2290results about How to "Improve training efficiency" patented technology

The invention relates to the technical field of data processing, and discloses a coal and gas outburst dynamic monitoring and intelligent early warning method and device. The method comprises the following steps: collecting and preprocessing multi-source sensor data arranged in a target area to obtain a multi-dimensional data set; performing multivariable time sequence analysis on the multi-dimensional data set to obtain coal seam gas outburst risk prediction data; based on coal seam gas outburst risk prediction data, performing dynamic risk assessment and spatial interpolation processing on the multi-dimensional data set to obtain real-time risk distribution data of the target area; performing multi-dimensional threshold analysis on the real-time risk distribution data to obtain preliminary early warning data; performing multi-modal information fusion on the preliminary early warning data to obtain target early warning data; and performing intelligent decision tree analysis on the target early warning data to obtain a target early warning scheme. According to the invention, the accuracy and reliability of dynamic monitoring and intelligent early warning of coal and gas outburst are improved.

The invention relates to the technical field of knowledge question answering, in particular to an intelligent question answering method and system based on multi-module collaborative optimization, and the method comprises the steps: inputting a question to be answered into a knowledge question answering model, and outputting a knowledge question answering result by the knowledge question answering model; a knowledge range judgment module in the model judges whether the problem can be solved by relying on own knowledge, and if not, a dynamic retrieval module is entered; the dynamic retrieval module performs similarity retrieval on the content of the memory knowledge base according to the question to be answered, and if the retrieval result does not meet the requirement, the multi-level question rewriting module is entered; the multi-level question rewriting module rewrites questions to be answered and inputs the rewritten questions into the knowledge screening module; the knowledge screening module outputs the screened documents according to the rewritten questions, the auto-reflection optimization module generates preliminary answers according to the documents and the questions and judges whether the preliminary answers are reasonable or not, auto-reflection optimization is carried out if the preliminary answers are not reasonable, and a new solution is provided for development of the intelligent question and answer technology.

The invention belongs to the technical field of image classification neural networks, and discloses a lightweight image classification neural network architecture system based on knowledge distillation. The invention provides a lightweight image classification neural network architecture system based on knowledge distillation. The lightweight image classification neural network architecture system comprises a data set preprocessing module, a teacher model preprocessing module, a subnet model construction module, a personalized training module, a real loss calculation module, a distillation loss calculation module, a total loss calculation module and a student model construction module. The invention provides a lightweight neural network architecture system based on knowledge distillation, and designs a brand new training mode by using the superiority of knowledge distillation for teacher model weight extraction: the knowledge distillation of teacher and student models is combined with a deep compression method; the system for constructing the lightweight network can be used for training various complex image classification neural networks so as to improve the network performance.

The invention discloses a method for realizing high-efficiency low-consumption micro-aerobic hydrolytic acidification of petrochemical wastewater by regulating and controlling the aeration rate in combination with a space-time diagram neural network and reinforced learning, and relates to a method for realizing high-efficiency low-consumption micro-aerobic hydrolytic acidification of petrochemical wastewater by regulating and controlling the aeration rate. The method comprises the following steps of: 1, collecting and cleaning data; 2, constructing a graph data set; 3, training the ST-GNN model; 4, constructing a deep Q reinforcement learning model; 5, the trained ST-GNN model is embedded into an automatic control system of a sewage treatment plant, and the model outputs the optimal aeration rate of the current time step and predicts the micro-aerobic hydrolytic acidification effect through interaction of the current working condition and historical data; and adjusting operation parameters of aeration equipment according to the output of the model, and carrying out hydrolytic acidification treatment. The method is high in regulation and control efficiency and low in operation error, and can be applied to the field of digital and intelligent management of sewage treatment plants.

The invention provides a multi-modal large model construction and operation method and system for reservoir dam safety. The method comprises the following steps: constructing a training set, wherein the training set comprises a single sample; multi-modal data as model input: sensor data arranged on the dam, historical hidden danger records, engineering technology documents formed in various stages of planning, design, construction and operation of the dam, information resources related to dam safety, geometric and material information of the BIM model, timestamps and spatial position information; the probability value of occurrence of the hidden danger event serving as the training label is obtained; the training set is adopted to train a multi-mode pre-training model based on a Transform framework; performing real-time prediction and early warning on potential safety hazards of the dam; and calculating the actual influence degree, the comprehensive risk score, the dynamically set early warning threshold and the emergency measure suggestion of the hidden danger event according to the probability value of whether the hidden danger event occurs or not output by the model. The scientificity and effectiveness of dam safety monitoring are comprehensively improved.

The invention relates to the technical field of natural language processing, and discloses a question and answer task processing model training method, device and equipment and a storage medium, and the method comprises the steps: adjusting a question and answer task processing model according to an initial training data set and a first model training algorithm, and obtaining a first intermediate question and answer task processing model; according to the initial training data set and the first intermediate question and answer task processing model, obtaining a first reasoning step and first annotation information for processing the question and answer task, and generating a first target training data set; according to the initial training data set and a second model training algorithm, adjusting a question and answer task processing model to obtain a second intermediate question and answer task processing model; and adjusting the second intermediate question and answer task processing model according to the first target training data set to obtain a target model. The problems that when the model for processing the question and answer task is trained, the accuracy of the model is affected by the quality of the manually-labeled data due to the dependence on the manually-labeled data, and the training process is high in cost and low in efficiency are solved.

The invention relates to a PCB defect detection method and system based on a YOLOv8 network, and belongs to the technical field of target detection. Collecting and preprocessing a PCB sample image data set for training a PCB defect detection model; inputting a to-be-detected image into the trained defect detection model to obtain a detection result; the to-be-detected image is generated by collecting and processing image data of the to-be-detected PCB; wherein the defect detection model comprises a trunk network, a neck network and a head network, and the trunk network extracts features through a mobile reverse bottleneck convolution module and a C2f module to generate an intermediate feature map; and the neck network performs splicing fusion on the middle feature map to generate a spliced feature map, the head network performs re-weighting on the spliced feature map through a convolution kernel attention fusion module to generate a third feature map, and then the detection module outputs a detection result. The method not only improves the precision of the defect detection model in detecting the features of the tiny target, but also improves the detection speed and generalization ability, and reduces the calculation cost and complexity at the same time.

The invention relates to the technical field of machine learning, in particular to a heating fault prediction method and system for a high-voltage circuit breaker and an isolating switch of the high-voltage circuit breaker. The method comprises the following steps: carrying out multi-source data acquisition on a high-voltage isolation switch and an associated high-voltage circuit breaker through an SCADA system, and carrying out data preprocessing to obtain a preprocessed data set; performing operation feature correlation analysis on the preprocessed data set to obtain a correlation operation feature set; performing dynamic association network construction on the association operation feature set to obtain a dynamic association network graph; acquiring historical fault data; performing propagation risk path search according to the historical fault data and the dynamic association network diagram to obtain a candidate risk path set; and performing path propagation probability calculation on the candidate risk path set to obtain a path probability data set. According to the method, the influence of the associated high-voltage circuit breaker on the heating risk of the isolating switch is effectively identified, so that the accuracy of fault prediction and the timeliness of early warning are improved, and a more reliable guarantee is provided for safe and stable operation of a power system.

The invention discloses an online reinforcement learning data increasing and expanding method based on a diffusion model. The method comprises the following steps: processing original trajectory data to generate enhanced feature data; extracting global structure representation and local detail representation; carrying out fusion by adopting a hierarchical integration method to obtain unified hierarchical representation data; generating constraint coding data based on pre-stored physical constraint parameters and task constraint parameters, and fusing to generate constraint perception representation data; generating an evaluation result based on the current strategy parameter; performing adaptive adjustment on the constraint perception representation data to obtain adjusted representation data; modal analysis is carried out, diversified trajectory data is generated, and a candidate trajectory set is obtained; and carrying out quality evaluation, carrying out trajectory screening through a multi-objective optimization method, and updating strategy network parameters to obtain updated strategy parameters. According to the invention, high-quality training data can be automatically generated, and the training efficiency and performance of a reinforcement learning system are improved.

The invention discloses a power equipment fault prediction method based on support vector regression, and aims to improve the prediction accuracy. The method comprises the following steps: firstly, collecting multi-dimensional operation parameter data of power equipment, and constructing an original monitoring data set; a data set is segmented through a sliding time window, wavelet transform is used for noise reduction, and then a normalization method is applied to generate a standardized data set. Time domain and frequency domain features are further extracted, a feature vector space is constructed, an optimal feature subset is screened through a mutual information method, and a training data set is generated; performing preliminary training on a support vector regression model by using the training data set to generate candidate support vectors, and screening a support vector set with the maximum contribution through an optimization algorithm; a grid search method is adopted to adjust kernel function parameters and penalty factors, and a support vector set is further optimized. And evaluating the performance of the model through cross validation, applying the optimized support vector regression model to power equipment fault prediction, and generating a fault occurrence probability prediction value.

The invention belongs to the field of power distribution network low-carbon economic optimization scheduling, and provides a power distribution network source network load storage low-carbon optimization scheduling increment reinforcement learning method and system, and the method comprises the steps: carrying out the intelligent agent division of a power grid, obtaining a plurality of intelligent agent regions, and collecting the observation data of each intelligent agent region; on the basis of the observation data, constructing a low-carbon economic dispatching model of source-grid-load-storage cooperation by taking the operation cost and carbon emission of each agent regional power grid as objective functions; designing the source-network-load-storage coordinated low-carbon economic dispatching model into a reinforcement learning model in a multi-agent environment according to a state space, an action space, an environment and a reward function; and solving the reinforcement learning model in the multi-agent environment to obtain an optimal scheduling solution. According to the incremental optimization method, the environment can help the intelligent agent to detect environment changes in training, excessive exploration risks are avoided, the training time is shortened, and meanwhile the flexibility of the system is improved.

The invention discloses an AI model adaptive tuning method based on deep reinforcement learning, and belongs to the technical field of industrial process control, the method comprises the following steps: firstly, constructing a deep reinforcement learning environment comprising a state space, an action space and a reward function, the state space comprising a process variable measurement value, a controller parameter and a performance index; the action space is a parameter adjustment quantity vector, and the reward function comprehensively considers the stability, rapidity and accuracy of the system; then, based on a deep Q learning network of a dual-network structure, training data are stored and sampled by adopting an experience playback mechanism, and network parameters are iteratively optimized through a deep Q learning algorithm; and finally, realizing online adaptive adjustment of controller parameters by using the optimized deep Q network. The method has the advantages of being high in adaptability, good in optimization performance, high in practicability and the like, intelligent optimization control over an industrial process control system can be achieved, and the overall performance of the system is improved.

The invention relates to the technical field of software reliability guarantee, in particular to a code vulnerability detection method based on efficient parameter fine tuning of a code pre-training model, which comprises the following steps: preprocessing source codes of a vulnerability data set; s2, converting the preprocessed source code, and extracting a token sequence and a code attribute graph path corresponding to the source code; s3, constructing a code vulnerability detection model, wherein the code vulnerability detection model comprises a semantic feature extractor, a structural feature extractor, a feature fusion layer and a classifier; s4, jointly training a code vulnerability detection model by using the token sequence corresponding to the extracted source code and the code attribute graph path; and S5, through the optimized code vulnerability detection model, outputting a result that whether the source code to be detected has vulnerabilities or not. According to the method, the model is finely adjusted through efficient parameter fine adjustment, training resources are saved, good performance is obtained, and the code vulnerability detection efficiency and accuracy are improved by fusing and learning semantic and structural features of source codes at the same time.

The invention provides a decision-making large model-oriented multi-level heterogeneous memory collaborative scheduling method, which comprises the following steps of: acquiring hardware configuration information and initial state information of a heterogeneous memory system, constructing a burst memory access model based on an Erlang distribution family, and acquiring dynamic memory access characteristics in combination with self-adaptive stratified sampling; representing the state of the memory system by adopting multi-dimensional efficiency measurement and a hierarchical affinity matrix; predicting load characteristics based on a generalized extreme value theory, and constructing an augmented Lagrange optimization model to generate a resource allocation scheme; formulating a data migration strategy through a Pareto optimization algorithm; and dynamic parameter adjustment of Thompson sampling and an exception handling mechanism based on a combined early warning index are introduced. According to the method, memory access features can be accurately described, resource allocation is optimized, migration overhead is reduced, and large decision model training efficiency is improved.

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 relates to the technical field of data packet transmission, and discloses a data packet transmission control method and device for a low-power-consumption dual-mode Bluetooth chip, and the method comprises the steps: obtaining a signal strength parameter, a power consumption parameter, a transmission rate parameter and an environment parameter of the dual-mode Bluetooth chip, inputting the parameters into a deep time convolution network, and carrying out the time sequence feature extraction, obtaining a transmission mode switching judgment result; calculating transmission state evaluation data; the chip transmitting power is adjusted in a grading mode, standby power consumption is controlled through a nanoamp LDO circuit, and a dynamic power control parameter is obtained; performing compression coding on the data packet to obtain a dual-mode transmission protocol configuration parameter; executing time sequence sampling, and constructing a dual-mode state feature sequence; the data packet delivery success rate, the end-to-end transmission time delay and the total power consumption of the system are calculated, transmission control parameter optimization is carried out through double-layer deep reinforcement learning, target transmission control parameters are obtained, and the optimal balance of the transmission performance and the power consumption of the dual-mode Bluetooth chip is achieved.

The invention belongs to the technical field of model training, and particularly relates to a large model increment training method and system based on dynamic sparsification. The method comprises the following steps: S1, evaluating the parameter importance of a large model by adopting a multi-dimensional evaluation method, and reflecting the contribution of parameters to the performance of the large model; s2, performing dynamic sparsification control on the large model structure by adopting a self-adaptive structure adjustment method; s3, performing incremental training management on the large model by constructing a capacity-adjustable empirical playback buffer pool and proposing a multi-objective loss function; and S4, carrying out model compression optimization on the large model by adopting a mixed precision quantification strategy. The method has the characteristics that the network structure can be dynamically adjusted by evaluating the importance of model parameters in real time, so that the efficient training is realized while the model performance is ensured.

The invention relates to the technical field of brain-computer interfaces, and discloses a self-adaptive dynamic feedback brain-computer interface training method and system based on virtual reality. The training method comprises the steps that a user performs motor imagery according to a training scene presented by the VR display device; the electroencephalogram acquisition equipment acquires electroencephalogram signals; configuring a data processing module, and operating a motor imagery continuous control model to calculate characteristic parameters by taking the electroencephalogram signals as input; under the condition that the task exists, the characteristic parameters are used as input, and a dynamic self-adaptive characteristic-feedback mapping model is operated to calculate control parameters; sending the control parameters to a functional electrical stimulation device to load electrical stimulation of corresponding intensity to the muscle to obtain tactile feedback; meanwhile, the dynamic adaptive feature-feedback mapping model is dynamically updated according to latest input feature parameters; the control parameters are sent to the VR display device to present visual feedback, and the user adjusts the motor imagery based on the visual feedback and the haptic feedback. The participation sense of the user and the training efficiency can be improved.

The invention relates to a construction method of a cooperative combat decision-making agent for ground unmanned equipment, and aims to solve the problem of space dimension disaster of a complex cooperative combat task. The DRL solution space is effectively compressed, the exploration efficiency is improved, and meanwhile intelligent decision making of tasks with different granularities in the whole combat process is achieved; aiming at the problem of generating a'task layer 'combat command action strategy, a cooperative combat decision-making agent network model is constructed to realize the unified coordination control from the effective representation of complex state input to the combat action; by constructing a distributed training framework, the sampling and training efficiency is improved, and high-throughput asynchronous parallel training of a cooperative combat decision-making agent network model is realized; by establishing a combat decision agent learning algorithm based on deep reinforcement learning and solving the combat decision agent learning algorithm, the learning efficiency and final performance of an agent network model are effectively improved.

The invention provides a high-resolution remote sensing image semantic segmentation method based on multi-scale depth supervision, and the method comprises the following steps: 1, obtaining an ISPRS Potsdam data set and a Vaihingen data set; 2, building a multi-scale deep supervision network MDSNet, wherein the multi-scale deep supervision network MDSNet comprises a spatial branch network, a semantic branch network and a multi-scale feature aggregation part; each of the spatial branch, the semantic branch network and the multi-scale feature aggregation part is of a four-layer structure; step 3, inputting the training set into a multi-scale deep supervised network MDSNet for training, calculating a loss function and performing back propagation, updating network parameters, and obtaining a trained parameter model; and step 4, inputting the test set into the trained parameter model, and outputting a segmentation image of the target image. According to the method provided by the invention, the feature extraction capability is improved, and meanwhile, the semantic segmentation accuracy, the training efficiency and the stability are improved.

The invention discloses a driving skill training method constructed based on a diversified virtual examination room, and relates to the technical field of data processing, and the method comprises the steps: constructing a system based on the diversified virtual examination room, constructing a virtual examination room scene to carry out the driving training of a training user, outputting a driving behavior data set in real time, and carrying out the scoring, and analyzing the data according to the driving score, generating a personalized training path in combination with historical data when the driving score does not reach the standard, and training the user to carry out training step by step according to the training path until a preset skill scoring target is achieved. The technical problems that in the prior art, a traditional driving training method cannot dynamically adjust a training path to meet the actual skill requirements of trainees, consequently, training content lacks pertinence and is low in efficiency are solved, the individuation and pertinence of driving skill training are improved, it is ensured that the training content is highly matched with the actual skill requirements of the trainees, and the driving skill training efficiency is improved. And the training efficiency and effect are improved.

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 large language model training method and system based on elastic federal low-rank adaptive fine tuning, which adopts federal aggregation based on singular value decomposition (SVD) to reconstruct a local LoRA module of a client into a local increment matrix, then aggregates the local increment matrix into a global increment matrix, and generates a LoRA module of the next round through SVD, thereby effectively eliminating aggregation errors of traditional FedLoRA. According to the method, the LoRA rank is dynamically distributed for each weight matrix, and the balance between statistics and hardware efficiency is realized. In order to further reduce communication overhead and maintain model precision, a self-adaptive matrix freezing mechanism is introduced, and whether freezing is carried out or not is judged according to training stability of a weight matrix. According to the method, challenges of traditional FedLoRA in the aspects of training efficiency, communication overhead, model precision and the like are solved.

The invention relates to the field of degradation trend evaluation of rotary machinery, in particular to a motor abnormity identification method fusing low-frequency characteristics and an auto-encoder, and the method comprises the following steps: S1, collecting a vibration signal of target motor equipment; s2, data preprocessing; s3, building an auto-encoder network model; s4, training an auto-encoder network model; s5, calculating an equipment anomaly detection threshold value index; and S6, deploying applications. According to the method, vibration signal low-frequency feature mapping of the healthy operation state of the motor is self-learned through the self-encoder, the mean square error of the reconstructed feature and the original low-frequency feature is tracked, and the statistical abnormality trigger threshold value is calculated, so that feature information loss caused by direct extraction of a vibration signal monitoring index is avoided; extraction of original vibration low-frequency signal features is enhanced, the abnormal state of the motor is estimated in advance, and early warning and operation and maintenance of early degradation of the motor are achieved.

The invention discloses a two-way staggered assembly line parallel method for accelerating large model training, and compared with an existing method, the method introduces V-shaped staggered scheduling into a two-way assembly line to form a two-way staggered assembly line parallel mode, and improves the training efficiency of a large model and the use balance of a video memory. A V-shaped staggered assembly line and an inverted V-shaped staggered assembly line are fused to form a bidirectional staggered assembly line, the number of parallel devices is increased, meanwhile, the calculation time of a single micro-batch is shortened, the cavitation rate of the assembly line can be effectively reduced, and more balanced video memory occupation is achieved; in addition, a communication optimization strategy is introduced for overlapping or reducing part of communication overhead, and global gradient synchronization is performed by optimizing pipeline equipment mapping and utilizing a high-speed network in a server, so that the parallel training efficiency of the large model is further improved. The invention further provides a two-way interleaving assembly line parallel system and equipment which are used for achieving the two-way interleaving assembly line parallel method.

The invention discloses an image generation method and system based on diffusion model adaptive reasoning. The method comprises the following steps: constructing a next noise intensity prediction module TPM; improving an original diffusion model, and adding a TPM; the improved diffusion model is trained by using a reinforcement learning method, the whole denoising process is expanded for multiple times, the next time step is predicted in each iteration, an award is calculated according to the quality of a finally generated image and the number of steps, and TPM parameters are updated by using a PPO loss function; in the actual reasoning process, noise is randomly sampled from Gaussian noise and input into the trained diffusion model, the diffusion model is used for predicting a denoising result, meanwhile, the TPM is used for outputting distribution of time steps based on next denoising, and a distribution mode is used as the next time step used in actual reasoning; and when the predicted time step is smaller than a set threshold value, a final image generation result is obtained based on model output. According to the method, the image generation process can be dynamically adjusted, and a reasoning result with both efficiency and quality is realized.

The invention provides a deep learning large model training method and system for heterogeneous equipment, belongs to the technical field of model training, and aims to solve the problem that a heterogeneous GPU cluster cannot be effectively utilized when a traditional scheme is used for training a deep learning large model. Different network layers of a deep learning large model to be trained are divided into a plurality of stages, forward propagation and back propagation calculation of all network layers in each stage is executed by independent virtual equipment, and meanwhile, utilization of GPU resources of different structures is coordinated in combination with a proposed hybrid parallel training strategy, so that efficient model training is realized.

The invention discloses a system and a method for security enhancement of generated content information of a large model, and the method comprises the steps: firstly, carrying out the bidirectional LoRA fine tuning technology and knowledge distillation technology on the large model, and enabling the large model to adapt to a factual output task from the illusion dimension and the factual dimension; performing extraction of intermediate layer representation in a fact space on the fine-tuned large model, and obtaining different mappings from fine-grained illusion types to a fact direction through a comparative learning method; and finally, in the reasoning generation process of the large model, extracting the representation of the middle layer of the large model to judge the potential illusion type, then applying the learned mapping corresponding to different illusions to the middle representation of the reasoning process, correcting factual representation, reducing the illusion output probability, and in the pre-training stage and the reasoning generation stage, obtaining the illusion type of the large model. Parameters and generated contents of the large model are controlled, and the factuality and reliability of the generated contents of the large model are greatly improved while the generation capability of the large model is guaranteed.

The invention relates to an AI online education intelligent question and answer information processing method, which comprises the following steps of S1, collecting teaching materials, and performing preprocessing and labeling to form a text data set with labels; s2, constructing a question and answer model based on XLNet; s3, introducing a specific context optimization question and answer model for a specific subject or topic to obtain an optimized question and answer model; s4, constructing an auxiliary understanding information knowledge graph by considering hierarchical design of age groups based on the labeled text data set; s5, inputting a query by the user, and obtaining an optimally matched answer based on the optimized question and answer model; according to the age group of the user and the best matching answer, auxiliary understanding information is obtained from the knowledge graph, and a complete answer is obtained; and S6, adjusting provided content and difficulty through user interaction data, and recommending related domain knowledge based on user behaviors and preferences. According to the method, the direct answers required by the user are provided, the supplementary background information is provided to enhance the understanding, and the requirements of the user are presented in a personalized manner according to the characteristics of the user.

The invention discloses a tool wear monitoring and repairing method based on artificial intelligence. The method comprises the following steps that a terminal layer collects original machining data and uploads the original machining data to a cloud computing layer; the cloud computing layer trains a power increment diagnosis model; the terminal layer collects processing data in the processing process in real time as monitoring data; the cloud computing layer selects a deep learning algorithm or a transfer learning algorithm to train a final processing precision fault diagnosis model; constructing an edge calculation distribution optimization algorithm and performing task scheduling; and based on the machining precision fault diagnosis result, a laser surface strengthening path is constructed, and the abraded tool is repaired through laser surface strengthening treatment. The numerical control machining process can be diagnosed in real time based on the transfer learning mechanism, the laser surface strengthening path is planned based on the diagnosis result, the laser surface strengthening operation is guided in real time, the abnormal state of the tool is repaired in time through the laser surface strengthening technology, and the machining precision is ensured.