405 results about "Data provider" patented technology

The invention discloses an urban multi-mode digital twin data asset security management method, and relates to the technical field of urban digital twin and data security, and the method comprises the steps: firstly building a unified access gateway, converging multi-department and multi-type data, and generating sensitivity annotation and privacy level metadata; performing differential privacy or desensitization and dynamically calibrating parameters at the local part of the data provider according to the labels; bookkeeping access, authorization and training on a permission alliance chain, and performing fine-grained permission control; through on-chain authorization, each node only uploads disturbed and encrypted model update, and a global model is obtained after secure aggregation; the governance layer continuously monitors logs, budget and model indexes and triggers strategy closed-loop regulation and control; and multi-agent reinforcement learning of a privacy agent and a performance agent is further introduced, a unified multi-target optimizer is formed through distillation, privacy, federation and permission strategies are refreshed online, and collaborative analysis and compliance sharing operation without data out of a domain are realized.

The embodiment of the invention provides a credit scoring method and device for a credit white user. Wherein the data provider comprises a government affair platform party, a transaction opposite party and a financial institution party, and the user data of the financial institution party comprises a user identifier of a credit white user. And the plurality of data providers align the local user data of each party through a privacy intersection algorithm, so that each party determines the first user data of the aligned credit white user from the local user data. And the plurality of data providers respectively encrypt the local first user data of each party and send the encrypted first user data to the service platform. And the service platform performs secret state model prediction based on a local credit scoring model and the first encrypted user data of each party, obtains a secret state credit score of the credit white user, and provides the secret state credit score to a score user. And the score user decrypts the credit score from the secret state credit score, and determines a risk control decision for the credit white user based on the credit score.

The invention discloses a data security sharing method and system, and relates to the technical field of data sharing. The method comprises the steps that a data provider uploads original data, a privacy budget value is calculated through a differential privacy algorithm, noise is added to obtain noisy data, and the noisy data is processed through an anonymous privacy protection algorithm based on maximum dissimilarity degree clustering to obtain desensitized data; encrypting the desensitized data by adopting a block chain decentralization-based ciphertext policy attribute-based encryption method, obtaining an encrypted data ciphertext, uploading the encrypted data ciphertext to a cloud server, and obtaining a content addressing hash value; encrypting the hash value through an elliptic curve encryption algorithm, and storing the encrypted hash value to a block chain account book; and when an access request of a data requester is received, the cloud server verifies the authority by using a non-interactive zero-knowledge proof protocol and returns an encrypted hash value after passing the verification, and the requester decrypts to obtain the hash value and decrypts the encrypted ciphertext to obtain desensitized data, thereby realizing data sharing.

The invention discloses a large model corpus data interaction system and method based on a trusted execution environment, a terminal and a medium. The system comprises a data provider, a data demander and a trusted data space service platform. And the data provider is used for encrypting the corpus data, and performing preprocessing, directory sorting and packaging on the corpus data in the data provider connector to obtain the data capsule. And the data demander is used for submitting a calculation task in the data demander connector and obtaining corpus data of the data capsule for calculation after authorization. And the trusted data space service platform is used for storing the encrypted corpus data, controlling access of a data user, scheduling a calculation task, managing a key and generating an audit log. Through trusted execution environment hardware isolation and full-link encryption, it is ensured that corpus data only exists in a plaintext form in the trusted execution environment in the full life cycle from access to destruction, and unauthorized access and leakage are completely eradicated.

The invention discloses a trusted data sharing method based on a block chain consensus mechanism. The method comprises the following steps: S1, constructing an alliance chain network; s2, completing KZG polynomial commitment generation, ML-KEM algorithm encryption storage and pointer registration; s3, the data provider medical institution completes an evidence storage transaction of the FROST threshold signature; s4, the target medical institution completes the access request transaction; s5, the data provider medical institution sends a KZG unpacking proof and a data item, the target medical institution obtains a storage pointer and a commitment value, KZG verification check is executed, and after verification is passed, an ML-KEM algorithm is executed for depacking to obtain a session key; and S6, the target medical institution completes the audit transaction, and after the alliance chain network broadcast, the consensus node executes rule verification of the access control contract and the audit contract. The multi-node electronic medical record sharing and tamper-proof evidence storage method is high in performance and traceability, and is suitable for credible circulation of sensitive health data among multiple medical institutions.

The invention provides a data capsule generation and verification method and device, equipment and a medium. The method is applied to a data sending end, and comprises the following steps: determining an encryption key and an access strategy corresponding to a data provider; performing encryption processing on the to-be-encrypted data based on the encryption key to obtain encrypted data, and determining a first encryption parameter corresponding to the encrypted data according to the encrypted data and an access policy; based on the first encryption parameter and the identity information, adopting a preset calculation rule to generate a capsule identifier corresponding to the to-be-encrypted data; and packaging the capsule identifier, the access strategy, the encrypted data and a preset calculation rule to obtain a corresponding data capsule. According to the scheme, the verifiable and non-tampering capsule identifier is generated based on the encrypted data, the access strategy and the identity information, so that the risks of data packet switching, content replacement, strategy tampering and the like are effectively prevented, and the structural security and the use control credibility of the data capsule are improved.

The invention discloses a data fine-grained access control method, system and device and a medium, mainly relates to the technical field of access control, and is used for solving the problems of identity and attribute separation, low strategy updating efficiency and insufficient auditing capability in the existing scheme. Comprising the steps that a data user generates a distributed digital identity document containing at least one role attribute through a distributed digital identity system, and the distributed digital identity document is subjected to uplink storage after being audited by a registration mechanism; the data provider generates an ABE private key according to the main public key and an access control strategy, encrypts the ABE private key by using the DID public key of the data user, and sends the encrypted ABE private key to the data user; the data user obtains an ABE private key by using the DID private key; decrypting the ABE ciphertext on the block chain by using the ABE private key to obtain a symmetric key; and obtaining the original data in the trusted data space through symmetric key decryption.

An example method includes determining a provider distribution by television viewing area using a provider-reported number of subscribers for a television viewing area and a sum of weights of panelist households that are located within the television viewing area. The method also includes obtaining a target distribution of a characteristic for the television viewing area. In addition, the method includes determining, using iterative proportional fitting, provider-specific distributions of the characteristic for the television viewing area. And the method includes using the provider-specific distributions of the characteristic for the television viewing area as a basis for assigning values of the characteristic to households that are subscribers of the return path data provider and located in the television viewing area.

An example operation may include one or more of receiving, at a data provider, a data file from a data modifier which comprises a modification to an initial content state of a data file, generating a hash value of the initial content state of the data file prior to modification and generating a hash value of a modified content state of the data file after the modification, and transmitting the generated hash values to a blockchain peer node for inclusion within one or more data blocks among a hash-linked chain of data blocks.

The embodiment of the invention provides a structured data field use control method and device, a medium and a product, and relates to the technical field of data use. The method comprises the steps of obtaining a data product published by a data provider; the data product is formed by accessing structured data into a data space in a data source form by a data provider; binding a target strategy generated based on the structured data to the data product, and determining a bound target data product; the target strategy comprises a post strategy and a calculation strategy executed at a first trusted connector of the data user, and a pre strategy executed at a second trusted connector of the data provider; and performing data contract signing with the data provider according to the target data product. The method is based on a structured data form, and is more accurate than traditional privacy calculation control; the target strategy and the data product are directly bound, and a traditional strategy configuration mode based on a central server is replaced.

The invention discloses a port wave spectrum parametric modeling algorithm based on machine learning, and relates to the technical field of ocean engineering, and high-precision modeling is realized through three steps: step one, constructing a federated learning framework, training sub-models by data parties only sharing parameters, combining homomorphic encryption fusion features and dynamically adjusting weights, and constructing a model; privacy protection type data fusion is realized; a second step of deploying a generative adversarial network at each local node, extracting multi-scale wave features through a frequency domain hierarchical attention branch network, implanting a sea wave energy conservation constraint and optimizing a generator, generating an extreme sample conforming to a physical law, and forming a mixed training data set; and a third step of training a CNN-LSTM basic model, and realizing dynamic optimization of the model through a sliding window, a forgetting factor, Bayesian optimization and performance monitoring reconstruction. The method effectively improves the wave spectrum prediction precision and long-term stability, reduces the maintenance cost, and can be used for scenes such as port ship berthing and disaster prevention early warning.

The invention discloses a data use control method and system based on a smart contract, and relates to the technical field of data use control, and the system comprises an identity authentication module, a data classification and grading module, a data sandbox module and an evidence storage traceability module. Performing identity authentication on a user request of a data user based on an authentication protocol; performing classification rating on the accessed data; the data user and the data provider negotiate a contract signing detailed rule; the data user and the data provider sign a block chain smart contract; deploying the intelligent contract to a data sandbox, performing authority evaluation and distribution on the user, and performing behavior monitoring on the user; when the data user violates the signed smart contract, terminating the data access permission of the user, and calling the data sandbox to execute operation according to the contract signing content; logs are automatically generated, data access and use circulation are traced in the whole process, and it is ensured that data can be traced, audited and managed from authorization to use. According to the invention, the security and credibility of data circulation are guaranteed in a data transmission use control mode with decentration and multi-party cooperative participation.

In an embodiment, a method provides an environment for privately exchanging data for AI tasks. Identification of a task to perform, and a characteristic describing data needed to execute the task, is received. A data provider within the environment is located that has access to a data set according to the characteristic. A task provider within the environment is located. The located task provider is configured to execute the task. A real-time, private, and secure network connection between the data provider and the task provider is established. The established connection is configured such that the data provider and the task provider are able to communicate via the network connection without using publicly accessible network addresses. The data set is transferred from the data provider to the task provider via the established network connection. In response to the transfer, the task provider executes the task using the data set.

The invention discloses a data processing method and device, a medium, equipment and a product. According to the scheme, after the data platform receives the data processing request sent by the data demander, the encrypted first privacy data set can be determined according to the data processing request, and the privacy data set can be processed based on the user data adopted by at least one data provider. The method comprises the following steps: acquiring a first private data set, acquiring a second private data set encrypted by adopting an encryption mode of encrypting the first private data set, comparing the first private data set with the second private data set to obtain an intersection data set, and further returning a service result for a specified service to a data demander based on the obtained intersection data set.

Provided in the present disclosure are a data circulation method and apparatus, and a first platform and a first node. The method comprises: a first platform receiving information which is related to a data resource and is sent by a first node; and the first platform adding to a global data directory the information related to the data resource, wherein the first node is a trusted computing node of a data provider, and the first platform is a data scheduling center platform.

The invention provides a financial big data information processing system based on a block chain. The financial big data information processing system based on the block chain comprises a block chain network access module used for accessing financial institution nodes and data provider nodes to an alliance chain network and synchronizing distributed account books among the nodes through a Byzantine fault-tolerant consensus algorithm so as to realize tamper-proof evidence storage and multi-party trust cooperation of financial big data information. According to the financial big data information processing system based on the block chain, through homomorphic encryption, zero-knowledge proof and other technologies, operation and verification of data in an encryption state are ensured, privacy of sensitive information is effectively protected, and data sharing and calculation can be smoothly carried out while confidentiality is ensured.

The invention provides an exception handling method and device, a storage medium, electronic equipment and a product. The exception handling method is applied to a credit investigation system corresponding to a credit investigation mechanism, and comprises the following steps: receiving a data query request for target data sent by a data demand side, and querying the target data from a data provider according to the data query request; processing the target data returned by the data provider to obtain a processing result; if the data processing result is successful, credit investigation data obtained after the target data is processed is returned to the data demander; if the data processing result is failure, determining a failure type causing data processing failure based on an abnormal state code carried in the data processing result, and triggering an exception processing flow matched with the failure type; wherein different abnormal state codes correspond to different failure types, and the failure types comprise service side failures caused by inconformity with service rules and system side failures caused by abnormity of the credit investigation system.

A computer-implemented method and a distributed computer system for privacy-preserving distributed training of a global neural network model on distributed datasets. The system has data providers communicatively coupled with each having a respective local training dataset and a vector of output labels for training the global model. Further, it has a cryptographic distributed secret key and a corresponding collective cryptographic public key of a multiparty fully homomorphic encryption scheme, with the weights of the global model being encrypted with the collective public key. Each data provider computes and aggregates, for each layer of the global model, encrypted local gradients using the respective local training dataset and output labels, with forward pass and backpropagation using stochastic gradient descent. One data provider homomorphically combines the current local gradients of the data providers into combined local gradients, and updates the weights of the current global model based on the combined local gradients.

A method, a system, and computer program product for managing tokenized biospecimen transfers are provided. A file including private data associated with one or more donors is retrieved by a biobank node connected to a blockchain network and from a database of a data provider. The file is processed to generate tokens corresponding to the private data, each token representing a biospecimen and being assigned to a respective donor. An inventory is updated by adding identifiers of the plurality of tokens to the inventory. A request to transfer one or more tokens corresponding to a portion of the private data is received. An authorization to transfer the one or more tokens to a target entity is received. The token is transferred to the target entity with a consent to perform one or more operations using the token.

The invention belongs to the technical field of cryptography and secure multi-party computing, and provides a homomorphic encryption multiplication triple generation method and system based on the Chinese remainder theorem.A data application party and a data provider generate private random vectors respectively, and the private random vectors are decomposed into a plurality of component matrixes by means of the Chinese remainder theorem; the data provider executes ciphertext multiplication and addition operation in the corresponding parallel channels according to the number of the component matrixes, the ciphertext of each channel is calculated based on a BFV homomorphic encryption algorithm, and the ciphertext result is sent to the data application party; and the two parties decrypt each ciphertext by using the private key to obtain a plaintext component matrix, reconstruct through the Chinese remainder theorem to obtain a plaintext vector, and calculate a local triad component based on the plaintext vector to generate a triad, and the triad meets the multi-party multiplication constraint. According to the method, the Chinese remainder theorem and the homomorphic encryption algorithm are ingeniously combined, efficient and extensible multiplication triple generation is achieved, and the efficiency and space limitation in the prior art is broken through.

The invention provides a regression test method and device, a storage medium, electronic equipment and a product. The regression test method comprises the following steps: acquiring credit investigation service data generated by a credit investigation system in a process of executing an actual credit investigation service, the credit investigation service data comprises input request parameters input by the data demander to the credit investigation system, original data returned by the data provider to the credit investigation system, actual output request parameters sent by the credit investigation system to the data provider and actual credit investigation data returned by the credit investigation system to the data demander; after business change is executed on the credit investigation system, inputting the input request parameter into the credit investigation system to obtain an analog output request parameter, and inputting the original data into the credit investigation system to obtain analog credit investigation data; and according to the deviation between the actual output request parameter and the analog output request parameter and the deviation between the actual credit investigation data and the analog credit investigation data, determining whether the credit investigation system successfully completes the business change.

The disclosure is generally directed to a method and system for charge station management including collecting data related to a plurality of charge stations, the data identifying location data, an operator, and a data provider for each of the plurality of charge stations, collating the data to match the location data with the operators of each of the plurality of charge stations, and merging the location data based on a set of criteria including the data from each of the data providers within an identified geohash location. Merging includes setting a geohash about a data provider, and merging location data within the predetermined perimeter to remove redundant locations based on a set of criteria, including criteria identifying a same operator within the geohash.

The invention relates to the technical field of data circulation and data security, and discloses a digital ecological data market circulation system, comprising: a data provider node deployed with a federated learning client and used for locally training a model by using original data, generating an encrypted intermediate result and managing a corresponding data asset voucher; the data demand side node is deployed with a federated learning coordination server and is used for defining a federated learning task, distributing an initial model and aggregating intermediate results from each data provider node to update a global model; the data element circulation method comprises the following steps of data capitalization and voucher generation, federal learning and process evidence storage, under-chain credible contribution degree evaluation and intelligent contract driven settlement. Compared with the prior art, the method has the advantages that the leakage risk is completely eradicated from the root of technology, a dynamic and accurate value evaluation and distribution system is achieved, a credible environment which is traceable in the whole process and transparent in rule is constructed, and the mobility and financial attributes of data assets are improved.

The invention provides a block chain-based data security processing platform, which relates to the technical field of computer software and information, and comprises a block chain architecture system, a data security processing system and a data sharing system, the block chain architecture system comprises a data provider node, a data user node, a supervision node and a consensus node; according to the invention, multiple system modules are covered, a data security processing system combines AES and RSA encryption, integrity is verified by means of a Hash algorithm, access control is set by means of a smart contract, a data sharing system sets a sharing rule according to the smart contract, data is traced by means of a block chain, and sharing is promoted by means of an incentive mechanism; various block chain types and adaptive consensus mechanisms are provided, a system management and maintenance module checks nodes every day, full data backup is performed to three places every week, a system is audited every month, node faults are processed within 24 hours, safety problems are repaired in seven workdays, and stable, safe and compliant operation of a platform is guaranteed.

The invention discloses a privacy protection fine tuning and security testing method for a large model, and belongs to the technical field of artificial intelligence, and the method comprises the steps: 1, enabling a data provider to cooperate with an edge coordinator to generate a feature extraction edge auxiliary model based on edge-end federal pre-training, and carrying out the feature matching of distillation privacy data based on multiple spatial data; 2, the data provider generates distillation data with an invisible backdoor; and step 3, the task initiator finely adjusts the cloud target large model and performs a security test. The method aims at protecting the privacy of private data of the data provider, reducing the scale of fine adjustment data and realizing the security test of the fine adjustment process of the large model.

The invention relates to the technical field of data security, and provides a decision generation method and device, electronic equipment and a storage medium. The method comprises the following steps: receiving a data request comprising request related information, and evaluating whether the request related information meets a compiling strategy to obtain an evaluation result; when the evaluation result represents that the request related information meets the compiling strategy, generating an allowable decision; the compiling strategy is obtained by compiling an abstract syntax tree, the abstract syntax tree is obtained by analyzing strategy description defined by the data provider, and the strategy description comprises a use rule of the data resource corresponding to the data resource identifier. According to the method, the strategy description obtained by describing the use rule of the data resource by the data provider is converted into the abstract syntax tree, then the abstract syntax tree is compiled to obtain the compilation strategy, and then the request related information is evaluated based on the compilation strategy, so that the execution process of the compilation strategy generated based on the abstract syntax tree is simplified, and the user experience is improved. Therefore, the decision generation efficiency is improved.

The invention discloses an early warning method, electronic equipment and a computer program product, and relates to the technical field of data mining. The early warning method comprises the following steps: connecting a plurality of data providers through a data network, wherein each data provider has a corresponding data source; based on the data source of each data provider, a federated learning algorithm is utilized to establish a risk assessment model, the risk assessment model is used for determining the probability that the input data is a positive sample, and the data of each data provider is not out of a domain; determining a risk score of a person to be pre-warned based on the risk assessment model; and carrying out risk early warning based on the risk score.

The invention discloses a multi-party data circulation method and system and a readable storage medium, and belongs to the technical field of data circulation. Comprising the following steps: selling data based on at least one data provider node and a trained selling model; based on the at least one data demander node and a preset scene and demand, purchasing data; and data configuration is performed, so that the data of the data provider and the data demander can be effectively circulated. According to the method, free issuing and automatic matching between the data provider and the data demander can be realized, meanwhile, data configuration is optimized, multiple transactions are matched each time, the data circulation time is saved, the data circulation efficiency is improved, the calculated amount is small, the convergence speed is higher, and the practical value is very high.

The invention relates to a data acquisition method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining current collection data item information through a target interface; generating collection configuration information based on the current collection data item information and a preset template, accessing an endpoint of the data agent collection tool according to the collection configuration information, and obtaining an index name and label data in a target format through the endpoint; the data agent acquisition tool determines a data provider by reading the acquisition configuration information, acquires to-be-processed data from the data provider, screens out target data from the to-be-processed data based on the acquisition configuration information, and converts the target data into an index name and label data in a target format; and sending the index name of the target format and the label data to a target database to complete data acquisition. By adopting the method, the efficiency of data acquisition configuration can be improved, so that the flexibility and expandability of data acquisition configuration are improved.

The invention discloses a medical data sharing transaction method based on trust and credibility in a block chain environment, and the method comprises two stages and four roles, and employs four intelligent contracts. The two stages are a request stage and a data transaction stage, and the four roles are a data request user DR, a block chain network, a cloud service CS and a data provider DP; the four intelligent contracts are a data request contract DRC, a recommendation management contract RMC, an attribute management contract AMC and a data sharing traceability contract DSTC; according to the EHR sharing method based on profit driving, the data transaction volume is converted into cost and profit earnings based on the credibility of the DR and the global trust of the DP, and an EHR data credible sharing platform based on trust-driven profit is constructed; a comprehensive trust calculation method of the DP is designed, a trust management model based on global trust is constructed, and profits and earnings of the DP are quantified based on the global trust; normal and malicious DRs are identified through a credibility calculation method of the DRs, and the sharing cost of the DRs is quantified based on credibility.