332 results about "Client data" patented technology

A system and method are provided for providing advisory notifications to mobile applications. The method includes interfacing the server device with at least one endpoint within an enterprise system and storing a model trained by a machine learning engine to automatically determine advisory notifications relevant to client data sets stored by the endpoint(s) and / or the at least one endpoint. The method also includes determining a current state of a client account, using the model to determine an advisory notification for the client account based on the current state, referring to a set of rules to determine when to provide the advisory notification in the mobile application, and in what portion of the mobile application to display the notification; and sending the advisory notification via the communications module to a client device to display the advisory notification in the mobile application.

System, methods, apparatuses, and computer program products are disclosed for network policy generation using a fine-tuned large language model (LLM). Client data associated with a user device is determined and provided to the fine-tuned LLM in a prompt requesting a network policy. Client data may include device information, network information, application information, and connection information. The fine-tuned LLM generates a network policy based on the client information. The generated network policy is provided to the client to enable the client to enforce the network policy on the user device.

The invention belongs to the technical field of federated learning dual optimization, and discloses a federated learning dual optimization method and system based on cluster knowledge distillation and adaptive local differential privacy, and the method comprises the steps: carrying out the data statistical feature extraction of a client; clustering the clients; local training of the client is carried out; applying an adaptive local differential privacy mechanism (ALDP); carrying out model aggregation FedAvg in the cluster; distilling structural knowledge; updating the global model; and evaluating model performance and privacy protection capability. The invention provides a federated learning optimization method which combines client clustering, structural knowledge distillation and a self-adaptive local differential privacy mechanism aiming at the problems of client data heterogeneity, unstable model distillation and difficulty in considering privacy protection and performance in the existing federated learning method. According to the method, client data statistical feature clustering and structural relationship knowledge distillation are combined, and a disturbance mechanism with a dynamic adjustment capability is introduced, so that efficient protection of privacy information is realized while the model performance is improved.

The invention discloses a federated learning stability improvement method and system based on a block chain and knowledge distillation, and relates to the technical field of federated learning. The federal learning stability improvement method based on the block chain and the knowledge distillation comprises the following steps of performing double-model training; obtaining a fault risk assessment value; and verifying the smart contract. According to the invention, dual-model training is carried out through the obtained local private financial data of each participant client, the dual-model training result is uploaded to the constructed block chain data sharing platform, the fault risk assessment value is obtained and whether a single-point fault risk instruction is sent is determined, if yes, smart contract verification is carried out, and if not, the smart contract verification is carried out. And otherwise, completing federated learning optimization, so that the effect of improving the matching degree of the financial customer-oriented unlabeled public data and the client data volume in the federated learning scene is achieved, and the problem of low matching degree of the financial customer-oriented unlabeled public data and the client data volume in the federated learning scene in the prior art is solved.

The invention discloses a non-independent identically distributed data asynchronous federal learning method based on an improved aggregation algorithm. The method comprises the steps that a server initializes a global model and issues the global model to all clients; and the client performs local training on the received global model by using local data, and uploads the model and model parameters to the server after training is completed. Then, the server adjusts a model lag degree based on a client data volume proportion, calculates model difference consistency, client historical contribution stability, old degree penalty of the client model and cosine similarity of the client model and the global model based on parameters of the client model and the current global model, and generates an asynchronous federal aggregation factor accordingly; and updating the global model parameters to generate a new global model. And finally, testing the global model by the server, and judging whether the learning process is stopped or not. According to the method, fair and effective model aggregation can be realized, and the model convergence stability and the final model detection precision are improved.

According to the matrix multiplication operation method and device and the storage medium, an original input matrix of a client side is packaged and encrypted through homomorphic encryption, a server side is allowed to operate in a ciphertext mode, and therefore the data privacy of the client side is protected. Afterwards, verification is carried out on the result of matrix multiplication of the server side by using homomorphism of encryption operation through homomorphic hash, and the matrix multiplication and the result of matrix multiplication form a closed loop through a polynomial packaging technology, so that the data security of the client side and the verifiability of a reasoning result are effectively ensured. Moreover, under dual verification of commitment verification and result verification, the accuracy of the target operation result is ensured.

The invention belongs to the technical field of federated learning, and particularly relates to an autonomous adjustment and data balance federated learning system and method based on an incentive mechanism. The system comprises a client screening module for global heterogeneity perception, which is used for realizing dynamic evaluation and screening control of client data quality through a global label distribution offset perception mechanism; the server-side utility evaluation and reverse auction module is used for quantifying the actual contribution value of the client to global model training and realizing the distribution of excitation resources through an auction mechanism; and the client participation rate self-adaptive adjustment module is used for guiding the client to autonomously optimize the participation frequency according to the historical income and cost of the client based on a utility function so as to realize a long-term participation behavior. The method has the characteristics that an incentive mechanism is taken as a core, high-value participants are dynamically identified in combination with data characteristics and participation behaviors of a modeling client, and the system stability and the model performance are improved through a verifiable return strategy.

The invention provides an agro-ecological member data security management method and system, which is applied to the technical field of data security management, and is characterized in that client data abstracts, server data abstract comparison, chain structure storage, multiple independent subject confirmation vouchers and multiple security verification mechanisms are introduced; the method effectively solves the problem of integrity and non-tampering verification of the agro-ecological member data in a multi-subject, long-period and dynamic updating environment, ensures the truth and credibility of the data, and can effectively solve the problem of integrity and non-tampering verification of the agro-ecological member data in the multi-subject, long-period and dynamic updating environment. And the truth and credibility of the data are ensured.

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 invention belongs to the technical field of computers, and particularly relates to a forgetting-free and data-free distillation method for heterogeneous federal learning. The method comprises the following steps: 1) initializing a generator at a server side, training the generator by jointly optimizing fidelity loss, diversity loss and transferability loss, ensuring that generated samples are aligned with client data distribution and are diversified, and introducing an elastic weight consolidation (EWC) penalty term at the same time; 2) in each round of communication, parameters of a historical difference generator are updated by accumulating differences of the historical generators, so that samples containing historical round knowledge can be synthesized; 3) performing knowledge distillation by using the samples synthesized by the current round generator and the historical difference generator, and minimizing the output difference of the global model and the local model in the aspect of sample generation; and 4) after knowledge distillation is completed, performing heterogeneous fine adjustment on the global model by introducing the difference between the historical global model and the local model.

The invention is applied to the technical field of federated learning and privacy protection, and discloses a differential privacy federated learning method for minimizing noise mechanism and sharpness perception, which comprises the following steps: starting federated learning, initializing global model parameters by a server, enabling a global model to comprise a linear conversion layer of the model as an initial layer, then, the server randomly selects part of clients with a fixed number and sends initial model parameters to the clients, and the clients train a local model on the basis of the initial model parameters. According to the differential privacy federated learning method for minimizing the noise mechanism and sharpness perception, the adaptive noise mechanism is introduced, adaptive adjustment of the cutting threshold is combined, it is ensured that the requirement for differential privacy is effectively met in the federated learning process, strong noise is introduced through the large cutting threshold, user data privacy is ensured, and user experience is improved. And along with the deep training, the cutting threshold value is gradually reduced, the noise is gradually reduced, and the balance between privacy protection and model precision is ensured.

The invention discloses a BDDR backdoor detection and data recovery method and system oriented to a large model, and belongs to the field of backdoor defense. Comprising the following steps: constructing a knowledge distillation architecture under federal learning, including an edge server and a plurality of clients, and obtaining distillation data; inputting the distillation data into a randomly initialized model for training, recording the loss change of each batch of data, and screening out abnormal batches to form a backdoor data set; the edge server initializes two independent models, respectively uses a distillation data set and a backdoor data set for training, and guides learning of backdoor features; using probability distribution to calculate and correct a backdoor label, generating a clean data set by adding noise, finely adjusting a large model, detecting residual backdoor feature intensity, and adjusting probability distribution calculation parameters to further weaken backdoor features according to the residual backdoor feature intensity so as to obtain a final repaired data set; while the generalization ability of the large model is improved, backdoor attacks can be effectively identified and defended, the data privacy of the client is protected, and the model security is ensured.

The invention discloses a verifiable heterogeneous federated learning system based on zero-knowledge proof, and mainly aims to solve the problems of insufficient transparency, verifiability deficiency, vulnerability to data poisoning attack and the like in the existing heterogeneous federated learning. The system is composed of a plurality of client devices with different computing capabilities, data distribution and model architectures, and a block chain verification platform. The client device is responsible for training a local model, converting the model into a standard ONNX format, generating a proof by using a zero-knowledge proof tool, and submitting a model update and the proof to the block chain verification platform. And the block chain verification platform is responsible for verifying zero-knowledge proof, recording model update, constructing a global model and ensuring verifiability and transparency of the global model. According to the method, the privacy of client data is effectively protected, the credibility of the training process is enhanced, the verifiability of a global model is ensured, an enhancement path is provided for decentralized heterogeneous federated learning, and a new development direction of credible federated learning is expanded.

The invention discloses a heterogeneous perception traffic prediction method based on federated learning, and the method employs federated learning to design a unified heterogeneous perception framework, and supports an existing centralized traffic prediction model. Clients with similar traffic flow data distribution are gathered together by utilizing multi-dimensional positive sample comparative learning, so that the clients of the same kind can cooperatively train a model, and the influence of data isomerism between different clients is avoided; the model of each stage is trained in sequence based on a time window by using data partition, so that the influence of data missing on traffic prediction is reduced; noise detection is used for global detection and local denoising, so that the quality of client data is ensured.

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.

A computer-implemented method for automatically transforming client data to a common data normalization schema associated with a collaborative multi-client federated learning system while preserving data privacy. The method may include automatically generating a local data ontology based on the client data associated with a client, and automatically generating synthetic data based on the client data and the local data ontology. The method may also include automatically computing an inference risk score comprising determining a privacy risk associated with sharing the synthetic data, and automatically computing a task utility score comprising determining a utility of the synthetic data. The method may further include generating a global data ontology using ontology matching algorithms on the synthetic data associated with each local data ontology. The method may also include automatically recommending and implementing data transformations to the client data.

The invention relates to a robust federated learning method based on dynamic aggregation weight and prototype guidance, and belongs to the technical field of federated learning. The method comprises the following steps: classifying clients into credible clients and drifting clients based on mutual evaluation; extracting trainable vectors in the client, and constructing a positive prototype set and a negative prototype set; calculating the similarity and complementarity of each client, obtaining the dynamic weight of each client in global model aggregation, and combining to obtain a dynamic aggregation weight matrix; based on a preset merging threshold value, performing merging operation on the models in the trusted clients to obtain a trusted client aggregation model; and carrying out distillation training based on the trusted client aggregation model, the positive prototype set and the negative prototype set, issuing the trained model to each client for the next round of iteration, and realizing robust federated learning through multiple rounds of iteration. The objective of the invention is to solve the problem of global model performance reduction caused by dynamic change of client data distribution and malicious client interference in federated learning.

A network service incorporating service groups to increase fault tolerance and data isolation for integrated network services and client data is provided. The network service provider can process network requests utilizing individual service groups that correspond to a set of integrated services and client data (e.g., cells). The service groups can be associated according to customer identifier. Computing resources within a service group are isolated from computing resources utilized in other service groups and resources that host / provide the service or the integrated data can be independently scaled by the service provider.

A data analytics platform provides secure access to federated data for advanced analytics and machine learning. No raw data is exposed or moved outside its original location, thereby providing data privacy. A coordinator located in the provider cloud communicates with runners in each client data silo. The runners ensure that no raw private data is ever exposed to the coordinator. Silo managers are implemented in the client data silo in order to manage and maintain the client cloud components of the platform remotely. In some embodiments, the platform can anonymize verified models for privacy and compliance, and users can export and deploy secure models outside the original data location.

Techniques are provided for implementing a persistent key-value store for caching client data, journaling, and / or crash recovery. The persistent key-value store may be hosted as a primary cache that provides read and write access to key-value record pairs stored within the persistent key-value store. The key-value record pairs are stored within multiple chains in the persistent key-value store. Journaling is provided for the persistent key-value store such that incoming key-value record pairs are stored within active chains, and data within frozen chains is written in a distributed manner across distributed storage of a distributed cluster of nodes. If there is a failure within the distributed cluster of nodes, then the persistent key-value store may be reconstructed and used for crash recovery.

The invention particularly relates to a GIS map mass point location loading optimization method. According to the GIS map mass point location loading optimization method, an appropriate level range for using point location aggregation is preset according to the characteristics of client data access; sVG is selected as a map marking format, and point location data is rendered based on the boundary of a map viewport; and when the map zooming level is lower than the user-defined threshold value and the data volume exceeds the user-defined threshold value, reducing the number of the independent marks on the screen by using a Marker Cluster strategy so as to improve the loading speed of the map and the user experience. According to the GIS map mass point location loading optimization method, the mass point location loading speed and rendering efficiency are remarkably improved, repeated calculation and DOM operation are reduced, system resource occupation is reduced, map interaction smoothness is enhanced, and therefore user experience and the stability and practicability of a GIS system are effectively improved.

Techniques are provided for customizing or fine-tuning a pre-trained version of a machine-learning model that includes multiple layers and is configured to process audio or textual language input. Each of the multiple layers is configured with a plurality of layer-specific pre-trained parameter values corresponding to a plurality of parameters, and each of the multiple layers is configured to implement multi-head attention. An incomplete subset of the multiple layers is identified for which corresponding layer-specific pre-trained parameter values are to be fine-tuned using a client data set. The machine-learning model is fine-tuned using the client data set to generate an updated version of the machine-learning model, where the layer-specific pre-trained parameter values configured for each layer of one of more of the multiple layers not included in the incomplete subset are frozen during the fine-tuning. Use of the updated version of the machine-learning model is facilitated.

The invention provides a time-domain-crossing non-intrusive load monitoring method fusing federated learning and Mama, and the method comprises the steps: dividing UK-DALE data into a time-domain-crossing client data set according to a time period, and carrying out the normalization preprocessing at a local side; the method comprises the following steps of: constructing a non-intrusive load monitoring model based on a Mama structure by utilizing Mama state space modeling and long sequence dependence capture capability; under a federated learning framework, each client executes local training and designs a diversity correction strategy to inhibit the influence of data heterogeneity on model convergence, and meanwhile, global model parameters are optimized through weighted aggregation. According to the method, the problems of privacy leakage risk, insufficient model generalization ability, overweight calculation burden and the like existing in traditional load monitoring are effectively solved.

Network elements and methods of use, including a transmitter comprising a client-side input, signal and clock conditioning blocks, a modulation block, and antennas. The client-side input receives baseband signals having client data. The signal conditioning block adjusts signal characteristics of the baseband signals to generate intermediate signals. The clock conditioning block receives a first clock signal having a first clock frequency and adjusts signal characteristics of the first clock signal to generate a second clock signal having a harmonic frequency of the first clock frequency. The modulation block modulates the intermediate signals onto the second clock signal to generate antenna feed signals. The antennas generate radiated signals based on the antenna feed signals and couple the radiated signals into hollow waveguides. The radiated signals are radiated electromagnetic waves configured for coherent detection with a transmission frequency in a range between 300 Gigahertz (GHz) and 10 Terahertz (THz).

The invention relates to a federal semi-supervised domain adaptive time sequence learning method, which comprises the following steps: aiming at a target classification network formed by a coding feature extraction layer and a classifier head, firstly, executing pre-training by a server based on local label data, freezing the classifier head, and then, respectively executing pre-training by each client based on local label-free data; unsupervised training is carried out on the coding feature extraction layer, federated learning is realized and a mobile behavior recognition model is obtained in combination with fusion of each trained parameter of the local coding feature extraction layer of each client by the server, and each preset mobile perception data acquisition is analyzed and a corresponding mobile behavior label is output, so that mobile behavior perception application is realized. The design method not only can improve the classification accuracy of the target classification network on the client data, but also lays a solid foundation for promoting the wide application of semi-supervised federal learning in a complex real scene.

The invention relates to the technical field of artificial intelligence, in particular to a low-altitude federal learning security robust aggregation method based on interpretation gradient attribution. According to the method, the XAI technology is utilized, the quality of the local model is evaluated at the server side by using the XAI basic model, and the model only needs a small amount of verification data, so that the accuracy and the reliability of global model updating are ensured. By introducing the XAI, the method can dynamically adjust the aggregation weight according to the correlation contributed by the client, and effectively alleviates the negative effects caused by data heterogeneity and unreliable client behaviors. According to the scheme, the accuracy, the convergence speed and the robustness of the global model can be remarkably improved in a non-IID data and Byzantine attack scene only by depending on a small number of verification sets without accessing client data, auditable contribution degree interpretation is provided at the same time, the computing communication overhead is low, and the method is suitable for a resource-limited Internet of Things environment.

The invention relates to a dynamic hyper-parameter adjustment method and device for asynchronous federated learning and a medium, the method is characterized in that when a local model of a client is updated, hyper-parameter adjustment is carried out based on a reward function of reinforcement learning, the reward function is divided into two parts, the first part quantifies reduction of relative loss of the global model on the client data set, and the second part quantifies characterization inconsistency of the global model and the local model. Compared with the prior art, the method introduces the reinforcement learning algorithm to dynamically optimize the hyper-parameters, and enhances the generalization ability of the model by designing the special reward function, thereby improving the accuracy and training efficiency of the global model.

Technical solutions are directed to creation and deployment of multi-stage test problems. A processor can provide, to a client, a first data structure for a first stage of a multi-stage test problem including a description for generation of a client solution for the first stage and a test case to evaluate the client solution. The processor can receive, from the client, a client data structure comprising the client solution including a client computer code generated at the client for the first stage. The processor can determine, by evaluating the client solution using an input value and an output value of the test case, that the output of the client solution satisfies a validity condition of the output value. The processor can provide, to the client, based on satisfying the validity condition, a second data structures for a second stage of the multi-stage test problem.

A computing system can initially receive client data of a client of the financial health service. Using the client data, the system generates an individualized action plan and a financial health score for the client. The system further receives, in real-time, financial update data indicating changes to a financial situation of the client. In response to receiving the financial update data, the system updates the individualized action plan and the financial health score for the client. Thereafter, the system may receive a financial health request from a transaction entity with which the client transacts, and based at least in part on the financial health request, the system can transmit the updated financial health score to the computing device of the transaction entity.

The invention provides a data online migration method and device in a dual-system parallel period. The method comprises the following steps: acquiring a client data set to be migrated at a preset moment, storing final state data into a first intermediate database before the preset moment, storing non-final state data into a second intermediate database at the preset moment, traversing each piece of non-final state data in the second intermediate database, and performing migration detection processing on each piece of non-final state data, and under the condition that the migration detection result represents that the detection is passed, executing a transaction locking operation on the non-final-state data of which the migration detection result represents that the detection is passed to obtain multiple pieces of locked client data, and migrating the locked client data from the second intermediate database to a target system. And migrating the final-state data from the first intermediate database to the target system after each piece of locked client data is migrated to the target system. The problem that in the prior art, in the online data migration process, service continuity is poor is solved.