73results about How to "Protect data privacy" patented technology

The invention provides an aerial remote sensing multi-platform collaborative observation task planning and optimization method and system, and relates to the technical field of collaborative planning, and the method comprises the steps: receiving the observation demand information of a target region and the resource information of a plurality of aerial remote sensing platforms, building a multi-platform collaborative observation task model based on a deep reinforcement learning algorithm, generating an initial task planning scheme by utilizing the constructed multi-platform collaborative observation task model, optimizing the initial task planning scheme by adopting an improved multi-target particle swarm optimization algorithm, and distributing corresponding specific execution instructions to each aerial remote sensing platform through a security encrypted communication link; state information, including positions, postures, energy levels and equipment working states, fed back by the aerial remote sensing platforms is received and processed in real time, and a current task planning scheme is dynamically adjusted according to the real-time state information based on a federated learning framework by utilizing edge nodes and cloud cooperative computing capability, so that adaptive optimization of tasks is realized.

The invention discloses a satellite remote sensing target data identification method based on artificial intelligence, which belongs to the technical field of data processing, and realizes distributed model training and data mining of a multi-node joint model by performing satellite remote sensing target identification on an acquired spectral vector and adopting a model training architecture of distributed federated learning; carrying out manual annotation on the acquired spectral vector data; a generative adversarial network based on multi-scale spectral decomposition is adopted for sample generation, and then data expansion is achieved; and performing data identification by adopting a satellite remote sensing target data identification model. According to the method, the generative adversarial network based on multi-scale spectral decomposition is adopted for sample generation, and the data set is expanded. A self-encoder algorithm is used for carrying out feature dimension reduction, feature independence is enhanced through a nonlinear conversion layer, and redundant information between features is reduced. A kernel extreme learning machine algorithm based on conjugate gradient compensation is adopted, a kernel function is mapped to a high-dimensional space, and the classification accuracy and efficiency are improved.

The invention discloses a human face sensitive data protection method based on an elastic anti-interference privacy protection mechanism, belongs to the field of information processing, and provides a dynamic self-adaptive sampling strategy based on information entropy in a data preprocessing stage, and the sampling rate is adjusted according to the distribution characteristics of a human face data set and the weight of sensitive information. And the model performance is maximized on the premise of ensuring user privacy. In order to obtain a better privacy protection effect, an entropy adjustment differential privacy mechanism is designed, and Gaussian noise of different degrees is adaptively added according to an information entropy value of face data after a face data set is dynamically and adaptively sampled, so that refined privacy protection of face sensitive data under differential privacy constraint is realized. In a model training stage, an elastic anti-interference training method is provided, diversified adversarial samples are dynamically generated in different stages of model training, and the over-fitting risk of the model is reduced while the robustness of the model to various types of adversarial attacks is enhanced.

The invention provides a federated learning-based chip manufacturing process parameter optimization method and system, and relates to the technical field of chips, and the method comprises the steps: collecting multi-factory process parameters and yield data, screening key parameters through wavelet transform and dual evaluation, and constructing a deep Q network model; ethnic group division is carried out based on process trajectory similarity, differential privacy and homomorphic encryption are adopted to protect data security, and ethnic group optimization is realized through an attention mechanism and knowledge distillation; and setting a third-level time window monitoring yield, and dynamically adjusting an optimization strategy. According to the method, the chip manufacturing yield can be effectively improved, data privacy is protected, and intelligent optimization of process parameters is realized.

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 provides an attention federated learning-based electric vehicle power battery health state prediction method, and mainly relates to the field of deep learning and battery health state prediction. The method mainly comprises the following steps: importing and preprocessing battery data of the electric vehicle, and taking the battery data of each electric vehicle as local data of a client; in federal learning, designing a global-local attention network model structure as a client model to learn battery aging characteristics; designing a time-guided model selection strategy, and uploading the screened client model to a server; designing an attention-based model adaptive aggregation strategy, and aggregating the uploaded client model to generate a global model; the global model is issued to each client, the round of federated learning is completed, training is ended when the global model converges, and a high-generalization SOH prediction model is obtained; and performing fine adjustment on the obtained model by using partial data of the target electric vehicle battery to realize SOH prediction of the target electric vehicle battery. According to the method, a global-local attention network model is designed for interaction between local features and global features of battery monitoring signals to improve the data feature representation capability, meanwhile, for the problem that a single electric vehicle SOH prediction model is weak in generalization, a federal learning method is optimized on the basis of considering data privacy, and the prediction efficiency of the SOH prediction model is improved. The health state of the target electric vehicle battery is accurately predicted, the service life of the battery is prolonged, and the driving safety is improved.

The invention discloses a polyester fabric defect detection method and system based on a visual image, and relates to the field of fabric detection.The method comprises the steps that a multi-scale feature map of a polyester fabric is obtained; generating change track characteristics of each key process; extracting integrated features from the multi-scale feature map of the polyester fabric by using a convolutional neural network, and constructing a multi-granularity feature matrix in combination with the change trajectory features of each key process; based on federated learning and a random forest technology, performing importance scoring on each feature in the multi-granularity feature matrix, and performing feature screening according to importance scores to obtain polyester fabric defect identification input features; and performing score prediction on the polyester fabric defect identification input features through a neural network, and identifying a potential polyester fabric defect area. According to the method, the accuracy and robustness of defect detection of the polyester fabric are improved, and the method has the advantages of data privacy protection and multi-source information integration.

The invention belongs to the technical field of communication, and discloses a federated learning service method and system oriented to data circulation, which effectively protects the data privacy and security of participants by introducing mechanisms such as task auditing, qualification verification, encrypted data interaction, model update parameter screening and contribution value-based reward distribution. Potential hostile attacks are prevented, and fair and reasonable benefit distribution is realized.

The invention relates to the technical field of virtual power plant differentiated contribution distribution and distributed carbon transaction under a multi-agent cooperation framework, and provides a differentiated multi-agent cooperative game-based virtual power plant low-carbon bargaining optimization method, and the method comprises the steps: constructing a multi-virtual power plant-load aggregator MVPP-LA cooperation alliance framework; a wind power system, a photovoltaic system, a combined heat and power generation system and an energy storage system are integrated, supply and demand interaction is enhanced, and a carbon emission quota distribution mechanism, a carbon transaction mechanism framework, a cooperative objective function and an energy system operation constraint condition based on energy interaction are constructed. Cooperative benefits are quantified through a Nash bargaining model, and a distributed adaptive iterative algorithm is adopted for solving, so that fair benefit distribution is realized, and carbon emission and transaction cost are reduced. The method plays a positive role in promoting the utilization of renewable energy sources, improving the utilization efficiency of energy sources and enhancing the flexibility and stability of the system.

The invention provides a new-generation information technology and landscaping supply chain fusion system, and belongs to the technical field of information technology and landscaping supply chain fusion. Landscaping supply chain management and data acquisition are improved in multiple aspects, data of each link are accurately acquired through multiple sensors and interfaces, manual recording errors are avoided, and the system is convenient to use. According to data analysis and processing, advanced technologies are utilized to predict growth trends and market demands, inventory management is optimized, an intelligent decision support module provides scientific purchase suggestions based on data results, an information interaction platform promotes information sharing and cooperation of all parties, and a visual monitoring module can find and process abnormities in time. The expandability and security of the system and the application of the mobile terminal adapt to development requirements, data privacy is protected, business processing is facilitated, the management efficiency and quality are integrally improved, and smooth implementation of a project is guaranteed.

The invention discloses a traffic police dynamic gesture recognition method and system based on vehicle-mounted federal learning, and the method enables a key feature extraction model and a preset global model to be combined as a traffic police gesture recognition model shared by vehicle-mounted terminals of a whole network, and facilitates the improvement of the gesture recognition precision of the traffic police. Different vehicle-mounted terminals are organized to train the models based on the collected traffic police gesture image data through vehicle-mounted federal learning, and then each vehicle-mounted terminal only shares model update data instead of original training data, so that the data privacy of vehicle users is protected, the communication cost for uploading mass data to a central server is saved, and the user experience is improved. Meanwhile, real-time traffic police gesture image data dispersed in different vehicle-mounted devices are fully utilized in vehicle-mounted federation learning, training data from vehicle-mounted images have different observation angles, different environment conditions and the like, the diversity of model training data is enriched, and the training efficiency is improved. And thus, the adaptive capacity of the trained traffic police gesture recognition model in a variable traffic environment is enhanced.

The invention discloses a pathological image self-supervised dyeing normalization method and device, and belongs to the technical field of combination of digital pathology and image processing, and the method comprises the steps: constructing a pathological image database; a dyeing normalization model is designed, the dyeing normalization model comprises a public feature domain extraction module, a content perceptron, a scene perceptron and a fusion module, and the dyeing normalization model can perform color conversion on the pathological image to obtain a dyed normalized image; a self-supervised loss function is constructed based on the pixel level difference of the input original pathological image and the dyed and normalized image, and a dyeing and normalization model is trained. The model can perform adaptive dyeing style normalization on any image of an unknown pathological data center towards a selected pathological data center image.

The invention relates to the technical field of data center management, and discloses a prefabricated cabin type data center monitoring system, which comprises a data acquisition module arranged in a prefabricated cabin and used for acquiring environment data, electric power data and IT equipment operation state data in the cabin, converting the acquired data into a standardized data format, and transmitting the standardized data format to a server through a protocol conversion interface; and uniformly converting the acquired data of different communication protocols into a preset standard data format. A data cleaning and compression mechanism is designed in an edge calculation module, collected environment data, power data and IT equipment operation state data are preprocessed in real time, abnormal data are rapidly judged based on set upper and lower limit values, the abnormal data are marked as alarm data and are preferentially transmitted to a subsequent module, transmission of invalid data is reduced, and the efficiency is improved. The network bandwidth utilization rate is improved, rapid fault detection and response are realized, and the fault diagnosis and repair time is shortened.

The invention provides a substation terminal network equipment defect elimination checking method and system based on deep learning, and the method comprises the following steps: constructing an equipment configuration heterogeneous graph network by a substation client through combining an equipment configuration file, an equipment operation log and equipment network flow data, all the transformer substation clients utilize a heterogeneous graph network to train a local model, the federated learning server updates a shared learning model by combining local training parameters of all the clients, and the clients needing to be checked continue to update the model according to updating parameters of the server; and identifying a configuration mode of local network equipment through the updated model and obtaining a configuration parameter mapping table, generating an equipment checking strategy in combination with the configuration mode and the configuration parameter mapping table, and finishing checking work of all the network equipment through the equipment checking strategy. According to the invention, the transformer substation can accurately complete network equipment checking.

The invention belongs to the field of distributed machine learning, and relates to a heterogeneous data-oriented decentralized learning method based on differential privacy protection. Comprising the steps that a decentralized scene is constructed, global parameters are set, and user setting is completed; the user sends model parameters to neighbor users, calculates a self-gradient and a cross-gradient, cuts the self-gradient and the cross-gradient respectively, adds noise to the self-gradient and the cross-gradient, and transmits the cross-gradient to neighbors; each user obtains a corrected gradient through similarity correction according to the self-gradient and the received cross-gradient; updating the model, broadcasting the updated momentum and model to neighbors, and performing weighted averaging according to the received momentum and model; and repeating the steps until the model of each user converges or reaches the upper limit of global iteration times. According to the method disclosed by the invention, in a decentration environment, a model for effectively processing heterogeneous data is obtained in a limited learning round, the user data privacy is protected in the learning process, and the differential privacy requirement is met.

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.

The invention discloses a data encryption method and system based on multi-stage processing, and relates to the technical field of data encryption, and the method comprises the steps: determining stages of multi-stage parallel processing; the stages comprise a data classification stage, a key management and distribution stage and an encryption execution stage; in the data classification stage, data are analyzed, and the data are classified into sensitive blocks and non-sensitive blocks; in the key management and distribution stage, a corresponding encryption key is selected according to the sensitivity of data; in the encryption execution stage, encrypted data are generated according to different encryption keys. According to the method, the data processing efficiency is greatly improved through parallel processing of multiple stages, and the method is suitable for processing large-scale data sets. The dynamic key management strategy enhances the security and flexibility of the system, allows real-time generation and distribution of keys according to data sensitivity, and effectively protects various security threats. And the integrated homomorphic encryption technology enables the encrypted data to be directly subjected to complex operation, so that the use scene of the encrypted data is expanded, and meanwhile, the data privacy is protected.

The invention discloses a low-cost video edge caching method based on federal deep reinforcement learning, and belongs to the technical field of edge caching of cloud edge collaboration. The method comprises the following steps: establishing a network model; the bottom-layer mobile terminal uses local implicit feedback data to train an auto-encoder, the edge server of the middle layer uses a federated learning framework to aggregate local models of the mobile terminal, and a global model is obtained after iteration; predicting by using the global model; according to the method, calculation and communication resources consumed in the federation training process are modeled as a comprehensive system cost problem, and a user calculation resource allocation problem is further expressed as a Markov decision process, so that the calculation resources of each federation training client can be effectively allocated on the premise of meeting resource constraints, and the resource allocation efficiency is improved. And the total cost of the federal learning process is reduced to the greatest extent. Experiments show that the cache hit rate of the method is higher than that of a baseline algorithm and is close to that of an optimal algorithm, and the system cost can be effectively reduced under the condition that local resources are limited.

The federal knowledge distillation method and application for rubber tire production parameter sharing divide the federal learning process into preheating and distillation two parts, the preheating part adopts the FedAvg federal training strategy, the distillation part utilizes the knowledge generated by each client, carries out the binned formation grouping knowledge, carries out the aggregation after the distribution to each client for the knowledge distillation in the server side.The invention proposes a new federal knowledge distillation method, through the method in the invention, the distributed training of the production line prediction model can be realized, and the model prediction accuracy of the server side is also higher than that of ordinary training.The invention can be used for the distributed training of the rubber tire production line key parameter prediction model, to improve the training efficiency, and in the case of not sharing data, the training result generated by the data can be shared, and the privacy can be well protected.

The invention provides an application access control method based on system call limitation, relates to the technical field of network security, and provides an application behavior learning module and an application authority control module. The application behavior learning module executes the following steps: A1, creating an application behavior list; a2, dynamic training monitoring: training and monitoring each item of content in the application behavior list; a3, generating a mapping table, and establishing a mapping relation between each item of content in the application behavior list and system calling; the application authority control module executes the following steps: B1, user authorization application: initiating an application access request to an authorization center; b2, authorization approval: after receiving the application access request, the authorization center authorizes the application as required; and B3, issuing the authority. According to the method, the granularity of authority management is refined, the exposure surface of the application is reduced, enterprises are guaranteed, the malicious behavior risk is reduced, the system security and data privacy are protected, and the overall security is improved.

The invention discloses a zero-knowledge proof method based on a quantum optimization integer decomposition algorithm, and the method comprises the steps: taking quantum calculation as a basis, and achieving the efficient calculation of candidate verification points through combining an elliptic curve point addition rule and a point doubling rule; a Grover algorithm is adopted to optimize candidate point search, so that verification efficiency is improved; according to the scheme, a three-stage process is taken as a core, the verification range is gradually reduced, a target value is dynamically generated or verified, and the accuracy and safety of the verification process are ensured; the proving party constructs zero-knowledge proof based on the complexity of integer decomposition, and provides smooth parameters, a calculation path and a verification point abscissa; the verification party verifies whether the candidate points meet the expected mathematical characteristics or not by reproducing the calculation path of the proving party, and original data does not need to be contacted; the scheme is widely applicable to block chain transaction verification, digital signature enhancement and data integrity protection, and has the characteristics of high efficiency, zero knowledge and high adaptability.

This invention provides a training method, localization method, and system for an intelligent agent localization model based on dialogue and vision collaboration. The training method is applied to a federated learning system and includes: a server initializing a global model and distributing it to a client; the client receiving model parameters, training the model using local dialogue commands and visual data, generating multimodal representations, and then inputting them into two structurally identical but parameter-independent localization branches for parallel processing, outputting localization representations and prediction results, and executing navigation decisions based on the localization results; constructing a total loss function that includes a loss term constraining the consistency of the bi-branch representations and constraining the consistency of navigation state changes, and updating the local model; the client evaluating reliability based on representation consistency and navigation stability, uploading the model update and reliability to the server, and the server using this data to weighted aggregate and update the global model, iterating until convergence. This invention can suppress noisy dialogue interference and improve localization accuracy, navigation stability, and model generalization ability in federated learning scenarios.

This invention relates to the field of industrial fault diagnosis technology and discloses a federated incremental mechanical fault diagnosis method in a dynamic client environment. The method includes: constructing a federated learning system composed of a cloud server and a dynamic client, configuring a shallow neural network, a sample dataset, a fault diagnosis model, and a local memory; training the fault diagnosis model on the client and storing prototype samples corresponding to historical fault categories in the local memory; applying perturbation to the prototype samples, inputting them into the shallow neural network to calculate gradient vectors, and uploading these vectors, along with model parameters and network parameters, from the client to the cloud server; performing gradient inversion iterations on the cloud server to construct a validation set to evaluate model performance, and calculating the aggregate weights of each model based on the validation loss, thereby constructing a global diagnostic model and distributing it to the client to achieve real-time fault diagnosis of mechanical equipment. This invention achieves collaborative, continuous, and high-precision mechanical fault diagnosis across distributed dynamic clients.

The present invention relates to a multi-party collaborative data learning system and a learning model training method, which fully utilizes the advantages of active learning and federated learning, uses a small amount of labeled data of each client to perform collaborative training of the model under the premise of protecting data privacy, generates probability distribution with predicted loss value in each round of federated learning training, selects clients to participate in training, can accelerate the convergence of the global model and reduce the communication volume; the client loads the current global model parameters into the local model for active learning, uses the local model to guide sample query, and samples highly informative samples for labeling; the labeled data set of each client is expanded, and federated learning training is performed again to obtain a model with better performance. The accuracy and generalization performance of the model are improved under the premise of reducing the sample labeling cost as much as possible.

The present invention discloses a service identification method based on federated learning, and belongs to the field of communication network technology. The method constructs an edge collaborative system composed of several wireless routers as edge terminals; then collects network traffic data sets through several wireless routers in the system, and processes the data sets into the format required by the training model; according to business needs, different distributed federated learning mechanisms are selected to train the initial model, and the global model is obtained through aggregation and update; the trained global model is placed in the service identification classifier model library, and then different algorithm models are selected according to the different business types identified; finally, through the collaborative training means of federated learning, the data flow features identified by many routers participating in the training are merged and deployed to more routers, so that each router can identify all business types, effectively enhance the generalization ability of the identification model, and continuously improve the overall performance of the system.

The present invention discloses a privacy protection method and system for a power grid database, which relates to the field of data security technology, including: filing power grid data source information, setting corresponding authority nodes according to the power grid data source; constructing corresponding data carriers in each authority node, loading the power grid data in the authority node into the data carrier, and performing transmission encryption processing on the data carrier; setting a data filtering mechanism for a power grid database used to store power grid data, and filtering data on the data carrier according to the set data filtering mechanism, thereby ensuring that the data transmitted through the data carrier is not tampered with, and protecting the data privacy of the power grid data during the transmission process.

One or more embodiments of the invention provide a privacy-protecting machine learning model training method and device. The method comprises the steps of inputting an original sample into a bottom model to obtain a first type of intermediate features; inputting the first type of intermediate features into a feature protection network to transform the first type of intermediate features to obtain transformed features; inputting the transformation features into a trained reverse model so as to restore the transformation features through the reverse model to obtain a reverse sample output by the reverse model; calculating sample loss caused by intermediate feature transformation based on the reverse sample and the original sample, and updating the feature protection network by taking increase of the sample loss as a target; the transformation features are sent to a server side, so that the server side inputs the transformation features into the top model to obtain a prediction label of the original sample; a bottom gradient sent by the server side is received, the bottom model is updated based on the bottom gradient, and the bottom gradient is obtained by the server side through calculation based on the prediction label and the sample label of the original sample.

The invention discloses an advertisement putting method and device, equipment, a storage medium and a product, and relates to the technical field of data security, and the method comprises the steps: collecting the authorization information of a user, and initiating an encryption query request to an operator based on the encrypted authorization information, so as to enable the operator to feed back an encrypted number matched with the authorization information; based on the encrypted number and the strategy identification number, initiating a hidden trace query request to an operator, so that the operator feeds back a corresponding delivery strategy; and performing advertisement putting on the user based on the putting strategy fed back by the operator. According to the mode, after the query party initiates the query request, matching is carried out based on the encrypted authorization information, then the query request is initiated through the encrypted number obtained through matching, finally, the delivery strategy is output, the parameter needing to be input in the whole process is only the authorization information of the user, the corresponding delivery strategy is output, data privacy is protected, and meanwhile, the delivery strategy is not required to be input. And the advertisement putting accuracy and efficiency are improved.

The invention discloses a cardiovascular metabolism health prediction platform based on big data, and aims to integrate multi-source heterogeneous data and realize accurate prediction of cardiovascular metabolism health risks by constructing a hybrid prediction model combining a static feature sub-network and a dynamic feature sub-network. The static feature sub-network is used for processing data such as gene information, age and gender which do not change along with time, the dynamic feature sub-network is used for processing time sequence data such as heart rate and blood pressure, the two sub-networks generate joint features through weighted fusion, and the joint features are input into the classification network to output risk probability. The platform adopts a random forest algorithm to perform feature selection, the correlation and prediction efficiency of model input features are improved, and user privacy protection is realized through a federated learning framework. The platform provides dynamic trend analysis of health risk scores, outputs personalized health intervention suggestions including lifestyle adjustment and medication guidance, and generates real-time early warning for abnormal fluctuation of key indexes.

The invention provides a power plant thermal mechanical equipment lubricating oil quality on-line monitoring method and system, and the method comprises the steps: collecting a plurality of parameters of power plant thermal mechanical equipment lubricating oil, transmitting the parameters to a data processing and analysis module, carrying out the comprehensive analysis and evaluation of the parameters through a multi-sensor data fusion strategy based on deep learning, and carrying out the monitoring of the quality of the lubricating oil. Comprising the following steps: constructing an oil product state analysis model, extracting oil product health features, and generating oil product state early warning; constructing a predictive maintenance decision model, and generating an optimization maintenance strategy; constructing a multi-device collaborative monitoring framework, and realizing model sharing and collaborative learning among a plurality of sensors; and based on the result after comprehensive analysis, oil state early warning and equipment maintenance suggestions are generated, and real-time monitoring results and decision support are provided for users through a user interface and a remote monitoring module. And deep fusion analysis is carried out on multiple parameters of the oil product, and online intelligent evaluation and prediction are carried out, so that the problems of one-sided monitoring and slow alarm are effectively solved.