3686 results about "Global model" patented technology

The invention discloses a trajectory optimization method based on a multi-source heterogeneous positioning data fusion algorithm, and relates to the technical field of intelligent navigation and high-precision positioning, multi-modal data are acquired through a multi-modal sensor array, positioning redundancy of scenes such as tunnels and indoor scenes is enhanced, a weight distribution strategy is dynamically adjusted through an Actor-Critic network architecture, and the positioning accuracy is improved. The state space input comprises an environment semantic tag, a historical error sequence and a real-time noise variance, the output action space is continuous weight distribution of each data source, a multi-target reward function optimization strategy is combined, scene adaptability is realized, a local SLAM map, inertial navigation error parameters and a weight distribution strategy are shared in real time based on a V2X protocol, and the real-time performance of the system is improved. According to the method, a single device accumulative error is compensated by using adjacent vehicle data, a terminal locally trains an error compensation model, parameters are uploaded to a cloud end through differential privacy encryption, the cloud end adopts a FedAvg algorithm to aggregate a global model and issue the global model, the error difference between devices is inhibited, and dynamic road network updating and scene differentiation model distribution are supported at the same time.

The invention discloses a multi-modal large model federated training platform and a heterogeneous data alignment algorithm. The algorithm comprises a time sequence data processing module, a text processing module, an embedded generation module, a local federated learning module, a comparative learning alignment module, a global model aggregation module and a privacy protection verification module. The time sequence data processing module generates a time-frequency matrix signal; the text processing module outputs a text feature signal; the embedding generation module generates a time sequence embedding vector and a text embedding vector; the local federal learning module forms a local encryption signal; comparing the learning alignment module and generating a gradient signal; the global model aggregation module processes the gradient signal through a federated average algorithm and forms a parameter update quantity; and the privacy protection verification module generates confusion gradient signals and transmits the confusion gradient signals back to each module for data alignment. According to the multi-modal large model federation training platform and the heterogeneous data alignment algorithm, the problem that effective alignment and fusion of a logging curve and a geological report are difficult due to modal difference and semantic gaps can be solved.

The invention relates to the technical field of data privacy protection, and discloses a cross-platform social privacy collaborative protection system based on federated learning and a block chain. The system comprises a federal learning initialization module, a private data encryption module, a cross-platform data synchronization module, a block chain consensus verification module and an intelligent contract execution module. Global model initialization parameters are generated through a multi-party security aggregation algorithm, user data privacy is protected through hierarchical encryption, data are synchronized through a Hash time lock protocol and an intelligent contract, model updating is verified through an improved Byzantine fault-tolerant algorithm, and a privacy protection rule is triggered based on a differential privacy noise injection algorithm. The system effectively solves the problem of cross-platform social privacy protection, guarantees data security and privacy, improves federal learning reliability, optimizes data sharing and utilization, and is suitable for various cross-platform social scenes.

The invention discloses a real-time health risk prediction method and system based on a dynamic knowledge graph, and relates to the technical field of medical information. The method comprises the following steps: carrying out multi-modal fusion and privacy protection preprocessing on medical and nursing heterogeneous data, and realizing semantic consistency of cross-mechanism data based on an entity alignment method of a cross-modal graph neural network; based on a hierarchical federated learning framework, local model parameters are subjected to hierarchical encryption and aggregation through a secure multi-party computing protocol to generate an initial global model, and prediction distribution of the global model is optimized in combination with knowledge distillation of differential privacy constraints; designing a gradient difference dynamic updating trigger mechanism of noise robustness, smoothing noise interference through a sliding window mean value, and realizing adaptive threshold calibration through linkage model performance verification; and light-weight deployment real-time reasoning is realized based on redundant edge pruning of confidence and 8-bit symmetric quantization. On the premise of protecting data privacy, the real-time performance and accuracy of health risk prediction are remarkably improved, and the method is suitable for a cross-institution medical care collaborative decision-making scene.

The invention discloses a dynamic optimization and real-time decision-making method and device for multi-agent collaborative target search, and the method comprises the steps: constructing a global model by a global optimization layer, obtaining an initial path plan and an initial task distribution scheme of multiple agents, and transmitting the initial path plan and the initial task distribution scheme to each agent; meanwhile, the global optimization layer updates the global model at a first preset frequency; each agent adjusts the initial path plan according to the initial path plan and the initial task allocation scheme in combination with the real-time sensing data to obtain an execution result, and sends the execution result to the global optimization layer; meanwhile, each agent updates the execution result at a second preset frequency; the global optimization layer judges whether a global model needs to be updated or not according to the execution result of each agent, if yes, the global model is updated and sent to each agent, and if not, the execution result of each agent is stored; and obtaining a path planning and task allocation scheme in real time. The task execution efficiency and completeness can be improved.

The invention discloses an adaptive differential privacy federal learning method, a client, a server, a storage medium and a product, and the method is applied to the client, and comprises the steps: determining a gradient cutting threshold based on a current training round and a cutting threshold adjustment strategy, the cutting threshold adjustment strategy is constructed according to the data distribution similarity and the gradient change rate corresponding to each training round; cutting the gradient of each sample to obtain a target gradient of each sample; adding noise disturbance to the target gradient of each sample according to an adaptive differential privacy algorithm and the target privacy budget to obtain adaptive noise; and performing model updating in combination with the target data set and the global loss function to obtain local model parameters, sending the local model parameters to a server, and updating the parameters by the server according to the local model parameters to obtain a global model. Through the above mode, the robustness of the model to noise and attack is enhanced, and the capability of protecting data privacy, the accuracy of the model and the generalization capability of the model of the client are improved.

The invention belongs to the field of federated learning communication optimization, and provides a federated learning communication optimization method based on adaptive rarefaction and quantization, so as to reduce communication overhead and improve energy efficiency. The method comprises the following steps: a central server issues a global model, randomly selects part of clients for local training, calculates gradient update, dynamically screens important gradients for transmission by adopting a dynamic quantization strategy, and further compresses residual gradients by applying an adaptive rarefaction method; meanwhile, an error feedback mechanism is introduced, and quantization errors are accumulated to improve the convergence effect of the model. And the client uploads the compressed gradients to the server, the server aggregates and updates the gradients and then continues to distribute the gradients, loop iteration is carried out in this way, and finally an efficient convergence global model is obtained. According to the method, the communication cost in federated learning is remarkably reduced by combining adaptive rarefaction, dynamic quantization and error compensation, and convergence is accelerated on the premise of ensuring the model performance, so that the method is more suitable for a distributed learning environment with limited resources.

The invention relates to the technical field of environment detection, and discloses a GIS map-based multi-class environment parameter automatic prediction method, which comprises the following steps: collecting noise intensity, vibration spectrum, sewage turbidity, illumination intensity and PM2.5 concentration in real time through a distributed sensor network, combining social behavior data, carrying out space-time alignment, and generating a multi-dimensional space-time matrix; calculating an energy overlapping degree by adopting a space-time diagram attention network, marking a high-risk collaborative pollution area, and predicting a pollution diffusion path; constructing a self-adaptive prediction model containing physical and behavior driving channels, and dynamically adjusting the weight to optimize the prediction precision; based on the optimization model, reversely deducing a pollution source of an overproof area, matching equipment characteristics and generating a control instruction; and opening an AR (Augmented Reality) interface to verify the treatment effect, and when the virtual-real data deviation exceeds a data deviation threshold, triggering federal learning to update the global model, and generating an environmental protection compliance report. According to the invention, the accurate decision-making efficiency of environmental governance can be improved.

The invention provides a user opinion privacy protection method and system based on federated learning and privacy difference, and relates to the technical field of privacy protection, and the method comprises the steps: a server receives a client request, divides a data set, and distributes the data set; the client performs local training by using a differential privacy machine learning algorithm, and disturbs model parameters by using Laplacian noise; the server uses secret sharing and homomorphic encryption technologies to aggregate parameters and update a global model; and the client receives the privacy protection strategy, carries out privacy processing on the user opinions and then sends the user opinions to the server for analysis. The method effectively protects user privacy and improves data utilization efficiency.

The invention relates to the technical field of cardiovascular disease treatment, and discloses a cardiovascular disease medical decision support method based on a large model, and the method comprises the steps: obtaining multi-modal cardiovascular disease medical data, constructing a multi-source heterogeneous data set, carrying out the preprocessing and feature fusion, and constructing a combined representation model based on the pre-training large model and the fusion of traditional and western medicine knowledge. And designing a hierarchical space-time diagram convolutional network to generate a dynamic physiological state code of the patient, and constructing a multi-target optimization decision tree to generate a treatment scheme containing western medicines, traditional Chinese medicine prescriptions and non-drug intervention. A federal learning framework is adopted to cooperatively train a local model, data security is guaranteed, a global model is optimized, and a curative effect attribution module is further arranged to correct decision deviation. According to the method, multi-modal data and traditional Chinese and western medicine knowledge are integrated, personalized treatment scheme generation is achieved, data safety is guaranteed, and the cardiovascular disease diagnosis and treatment level is improved.

The invention provides an investment decision-making system and method based on federated learning and multi-modal risk control, and the system comprises a data collection layer which is used for integrating satellite remote sensing data, supply chain Internet of Things data and financial market data; the federal processing layer is used for constructing a distributed training framework based on a FedAvg algorithm and realizing cross-mechanism data fusion and global model parameter updating through homomorphic encryption and differential privacy; the intelligent decision-making layer adopts a TD3 reinforcement learning engine and adopts a dynamic gating mechanism to adjust fusion weights of texts, time sequences and image modalities in real time; and the execution monitoring layer is used for detecting transaction execution deviation in real time through a digital twinning technology, realizing abnormal response by adopting a CUSUM algorithm, and dynamically adjusting a federal learning rate through Bayesian optimization. The key technical defects of data islands, tail risk response delay, insufficient cross-market linkage analysis and the like of a traditional investment system are overcome through an innovatively designed federated learning architecture and a time-varying risk control model.

The invention belongs to the technical field of Internet of Vehicles, and particularly provides a federated learning optimization system and method for an intelligent network connection automobile scene, which improves an asynchronous federated learning framework, divides a plurality of vehicles into different clusters due to the isomerism of computing power, and adopts a cloud-edge-end three-layer federated learning framework, so as to realize the optimization of the federated learning of the vehicles. An edge server is deployed on a roadside unit RSU, received model parameters are subjected to pseudo-asynchronous aggregation in a self-adaptive dynamic time window, the received model parameters are subjected to real-time aggregation at a cloud end, the system model training efficiency and quality are improved, meanwhile, the data security is ensured, the user privacy is protected, and the user experience is improved. And the efficiency of the federated learning optimization system and the quality of the global model in the intelligent network connection automobile scene are ensured.

The invention discloses an artificial intelligence machine vision image acquisition system, and the system comprises a multi-mode perception layer which integrates a self-adaptive optical module, inhibits metal reflection, captures a visible light to short wave infrared image, and captures a motion edge; the dynamic adaptive layer adopts an illumination compensation and motion compensation module to dynamically adjust camera parameters and micro displacement compensation, feeds back an illumination trend, outputs a motion vector to the cognitive layer, generates a confrontation sample through a GAN, simulates virtual defects in combination with a physical engine, and expands training data; the cognitive reasoning layer is used for deploying a dynamic routing network, distributing computing resources according to image complexity and optimizing feature extraction efficiency; reducing data deviation through anti-fact analysis, and generating a thermodynamic diagram to explain a detection basis; and the collaborative decision-making layer is used for rapidly screening samples by edge nodes, training a global model by cloud aggregated data, automatically triggering manual rechecking when the confidence coefficient of the model is insufficient, synchronously optimizing a training set and a causal reasoning module by a rechecking result, and improving the labeling efficiency through AR assistance.

The invention discloses a remote sensing image generation method based on a federal visual language model, which belongs to the technical field of machine learning and specifically comprises the following steps: receiving text instruction description by each client; extracting a multi-scale feature map from private remote sensing image data through a visual encoder, and generating a semantic embedding vector by text instruction description through a language encoder; inputting the semantic embedding vector and the multi-scale feature map into a dynamic attention mask generator to generate pixel-level space weight distribution; carrying out weighted fusion operation on the multi-scale feature map, and generating visual feature representation of text conditionalization; generating a remote sensing image according with the description of the text instruction through an image decoder; the client uploads model parameter increments of the visual encoder, the language encoder and the dynamic attention mask generator to the central server; the central server aggregates the model parameter increments, and distributes the updated global model parameters to each client; according to the method, the flexibility and semantic consistency of remote sensing image generation are effectively improved.

The invention discloses a power distribution room anomaly detection system based on cloud side-end cooperation, and belongs to the technical field of intelligent power grids. In order to solve the problems of high network bandwidth pressure, insufficient edge computing capability, low anomaly detection accuracy, difficulty in multi-source data fusion and the like caused by the adoption of an end-cloud direct connection architecture in an existing power distribution room monitoring system, the system comprises: a data acquisition layer configured with various heterogeneous sensors to acquire operating parameters and environmental data in real time; the edge storage and calculation layer carries out local real-time processing, anomaly detection, model training and visual display, an anomaly detection module of the edge storage and calculation layer carries out research and judgment on real-time data to generate early warning information, and a prediction and detection linkage module monitors an anomaly probability trend and adjusts a sampling frequency; the edge gateway realizes protocol conversion and data forwarding; and the cloud decision-making layer aggregates multi-edge node data, optimizes a global model through federal learning, and issues and updates a local model. The system is used for improving the accuracy, real-time performance and reliability of anomaly detection of the power distribution room, reducing the operation and maintenance cost and realizing intelligent operation and maintenance.

The invention discloses a privacy protection system based on federated learning, and relates to the technical field of privacy protection. The system comprises a distributed participating node cluster, wherein each participating node is configured with a local model training unit and a privacy protection module; the coordination server is connected with each participating node through a secure communication layer and comprises a model aggregation module and a dynamic trust evaluation module; the global model distribution channel is used for broadcasting the encrypted global model parameters to participating nodes; and the privacy protection module is integrated in a local participating node and comprises a homomorphic encryption engine and a local differential privacy injector. According to the method, privacy protection strength improvement, model utility optimization, system efficiency breakthrough and security boundary expansion are synchronously achieved under a federated learning framework, and an industrial-grade solution is provided for cross-domain data collaborative learning.

The invention discloses a federal learning data processing method based on privacy protection, and the method comprises the following steps: S1, a client uses local data to train a generator of a generative adversarial network, and generates virtual data similar to the local data in distribution; s2, setting three privacy protection levels according to the privacy sensitivity of the local data; s3, performing model updating operation by using a homomorphic encryption technology; s4, utilizing a dynamic weight optimization mechanism based on a multi-arm bandit algorithm to obtain a priority processing data set; s5, preliminarily updating the global model, analyzing generated data through a reverse inference detection mechanism, and judging whether a privacy disclosure risk exists or not; s6, the server feeds back the updated global model to the client, and the client continues personalized model training in combination with local data; and S7, generating new virtual data, and carrying out the next round of global model training. According to the method, the generative adversarial network, differential privacy and homomorphic encryption are combined, so that efficient federated learning under privacy protection is realized.

The invention discloses an Internet of Vehicles communication resource allocation method based on federal multi-agent deep reinforcement learning, and belongs to the technical field of deep crossing of intelligent transportation, wireless communication and distributed machine learning. According to the technical scheme, in an Internet of Vehicles scene, a vehicle is taken as an agent, and local training is performed through a multi-agent depth deterministic strategy gradient algorithm: each agent decides spectrum access, power control and bandwidth allocation based on a local state; asynchronous federation learning is adopted, each agent uploads local model parameters to a global server, weights are dynamically adjusted based on model updating quality, communication quality and updating frequency, and a global model is generated through weighted aggregation; and issuing the updated global model to an intelligent agent to realize distributed privacy protection and dynamic optimization of communication resources. The method has the beneficial effects that the spectrum efficiency, the transmission success rate and the system adaptability are remarkably improved on the premise of ensuring the data security, and the method has wide application prospects and commercial values.

The invention provides a private weight self-adaptive heterogeneous data federated cooperative training method and system in the technical field of federated learning and privacy computing, and the method comprises the steps: S1, enabling each client to carry out the differential privacy operation on a local data set based on a private weight, and obtaining a desensitized data set, encoding the desensitized data set through a heterogeneous data encoding model; s2, performing semantic alignment on each coding vector through a contrast learning model to obtain an aligned vector set; s3, training a local model through the alignment vector set, generating a local gradient, extracting local model parameters, and uploading the privacy weight, the local gradient and local difference parameters to a server; and S4, the server trains the global model based on the local difference parameter and the global gradient, extracts the global model parameter and issues the global model parameter to each client for training. The method has the advantages that the compatibility, the flexibility and the efficiency of heterogeneous data federation cooperative training are greatly improved.

The invention relates to the field of industrial intelligent control, in particular to a real-time production efficiency optimization system based on an artificial intelligence technology, and the system comprises an equipment fault prediction module which is used for collecting multi-modal time sequence data, and predicting the equipment fault probability based on a deep learning network; the process parameter adjusting and optimizing module is in communication connection with the equipment fault prediction module and is used for receiving the fault prediction probability and dynamically adjusting process parameters based on a reinforcement learning algorithm; the federated learning and incremental training module is in communication connection with the equipment fault prediction module and the process parameter tuning module, and is used for realizing collaborative optimization and privacy protection of a local model and a global model, greatly improving the fault prediction accuracy, reducing the false alarm rate from 20% to 5% or below, prolonging a prediction window from 10 minutes to 30 minutes or above, and improving the prediction efficiency. A sufficient preventive maintenance time window is provided for a production system; and the process parameter optimization effect is remarkably improved, and the comprehensive efficiency improvement space of the equipment is expanded to 8-12% from the traditional 5%.

The invention provides a data privacy protection method, which comprises the following steps of: acquiring an original data set, extracting a high-sensitivity field, calculating the correlation between the high-sensitivity field and other fields, and determining a high-correlation field combination; performing intelligent segmentation and scattered storage on the high-relevance field combination, and constructing a distributed hash table index; realizing encryption aggregation and asynchronous updating of global model parameters through a federated learning framework; constructing an adversarial sample for the high-relevance field combination, and training a privacy protection defense model; differential privacy perturbation processing is carried out on the high-sensitivity field; calculating an association risk index of the high association field combination in real time, and generating an association risk analysis report; dynamically adjusting a data segmentation strategy according to the associated risk analysis report, and optimizing local model training sample selection; and if the association risk index exceeds a preset security threshold, triggering adaptive updating of a differential privacy deassociation processing flow.

The invention belongs to the technical field of federated learning, and particularly relates to a self-adaptive bilateral distillation personalized federated learning method based on a diffusion model. According to the method, a guidance mechanism is designed, so that mutual distillation is carried out between a global model and a local model, efficient transmission of knowledge is realized, and the adaptability of a personalized model to specific data distribution of a client is enhanced. Meanwhile, a conditional diffusion model is introduced to generate high-quality pseudo data, and the aggregated global model is finely adjusted by using the pseudo data. The process not only effectively makes up global information possibly lost in the local-global mutual distillation process, but also further optimizes the performance of the global model. By combining the mutual distillation and conditional diffusion fine tuning technology, the data privacy is protected, meanwhile, the balance between the personalized performance and the global generalization ability is achieved, and the method is suitable for a multi-client cooperation scene in a non-independent identically-distributed non-IID data environment.

The invention discloses a privacy protection recommendation method in combination with federated learning and a knowledge graph. The method comprises the steps that 1, a server initializes and distributes a federated learning global model; the client uses a differential privacy edge camouflage algorithm to increase the confusion degree of the original data; step 2, the client loads original data to the federated learning local model for training to obtain a declined federated learning local model gradient; step 3, the client uses an induction order RDP privacy algorithm to carry out gradient noise addition on the descending federal learning local model and uploads the model to the server; 4, the server receives the federated learning local model gradient after noise adding, and updates and evaluates a federated learning global model; repeating the step 2 to the step 4 until the model converges or reaches a preset number of iterations, and obtaining an optimized federated learning global model; and 5, inputting user data into the optimized federal learning global model, outputting an interest probability value, and judging the potential preference of the user.

The invention provides a road monitoring multi-mode sensing method and a road monitoring multi-mode sensing system adapting to a dynamic environment, and belongs to the field of road monitoring. Performing multi-modal weighted fusion to obtain a feature set after weighted fusion; performing classification processing on the fusion features by using a multi-layer perceptron network; generating a comprehensive evaluation result; dynamically adjusting the working priority of each sensor; alignment is carried out in time and space; automatically adjusting a data fusion strategy; and carrying out data cooperative processing by utilizing edge computing and cloud computing to generate a local model generated by the edge computing and a global model and an optimization result generated by the cloud computing. According to the method, the defects of a traditional road monitoring system in the aspects of environmental adaptability, sensor fusion, calculation efficiency and compatibility are overcome, the overall performance and reliability of the system in a complex and changeable environment are remarkably improved, and the method has wide application prospects especially in the fields of automatic driving and intelligent traffic.

The invention discloses a federated learning-driven cross-domain supply chain elastic inventory optimization system and a method thereof, and aims at realizing inventory data collaboration among same-level enterprises or regional nodes through transverse federated learning and ensuring data security by adopting a self-adaptive differential privacy protection mechanism. The method comprises the steps of constructing a transverse federated learning network, locally performing data preprocessing, adding differential privacy noise, iteratively training a global model based on federated deep reinforcement learning, generating a transverse inventory allocation and replenishment decision, and performing model adaptive adjustment in real time based on key performance indicators. According to the method, multi-target balance is considered, inventory configuration is dynamically optimized through a multi-target reward function, the inventory turnover rate is remarkably increased, the inventory holding cost is reduced, the service level is improved, and the method is suitable for various scenes such as retail chain, manufacturing industry distributed storage and cross-regional logistics distribution; and global optimal inventory configuration is realized on the premise of ensuring data privacy.

The invention discloses a dynamic optimization updating method of a credible data intelligent detection system, which relates to the technical field of credible data detection, and comprises the following steps: deploying heterogeneous feature acquisition nodes, acquiring data association features, operating behavior fingerprints and setting a dynamic credible evaluation threshold value; constructing a gradient aggregation channel based on differential privacy encryption, performing security fusion, generating a global model optimization vector, and generating an adversarial sample set; carrying out weight distribution, configuring a dynamic update step length, and generating an update instruction set; and activating the adversarial sample generation network, generating an incremental update package, triggering asynchronous hot deployment of the edge computing nodes, reconstructing a model topological structure of the federated incremental learning framework, and generating an update log. The technical problems of poor adaptability and low real-time performance in the aspects of data credibility evaluation, privacy protection and security defense in the prior art are solved, and the technical effects of improving the data credibility, enhancing the privacy protection capability and improving the attack defense capability are achieved.

The invention relates to a gradient aggregation federated learning method based on combination of zero knowledge proof and a block chain technology, and belongs to the field of distributed machine learning. Through combination of zero knowledge proof (zk-SNARK) and an extensible block chain technology, limitations of a traditional method in aspects of data privacy protection and model verification are broken through. According to the method, the correctness of a global model is verified by using zero-knowledge proof, the transparency and data privacy of an aggregation process are ensured, the Chinese remainder theorem is introduced to compress the proof, and the storage burden of block chain nodes is reduced. And the hash value updated by the encryption model is recorded through the block chain, verification is carried out based on a block chain consensus node, and the data integrity and the system transparency are further improved. Besides, a dynamic client selection mechanism is introduced in the method, participants are optimized based on training performance scores, and the training efficiency and the model quality are improved. As a whole, the invention provides a safe, efficient and transparent distributed learning solution.

The invention discloses a big data privacy protection modeling method and system based on federated learning and a block chain, and relates to the technical field of privacy protection and joint modeling. According to the method, homomorphic encryption, differential privacy, federated learning, secure multi-party computing and block chain technologies are fused, big data privacy protection and joint modeling are realized, encryption and dimensionality reduction are performed on original data through homomorphic encryption and differential privacy, an encrypted training sample of secure privacy is generated, a local model is trained on an encrypted data set through federated learning, and a big data privacy protection result is obtained. The method comprises the following steps: calculating aggregation parameters by using security multiple parties, constructing a verification network in combination with a block chain, ensuring credibility and integrity of model training, and finally, adding noise optimization performance for a global model by using differential privacy, testing generalization ability through cross validation, and determining a deployable privacy protection joint learning model, thereby breaking traditional data islands, promoting cross-mechanism data cooperation, and improving the privacy protection performance. Big data values are released, and data protection regulations and privacy requirements are met.

The invention provides a knowledge question and answer rapid processing method and system based on artificial intelligence, and relates to the field of artificial intelligence. A multi-modal knowledge graph is constructed, collected multi-source teaching data is fused through a mixed retrieval strategy, and the mixed retrieval strategy comprises semantic retrieval, vector retrieval and metadata retrieval; multi-level question and answer processing is executed based on an RAG enhancement framework, a multi-modal input intention is analyzed, cross-library joint retrieval is performed, and an optimization answer is generated in combination with a teaching scene; distilling the global model to a lightweight TinyBERT architecture, dynamically optimizing question and answer quality through a cognitive reinforcement learning framework, positioning a key document from a comprehensive retrieval list, evaluating an optimized answer, and reconstructing an answer with a key document verification score; according to the invention, the professional skill level of teachers and students in the fields of artificial intelligence and large model application can be improved, and the personalized requirements of teachers and students in teaching, scientific research and innovation courses can be met.

The invention discloses a federated learning model training method and system based on differential privacy image noise addition. The method comprises the following steps: S1, initializing an evaluation network, a target network and hyper-parameters; s2, initializing a global model and parameters; s3, acquiring a selected client and a privacy budget; s4, the selected client performs local training and uploads the disturbance gradient to the central server; s5, the central server aggregates the disturbance gradient of the client to obtain an updated global model and a reward corresponding to the current state; s6, the next state of federated learning is obtained, and the evaluation network and the target network are updated; s7, repeatedly executing the steps S3 to S6 until the set number of global iterations is reached; and S8, updating the exploration rate and repeatedly executing the steps S2 to S7 until the set federal learning times are reached. The invention provides a dynamic differential privacy method in combination with a federal learning framework, which can improve the image recognition rate while ensuring the privacy of the user.