236 results about "Client data" patented technology

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.

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.

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.

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.

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.

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.

The invention discloses a cross-device federated learning method and device, equipment and a medium, and relates to the technical field of cross-device federated learning incentive, and the method comprises the steps: firstly obtaining a weight matrix representing the data distribution condition of each edge client, and a feature vector of the weight matrix, and obtaining a norm of the feature vector corresponding to each type of elements in the weight matrix; according to the method, data distribution of each edge client is deduced based on norms, enhanced data is designed for each edge client according to a data missing proportion, in the process, client data distribution is accurately deduced through analysis model updating, and enhanced data for a data missing category of each client is generated for each client; meanwhile, a deep reinforcement learning dynamic multi-round auction strategy is combined, an incentive strategy is made, whether enhanced data is used to participate in training or not is selected, the method does not depend on local data on the whole, a distributed incentive decision-making mechanism abandons a traditional centralized decision-making framework, efficient and intelligent distribution of incentive resources is achieved, and the training efficiency is improved. Therefore, the overall performance of cross-device federated learning is greatly improved.

Digitally distributing media content using a distribution backbone system, including: receiving a request for media content from a client, the request including a client profile; performing inventory and analysis of source assets by iteratively progressing through the client profile to create output; performing a capability mapping in which a series of rules that allow the source assets to be mapped to the client profile; and planning a manufacturing process, which determines work items and execution steps from capabilities mapped in response to the request for media content from the client.

A method comprising: at an importer of an IBOC digital radio broadcasting system: establishing a data link to an audio client configured to buffer audio from an audio source over a buffering duration, to produce buffered audio; receiving, from the audio client, an indication of the buffering duration; identifying a logical channel of an IBOC waveform assigned to the audio client and configured to transmit PDUs of the audio at a PDU rate; computing a quantized number of PDUs that is greater than one into which the buffered audio is to be divided at the audio client based on the buffering duration and the PDU rate; sending, to the audio client, an indication of the quantized number of the PDUs; and upon sending importer data requests to the audio client over the data link, receiving, from the audio client, client data responses each including the quantized number of the PDUs.

The invention provides a polyp image segmentation method based on federal domain generalization and re-parameterization Unet, and belongs to the field of medical image segmentation. Comprising the following steps: S1, preparing different data sources at different clients; s2, constructing a re-parameterized segmentation network at each client; s3, training the segmentation model by adopting federal learning, and executing local updating; s4, a cross-domain generalization mechanism is introduced in the training process, and meanwhile, frequency domain transformation or style disturbance is performed on the polyp medical image, so that the model learns consistent feature representation under different client data distribution; and S5, aggregating the model parameters of each client, and synchronizing the global model parameters to each client.

Media data may be exchanged using an HTTP-based streaming protocol over a radio access network (RAN). Metrics, such as common media client data (CMCD), for such a media streaming session may be exchanged between RAN devices, such as a client device and server device (s), such as an application server (AS), an application provider (AP), and / or an application function (AF). The AS may send CMCD reporting configuration to a client device, and the client device may collect and report CMCD data to the AS. The AS may send the CMCD data to the AF and / or the AP. These devices may use the CMCD data to improve performance for the media streaming session. For example, the AF may determine that media handling functions, such as network assistance, are to be initiated.

The invention discloses a customer information management system based on authority grading and a dynamic sharing mechanism, which relates to the technical field of customer information management and comprises the following modules: a system establishment module for establishing an enterprise account and establishing a plurality of independent manager accounts under the enterprise account, establishing a plurality of independent operation accounts under each manager account; when an operation shadow account is established between operators, a manager shadow account can be automatically established between corresponding customer managers, so that on one hand, the customer managers can conveniently carry out multiple supervision on project progress and customer data modification, on the other hand, the phenomenon that the operators exchange customer data privately can be avoided, and when the operators share the customer data, the user experience is improved. The customer managers of the two parties can grasp the data exchange condition in the first time, and customer privacy and enterprise benefits can be maintained.

The application discloses a heterogeneous federated learning method based on space-time data distillation, which is used for solving the problem that related technologies cannot fully solve the time problem of knowledge reservation, resulting in knowledge forgetting when training a new global model, and the unique space-time characteristics of each client data are not fully considered, so that the efficiency and convergence of federated learning are poor. The server receives the local encoding data obtained by encoding based on the local data sent by each client for data-free global distillation, obtains a first global model, and distributes the first global model to each client; the client performs partial parameter local distillation and non-real-time distillation according to the local data and the first global model combined with dynamic temperature adjustment optimization, generates a local model, and sends the local model back to the server; the server updates the first global model according to each local model through a data-free global distillation strategy, obtains a second global model, and distributes the second global model to each client for next round training.

The application discloses an adaptive clustering federated learning modeling method for precision medicine, and relates to the technical field of precision medicine, and comprises the following steps: data collection and preprocessing and model construction and training; the application accurately determines the optimal number of the global model through adaptive clustering, and divides clustering groups according to the similarity of the client model parameters, realizes independent training of the groups, effectively improves the adaptability of the model to different client data characteristics, samples and label distribution differences, avoids the problem that a single model has poor performance in some clients, and significantly enhances the ability of the model to capture complex medical patterns; the model generalization is optimized through grouped training, so that the model can better cope with new data distribution, under the premise of ensuring the privacy and security of medical data, the accuracy and reliability of the model in precision medical scenes such as disease diagnosis and prognosis prediction are greatly improved.

A device may receive and process client data, with a first machine learning model, to determine current state data identifying a current state of a client. The device may process the current state data and prior client data, with a second machine learning model, to determine a problem statement for the client and future state data of the client. The device may utilize the second machine learning model to identify initiatives for the client, and costs of the initiatives, based on the problem statement, the current state data, and the future state data, and to assign benefits and priorities to the initiatives. The device may process the initiatives, the benefits and priorities of the initiatives, and the costs of the initiatives, with the second machine learning model, to generate an initiative plan for solving a problem of the problem statement, and may perform actions based on the initiative plan.

A computer-implemented method of training a neural network with federated learning, the method comprising sending a portion of a server-maintained machine learning model to a client, using a local model without cluster tags at the client, estimating cluster tags at the server for potential features from the client using k-means, and training the neural network using federated learning. Using globally shared encoder parameters and cluster shared prediction headers, training a local model with client data, updating the global encoder parameters at the server by aggregating cross entropy loss updates from the clients, updating the cluster shared prediction headers at the server by aggregating updates from the clients within each cluster, and updating the cluster shared prediction headers at the server by aggregating cross entropy loss updates from the clients within each cluster. The updated global and cluster sharing model parameters are sent to the client, and final parameters, including global sharing encoder and cluster sharing model parameters, are output after a threshold is satisfied.

When a client requests a data import job, a remote storage service provider provisions a shippable storage device that will be used to transfer client data from the client to the service provider for import. The service provider generates security information for the data import job, provisions the shippable storage device with the security information, and sends the shippable storage device to the client. The service provider also sends client-keys to the client, separate from the shippable storage device (e.g., via a network). The client receives the device, encrypts the client data and keys, transfers the encrypted data and keys onto the device, and ships it back to the service provider. The remote storage service provider authenticates the storage device, decrypts client-generated keys using the client-keys stored at the storage service provider, decrypts the data using the decrypted client-side generated keys, and imports the decrypted data.

Transmitters, receivers, transceivers, transport networks, and methods of use are described herein, including a transmitter comprising a client-side input, transmitter circuitry, and antennas. The client-side input receives baseband signals having client data encoded therein. The transmitter circuitry receives the baseband signals from the client-side input and generates antenna feed signals based on the baseband signals. The antennas receive the antenna feed signals from the transmitter circuitry, 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 and having one or more frequencies in a range between 300 Gigahertz (GHz) and 10 Terahertz (THz). The antennas include one of a helical antenna, a waveguide probe antenna, a tapered antenna, a patch antenna, and a slot antenna.

The invention discloses a data processing method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining a version number and service information sent by a server, judging a client data processing tool version based on the version number, if the version number and the version number are consistent, expanding the service information according to a client data processing tool to obtain to-be-displayed data, and displaying the to-be-displayed data according to the to-be-displayed data. And displaying the business logic layer based on the to-be-displayed data. According to the embodiment, the processing flow of the data at the client and the expansion flow of the business data are realized, the data processing pressure of the server is reduced, the system crash is avoided, and the business processing performance of the system is improved.

A key master service capable of operating on a service provider in a network enables is disclosed. The key master enables authorized parties to securely exchange client information without compromising client security. One feature of the key master service is the generation of a unique key for each client. All parties in an authorized universe access, exchange and modify client information by referencing the universal key, rather than using known client identifiers. Client information is further secured by advantageously applying an obfuscation function to the data. Obfuscated client information is stored together with the universal key as keyed client data at the client and / or server, where it may be directly accessed by the service provider or third parties. Because client information is stored and exchanged without the ability to discern either the client identity or the nature of the information, such information is secured against malicious third-party interception.

The invention provides an insurance industry meeting place seat number automatic distribution method. The method comprises the steps that client data are acquired through a system input interface and an API interface and preprocessed; calculating a customer value score based on a predefined mathematical model and generating a customer tag; configuring a seat distribution rule set, setting priorities, and establishing a mapping relation between rules and areas; executing automatic seat distribution by adopting a hierarchical-backtracking model, and optimizing a distribution result through a greedy algorithm and a backtracking mechanism; providing a visual interface to display a distribution result and supporting manual adjustment; and finally generating a complete seat arrangement report. According to the invention, the problems of low efficiency and poor accuracy of traditional manual distribution are solved, intelligent and precise management of seat distribution of the meeting place in the insurance industry is realized, and the distribution efficiency and customer satisfaction are remarkably improved.

The application provides a fair federated learning method based on function encryption, designs a privacy protection federated learning framework QPFFL based on multi-client function encryption MCFE and privacy protection reputation mechanism PPRM, and aims to solve quantum resistance, privacy protection and fairness and other challenges in federated learning. Among them, the multi-client function encryption guarantees the privacy of the client data and realizes the safe aggregation of the model. The privacy protection reputation mechanism identifies and mitigates malicious behavior, evaluates the contribution of each client, and adjusts the model weight according to the reputation value. Through the integration of MCFE and PPRM, the framework can resist attacks such as free riding and poisoning, and ensure fair model distribution while not compromising data privacy.