralized transaction data.
  • each participant on the blockchain first verifies the transaction. Once all participants reach a consensus, the transaction information will be stamped with the Timestamps in sequential order. The timestamp function ensures the traceability of transactions.
  • the application of blockchain technology solves the pain point of high credit risk in traditional transactions and improves the security of transactions.
  • each participant in the blockchain has a complete set of ledgers, which has unique advantages in reconciliation, which reduces the cost of reconciliation and improves the efficiency of liquidation.
  • the blockchain technology with the characteristics of decentralization, trustlessness, and time stamping of the product makes all transaction information open and transparent and cannot be tampered with, greatly reducing the occurrence of operational risks and credit risks, making transactions safer.
  • Step 102 constructing a database model corresponding to the characteristics of the participants in the metaverse virtual reality application scenario according to the transaction data block chain.
  • the participants in the online activity will upload the transaction data and store it in the cloud database in a unified manner.
  • the upload of data is not performed locally, and it is easy to be malicious outside the system. Interception, there is a risk of privacy leakage.
  • the online information data is fused, and the behavior characteristics of the participants are extracted to build a database model.
  • the sharing of data information is maintained, At the same time, it also protects the data information from going out of the local area, including the online information of the data information, so as to protect the privacy; at the same time, the offline information does not go out of the local area, so as to protect the privacy.
  • differential privacy is used for privacy protection, and some differential privacy is added to the data to protect the privacy of the participants. It can be used in all aspects of modeling, such as adding in the process of data collection of participants, or in the process of modeling, such as gradient calculation, adding differential privacy noise to model parameters, and adding noise.
  • the step of constructing a database model corresponding to the characteristics of the participants in the metaverse virtual reality application scenario according to the transaction data block chain includes: when the characteristics cross between the participants, Obtain the model parameters passed between the participants; the model parameters include the item configuration file; encrypt the item configuration file and send it to each participant; after each participant receives the item configuration file, recommend each participant itself through horizontal federation matrix decomposition User configuration files and item configuration files; build corresponding database models based on recommended user configuration files and item configuration files.
  • the data exchange between parties is not encrypted too much.
  • feature crossover is performed during data transmission, and model parameters passed between participants are encrypted, wherein the model parameters include item configuration files, and the encrypted item configuration files are sent to the district through a third-party server.
  • All participants on the block chain after receiving the item configuration files, the participants recommend their own user configuration files and item configuration files to the database model through horizontal federated matrix decomposition, and build a database based on all user configuration files and item configuration files Model.
  • the above-mentioned horizontal federated matrix decomposition process belongs to the horizontal federated learning of federated learning, and in corresponding cases, there is also vertical federated learning for building a database model. In the process of building the model, the original data does not go out of the local area, and the parameters of the model are exchanged under encrypted conditions to build the model and protect the privacy of the participants.
  • feature crossover as a factorization machine is a common algorithm for dealing with crossed features. In the case of data that can be freely transmitted, it is easy to process.
  • the optimized objective function of the federated factorization machine consists of three parts: feature crossover within party A and party B, and feature crossover between party A and party B. We do part of the calculations on side A and side B respectively, and then combine them, and the data does not come out of the local area.
  • the model parameters and the intermediate results of feature cross-summation are transferred between Party A and Party B in an encrypted state.
  • the step of obtaining model parameters passed between participants includes: when feature intersection occurs between participants, Estimated value gradients and loss functions between interactive participants; masked and encrypted estimated value gradients are sent to third-party servers; aggregated estimated value gradients decrypted by third-party servers are obtained; aggregated estimated value gradients are Corresponding to the mask, update the model parameters of the participating parties; if the model parameters are no longer updated through cyclic training, the final model parameters are obtained.
  • the predicted value gradients are calculated based on their respective features and interacted through mask encryption
  • the final loss function is calculated based on the encrypted gradient values
  • the structure Summarized to the third-party server, the third-party server sends the gradient back to the participants after decryption, the participants update their model parameters according to the gradient, and repeat the above steps until the loss function converges, that is, the entire training process of the federated factorization machine.
  • the respective data of the participants are kept locally, and the data interaction during training will not lead to data privacy leakage.
  • the step of interacting with the feature estimation gradient and loss function between participants includes: when the first participant When a characteristic crossover occurs between the party and the second party, the first estimated value calculated based on the characteristics of the first party and part of the loss are encrypted and sent to the second party; the second estimated value calculated based on the characteristics of the second party value and the first estimated value, calculate the loss function and the gradient of the estimated value, and control the second participant to send the loss function and the gradient of the estimated value to the first participant.
  • the first participant and the second participant respectively initialize their respective models, and the third-party server sends the public key to the first participant and the second participant for processing the data that needs to be interacted.
  • the first participant calculates part of the estimated value and part of the loss based on its own characteristics, and encrypts and sends it to the second participant.
  • the second participant calculates part of the estimated value based on its own characteristics, and combines the first The estimated value of the participant, calculate the final loss function and gradient, and then send the gradient and loss function required by the first participant back to the first participant to protect the privacy data of the participant during the process of feature interaction between the participants .
  • the step of recommending each participant's own user configuration file and item configuration file through horizontal federated matrix decomposition it also includes: controlling each participant to decrypt the item configuration file; The local data calculates the loss of the decrypted item profile; updates the user profile of each participant according to the loss.
  • the participants obtain the item configuration file encrypted by the server, they decrypt the item configuration file, calculate the loss during the interaction process based on local data, and update their respective user configuration files according to the calculation results to realize Alignment of party characteristics.
  • Step 103 based on the smart contract of the transaction data block chain, control the running node to acquire the federated learning training task based on the information data in the database model.
  • an intelligent analysis model of Metaverse user behavior characteristics is established based on the knowledge map of Metaverse online information and data, and blockchain smart contract technology is used to The demand side releases machine learning model training tasks in the form of smart contracts on the blockchain, and the running nodes will obtain the federated learning training tasks of interest based on the constructed database model selection, which is conducive to the information sharing of multi-metaverse online data.
  • the step of controlling the running node to obtain the federated learning training task based on the information data in the database model includes: deploying through the transaction data block chain Task management smart contract; according to the task management smart contract, the running node is controlled to obtain the smart contract for publishing tasks; according to the API of the smart contract, the running node is controlled to read the task list and select the federated learning training task of interest.
  • a task management smart contract is deployed based on the blockchain smart contract technology to record and manage all released task smart contracts, as shown in Figure 2 task management smart contract task release flow chart, the running node
  • the smart contract for publishing tasks will be obtained from the task management smart contract.
  • the running nodes include but are not limited to SDK proxy nodes. Through the API interface provided by the smart contract, the running nodes can read the task list and choose to participate in the training tasks of interest. .
  • the smart contract that publishes the task will specify the model calculation graph, training data set, test data set, and accuracy requirements. Considering that smart contracts are not suitable for storing large files, data files will be stored in centralized or decentralized file systems.
  • the smart contract will store its hash and the path to get it.
  • the blockchain technology with the characteristics of decentralization, trustlessness, and time stamps makes all relevant information open and transparent and cannot be tampered with, greatly reducing the occurrence of operational risks and credit risks. Make online information sharing more secure.
  • Feature-based transfer learning The input of training data corresponds to an original input space.
  • the original input space of a piece of news is a space composed of many words. This leads to a problem that the original input space where the existing knowledge resides may not overlap with the original input space of the new task to be solved, hindering the direct reuse of knowledge.
  • feature-based transfer learns an abstract feature space, so that existing knowledge can be easily transferred to new tasks through this abstract feature space.
  • relationship-based transfer learning is processed through dual cold-start recommendation.
  • the related domain i.e., the historical online activity domain
  • the transaction behavior of the user's historical online activity is available.
  • the historical online activity domain there is a triplet, namely (u, g, Gug), indicating that user u has conducted online activities of type g Gug times.
  • the data in the historical online activity field can be expressed as a user type matrix G, as shown in the NTL method recommended by the double cold start in Figure 3.
  • a user item matrix R representing the items that the user has traded.
  • An item i is associated with a primary category c1(i) ⁇ l1 and a secondary category c2(i) ⁇ l2. So there is a set of 4-tuples, namely (u, i, c1(i), c2(i)), indicating that user u has traded item i belonging to c1(i) and c2(i).
  • a user category matrix C can be obtained, where each entry represents the number of items belonging to a user's read category.
  • user-user (or item-item) similarity is a core concept, since the construction of neighborhoods can be used for preference aggregation of like-minded users and then for preference prediction of target users.
  • the mathematical form of user u’s preference prediction formula for item i is:
  • Nu represents a group of nearest neighbors of user u, which is measured by cosine similarity. Denotes user u''s preference estimate for item i. take the average As user u's preference for item i, it will be used for item ranking and k-item best recommendation.
  • Gu is the row vector of user u in the user type matrix G.
  • Step 104 after the running node completes the federated learning training task, share the information data.
  • the information data is shared after the running nodes complete the training tasks issued by the smart contract, which ensures the security of the user's private data when sharing online information and data in the Metaverse.
  • Figure 4 is a schematic flow diagram of the Internet of Things and online data interaction provided by this embodiment, and the first embodiment of the present invention also provides a blockchain message interaction method, as shown in Figure 5 in this embodiment
  • the basic flowchart of the blockchain message interaction method provided, the blockchain message interaction method includes the following steps:
  • Step 501 Construct a block chain message in the IoT device, and send a request to the block chain network to obtain the node information of the target SDK proxy node.
  • Step 502 according to the node information returned by the blockchain network, send the blockchain message to the target SDK proxy node.
  • blockchain messages including but not limited to AR, VR, MR and other physical IoT devices and blockchain Data interaction.
  • a transaction data blockchain is established in online activities based on the Metaverse virtual reality application scenario; a database model corresponding to the characteristics of the participants in the Metaverse virtual reality application scenario is constructed according to the transaction data blockchain ; Based on the smart contract of the transaction data blockchain, control the running nodes to obtain the federated learning and training tasks based on the information data in the database model; after the running nodes complete the federated learning and training tasks, share the information data.
  • the transaction data blockchain will be established in the online activities based on the metaverse virtual reality application scene, the database model will be established without leaving the local data, and the training tasks of shared machine learning will be issued in the form of smart contracts. Realize information sharing of online data while protecting the privacy of participants.
  • the method in FIG. 6 is a refined shared information privacy protection method provided in the second embodiment of the present application.
  • the shared information privacy protection method includes:
  • Step 601. Establish transaction data blockchain in online activities based on metaverse virtual reality application scenarios.
  • Step 602 when feature intersection occurs between participants, acquire item configuration files transferred between participants.
  • Step 603 Encrypt the item configuration file and send it to each participant.
  • Step 604 After each participant receives the item configuration file, recommend each participant's own user configuration file and item configuration file through horizontal federated matrix decomposition.
  • Step 605 constructing a corresponding database model according to the recommended user profile and item profile.
  • Step 606 based on the smart contract of the transaction data block chain, control the running node to acquire the federated learning training task based on the information data in the database model.
  • Step 607 after the running node completes the federated learning training task, share the information data.
  • the database model is constructed through corresponding federated factorization machine training and horizontal federated matrix training, and federated learning and training tasks are issued through blockchain smart contracts, and the running nodes are controlled to selectively acquire training tasks.
  • participants greatly reduce the occurrence of operational risk and credit risk, making online information sharing safer.
  • the transaction data blockchain is established in the online activities based on the Metaverse virtual reality application scene; according to the construction of the transaction data blockchain and the Metaverse virtual reality application
  • the database model corresponding to the characteristics of the participants in the scene; the smart contract based on the transaction data blockchain controls the running node to obtain the federated learning training task based on the information data in the database model; after the running node completes the federated learning training task, share the information data.
  • the transaction data blockchain will be established in the online activities based on the metaverse virtual reality application scene, the database model will be established without leaving the local data, and the training tasks of shared machine learning will be issued in the form of smart contracts. Realize information sharing of online data while protecting the privacy of participants.
  • FIG. 7 is an electronic device provided by the fourth embodiment of the present application.
  • the electronic device can be used to implement the privacy protection method for shared information in the foregoing embodiments.
  • the electronic equipment mainly includes:
  • the memory 701 and the processor 702 are connected through communication.
  • the processor 702 executes the computer program 703 the network device management method in the foregoing embodiments is realized.
  • the number of processors may be one or more.
  • the memory 701 can be a high-speed random access memory (RAM, Random Access Memory) memory, or a non-volatile memory (non-volatile memory), such as a disk memory.
  • RAM Random Access Memory
  • non-volatile memory non-volatile memory
  • the memory 701 is used to store executable program codes, and the processor 702 is coupled to the memory 701 .
  • the embodiment of the present application also provides a computer-readable storage medium, which can be set in the electronic device in each of the above-mentioned embodiments, and the computer-readable storage medium can be the memory in the example embodiment.
  • a computer program is stored on the computer-readable storage medium, and when the program is executed by a processor, the shared information privacy protection method in the foregoing embodiments is implemented.
  • the computer storage medium can also be various media that can store program codes such as U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), RAM, magnetic disk or optical disk.
  • the disclosed devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of modules is only a logical function division. In actual implementation, there may be other division methods.
  • multiple modules or components can be combined or integrated. to another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or modules may be in electrical, mechanical or other forms.
  • a module described as a separate component may or may not be physically separated, and a component shown as a module may or may not be a physical module, that is, it may be located in one place, or may also be distributed to multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional module in each embodiment of the present application may be integrated into one processing module, each module may exist separately physically, or two or more modules may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules.
  • the integrated modules are realized in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of software products, and the computer software products are stored in a readable memory
  • the medium includes several instructions to enable a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present application.
  • the above-mentioned readable storage medium includes: various media capable of storing program codes such as U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Bioethics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

Selon un procédé de protection de confidentialité d'informations partagées basé sur le métavers et un appareil associé fournis par la solution de la présente demande, une chaîne de blocs de données de transaction est établie dans une activité en ligne sur la base d'un scénario d'application de réalité virtuelle basé sur le métavers ; un modèle de base de données correspondant à des caractéristiques de participants dans le scénario d'application de réalité virtuelle basé sur le métavers est construit selon la chaîne de blocs de données de transaction ; un nœud d'exécution est commandé au moyen d'un contrat intelligent de la chaîne de blocs de données de transaction pour obtenir une tâche d'apprentissage pour des données d'informations dans le modèle de base de données ; et après que le nœud d'exécution achève une tâche de formation d'apprentissage fédéré, les données d'informations sont partagées. Au moyen de la mise en œuvre de la solution selon la présente demande, la chaîne de blocs de données de transaction est établie dans l'activité en ligne sur la base du scénario d'application de réalité virtuelle basé sur le métavers, le modèle de base de données est établi en partant du principe que les données sont toujours locales, que la tâche de formation de partage d'apprentissage machine est publiée sous la forme d'un contrat intelligent, et que le partage d'informations de données en ligne est réalisé à la condition de protéger la confidentialité des participants.
PCT/CN2022/073982 2022-01-26 2022-01-26 Procédé de protection de confidentialité d'informations partagées basé sur le métavers et appareil associé WO2023141809A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/073982 WO2023141809A1 (fr) 2022-01-26 2022-01-26 Procédé de protection de confidentialité d'informations partagées basé sur le métavers et appareil associé

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/073982 WO2023141809A1 (fr) 2022-01-26 2022-01-26 Procédé de protection de confidentialité d'informations partagées basé sur le métavers et appareil associé

Publications (1)

Publication Number Publication Date
WO2023141809A1 true WO2023141809A1 (fr) 2023-08-03

Family

ID=87470120

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/073982 WO2023141809A1 (fr) 2022-01-26 2022-01-26 Procédé de protection de confidentialité d'informations partagées basé sur le métavers et appareil associé

Country Status (1)

Country Link
WO (1) WO2023141809A1 (fr)

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116860114A (zh) * 2023-09-04 2023-10-10 腾讯科技（深圳）有限公司 基于人工智能的扩展现实交互方法及相关装置
CN116957110A (zh) * 2023-09-20 2023-10-27 中国科学技术大学 一种基于联盟链的可信联邦学习方法及系统
CN116992148A (zh) * 2023-08-16 2023-11-03 北京中关村软件园发展有限责任公司 一种元宇宙平台互动式资源智能匹配方法及系统
CN117081758A (zh) * 2023-10-16 2023-11-17 无锡容智技术有限公司 一种基于区块链的元宇宙通话方法及系统
CN117094687A (zh) * 2023-10-20 2023-11-21 湖南腾琨信息科技有限公司 基于元宇宙的设备精细化管理平台及构建方法
CN117094031A (zh) * 2023-10-16 2023-11-21 湘江实验室 工业数字孪生数据隐私保护方法及相关介质
CN117217710A (zh) * 2023-10-19 2023-12-12 深圳市金文网络科技有限公司 一种虚拟商品与快捷服务的智能化管理方法及系统
CN117251726A (zh) * 2023-08-28 2023-12-19 北京邮电大学 公共卫生事件检测模型训练方法、检测方法、装置及系统
CN117271459A (zh) * 2023-11-17 2023-12-22 广东广宇科技发展有限公司 一种基于共享数据库的数据处理方法
CN117319226A (zh) * 2023-11-29 2023-12-29 中南大学 基于元宇宙的数据处理方法、装置、电子设备和存储介质
CN117472866A (zh) * 2023-12-27 2024-01-30 齐鲁工业大学(山东省科学院) 一种区块链监管与激励下的联邦学习数据共享方法
CN117556919A (zh) * 2023-10-20 2024-02-13 杭州安恒信息技术股份有限公司 基于签名聚类的个性化图联邦学习方法、系统及存储介质
CN117711234A (zh) * 2024-02-01 2024-03-15 南昌菱形信息技术有限公司 一种基于元宇宙技术的职业教育实训系统及方法
CN117939618A (zh) * 2024-01-25 2024-04-26 齐鲁工业大学(山东省科学院) 一种基于数字孪生的车联网数据共享系统
CN117932686A (zh) * 2024-03-22 2024-04-26 成都信息工程大学 基于激励机制的元宇宙中联邦学习隐私保护方法和系统、介质
CN118132781A (zh) * 2024-04-30 2024-06-04 合肥链世科技有限公司 一种基于aigc的元宇宙场景生成系统
CN118157839A (zh) * 2024-03-20 2024-06-07 人民数据管理(北京)有限公司 基于人民链的公共数据运营授权方法及系统
CN118296136A (zh) * 2024-06-05 2024-07-05 烟台云朵软件有限公司 基于ai的元宇宙内容生成系统
CN118761052A (zh) * 2024-09-03 2024-10-11 湘江实验室 基于联邦学习和区块链的身份标识方法、装置及相关设备
CN119226065A (zh) * 2024-12-05 2024-12-31 中国电子技术标准化研究院（（工业和信息化部电子工业标准化研究院）（工业和信息化部电子第四研究院）） 一种基于区块链和数字人复制技术的非嵌入式元宇宙多种自动漫游性能测试方法
CN119228968A (zh) * 2024-12-03 2024-12-31 江西财经大学 一种联合drl和afl的元宇宙场景缓存方法
CN119273260A (zh) * 2024-12-10 2025-01-07 北京市大数据中心 基于联邦控制的多源数据协同方法、装置、电子设备及介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190188787A1 (en) * 2017-12-20 2019-06-20 Accenture Global Solutions Limited Analytics engine for multiple blockchain nodes
CN111125779A (zh) * 2019-12-17 2020-05-08 山东浪潮人工智能研究院有限公司 一种基于区块链的联邦学习方法及装置
CN111552986A (zh) * 2020-07-10 2020-08-18 鹏城实验室 基于区块链的联邦建模方法、装置、设备及存储介质
CN113011598A (zh) * 2021-03-17 2021-06-22 深圳技术大学 一种基于区块链的金融数据信息联邦迁移学习方法及装置
CN113657609A (zh) * 2021-08-18 2021-11-16 深圳技术大学 基于区块链与联邦迁移学习的数据管理方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190188787A1 (en) * 2017-12-20 2019-06-20 Accenture Global Solutions Limited Analytics engine for multiple blockchain nodes
CN111125779A (zh) * 2019-12-17 2020-05-08 山东浪潮人工智能研究院有限公司 一种基于区块链的联邦学习方法及装置
CN111552986A (zh) * 2020-07-10 2020-08-18 鹏城实验室 基于区块链的联邦建模方法、装置、设备及存储介质
CN113011598A (zh) * 2021-03-17 2021-06-22 深圳技术大学 一种基于区块链的金融数据信息联邦迁移学习方法及装置
CN113657609A (zh) * 2021-08-18 2021-11-16 深圳技术大学 基于区块链与联邦迁移学习的数据管理方法及系统

Cited By (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116992148A (zh) * 2023-08-16 2023-11-03 北京中关村软件园发展有限责任公司 一种元宇宙平台互动式资源智能匹配方法及系统
CN116992148B (zh) * 2023-08-16 2024-02-02 北京中关村软件园发展有限责任公司 一种元宇宙平台互动式资源智能匹配方法及系统
CN117251726A (zh) * 2023-08-28 2023-12-19 北京邮电大学 公共卫生事件检测模型训练方法、检测方法、装置及系统
CN116860114B (zh) * 2023-09-04 2024-04-05 腾讯科技（深圳）有限公司 基于人工智能的扩展现实交互方法及相关装置
CN116860114A (zh) * 2023-09-04 2023-10-10 腾讯科技（深圳）有限公司 基于人工智能的扩展现实交互方法及相关装置
CN116957110A (zh) * 2023-09-20 2023-10-27 中国科学技术大学 一种基于联盟链的可信联邦学习方法及系统
CN116957110B (zh) * 2023-09-20 2024-01-05 中国科学技术大学 一种基于联盟链的可信联邦学习方法及系统
CN117081758A (zh) * 2023-10-16 2023-11-17 无锡容智技术有限公司 一种基于区块链的元宇宙通话方法及系统
CN117094031A (zh) * 2023-10-16 2023-11-21 湘江实验室 工业数字孪生数据隐私保护方法及相关介质
CN117081758B (zh) * 2023-10-16 2024-02-27 无锡容智技术有限公司 一种基于区块链的元宇宙通话方法
CN117094031B (zh) * 2023-10-16 2024-02-06 湘江实验室 工业数字孪生数据隐私保护方法及相关介质
CN117217710A (zh) * 2023-10-19 2023-12-12 深圳市金文网络科技有限公司 一种虚拟商品与快捷服务的智能化管理方法及系统
CN117094687A (zh) * 2023-10-20 2023-11-21 湖南腾琨信息科技有限公司 基于元宇宙的设备精细化管理平台及构建方法
CN117094687B (zh) * 2023-10-20 2024-01-26 湖南腾琨信息科技有限公司 基于元宇宙的设备精细化管理平台及构建方法
CN117556919A (zh) * 2023-10-20 2024-02-13 杭州安恒信息技术股份有限公司 基于签名聚类的个性化图联邦学习方法、系统及存储介质
CN117271459A (zh) * 2023-11-17 2023-12-22 广东广宇科技发展有限公司 一种基于共享数据库的数据处理方法
CN117271459B (zh) * 2023-11-17 2024-04-09 广东广宇科技发展有限公司 一种基于共享数据库的数据处理方法
CN117319226A (zh) * 2023-11-29 2023-12-29 中南大学 基于元宇宙的数据处理方法、装置、电子设备和存储介质
CN117472866A (zh) * 2023-12-27 2024-01-30 齐鲁工业大学(山东省科学院) 一种区块链监管与激励下的联邦学习数据共享方法
CN117472866B (zh) * 2023-12-27 2024-03-19 齐鲁工业大学(山东省科学院) 一种区块链监管与激励下的联邦学习数据共享方法
CN117939618A (zh) * 2024-01-25 2024-04-26 齐鲁工业大学(山东省科学院) 一种基于数字孪生的车联网数据共享系统
CN117711234A (zh) * 2024-02-01 2024-03-15 南昌菱形信息技术有限公司 一种基于元宇宙技术的职业教育实训系统及方法
CN117711234B (zh) * 2024-02-01 2024-04-19 南昌菱形信息技术有限公司 一种基于元宇宙技术的职业教育实训系统及方法
CN118157839A (zh) * 2024-03-20 2024-06-07 人民数据管理(北京)有限公司 基于人民链的公共数据运营授权方法及系统
CN117932686B (zh) * 2024-03-22 2024-05-31 成都信息工程大学 基于激励机制的元宇宙中联邦学习隐私保护方法和系统、介质
CN117932686A (zh) * 2024-03-22 2024-04-26 成都信息工程大学 基于激励机制的元宇宙中联邦学习隐私保护方法和系统、介质
CN118132781A (zh) * 2024-04-30 2024-06-04 合肥链世科技有限公司 一种基于aigc的元宇宙场景生成系统
CN118296136A (zh) * 2024-06-05 2024-07-05 烟台云朵软件有限公司 基于ai的元宇宙内容生成系统
CN118761052A (zh) * 2024-09-03 2024-10-11 湘江实验室 基于联邦学习和区块链的身份标识方法、装置及相关设备
CN119228968A (zh) * 2024-12-03 2024-12-31 江西财经大学 一种联合drl和afl的元宇宙场景缓存方法
CN119226065A (zh) * 2024-12-05 2024-12-31 中国电子技术标准化研究院（（工业和信息化部电子工业标准化研究院）（工业和信息化部电子第四研究院）） 一种基于区块链和数字人复制技术的非嵌入式元宇宙多种自动漫游性能测试方法
CN119273260A (zh) * 2024-12-10 2025-01-07 北京市大数据中心 基于联邦控制的多源数据协同方法、装置、电子设备及介质

Similar Documents

Publication Publication Date Title
WO2023141809A1 (fr) Procédé de protection de confidentialité d'informations partagées basé sur le métavers et appareil associé
CN114417421B (zh) 一种基于元宇宙的共享信息隐私保护方法及相关装置
CN112183730A (zh) 一种基于共享学习的神经网络模型的训练方法
CN112257873A (zh) 机器学习模型的训练方法、装置、系统、设备及存储介质
CN111368319A (zh) 一种联邦学习环境下基于区块链的数据安全访问方法
CN112162959B (zh) 一种医疗数据共享方法及装置
CN113660327A (zh) 一种区块链系统、区块链节点加入方法和交易方法
CN111081337A (zh) 一种协同任务预测方法及计算机可读存储介质
Zhang et al. Application of blockchain in the field of intelligent manufacturing: Theoretical basis, realistic plights, and development suggestions
Cai et al. Building a secure knowledge marketplace over crowdsensed data streams
CN112600697B (zh) 基于联邦学习的QoS预测方法及系统、客户端和服务端
CN113011598A (zh) 一种基于区块链的金融数据信息联邦迁移学习方法及装置
Kurupathi et al. Survey on federated learning towards privacy preserving AI
CN112257112A (zh) 一种基于区块链的数据访问控制方法
CN114880715A (zh) 一种基于同态加密智能合约的电力数据安全共享方法及系统
Chen et al. Privacy-preserving swarm learning based on homomorphic encryption
WO2023124219A1 (fr) Procédé de mise à jour itérative de modèle d'apprentissage conjoint, appareil, système et support de stockage
Wang et al. Blockchain-Based Decentralized Reputation Management System for Internet of Everything in 6G-Enabled Cybertwin Architecture.
Bandara et al. Bassa-ml—a blockchain and model card integrated federated learning provenance platform
Parra-Ullauri et al. Federated analytics for 6G networks: Applications, challenges, and opportunities
Liu et al. ProSecutor: Protecting mobile AIGC services on two-layer blockchain via reputation and contract theoretic approaches
Jaberzadeh et al. Blockchain-based federated learning: incentivizing data sharing and penalizing dishonest behavior
Liu et al. Blockchain and mobile client privacy protection in e-commerce consumer shopping tendency identification application
CN114363089A (zh) 基于区块链的网络边缘终端数据共享方法和模型
CN113657609A (zh) 基于区块链与联邦迁移学习的数据管理方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22922660

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22922660

Country of ref document: EP

Kind code of ref document: A1