189 results about "Native client" patented technology

Disclosed embodiments relate to systems and methods for classifying network session activities. Techniques include identifying a session established using a native client between a network identity and a network resource; monitoring messages conveyed during the session to identify a first data element associated with the session; analyzing the first data element to identify a characteristic of the native client; monitoring messages conveyed during the session to identify a second data element associated with an action requested by the network identity; and analyzing the action and the characteristic of the native client to determine whether the action is a human-initiated action.

The present invention provides a traffic flow prediction method and apparatus, a medium, and a device. The method comprises: collecting historical traffic flow data in a target area; constructing initial prediction models in a central server; performing distributed collaborative training on the initial prediction models at local clients to obtain trained initial prediction models, and inputting the trained initial prediction models into the central server to perform quality screening and aggregation; performing credibility calculation on each local client at which the corresponding initial prediction model satisfying preset quality requirements is trained, and performing weight parameter customization on an aggregated initial prediction model to obtain a traffic flow prediction model; and inputting the historical traffic flow data into the traffic flow prediction model for traffic flow prediction to obtain a traffic flow prediction result in the target area. The traffic flow prediction model can be trained without sharing data of all parties and invading privacy, and the traffic flow in the target area is predicted by means of the traffic flow prediction model having relatively high performance, thereby improving the prediction precision of the traffic flow.

The invention belongs to the technical field of federated learning privacy protection, and particularly relates to a heterogeneous federated learning adaptive privacy protection method and device based on momentum optimization. The method comprises the steps that feature extractor parameters broadcasted by a central server are received, the local gradient of a current iteration round is calculated based on a local data set, and a momentum mechanism is introduced into local gradient updating for a classifier part; a gradient descent algorithm is applied, and local model parameters are updated through the local gradient obtained through calculation; for the feature extractor part, calculating a Fisher information matrix; performing normalization processing on the Fisher information of each layer, and screening strategies; and then differential privacy processing is carried out, the global model parameters are uploaded to a central server for parameter aggregation, and updated global model parameters are broadcasted back to each local client for next round of training. According to the method, the problems of negative influence of a differential privacy mechanism on model training, slow model convergence and poor privacy protection effect are solved.

The embodiment of the invention provides an incomplete multi-mode emotion recognition method based on a diffusion model and a federal model, and belongs to the technical field of data recognition. The method specifically comprises the steps that a client downloads a global model to the local; the client extracts incomplete multi-modal features through a shallow feature extractor, the missing modal features are input as random noise, the extracted original features are input into a global model for reverse diffusion denoising, and finally the missing modal features are complemented; sending the complemented full-modal features into an emotion classifier to perform an emotion classification task; the central node receives the model parameters uploaded by the clients, evaluates the contribution degree of each client, calculates the reputation of the clients, preferentially determines the final weight of each client according to the reputation of the clients, and carries out aggregation according to the final weight; and the central node updates the global model according to the local model set and the aggregated weight. Through the scheme disclosed by the invention, the recognition accuracy and safety are improved.

The invention relates to the technical field of path planning, in particular to a personalized path planning method and system based on federated learning and edge calculation. Comprising a model training stage and a path planning stage. In a model training stage, a client quantifies travel experience of a user in an access region into a credibility score of a path, optimizes the credibility score of the path according to a path selection frequency in a user social network, and locally stores the credibility score of the path in a known region; the clients upload the path trust degree scores of the clients to the central server, global aggregation of the trust degree scores is carried out, and then the central server issues the aggregated trust degree scores to the clients; the invention discloses a personalized path planning method and system based on federal learning and edge calculation, provides an evaluation dimension of path trust degree for the personalized travel problem of a user, and can provide personalized path planning according to the personal preference of the user.

The invention relates to a federal location recommendation method based on heterogeneous graph semantics, which comprises the following steps: constructing a corresponding local heterogeneous graph by using a local private data set, learning POI node features in the local heterogeneous graph by using a heterogeneous neural network, and learning meta-path semantic features through an attention mechanism. Fusing the track sequence features and the corresponding meta-path semantic features to train a local model; and fusing the parameters of the local model obtained after the training into global information through a knowledge distillation method. And encrypting and uploading the local model parameter, the local data volume parameter and the training result after the knowledge distillation of this round to a server. And after the server receives the uploads of all the clients, global aggregation is carried out, and global model parameters are updated by using the aggregated parameters, so that one-time training is completed. And for a new user, inputting the historical trajectory data of the new user into the optimal local model on the corresponding local client, and outputting the historical trajectory data as the next point of interest recommended for the new user.

A WTRU may receive a first message comprising one or more criteria associated with an application server. If one or more local application servers satisfy the one or more criteria, the WTRU may send a second message to the local client device. The second message may comprise information for accessing the one or more local application servers in the local network. If no local application servers in the local network satisfy the one or more criteria, the WTRU may send a third message comprising the one or more criteria to a central application management server. The WTRU may receive a fourth message from the central application management server indicating one or more non-local application servers that satisfy the one or more criteria. The WTRU may send a fifth message to the local client device with information for accessing the one or more non-local application servers.

The invention provides an efficient heterogeneous client federated learning method based on knowledge distillation. The efficient heterogeneous client federated learning method comprises the following steps: selecting a chairman model, namely an RC model, of a training round from client models participating in federated learning by using a heuristic chairman selection strategy; uploading the selected chairman model to a server; sending the chairman model to each local client; learning knowledge in the local model through knowledge distillation; the knowledge is obtained from a client model through local data training learning; uploading the trained chairman model to the server again; the server collects and aggregates the chairman models uploaded by the client to obtain the aggregated chairman model; redistributing the aggregated chairman model to each client; the chairman model guides the client model to update, and the client model is trained; and judging whether 200 rounds of training are reached or not, if not, returning, and if so, ending.

Examples of the present disclosure describe systems and methods for zero trust domain name system (DNS) (ZTDNS) based networking. A computing device implementing ZTDNS based networking blocks any outbound connections that are not included in a list of trusted IP addresses. The list of trusted IP addresses is updated in response to the computing device receiving from a trusted DNS server an IP address corresponding to a DNS request. In some examples, the ZTDNS based networking intercepts and evaluates outbound communications for applications that implement a custom application DNS client. In other examples, the ZTDNS based networking intercepts and evaluates outbound communications for virtual environments. The outbound communications for both the custom application DNS client and the virtual environments are proxied through a local DNS client of the computing device.

The invention discloses a medical auxiliary diagnosis method and electronic equipment based on quantum federated learning in the technical field of smart medical, and the method comprises the steps: carrying out the medical auxiliary diagnosis based on a pre-trained quantum federated learning model, and the obtaining process of the quantum federated learning model comprises the steps: constructing the quantum federated learning model, comprising a local client and a central server. Repeatedly executing the following steps until a preset training period is reached: in the current training period, training the local client according to the training sample set, and calculating the accuracy of the local client according to the test sample set; the local client sends the accuracy and the final model gradient to the central server after the current training period; the central server updates global model parameters according to the accuracy and the model gradient, and returns the global model parameters to the local client; and the local client updates the local model parameters according to the global model parameters. According to the invention, the accuracy and efficiency of medical auxiliary diagnosis can be improved.

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.

Provided in the present application are a large-model training method, apparatus and device, and a storage medium. A large model comprises an adaptor header, a model main body and an adaptor tail, wherein the adaptor header comprises a first cloud part and a first local part, and the adaptor tail comprises a second cloud part and a second local part; and during the process of training the large model, the first cloud part, the model main body and the second cloud part are deployed on the cloud, and the first local part and the second local part are deployed on a local client. In the method, only the adaptor header and the adaptor tail are distributed to the cloud and the client, encrypted client data is used to perform model training for an adaptor part, the majority of the structure of the model remains on the cloud, and cloud computing power is used to perform training and inference, thereby ensuring the computing power performance; in addition, an adaptor fine-tuning mechanism is effectively used, thereby realizing effective training of the large model while securely and fully utilizing the computing power.

The present invention relates to the technical field of privacy computing applications, and proposes a malicious security federated learning method based on data enhancement and L2 enhancement defense, comprising the following steps: local clients each generate average sample data, and encrypt and send them to a server; each local client trains its local model in combination with the encrypted average sample data and local data received from the server, obtains a gradient vector of the trained local model, and encrypts and sends the gradient vector to the server; the server retains the gradient vector whose component length does not exceed a preset component length threshold, calculates the L2 norm corresponding to the gradient value of the retained gradient vector, and obtains the gradient L2 norm; the gradient values ​​whose gradient L2 norm exceeds a preset upper limit are filtered, and the global model is updated using the final retained gradient value; the method can improve the performance of the global model, protect privacy, and reduce the risk of model destruction by resisting gradient increase.

The invention discloses a remote intelligent operation and maintenance system and method for coal mine equipment, and relates to the technical field of fault diagnosis, and the system comprises a local client which is used for obtaining fault sample data of the coal mine equipment and training a local model; the cloud server is used for aggregating the parameters of the local model to obtain a diagnosis model; and the controller is used for acquiring the real-time state data and the real-time operation data in the operation process of the coal mine equipment, and obtaining an early warning result of the fault of the coal mine equipment based on the diagnosis model. According to the method, the diagnosis model is constructed in a federated learning mode, and the diagnosis model is written into the controller of the coal mine equipment, so that fault early warning can be carried out in the operation process of the coal mine equipment, the downtime of the equipment is greatly shortened, and the benefits of coal mine production are improved.

The invention discloses a federal learning efficient training optimization method for a 6G network, and the method comprises the steps: transmitting a global model parameter to a client through a parameter server in a downlink communication stage, and transmitting the global model parameter to the client through a local training stage; according to the customized local training strategy, the convergence speed is improved by training the specified number of iterations at a local client and adding constraint terms in a target function, so that the total number of rounds of communication is reduced; in the uplink communication stage, part of clients participate in clients with relatively high rule selection calculation efficiency and upload training results of the clients at the same time, so that the communication cost of each round is reduced; in the model aggregation stage, a parameter server distributes reasonable weights for different local parameters based on a weighted aggregation strategy of data quality so as to improve model precision, and finally outputs optimized global model parameters so as to realize efficient model training and parameter updating, and an efficient and reliable solution is provided for distributed learning in a 6G network.

A system, method, and apparatus for estimating life-cycle impact while preserving data privacy uses federated learning to train machine learning models across multiple local clients without exposing private data. Local clients train local models on private datasets. Privatized update data from these local models may be transmitted to a central server which aggregates this data to enhance a global model. The global model is redistributed to clients, thereby improving its accuracy through successive federated learning rounds, without accessing any raw private data. Local clients can query their local models to obtain impact scores for products or processes based on the aggregated learning. A range of privacy-preserving computation protocols limit exposure of sensitive data. This cooperative framework enables collective model refinement reflective of broad data access without compromising confidentiality. The system provides accurate impact values alongside data security assurances for clients.

The invention discloses a large model security reasoning method and system fusing a trusted execution environment and differential privacy, and belongs to the technical field of artificial intelligence. The method comprises the steps that a large model is divided into an embedded layer and a core processing layer, the embedded layer is deployed in a local client SGX2 trusted environment, and the core processing layer is deployed in a local client SGX2 trusted environment; the core processing layer is deployed on a remote server equipped with multiple GPU acceleration cards; based on a local differential privacy technology, performing text confusion on original input data of a user by adopting an output noise maximum value algorithm; performing vector mapping on the confused text data through an embedded function; and the embedded vector is encrypted and transmitted to a server GPU, the embedded vector is processed through a self-attention mechanism and a feedforward neural network, and a prediction result is generated and returned to a client. According to the method, the problem of contradiction between data privacy protection and calculation efficiency in existing large model reasoning can be solved.

The invention provides a method and a system for performing information association review based on RPA and AI. The method comprises the following steps: an RPA client automatically controls a browser to log in an enterprise query website; the RPA client reads the supplier file, inputs supplier information into an enterprise query website for query, and stores basic information of each supplier to the supplier file; the RPA client calls an enterprise association relationship query function of an enterprise query website, and stores a supplier association relationship picture to the local; the RPA client calls the multi-modal model through an interface and identifies relation picture information; the RPA client sends the correctly identified information and the supplier basic information to a large language model, checks whether a preset association rule is triggered or not, and outputs a result; and the RPA client writes the review result into a local file and sends the review result to a designated person for review. According to the invention, the examination efficiency, accuracy and data integration capability of information association examination can be improved.

The invention relates to the technical field of privacy protection, and particularly discloses a privacy protection method and system for data cross-domain sharing and computer equipment, and the method comprises the steps: constructing a global GNN model based on federated learning, distributing the constructed global GNN model to local clients, constructing sub-graphs of the local clients, and distributing the sub-graphs of the local clients to the local clients; configuring a local GNN model of the local client based on the global GNN model; training local client data based on a local sub-graph and a local GNN model to obtain a local model and generate node embedding, uploading the node embedding of the local model to a central server by each local client, performing weighted aggregation operation on the node embedding based on node similarity, and generating global node embedding; according to the method, parameter weights based on a federated learning framework are updated, and the privacy problem of data elements in cross-domain circulation and sharing in a multi-source heterogeneous service fusion scene is solved by introducing a sub-graph, a graph neural network and a federated learning technology.

The invention discloses a multi-mode traffic demand prediction method based on federated learning, and the method is characterized in that an attention federated learning framework is adopted, the attention federated learning framework comprises a fine-grained graph convolution circulation network which is used for capturing the spatial-temporal characteristics of a single mode at each local client, each client independently trains a model and uploads the model parameters to a global server, and the global server is connected with the fine-grained graph convolution circulation network; model parameters are merged through an attention mechanism, the similarity between different modes is calculated, and the generated global prediction model realizes multi-mode traffic demand prediction under the condition of not directly sharing data. Compared with the prior art, the method has the advantages that spatio-temporal data of different traffic modes are integrated, efficient demand prediction of a multi-mode traffic system is realized without directly sharing data, the accuracy of multi-mode traffic demand prediction is further improved on the premise of not sacrificing data privacy, the problems of data privacy and data ownership are solved, and the traffic demand prediction efficiency is improved. The method is expected to be widely applied to an intelligent traffic system, and has good application prospects and commercial development value.

The invention relates to the field of federated learning and molecular discovery, in particular to a multi-party cooperation federated learning model method for molecular discovery. The invention discloses a multi-party cooperation federation learning model method for molecular discovery. A heterogeneous difference privacy technology is introduced into each local client, and it is ensured that molecular local model parameters are protected in the training process. Next, the protected local model parameter information is uploaded to a central server, projection transformation and weighted averaging are carried out through a Lanczos algorithm, and finally new global model parameters are generated and released to a client for multiple times of communication updating training; according to the method, the privacy protection problem of different molecular data sources is effectively solved by utilizing heterogeneous differential privacy, so that the privacy of the molecular data is guaranteed; and meanwhile, a Lanczos algorithm is adopted to carry out projection transformation to optimize a molecular model fusion mode in a multi-party cooperation process, new global model parameters are generated, and the prediction accuracy of the molecular model can be improved.

The embodiment of the invention discloses a traffic flow prediction and model training method based on federal space-time diagram learning. The specific implementation mode of the method comprises the following steps: generating a node feature matrix of a space-time diagram based on historical traffic flow stored by a local client; determining a space-time dependency relationship based on the node feature matrix, a pre-trained node embedding matrix and a pre-trained time embedding matrix; the time-space dependency relationship is sent to the server, and an aggregation time-space dependency relationship returned by the server is received, and the aggregation time-space dependency relationship is obtained by aggregating the time-space dependency relationships from different clients by the server; and determining future traffic flow through a pre-trained prediction model based on the aggregation space-time dependency relationship. According to the embodiment, the space-time dependency relationship between the clients and inside the clients can be effectively captured, so that the accuracy of traffic flow prediction is improved.

The invention relates to an industrial named entity recognition method based on privacy protection, and belongs to the technical field of natural language processing, the industrial named entity recognition method is composed of a plurality of local clients and a global model, and the industrial named entity recognition method comprises the following steps: step 1, obtaining an industrial fault detection data set, dividing a training set and distributing labels; 2, establishing an initial model; 3, each local client downloads global model parameters from the server; 4, after each local client sets an iteration round, the private data is used for training in the initial model, and model parameters are uploaded to the server; 5, the server aggregates the model parameters and updates the global model; step 6, repeating the step 3 to the step 5 until a set iteration round is finished; and 7, inputting data needing entity recognition into the trained model, and extracting a test set entity. According to the method, the data privacy of each client is protected while the performance of the local model is improved, and the accuracy of named entity recognition is enhanced.

A system for generation of recommendations based on a sale lead including a processor of a recommendation server (RS) node and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire sales lead data from the sales lead entity node comprising data entered into a sales form by a customer; derive a language indicator from the sales lead data; parse the sales lead data based on the language indicator to derive a plurality of features; query a local customers' database to retrieve local historical customers'-related data related to previous customers' engagements associated with previous lead data based on the plurality of features; generate at least one feature vector based on the plurality of features and the local historical customers'-related data; and provide the at least one feature vector to the ML module for generating a predictive model configured to produce at least one recommendation lead response parameter for generation of a lead-related recommendation for the at least one CRM entity node.

The invention relates to a singular value decomposition-based personalized federated learning method, which is used for solving the problem of uncertainty of a system caused by equipment isomerism and the problem that a client falls behind due to extra burden caused by a storage and transmission mechanism in the prior art. Firstly, a customer selection strategy based on resource awareness is determined, and a server side establishes a quantitative scoring system by comprehensively analyzing computing resources and communication conditions of clients. And screening a plurality of clients with optimal comprehensive performance from all online clients to participate in local training. During local training of the client, historical weight parameters are reserved by adopting self-knowledge distillation (SKDSVD) combined with a singular value decomposition method, residual errors after decomposition are personalized model parameters and are stored in the local client, and universal parameters are transmitted to the server for aggregation. The SKDSVD algorithm reduces the training time delay and the fall-behind rate of the local client while optimizing the global model of the server to obtain the optimal convergence precision.

The invention discloses a real-time library data service and interface management system based on a memory security language, which comprises a system access layer, an acquisition control layer and a business service layer, and is used for providing a synchronous or asynchronous external interface based on memory security and a native client interface. Strong-experience man-machine interaction and intensive calling of an upstream system are carried out; a hot loading mode based on scripts is provided, a past protocol loading mode is abandoned, and codes can be flexibly effective and executed in real time under the condition that compiling and restarting are not needed; a data transmission mechanism based on an MQ mode is provided, and data transmission between systems is facilitated.

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 present invention belongs to the field of distributed intelligent computing technology, and its purpose is to provide a method for training a federated learning model. In the implementation process of the present invention, by setting the periodic aggregation duration and adopting the semi-asynchronous federated learning model training method, a semi-asynchronous federated learning aggregation scheme with a fixed time period is constructed, which can solve the delay influence of the bottleneck node in the synchronous federated aggregation strategy in the device heterogeneous environment, and also prevent the skewness of the global model caused by the frequent uploading of local models by some devices in the fully asynchronous federated aggregation strategy; in addition, in the computing power imbalance environment of the federated learning system, the present invention ensures that the data in all local clients can participate in the model training when the global training time is fixed through the semi-asynchronous aggregation method, thereby effectively improving the data utilization rate in the local clients participating in the training in the federated learning system and improving the convergence accuracy of the model training.

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.