63 results about "Native client" patented technology

The invention discloses a federal learning method and system based on global prototype guidance. The method comprises the following steps: a server sends a global model and a global prototype to a local client; the local client performs rebalance comparison learning by using the global prototype, and updates the local model; the local client generates a balanced confrontation positive prototype instance set and trains a classifier; the local client side calculates a local prototype and uploads the local prototype and the updated local model to the server side; and the service aggregates the updated local model and local prototype, and updates the global model and global prototype. The system comprises a server and a local client. According to the method, the Non-IID problem in federated learning is solved, and the accuracy and generalization of the model are improved. The method can be widely applied to the technical field of distributed machine learning.

The invention relates to an intelligent mapping and two-way synchronization system and method for a cloud disk and a local file system, and belongs to the field of IT and software development.The method comprises the steps that the intelligent mapping relation between the cloud disk and the local file system is established, and when a cloud disk mounting request initiated by a user through a local client side is received, the cloud disk mounting request is sent to the local client side; the intelligent mapping module obtains a cloud disk root directory structure by calling an interface of a cloud disk interface module, and converts the cloud disk root directory structure into a local virtual directory tree; the expansion attribute of the local file system is adopted to store the specific attribute of the cloud disk; when it is monitored that the files in the cloud disk or the local file system change, the mapping relation is refreshed; the change of the cloud disk file and the local file system is monitored in real time, and the bidirectional synchronization of the cloud disk file and the local file is realized. According to the system and the method, cloud disk attribute visualization, cross-platform compatibility and access efficiency optimization are realized.

The invention relates to the technical field of risk assessment, and discloses a risk assessment method, a local client, a federated server and a system based on multimodal transport privacy computing, the method is applied to the local client in the risk assessment system, the risk assessment system further comprises the federated server, the local client is connected with the federated server for use, and the federated server is connected with the local client. The method comprises the following steps: acquiring historical local data, and training a local federated topology model based on the historical local data; determining a parameter update quantity based on the trained local federated topology model, and sending the parameter update quantity to a federated server, so that the federated server performs aggregation based on the parameter update quantity to obtain global model parameters; under the condition that the global model parameters sent by the federated server are received, the local federated topology model is updated according to the global model parameters; and performing risk assessment based on the updated local federated topology model. On the premise of protecting data privacy of each participant, collaborative risk assessment of multi-party data is realized.

The present application relates to geothermal energy development and utilization technical field, specifically to a kind of energy underground subway station design method based on federal learning, through parameter collection, local client local model update, calculation result is uploaded to central server, central server carries out update calculation, issue to local client local model, update iteration until global model robustness, the design result of each module is calculated, and heat exchange efficiency and thermal stress are predicted.The energy underground subway station design method proposed in the present application can fully consider the coordination between indoor user end, unit equipment selection and three kinds of energy station structure pipe end in station, and the design scheme obtained can greatly meet the energy-saving and emission-reducing design concept, with low calculation cost, the influence of heat exchange efficiency and heat exchange process on station structure can be accurately evaluated, and compared with traditional test method and field monitoring method, the cost of manpower and material resources can be greatly reduced.

Requests for artifact data for a containerized application cluster are proxied from a first region of a cloud service to a second region of the cloud service, or another cloud service. A request for the artifact data is received at a first container registry at the first region. The first container registry determines that the artifact data is locally unavailable and in response thereto identifies a peer container registry at the second region that has a copy of the artifact data. A request is sent to the peer container registry for the copy of the artifact data. If the request originated from a local client, then the artifact data is forwarded to the local client via an application programming interface, in some examples.

The invention relates to the technical field of federated learning algorithms, in particular to a fair federated learning method based on multi-agent reinforcement learning, which comprises the following steps: respectively initializing network parameters of a server and a local client, and calculating an initial state vector of a local environment by the local client according to the initialized network parameters; the server calculates the initial state of the global environment, and a local client selects and executes an action; the server updates the classification network and broadcasts the classification network to all local clients, and the local clients update local states and rewards; the server updates the global environment state and stores the data in an experience batch; and the server updates the value network, and the local client updates the strategy network. The strategy network is trained based on centralized training and distributed execution, and the convergence speed of the strategy network can be greatly improved.

The invention discloses a remote key security management method and device for a cloud virtualization cryptographic module, and aims to solve the problems of cloud key trust root, transmission security and the like. The core of the method is to keep the master key control right of a user locally, and through cooperative work of a local client, a cloud management platform and a distributed vHSM instance, through the four steps of system initialization and key fragmentation distribution, remote certification and secure channel establishment, distributed cooperative operation and local result synthesis, and by utilizing IBE, Shamir secret sharing, a threshold cryptographic algorithm and TEE technologies, the user master key control right and the distributed vHSM instance are subjected to remote certification and secure channel establishment, distributed cooperative operation and local result synthesis. And the key is available and invisible. The device comprises three modules, namely a local client, a cloud management platform and a vHSM cluster. The method guarantees secret key confidentiality and completeness, supports a national secret algorithm, meets compliance requirements, adapts to cloud native elasticity requirements, and is suitable for cloud secret key management in industries such as electric power and the like.

The present disclosure provides an image processing method and device, electronic equipment and medium, relates to the technical field of computers, and particularly relates to the technical field of electronic maps, cloud computing and cloud services. The specific implementation scheme is as follows: obtaining map update information of a target trajectory point from a server; the map update information comprises a target trajectory point identifier of the target trajectory point; determining a cache state of target index information in a local client according to the map update information; the target index information comprises the target trajectory point identifier; according to the cache state of the target index information, the target index information is obtained, and a target trajectory image of the target trajectory point is determined according to the obtained target index information. The present disclosure realizes the effect of reducing the data amount of data issued by the server under the premise that the target trajectory image can be determined, reduces the pressure of the server, and avoids the occupation of additional bandwidth of the server.

The invention provides a communication method and device, an electronic control unit and a readable storage medium, the communication method is applied to a client electronic control unit ECU, and comprises the following steps: when a plurality of processes in the client ECU request a first service on a server ECU, sending the first service to the server ECU; a local client identifier in the service request of each process is converted into a remote client identifier of the client ECU to obtain a plurality of request messages, the request messages comprise session identifier fields, and session identifiers of different request messages are different; establishing a mapping relationship between the local client identifier of each process and the session identifier in the corresponding request message; and sending the plurality of request messages to the server ECU.

This invention provides a network attack detection method and system for vehicle-to-grid (V2G) interaction. It includes: a local client capturing raw traffic data and extracting key features; then receiving the latest global model parameters, detecting the raw traffic data and encoding the attack detection results into metadata tags, while simultaneously using the key features to train the global model parameters to calculate the quantization gradient; extracting feature vectors from the raw traffic data and combining them with the metadata tags to perform attack prediction and obtain the attack prediction probability; the local client executing defensive actions based on reinforcement proxy learning on the attack prediction probability; the local client uploading the quantization gradient and metadata tags to the server via a secure sparse aggregation protocol; the server reconstructing the global gradient to update the global model parameters via a key exchange protocol and updating the attention weights of the global model using the metadata tags; the latest global model outputting the attack probability of V2G interaction, determining whether to issue an alarm and execute defensive actions.

The invention provides a deployment mode switching method and device, equipment, a medium and a program product, relates to the technical field of computers, and can solve the problem of insufficient flexibility of an overall deployment architecture. According to the technical scheme, when a service application is started, metadata information of all services in a configuration file is analyzed, and all the services are registered to a service directory; receiving a service request of a client through the data operation service; judging a deployment mode identifier of the service application; if the mode is a distributed deployment mode, acquiring an address of a customer transaction service corresponding to the unique identifier of the target service from a service directory through a data operation service, and calling a remote customer transaction service based on the address; if the mode is the single deployment mode, corresponding service metadata information is acquired locally through the data operation service according to the unique identifier of the target service, and the business process of the local customer transaction service is executed based on the service metadata information. And a process for deploying and calling services.

The application provides a browser remote access method and system. When a local server determines that a local client operating environment is incompatible with a first browser, the method captures and encrypts the operation data of the local client, generates encrypted operation event text and transmits it to a transmission server. The transmission server decrypts and verifies the encrypted operation event text and performs virus scanning, generates first security data, encrypts the first security data to generate first encrypted data and transmits the first encrypted data to a remote server. The remote server analyzes the first encrypted data, obtains operation instructions, executes the operation in the remote first browser according to the operation instructions, encrypts the operation result and transmits it back to the local client in real time through the transmission server. The method and system ensure the real-time performance and efficiency of data transmission on the basis of determining the integrity and security of the transmission data, and improve the real-time performance and convenience of user interaction through remote simulation of user operation.

The invention relates to a personalized federal learning group caching method, which belongs to the technical field of edge caching, and comprises the following steps: S1, selecting a client; s2, the cloud server is initialized randomly, and the client is initialized independently; s3, calculating the social similarity of the client users; s4, training a local client model; s5, performing global embedding after the CKKS homomorphic encryption update; and S6, the server decrypts, aggregates and updates. According to the method, a user social network is constructed through a geographic unit, and an isolated node is selected as a client; the server and the client complete embedding initialization and CKKS key distribution, and after the client calculates the social similarity of users, similar user embedding is fused, and local training is carried out through a dynamic regularization loss function; and the client encrypts and uploads the global item embedding through the CKKS, and the server decrypts the global item embedding and updates the global embedding through weighted aggregation, so that the balance between privacy protection and personalized recommendation is realized.

Methods, systems, and computer storage media for providing speculation management using a speculation management engine of a cloud access management system are described. The speculation management engine operates based on speculation data, a multi-dimensional speculation framework, and two sets of operations defined based on an initialization sequence. In operation, speculation data for a user associated with a local client is accessed. A determination of a plurality of speculated remote resource candidates is made, based on the speculation data associated with the user. Execution of a first set of operations (i.e., remote resource resolution) and a second set of operations (i.e., remote resource connection configuration) are triggered. A determination is made whether a remote resource identified from the remote resource resolution matches a speculated remote resource candidate in the plurality of speculated remote resource candidates. Based on the speculated remote resource candidate, a connection for accessing a remote resource is established.

The invention discloses a data copying method and system, a program product and a storage medium, and the method comprises the steps: receiving a copying request sent by a virtual client, the copying request being used for requesting to copy target text data included in text data displayed in the current virtual client to a local client, the text data is data generated by a remote device, and the remote device is a device for executing remote management operation through a virtual client in the local client; in response to the copy request, obtaining target text data from a first file which is a file generated in advance based on the text data and stored in a local client; and sending the target text data to a local client to display the target text data at the local client. By means of the method and device, the problem that text data cannot be copied in the prior art is solved, and then the effect of copying the text data is achieved.

The application discloses a method for alleviating Non-IID influence based on explainable federated learning. The application mainly introduces a validation set explainable mechanism to depict the explainable results of the validation set samples in the center server based on the influence of local client update on the learning ability of each category of the aggregated model, and evaluates the explainable results of each category by using a structural similarity index (SSIM), so as to deduce the data imbalance clients. Then, the parameters of the data imbalance clients are adjusted, the gradient distance between the model of the data imbalance client and the parameter of the global aggregated model in the last round is minimized, and the parameters of the model of the data imbalance client are corrected through the convergence of the gradient distance, so that the negative influence caused by the data imbalance is weakened.

The application discloses a kind of for virtual production photo batch generation three-dimensional model method, comprising the following steps: user submits image alignment task to solving server in local client;Setting load image alignment generation parameter;Setting running instance number, allocate the CPU and GPU resources of each instance, determine task priority;Submit task, and solving server starts image alignment generation work in turn according to task priority;Save image alignment engineering file;Manual inspection alignment data, operator checks the image alignment file that has been completed, confirms whether image alignment file satisfies generation three-dimensional model demand;Client submits the task that needs three-dimensional model and texture generation;Load setting three-dimensional model, texture, export generation attribute;Setting running instance number, allocate the CPU and GPU resources of each instance, for model texture export setting lower running instance number and corresponding CPU and GPU resources, determine task priority.

The invention discloses a personalized semantic communication method based on knowledge distillation, which belongs to the technical field of semantic communication, and comprises the following steps: S1, executing a pre-training process of a model on a local client by adopting a federal learning architecture; the student model efficiently learns semantic extraction capabilities through distillation based on a local data set. The student model participates in the model aggregation process of federated learning, and the overhead of communication resources is greatly reduced due to the small scale. S2, an encoder of the student model in the first stage is reserved, the encoder contains personalized knowledge of a client side, on this basis, a channel encoding module is added, a proper semantic decoder is designed according to a specific task, and a semantic communication function including image classification and image reconstruction is trained based on a public data set; according to the scheme, a personalized semantic communication function can be realized under the condition of protecting user privacy, and two processes of channel coding and semantic coding are effectively separated.

The invention provides a federal feature forgetting method based on adversarial samples. The method comprises the following steps: a central server broadcasts trained global model parameters to each client; a client initiates a feature forgetting request, identifies a to-be-forgotten feature subset, and constructs a confrontation disturbance vector for the feature subset; the method comprises the following steps: calculating feature sensitivity through model output differences before and after confronting disturbance, introducing the feature sensitivity as a regular term into a loss function, guiding local model training, and after the local model training is completed, uploading updated local model parameters to a central server by a client for participating in global model aggregation and updating. According to the method, on the premise of not depending on other local client data, the dependence of the model on specified features can be efficiently deleted, and data privacy protection and model security enhancement are effectively realized.

This invention relates to the field of machine learning technology and discloses a forgetting learning method, system, device, and medium for local client-side model training. The method includes: distributing a global model to clients participating in federated learning to obtain client-side models; initializing the client-side models to obtain initial client-side models and assigning privacy labels to the training data to obtain privacy-labeled data; calculating the binary cross-entropy loss function value of the initial client-side models; updating and optimizing the initial client-side models based on the binary cross-entropy loss function value to obtain a target client-side model; aggregating the target client-side models to obtain an aggregated global model; and iteratively updating the aggregated global model to obtain the target global model. This invention can improve the efficiency and accuracy of forgetting learning training for client-side models.

The application relates to the technical field of data processing, in particular to a federated recommendation method based on a generative adversarial network and a social graph attention network, which comprises the following steps: after local updating of each local client, target users and interactive items are subjected to an embedding layer to obtain item preference information; an adversarial network generator is used to score the interactive items based on the item preference, so that interactive score samples are obtained; a loss function value is calculated by using the interactive score samples and real scores of initial user-interactive items of the target client; after local model gradients and embedding gradients are derived by using the loss function value, homomorphic encryption is performed, and then aggregation is carried out, so that global model gradients are obtained; the global model gradients are decrypted and distributed to the target client; the target client performs local model updating based on the decrypted global model gradients; and until the social graph attention network converges to a preset degree, a final prediction result is obtained.

A method performed by a local client computing device is provided. The method includes training a local model using data from the local client computing device, resulting in a local model update; sending the local model update to a central server computing device; receiving from the central server computing device a first updated global model; determining that the first updated global model does not meet a local criteria, wherein determining that the first updated global model does not meet a local criteria comprises computing a score based on the first updated global model, wherein the score exceeds a threshold; in response to determining that the first updated global model does not meet a local criteria, sending to the central server computing device context information; and receiving from the central server computing device a second updated global model.

This invention discloses a method for fast storage of local client data in iOS, relating to the field of mobile application product development technology. The specific steps are as follows: S1, generating a debugging tool interface; S2, binding debugging tool methods. In S2, the model object itself performs database operations, adding, deleting, modifying, and querying data. MJExtension is used to obtain all the key and value of the model, which are then reassembled into a new insert SQL statement and written to the database. The key technical points are: using this method improves usability: local caching can be achieved simply by inheriting the storage base class; localized operations can be performed simply by manipulating the model; and the operation is more efficient: the simplified operation steps reduce the time wasted on tedious operations such as writing SQL, and avoid errors in the operation steps.

The invention relates to the field of logistics, and discloses a cross-domain customer loss early warning method, device and equipment and a storage medium, and the method is used for predicting and early warning customer loss conditions. The method comprises the steps of obtaining source domain local customer data and target domain local customer data, and performing feature alignment and preprocessing to obtain source domain preprocessing features and target domain preprocessing features; identifying and obtaining key causal features of a source domain and key causal features of a target domain by using a causal inference method, carrying out domain self-adaption by using a federated transfer learning technology, transferring knowledge of the source domain to the target domain, and generating domain-invariant shared feature representation; based on the domain-invariant shared feature representation and the local customer loss label, updating a pre-trained local customer loss classifier, updating a pre-trained global customer loss early warning model, and obtaining a cross-domain customer loss early warning model; and inputting the new customer data of the target domain into the cross-domain customer loss early warning model to obtain a predicted loss probability, and generating an early warning signal.

The invention provides a cloud platform model training instance secure access method and device, and relates to the technical field of cloud computing, and the method comprises the steps: receiving a model training instance creation request sent by a local client; based on the model training instance creation request, creating a target model training instance in a container arrangement system cluster, determining a port of the target model training instance, and mounting a public key pre-uploaded by a local client to the target model training instance; arranging a network address of the system cluster based on the port and the container, and generating secure connection information; and sending the secure connection information to the local client, so that the local client establishes a secure session with the container arrangement system cluster based on a private key corresponding to the public key and the secure connection information, and accesses the target model training instance based on the secure session. According to the method and the device provided by the invention, the use experience of a user on the cloud platform is improved, and the security of cloud platform model instance access is improved.

Methods, systems, and computer storage media for providing speculation management using a speculation management engine of a cloud access management system are described. The speculation management engine operates based on speculation data, a multi-dimensional speculation framework, and two sets of operations defined based on an initialization sequence. In operation, speculation data for a user associated with a local client is accessed. A determination of a plurality of speculated remote resource candidates is made, based on the speculation data associated with the user. Execution of a first set of operations (i.e., remote resource resolution) and a second set of operations (i.e., remote resource connection configuration) are triggered. A determination is made whether a remote resource identified from the remote resource resolution matches a speculated remote resource candidate in the plurality of speculated remote resource candidates. Based on the speculated remote resource candidate, a connection for accessing a remote resource is established.

The invention relates to a data co-processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring original data, encrypting the original data to obtain target encrypted data, and registering to a central server to receive a to-be-trained initial model corresponding to a task issued by the central server; training the initial model based on the target encrypted data to obtain a local gradient; performing homomorphic encryption processing on the sensitive information in the local gradient to obtain an encryption gradient, and uploading the encryption gradient to a central server, so that the central server performs global training based on the encryption gradient uploaded by each participating terminal to obtain a trained target global model; and receiving the target global model issued by the central server, and processing based on the target global model and the local client data of the participating terminals to obtain a task classification result.

The present application relates to the technical field of computer sentiment analysis, and particularly relates to a layered noise injection based on dynamic sensitivity driven association sentiment knowledge model construction method. It comprises the following steps: downloading the model to the local client; obtaining the local client user emotion entity sensitivity classification; injecting noise into the information input in the local client; training the downloaded local client emotion knowledge classification model; updating the server emotion knowledge classification model. Through the fusion of semantic correlation, social influence weight and data sparsity and other multi-dimensional features, the present application realizes the fine sensitivity classification of different emotional data. The method effectively solves the problem that the traditional unified noise injection mechanism cannot adapt to the sensitivity difference of emotional data. Users do not need to rely on complex privacy risk assessment experience, and can configure the optimal privacy protection strategy for different types of emotional data according to the sensitivity classification results generated by the system.

The invention belongs to the technical field of power optimization configuration, and particularly relates to an energy power configuration method and system based on federated learning and dynamic gaming, and the method comprises the steps: firstly constructing a three-party federated learning framework of a thermal power enterprise, a new energy enterprise and a carbon exchange, and enabling the federated learning framework to comprise a carbon exchange federated server and local clients of all parties; the local clients of all parties are constructed based on respective carbon price influence factors; then training the federated learning framework, and carrying out carbon price dynamic prediction by utilizing a trained model; and then constructing an energy power configuration income model of the thermal power enterprise and the new energy enterprise, solving an equilibrium solution of the energy power configuration income model through a dynamic game based on a carbon price dynamic prediction result, and obtaining an optimal energy power configuration decision combination. According to the method, the risk caused by extreme carbon price fluctuation can be effectively controlled while multi-party revenue maximization is considered, and a stable and reliable optimal energy power configuration decision combination is formed.

A method performed by a central server node is provided. The method includes: receiving local model weights and corresponding key from a local client node; and updating a model pool having a plurality of central models and corresponding keys associated with each of the central models. Updating the model pool is based on the local model weights, and one or more of the key corresponding to the local client node and the keys collectively corresponding to each of the central models. Updating the model pool comprises updating at least two of the plurality of central models contained in the model pool.