440 results about "Discriminator" patented technology

The invention discloses a high-temporal-spatial-resolution refined flow field reconstruction method, device and equipment and a medium, and relates to the technical field of ocean current reconstruction, and the method comprises the steps: carrying out the normalization and temporal-spatial alignment of satellite remote sensing, buoy observation and numerical simulation data; based on the alignment data, performing rehearsal on the unstructured nested grid through an FVCOM model, and then dynamically encrypting the grid according to the flow field gradient and generating a background flow field; inputting the background flow field into a PINN-GAN combined framework, and outputting a refined flow field through physical constraint loss and double-discriminator adversarial training; and scheduling a calculation task by adopting a heterogeneous accelerator, verifying the reconstructed refined flow field in real time, and performing feedback optimization. Through generation of the background flow field and refinement reconstruction, the ocean current flow field with high temporal-spatial resolution can be reconstructed efficiently and accurately.

The invention discloses an automatic code security optimization method based on a large language model, and belongs to the technical field of code security optimization. Acquiring large-scale programming data to establish a programming data set, establishing a primary training model, generating an initial code and establishing an initial code set; the predefined vulnerability mode set scans the initial code set, vulnerabilities in the initial code set are identified and defined as initial vulnerabilities, and the initial vulnerabilities are positioned and classified; static analysis is matched with a semantic discriminator to evaluate the code snippets to obtain a new generation strategy, and the primary generation strategy is adjusted to obtain an optimized training model; capturing potential vulnerabilities as training signals, and optimizing the optimization training model to obtain a continuous optimization training model; and establishing a vulnerability library and a repair strategy library, and optimizing vulnerability time and a repair algorithm by analyzing data of the vulnerability library and the repair strategy library. Potential vulnerabilities in generated codes can be automatically recognized and repaired, a large amount of manual intervention is not needed, and code generation safety is improved.

The invention discloses a backdoor attack chain method of a code-driven body agent based on a large language model. The method comprises the following steps: creating an initial poisoning prompt by using a generative adversarial network; the poisoning prompt is optimized through iterative confrontation training between the generator and the discriminator; inputting the optimized poisoning prompt into the target large language model; deploying the program with the backdoor defect to the intelligent agent with the body; when the body agent runs a program with a backdoor defect, a visual trigger in the environment activates the backdoor, causing the body agent to perform a preset specific behavior. By using poisoning prompts optimized by the generative adversarial network, the present invention can generate backdoor codes that are difficult to detect, thus having significant advantages in concealment and effectiveness.

The invention relates to an ECG anomaly detection method based on AE-GAN, and belongs to the field of artificial intelligence. According to the method, AE-GAN is constructed and trained for ECG anomaly detection, and a training network model is divided into an encoder training stage, the AE-GAN is only trained on a normal ECG sample, and an encoder, a generator and a discriminator are optimized by using confrontation loss and reconstruction loss; the encoder includes a channel attention module and a memory module. In a classifier training and detection stage, the AE-GAN extracts low-dimensional features from a real sample by using a trained encoder, adds weak random Gaussian noise to generate a pseudo normal sample, and adds strong random Gaussian noise to generate a pseudo abnormal sample; the classifier is trained by using a binary cross entropy loss function so as to distinguish normal samples from pseudo abnormal samples; during testing, the trained classifier uses features extracted by the encoder to detect whether data is abnormal or not.

The invention discloses a large language model security vulnerability automatic detection method and device based on scene nesting, and belongs to the technical field of large language model security, and the method comprises the steps: constructing an input transformation mode for an original cue word, constructing a corresponding decoding mode, and embedding the decoding mode into the input of a target large language model; performing task scene nesting in the target large language model, performing different input transformations on the original cue words, inputting the original cue words into the target large language model, decoding the transformed cue words according to an embedded decoding mode, and performing model reasoning to generate an output result in a corresponding task scene; and performing harmfulness judgment on an output result of the target large language model by utilizing the discriminator model, and if a judgment result is harmful, indicating that the target large language model has security vulnerabilities. The method can effectively reveal and detect the endogenous and exogenous security vulnerabilities existing in the large language model, and achieves the efficient and comprehensive detection of the security vulnerabilities existing in the large language model.

The invention relates to the field of knowledge engineering, and discloses a knowledge inference method based on adversarial reinforcement learning, comprising a generator and a discriminator, using an AttTuck Comp GCN embedding model in a KGE framework to obtain vector representation of entities and relationships, incorporating potential target entity vectors into an RL framework, and using a scoring function as a soft reward for calculating candidate entities; the generator maintains a coverage vector and then calculates the probability of each step of candidate action according to state information, and the discriminator captures context path representation and evaluates the accuracy of answers and the reasonability of reasoning paths; the method has the advantages that the problem that the long-distance dependency relationship and the high-dimensional complex relationship are insufficient in representation capability can be effectively solved, and the problems that convergence is slow and the performance is poor due to non-destination search are avoided. And the problem that false paths exist in the reinforcement learning framework is relieved.

The invention belongs to the technical field of power system application, and particularly relates to an intelligent power flow data filling method based on space-time coupling. The invention provides an intelligent power flow data filling method based on space-time coupling, which comprises the following steps: firstly, carrying out data preprocessing on original data through Hampel filtering, phase alignment and normalization, constructing a space-time encoder through joint coding of adaptive graph convolution (Adaptive GCN) and attention LSTM, capturing space-time coupling characteristics, and carrying out data processing on the space-time coupling characteristics; a multi-physical constraint generative adversarial network (Pry-GAN) is designed through generator physical constraints and a multi-scale discriminator to realize data filling, and it is ensured that a filling result has both numerical reasonability and physical feasibility.

Provided herein is a novel method named Knowledge-Constrained Tree Search Decoding (KCTS) is provided, which is a first discriminator-guided constrained decoding approach to knowledge-grounded generation. The KCTS method also employs a Monte-Carlo Tree Search decoding (MCTS) instead of conventional LM decoding methods, which re-orders each token's importance based on the estimated future faithfulness starting from that token with multiple simulations. Coupled with a novel token-level hallucination detection method, RIPA (Reward Inflection Point Approximation), trained to predict the starting point of the hallucinating token, enabling effective adaptation of the knowledge classifier defined on the sequence level to the token level, this novel method is able to greatly mitigate hallucination problems of LLMs without the need of fine-tuning, thereby preventing the incurrence of high computational costs.

It aims to more reliably manage abnormal communication. 【Solution means】 The abnormality management device 1 is configured such that a first learning unit 12 treats each observed value of a normal presence time series as discrete values independent of each other, and estimates probability parameters of a probability model representing the normal presence time after quantization based on the appearance frequency of each observed value; and a second learning unit 13 configured to fix the generator parameters of a generator 131 that generates pseudo-normal data sufficiently deviated from the distribution of true normal data, with each observed value of the normal presence time series being true normal data, and update only the discriminator parameters of a discriminator 132 that discriminates between true normal data and pseudo-normal data in a direction to maximize the discrimination accuracy, based on the probability parameters of the normal presence time estimated by the first learning unit 12.

The invention relates to the technical field of federated learning, and discloses a discriminator knowledge distillation personalized federated learning method based on a conditional generative adversarial network. The problems of appearance of massive participants and influence of non-independent identical distribution of data on federal learning data cost and personalized learning efficiency are solved; a discriminator knowledge distillation model fused with the conditional generative adversarial network is put forward to be embedded into a personalized federated learning framework; the differentiated feature representation of the client model is enhanced through the discriminator knowledge distillation model, so that the personalized model effectively recognizes and captures specific modes and features of individuals, the representation capability and the personalized effect of the model are enhanced, the higher model compression rate is achieved, and meanwhile, the user experience is improved. The conditional generative adversarial network fused with the discriminator generates synthetic data specific to each client, and the synthetic data improves the generalization ability of personalized federal learning and the adaptability of the model on the premise of fully ensuring the data privacy.

The embodiment of the invention provides an automatic driving model training method and device combining GAIL and PPO, and the method comprises the steps: collecting an expert driving track sequence through a simulation environment by designing a multi-stage training frame; a double-branch discriminator network is constructed, a frame-level branch analyzes single-frame behavior characteristics based on an attention mechanism, and a track-level branch adopts a recurrent neural network to process a continuous driving sequence so as to realize multi-scale characteristic fusion. Iterative training is carried out by adopting a near-end strategy optimization algorithm, a multi-task learning objective function is constructed, driving action generation and trajectory prediction are optimized at the same time, and an adaptive confidence interval constraint and experience playback mechanism is introduced. According to the method, the defects of the traditional technology in the aspects of driving behavior evaluation, strategy optimization and the like are effectively overcome, and the robustness and generalization ability of an automatic driving model are remarkably improved.

The invention discloses a federated learning method and system based on differential privacy, belongs to the technical field of federated learning, and aims to solve the technical problem of how to realize federated learning under the condition of ensuring local data privacy and defending FL inference attack at the same time. Comprising the following steps that a private generation model is constructed based on an auxiliary classifier GAN, and the private generation model comprises a generator and two discriminators; the classification loss of the real sample and the classification sample is introduced to carry out model training on the private generation model, and a trained generator is obtained; each client carries out local training on the local model based on the synthetic sample to generate local model parameters of the local model, and uploads the local model parameters to a server, and the server carries out aggregation calculation based on the local model parameters and weights corresponding to the clients to obtain global model parameters, and sends the global model parameters to the server; and returning the global model parameters to each client for iterative model training.

The invention discloses a converter batching data generation and optimization method, which comprises the following steps: acquiring an original industrial data set in a converter batching process, preprocessing the original industrial data set, inputting preprocessed training data into an encoder, generating a mean vector and a variance vector of potential variable distribution, and optimizing the mean vector and the variance vector; constraining the similarity between the potential variable distribution and the standard Gaussian distribution through KL divergence loss; inputting the potential variable and the random noise vector into a generator to generate a simulation sample, and distinguishing a real sample from the generated sample through a discriminator; a forced discriminator module is introduced, and a discrimination result is converted into an additional loss item; and carrying out data generation on the missing batching parameters, outputting a complete batching data set conforming to process constraints, constructing a cost objective function, a quality objective function and a resource consumption objective function, constructing constraint conditions of chemical element content of a target finished product, optimizing the converter batching data, and generating optimized converter batching data.

The invention discloses a few-sample target detection method and system based on an aggregation variational prototype. The method comprises the steps of constructing a data set containing a base class and a new class, dividing the data set into a support set and a query set, generating a class prototype by utilizing a P-VAE module in combination with CLIP semantic features and a feature discriminator, realizing bidirectional fusion of the support set and the query set features by means of an MFM module, fusing the query features and the class prototype, and inputting the fused query features and the class prototype into a detection head to complete target detection. The system comprises a data set construction module, a priori variational automatic encoder P-VAE module, a mutual fusion module MFM, a feature fusion module and a target detection module. According to the scheme, by introducing semantic priori, optimizing prototype generation and feature interaction, the problems of data imbalance and insufficient new class feature representation in a few-sample scene are solved, improvement of new class detection precision is verified on PASCAL VOC, MS COCO and other data sets, and an effective solution is provided for target detection of sample scarce scenes such as medical images and rare species monitoring.

The invention belongs to the technical field of energy consumption optimization, and particularly relates to a digital twin building energy consumption dynamic optimization system, which comprises a modeling module for acquiring physical, structural and equipment layout parameters of a building, and constructing a target building three-dimensional region segmentation model containing geometric transmission constraints by combining three-dimensional modeling and a grid segmentation algorithm; the control mapping module is used for collecting data such as regional people flow density and equipment energy consumption, and constructing multi-level association control mapping including people flow-rate first association mapping, rate-energy consumption second association mapping and comfort level score-based second association feedback mapping through an association analysis algorithm; the analogue simulation module constructs a generator and a discriminator through association mapping, performs synchronous confrontation simulation in combination with a three-dimensional region segmentation model, and solves an optimal energy consumption rate; and the feedback adjustment module compares actual operation with feedback data, corrects mapping parameters and optimizes algorithm weights, realizes building energy consumption dynamic optimization, and ensures that the overall energy consumption and comfort level score meet preset thresholds.

The invention belongs to the technical field of efficient fine tuning and continuous learning of visual language models, and discloses a visual language model continuous learning method based on a dynamic hybrid expert adapter. The method comprises the following steps: constructing a dynamic hybrid expert adapter on a part of layers of a pre-trained visual language model, wherein the expert adapter and a routing network dynamically expand along with an incremental task; whether a new expert adapter is added or not is adaptively decided through the dynamic expert extension controller, and parameter redundancy of static hybrid experts is avoided; a potential embedded self-selector is integrated in a model, potential features output by a freezing layer are utilized to automatically judge data distribution and select corresponding routes, an independent external distribution discriminator is replaced, and a unified framework is formed. According to the method, the problem of disastrous forgetting in continuous learning is effectively relieved, parameter redundancy and calculation burden are remarkably reduced, and meanwhile, the zero sample generalization ability of the model for unseen data is kept.

The invention discloses a large language model alignment method and device based on decoding probability correction, and belongs to the field of artificial intelligence. By introducing a lightweight probability correction model, the original generation probability distribution of a large language model is monitored and intervened in real time in the reasoning and decoding process. According to the method, the generation probability distributed to each candidate token by a large language model is analyzed, and the probabilities are dynamically adjusted in real time by utilizing a probability correction model. Meanwhile, a global evaluation mechanism based on a discriminator is also introduced, so that the quality control and the alignment guarantee of the generated content are further enhanced. The discriminator not only has the capability of integrally evaluating the generated text, but also can identify potential improper contents or deviations, so that more comprehensive and accurate feedback is provided for a probability correction model.

The invention discloses a rolling bearing fault diagnosis method, system and device, a medium and a program product, and relates to the technical field of rotating machinery fault diagnosis, and the method comprises the steps: training a dual-mode adversarial deep transfer learning network based on a source domain feature and a target domain feature; wherein the dual classifier is trained based on the source domain feature and the target domain feature to obtain a source domain classification error and a dual classifier certainty error, and the domain discriminator is trained based on multi-linear mapping formed by the source domain feature, the target domain feature and a prediction result of the dual classifier to obtain a domain classification error. Combining the maximum mean difference error of the source domain feature and the target domain feature as a loss function; and classifying the target domain samples by adopting a dual-mode adversarial deep transfer learning network to obtain a fault diagnosis result. And designing a dual-mode adversarial deep transfer learning network, retaining category information by using multi-linear mapping and dual-classifier deterministic difference, introducing maximum mean difference, and improving fault diagnosis performance.

The invention discloses a rolling bearing depth universal domain self-adaptive cross-working-condition fault diagnosis method and device and a medium, and can be applied to the technical field of rolling bearing intelligent fault diagnosis. According to the method, the fault diagnosis model comprising the feature extractor, the binary classification network and the adversarial domain discriminator is trained through the source domain data containing the fault type label and the target domain data not containing the fault type label, and the loss function in the training process is calculated; adjusting model parameters of the fault diagnosis model according to the total loss function and a preset model parameter optimization algorithm so as to realize shared class feature distribution alignment between the source domain training set and the target domain training set, and identifying a private fault type of the target domain data set according to a confidence coefficient threshold; and when the number of training iterations of the fault diagnosis model is greater than or equal to the maximum number of iterations, the trained fault diagnosis model is tested through the target domain test set, so that the fault diagnosis accuracy of the fault diagnosis model can be improved.

The invention discloses an electric power system transient stability evaluation sample enhancement method, system and device based on a timing constraint generative adversarial network and a medium, and belongs to the technical field of electric power system safety analysis, and the method comprises the steps: constructing a sample enhancement model, generating transient time sequence data based on random noise and system feature tags by a generator, the discriminator outputs a sample authenticity score and a time sequence consistency score through a time sequence neural network, the physical constraint module calculates physical constraint loss of the generated data, the model is alternately trained in combination with multi-dimensional loss, the trained generator is utilized to synthesize samples, and qualified samples are screened through physical verification. According to the invention, by introducing the LSTM time sequence constraint, the WGAN-GP stable training mechanism and the multi-dimensional physical consistency constraint, three core problems of poor time sequence coherence, modal collapse and physical law violation in the existing sample enhancement method are cooperatively solved, and high-quality transient scarce samples can be generated.

The invention relates to a method and device for establishing a three-dimensional rock model.The method for establishing the three-dimensional rock model.The method comprises the steps that a rock sample is cut into a plurality of sub-samples of the first three-dimensional space size; performing data enhancement processing on the plurality of sub-samples of the first three-dimensional space size to obtain a sub-sample group; performing normalization processing on each sub-sample in the sub-sample group; constructing a generator by adopting a simplified Laplacian pyramid structure, and constructing a discriminator by adopting a deep convolutional neural network structure and an integrated feature statistical hybrid regularization mechanism; generating a random noise vector group matched with a target size, inputting the random noise vector group into a generator, inputting an output array of the trained generator into a trained discriminator, and judging that the output array is true, so as to generate a floating-point number array; and carrying out binarization processing and de-noising on the floating-point number array based on a preset threshold value to obtain a binarized rock model. According to the method, the problems of low stability and low quality of the rock model generated in the prior art are solved.

The invention discloses a raw coal quality data optimization and reconstruction method based on clean coal ash content feedback, and belongs to the technical field of computers. Data completion is achieved through the generative adversarial network; a generator predicts missing raw coal data according to the high-sampling-frequency clean coal ash content, and a discriminator evaluates the authenticity of the data. According to the method, the characteristic that the clean coal ash sampling rate is higher in the dense medium separation process is used for guiding data reconstruction; meanwhile, a composite loss function including adversarial loss, reconstruction loss and regression loss is designed, and the generation quality is improved. The method effectively solves the problem of raw coal quality data missing in the coal dressing process, and has high engineering application value.

The invention provides a characteristic difference learning network traffic flow data prediction processing method and system, relates to the field of data processing, and can solve the problem of low accuracy of traffic time sequence prediction. The method comprises the steps that data preprocessing is carried out on input original traffic time sequence data, a feature difference learning sample is obtained, and the original traffic time sequence data comprises traffic data of a plurality of target road nodes in a duration range; thirdly, constructing a deep learning model DXGAN by integrating a sample positioning encoder, a feature difference generator and a discriminator; and then, inputting the feature difference learning sample into a deep learning model DXGAN to obtain a prediction result. Spatial and temporal feature difference distinguishing is performed through trending feature difference learning, and the accuracy of traffic time sequence prediction is improved by using the high accuracy of the DXGAN model.

The invention relates to the technical field of artificial intelligence, can be applied to the field of medical health, and discloses a supervised fine tuning method, device and equipment based on a large model and a medium. The method comprises the steps that multi-modal training data composed of texts, images and audios are acquired and subjected to standardized preprocessing; constructing a domain knowledge graph containing entity nodes and relation paths; carrying out feature fusion on the multi-modal data by adopting an attention mechanism; logic constraint conditions are generated based on entity relations in the knowledge graph, and the logic constraint conditions and the fusion features are jointly input into the large model to jointly optimize parameters; and finally, dynamically adjusting model parameters through an adversarial training framework of the generator and the discriminator, and improving the understanding ability of the model to a complex logic relationship in combination with a reinforcement learning strategy. According to the method, the problems of lack of knowledge logic constraints in the target domain and poor multi-modal semantic collaboration are effectively solved, and the joint analysis capability of the model on cross-modal data and the reasoning accuracy of the model on complex tasks are remarkably improved.

Disclosed in the present application is a generative adversarial network (GAN)-based test data automatic generation method, which comprises the following steps: step 1, for a required test task, acquiring training data conforming to an actual test; step 2, preprocessing the training data, wherein, in order to ensure more balanced and comprehensive learning of a GAN during a training process, triplet partitioning is used to preprocess the training data; and step 3, designing and building a GAN model, wherein the GAN comprises a generator network and a discriminator network, the generator network being used for capturing and learning the distribution of the training data, and the discriminator network being used for determining the realness of sample data, namely determining the probability of the sample data being from real training data. The present application constructs the generator network in the form of encoder-decoder, and then constructs the discriminator network in the form of processing a binary classification task, the generator network and the discriminator network jointly forming the whole architecture of the GAN.

The invention relates to the technical field of computers, and provides a locomotive driver fatigue state detection method, which comprises the following steps of: S1, establishing a user image sample data set of a locomotive driver fatigue state and marking; s2, inputting a generative adversarial network model, and training a generator and a discriminator of the generative adversarial network model to perform data expansion; s3, after data expansion, inputting the data into a feature extraction model, a feature dimension reduction model and a classifier model for model training to obtain a trained user image sample model; and S4, based on the trained user image sample model, monitoring the fatigue level of the locomotive driver in real time, and giving out safety measures. According to the scheme, the training data set is effectively expanded based on the generative adversarial network, the training efficiency of the feature extraction model is remarkably improved, the convergence speed of the training process is accelerated, the model development period is shortened, the data reconstruction quality is improved through optimization of the feature dimension reduction model, and the classification precision is improved through improvement of the classifier.

The invention belongs to the technical field of software engineering, and particularly relates to a unit test method for generating a discrimination model based on retrieval. Searching a to-be-tested function, namely a test case pair, and establishing a code library; constructing an efficient code retriever based on code embedding and mixed feature extraction; constructing a multi-input matching discriminator network, preparing an own data set, and training the network; integrating the code library, the retriever and the discriminator into a local knowledge base, and performing fine adjustment on the large model based on the local knowledge base to obtain a retrieval generation discrimination model; and generating a test case based on the retrieval generation discrimination model, and testing. According to the method, the discrimination model is generated by using retrieval, corresponding change is automatically carried out according to the previous test case, and the test with higher coverage rate and quicker speed can be realized.

The invention discloses an automatic penetration method and system based on generative adversarial imitation learning in a cloud environment, and the method comprises the steps: storing an execution action-state pair when a reinforcement learning model successfully penetrates a target drone through an Exploit open source tool and a Metasploit open source penetration tool, so as to construct a penetration expert knowledge base; inputting the content in the expert knowledge base into a discriminator in the imitation learning framework for training; training actions output by the rear discriminator by using an imitation learning framework, wherein the actions can be used for automatically infiltrating a specified host; and deploying the whole automatic penetration framework to a cloud environment through containerization and arrangement to simulate external network attacks. According to the method, imitation learning is carried out in the cloud environment, resources can be efficiently utilized, container resource allocation can be automatically adjusted by enhancing the GAIL network and penetration test tool containerization, and therefore the overall performance is improved, and resource use and response time is optimized.

The invention relates to the technical field of deep learning, in particular to a parameterized nonlinear system identification method based on a dynamic embedded GAN. The method comprises the following steps: forming a dynamic condition generative adversarial network by adopting a deep learning method and combining a dynamical generator and a discriminator, fusing system physical parameters and response data, realizing extrapolation of nonlinear system dynamic response of a parameterized system under variable parameters, and remarkably enhancing generalization ability; meanwhile, according to the method, under the condition that initial conditions and system parameters are given, long-time-period prediction of parameterized nonlinear system dynamic response is achieved, the dependency relation of response data on system physical parameters is recognized from the response data, and recognition and prediction of any nonlinear dynamic system are achieved.

The invention discloses an improved hemodialysis data generation method and system based on a generative adversarial network, and relates to the technical field of medical data generation and artificial intelligence, and the method comprises the steps: 1, collecting hemodialysis multivariable time series data; 2, mapping the original time sequence data to a low-dimensional potential space through an embedded network; original data are reconstructed from the low-dimensional potential space through the recovery network; step 3, a multi-scale attention mechanism is introduced into the generator, weights are dynamically distributed by calculating the similarity of query vectors and key vectors, and weighted context vectors are generated in combination with value vectors; the discriminator executes a dichotomy task and introduces a dynamic gradient clipping strategy: if the norm of the gradient L2 exceeds a preset threshold value c, scaling the gradient according to a proportion, otherwise, keeping the original value; 4, introducing a supervision loss function, and learning a time sequence dynamic rule through an autoregressive prediction task constraint generator; and 5, jointly optimizing the reconstruction loss, the confrontation loss and the supervision loss, and outputting synthetic hemodialysis data.