233 results about "Discriminator" patented technology

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 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 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 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 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.

The invention discloses a double-channel confrontation and progressive self-training driven cross-working-condition open set domain adaptive fault diagnosis method. In order to suppress an interactive negative migration effect, a three-stage two-way adversarial progressive self-training network DAPN is designed, separation of unknown target samples and feature aggregation of known samples are realized through cooperation of a gradient inversion layer and a two-way adversarial discriminator, and inter-class discrimination and intra-class aggregation are obviously enhanced. When the performance of the DAPN is evaluated in two open set domain adaptive scenes, for open set proportions of different intensity domain offsets and changes, the method always keeps high classification accuracy and unknown class detection rate, and the performance is obviously superior to that of a comparison baseline. According to the method, two-way confrontation and a progressive self-training mechanism are combined, so that accurate classification of known faults and effective identification of unknown faults are realized.

The invention relates to a mechanical arm control method and device, computer equipment and a readable storage medium. The method comprises the steps of generating a plurality of candidate trajectories for a target task through a target diffusion strategy model; the target diffusion strategy model is obtained by training an original diffusion strategy model based on collected example data; evaluating and screening the plurality of candidate trajectories according to a single-step value discriminator to obtain an optimal trajectory in the plurality of candidate trajectories; the single-step value discriminator is a multi-modal feature regression model constructed based on a target diffusion strategy model; and the target mechanical arm is controlled to execute the target task according to the optimal track. By the adoption of the control method and device, the control accuracy and safety of the mechanical arm can be improved.

Approaches presented herein provide for the use of reinforcement learning to fine-tune a generative model, such as a motion diffusion model, for a specific objective, such as to generate representations of human motion corresponding to provided text input. A discriminator can be used to guide the training of the generative model. In at least one embodiment, the discriminator can compare the input text and generated motion representation (or embeddings of each) to determine an alignment value or match score, for example, which can then be used to adjust the network parameters or weights of the generative model to improve the alignment between input text and generated motion.

Provided in the present application are an active learning and augmentation method for a complex skill in a heterogeneous scenario and a sim-to-real transfer method. The active learning and augmentation method comprises: first, collecting state data by means of the interaction of multiple executors and an environment; storing same in a shared experience replay buffer; after sampling, alternately training the executors and discriminators; and finally selecting the optimal executor to be deployed, so as to implement active learning and augmentation of a complex skill. The sim-to-real transfer method comprises: in a 3C assembly digital twin environment, collecting multi-modal data to construct a skill knowledge base; generating a policy sequence; using technologies such as residual reinforcement learning to perform optimization; and, by means of a coding and decoding model, transferring a skill policy from simulation to reality. Without a teacher model or teaching data, the solution provided in the present application improves skill learning efficiency by means of combining reinforcement learning and knowledge distillation techniques, and implements the sim-to-real transfer of operating skills from a simulation environment to a real assembly environment.

The invention provides an overseas study application intelligent recommendation method and system based on artificial intelligence, and relates to the technical field of overseas study application intelligent recommendation, and the method comprises the steps: obtaining the basic information of an applicant to construct a feature matrix, extracting college admission features through a variational encoder-decoder and an adversarial discriminator; and constructing a dynamic heterogeneous graph structure to execute graph convolution operation to update the matching probability, and analyzing a group decision based on an information cascade effect to obtain an optimal application combination sequence. According to the method, personalized accurate recommendation can be realized, the study abroad application success rate is improved, and the application decision complexity is reduced.

The invention relates to the field of vulnerability detection, and particularly discloses an Internet of Things terminal vulnerability detection method based on artificial intelligence, which takes an auto-encoder as a generator and combines the auto-encoder with a discriminator to form a generative adversarial network framework. Through adversarial training, the model is forced to carry out deep learning and accurately master the internal distribution rule and essential characteristics of normal network traffic. Therefore, in the detection stage, when the abnormal traffic containing the vulnerability utilization behavior is input, the mode of the abnormal traffic deviates from the learned normal normal form, and the trained generator cannot effectively reconstruct the traffic, so that a remarkable reconstruction error is generated; meanwhile, the discriminator can also sensitively identify the difference between the mode and the normal mode. Finally, by comprehensively considering the reconstruction performance of the generator and the discrimination result of the discriminator, sensitive and accurate detection of unknown vulnerabilities can be realized without depending on any attack priori knowledge, and the limitation of the prior art is effectively solved.

The invention relates to a world model simulation system training method and system based on real record constraint and condition deduction, computer equipment and a medium, and the method comprises the steps: extracting a time-space anchor point of a long-tail event from real road test data, and marking behavior fingerprints for traffic participants in the time-space anchor point, so as to generate a time-space anchor point tensor; constructing a world model simulation system, wherein the model comprises a constraint module, a deduction engine and a discriminator; the constraint module is used for coding the traffic participant state and the space-time relationship in the space-time anchor tensor into a causal constraint embedding sequence; the deduction engine is used for deducing to obtain a predicted scene state according to the causal constraint embedding sequence and the vehicle control action sequence; the discriminator is used for generating a rationality score for the predicted scene state; and performing full constraint training, mixed constraint training and free deduction verification training on the world model simulation system in sequence. According to the method, closed-loop deduction training of the automatic driving strategy under real data distribution can be realized, and the problems of distribution offset and causal fracture in long-tail scene simulation are solved.

A computer-implemented method for generating synthetic data is provided. The method includes receiving user input specifying domain-specific requirements for synthetic data generation and selecting a scenario type. The scenario type is one of Seedless, Seeded, or combination of Seeded and Knowledge Base (KB). The method defines a structured schema based on the user input. The structured schema includes data fields, relationships between data fields, and distributional targets. Based on the structured schema, the method generates an initial set of synthetic data samples using a neural template-driven generation model trained on domain-specific data. The method applies adversarial contrastive sampling. This involves training a discriminator neural network to distinguish between the initial set of synthetic samples and real data samples. The discriminator neural network is used to identify generated samples similar to real data. A contrastive set of samples dissimilar to those identified as similar by the discriminator is generated. The method integrates the initial set of synthetic data samples with the contrastive set to create the synthetic data.

This disclosure presents a technique for enhancing the performance of models such as large multimodal models (LMMs) without retraining or fine-tuning. This technique includes an iterative refinement process implemented by three main components: a forward generator, a backward generator, and a discriminator. The forward generator translates a prompt into an output in a different modality, the backward generator translates this output back into the original modality, and the discriminator compares the prompt and the translated prompt to generate a hint for refining the prompt to reduce differences. This cycle continues until the original prompt and the translated prompt match, achieving cycle consistency. The solution offers several advantages, including improving model performance without the need for costly fine-tuning, training data, or expertise. It simplifies system complexity by not relying on external environments like compilers and APIs and uses cycle consistency as a supervisory signal to iteratively refine a prompt.

The invention relates to the technical field of data privacy protection and artificial intelligence crossing, in particular to a differential privacy and contrast learning fused data synthesis method, which comprises the following steps: S1, data acquisition and clustering: acquiring a real training data set, and clustering the data set by using a DBSCAN algorithm; s2, establishing double discriminators: designing a double discriminator framework comprising a privacy discriminator and a utility discriminator, injecting adaptive differential privacy noise based on a clustering structure into gradient updating by the privacy discriminator to realize privacy protection, and focusing on keeping the quality and authenticity of generated data by the utility discriminator. Precise balance between privacy protection and data utility is realized through a double-discriminator architecture. The privacy discriminator focuses on differential privacy constraints to ensure that the generated data meet strict privacy requirements; the utility discriminator restrains the data distribution consistency through the Wasserstein distance, effectively reduces the damage of the noise to the data utility, and solves the problem that the privacy and the utility are difficult to consider in the prior art.

The invention discloses an LGR-GAN-based power system instability scene generation method, system and device and a medium, and belongs to the technical field of artificial intelligence in power systems, and the method comprises the steps: obtaining time sequence data of a power system, and carrying out the data preprocessing; constructing a generative adversarial network, carrying out adversarial training on the generative adversarial network by utilizing the preprocessed time sequence data, and stabilizing a training process by adopting a loss function containing a gradient penalty term in training; and generating new power system time sequence data by using the trained generative adversarial network. According to the method, the defects of training stability, feature capture comprehensiveness and physical compliance in the prior art are overcome. According to the invention, a long-short-term memory network and a gating circulation unit are embedded by constructing a framework in which the generator and the discriminator cooperate with each other, so that full-scale accurate description of long-range evolution trend and short-term mutation details in the power transient process is realized.

The invention discloses a control method and device of a computing power demand prediction system and a storage medium, and relates to the technical field of system resource management, and the method comprises the steps: splicing input condition features and random Gaussian noise, and carrying out the fusion of the condition features and random Gaussian noise, and obtaining a high-dimensional hidden space representation; performing sequence decoding on the high-dimensional hidden space representation, arranging according to a decoding sequence, and determining a resource demand prediction sequence in a future time period; based on the resource demand prediction sequence and a real load sequence, calculating weighted loss according to a preset quantile, and outputting a composite prediction error value; extracting long-range features of the resource demand prediction sequence and the real load sequence, and obtaining a scalar score through feature scaling processing; and performing weighted fusion on the composite prediction error value and the scalar score to construct a joint optimization target so as to alternately update a generator and a discriminator and iteratively generate a prediction generator model. The problem of low resource utilization rate is solved, and the server utilization rate is improved.

The invention discloses a robot generative adversarial self-imitation learning method based on large language model feedback, and belongs to the technical field of computer systems based on specific calculation models, and the method comprises the steps: (1) initializing a strategy network, a discriminator network and a demonstration pool; (2) constructing and training a large language model feedback network: obtaining a training sample of the large language model feedback network, and training the large language model feedback network according to the training sample; and (3) an iterative learning step (33): updating the strategy network according to the reward calculated by the new cost function. According to the robot generative adversarial self-imitation learning method based on large language model feedback, the advantages of the large language model in the aspects of semantic comprehension, reasoning and knowledge organization are used as a potential award priori source, and a stable award signal can be provided when the demonstration data quality is poor, so that a strategy exceeding original demonstration is learned.

The present invention discloses a method and computer automated system for translation using generative artificial intelligence, wherein the method leverages neural networks, discriminator networks, iterative processing, and feedback mechanisms to generate and optimize translations. By evaluating translation quality and continuously adjusting based on feedback, the system maximizes accuracy and context-specific appropriateness. The neural networks are equipped with advanced features like attention mechanisms and encoder-decoder architectures to capture semantic and syntactic nuances during translation. Furthermore, the approach can personalize translation output, validate translations against reference corpora, adapt to specific industries, and undergo iterative improvements, ultimately enhancing linguistic quality and readability.

The invention discloses a multi-modal data processing method and system, computer equipment and a readable storage medium, and the method comprises the steps: carrying out the data processing of an edge-end model and a cloud model, enabling the data processing results of the edge-end model and the cloud model to approach through a semantic and feature weighted total loss function, and carrying out the optimization of the edge-end model; performing adversarial training by taking the optimized edge-end model as a generator and the cloud model as a discriminator, and further improving the edge-end model; when the improved edge-end model is superior to the cloud model, the edge-end model and the cloud model exchange roles, and the edge-end model guides parameter updating of the cloud model; and carrying out data processing on the obtained multi-modal data according to the improved edge end model. Multi-level distillation and adversarial distillation break through traditional distillation bottlenecks from longitudinal knowledge deep extraction and transverse model dynamic optimization, so that the cross-modal feature fusion precision of multi-modal power grid data is guaranteed, and the overall performance of the system is continuously improved through competitive collaborative learning of an edge cloud model.

The invention discloses a multidimensional data anomaly detection method and device, a medium and a program product. The method can be applied to the technical field of big data, and comprises the following steps: obtaining a static feature vector and a dynamic behavior feature matrix according to input multi-dimensional data; according to the static feature vector and the dynamic behavior feature matrix, obtaining a first score and a second score output by the dual discriminator, and obtaining a dynamic weight of the dual discriminator under the target time step; wherein the dual discriminator comprises a static feature discriminator and a time sequence behavior discriminator; and obtaining an anomaly detection result of the multi-dimensional data according to the first score, the second score and the dynamic weight. By adopting the above technical scheme, anomaly detection can be carried out from two dimensions of static characteristics and dynamic behavior characteristics, the accuracy of anomaly detection is improved through a multi-dimension cooperative detection mode, the defect of limited single-dimension discrimination capability is overcome, and the recognition precision and robustness of a complex mode are improved.

The invention relates to a backdoor attack method and device, electronic equipment, a storage medium and a computer program product. The method comprises the steps of obtaining a text set; inputting the text set into a backdoor discriminator; under the condition that the backdoor judgment result indicates that the corresponding text is a clean text, clean semantic features of the text are extracted; otherwise, extracting a pollution semantic feature of the text, and performing weighted summation on the pollution semantic feature and a preset target category feature; and inputting the clean semantic features, the fused semantic features and the image samples into a multi-modal retrieval system to perform cross-modal retrieval. Therefore, the polluted text, namely the backdoor text, is obtained by performing style migration on the original text, so that the phenomenon that the text fluency and semantic coherence are damaged due to insertion of obvious trigger vocabularies can be avoided, the risk found by a defensive mechanism and manual inspection can be effectively reduced, and the user experience is improved. Therefore, the concealment and naturalness of the backdoor attack can be improved.

The invention discloses a flexible job shop scheduling method based on a generative adversarial training framework. The method comprises the following steps: establishing a Markov decision process model for flexible job shop scheduling, and completing the design of a state space, an action space and a reward function; collecting expert scheduling tracks through a plurality of algorithms, and carrying out data cleaning and standardization processing; constructing a state encoder based on a graph attention network, mapping a scheduling environment state into low-dimensional vector representation, and designing a hierarchical strategy network to decompose a scheduling decision task; constructing a value network to provide stable value estimation so as to accelerate a reinforcement learning process, and constructing a discriminator network to guide a strategy search direction by generating an imitation reward; and finally, hybrid training based on near-end strategy optimization and generative adversarial imitation learning is executed, and through adversarial training and strategy gradient optimization, an intelligent agent learns to obtain a high-performance scheduling strategy with expert empirical performance and environment adaptability.

The application discloses an inertial data position conversion method and system based on a noise codebook and multiple physical discriminators, and the method comprises the following steps: acquiring a target position of a target device and first inertial data; performing multi-dimensional data enhancement processing on the first inertial data to obtain second inertial data; constructing a position-adaptive first noise codebook according to the second inertial data; performing extraction operation on the second inertial data through a decoupling generator to obtain motion semantic features and position noise features; obtaining a target noise code word according to the first noise codebook and the position noise features; and obtaining target inertial data of the target position through a gated fusion mechanism according to the target noise code word, the motion semantic features and the position noise features. The application can improve the robustness of inertial data and can be widely applied to the technical field of inertial data processing.

The present application provides a method for bearing fault diagnosis across working conditions by using a minimum entropy optimized prototype contrast network, and relates to the technical field of intelligent fault diagnosis. In the pre-training stage, an auxiliary domain discriminator is constructed to assist DA with the discriminant information of the classifier, the classification difficulty is evaluated by sample entropy, and the performance degradation in the DA process is inhibited. In the training stage, the learning vector quantization method is adopted to find the prototype. Through intra-domain prototype contrast learning, the sample features are closely gathered around the same prototype in the feature space, while being separated from the different prototypes. Then, the intra-class consistency of the features is enhanced, and the inter-class distinguishability is improved, so as to realize the precise alignment in the feature space. In addition, the cross-domain instance-prototype learning aligns the semantic structure in the shared embedding space, alleviates the negative transfer problem through the fine-grained alignment strategy, and improves the generalization ability of the model. Through the pseudo-label generation and the weighted loss function, the generalization performance of the model in the cross-working-condition small sample scene is improved.

The approaches presented here provide the use of reinforcement learning to fine-tune a generative model, such as a motion diffusion model, for a specific goal: to generate representations of human motion that correspond to the provided text input. A discriminator can be used to guide the training of the generative model. In at least one embodiment, the discriminator can compare the input text and the generated motion representation (or embeddings of both) to determine, for example, an alignment value or match score, which can then be used to adjust the network parameters or weights of the generative model to improve the alignment between the input text and the generated motion.

The invention discloses a catalytic cracking regeneration process parameter optimization method based on two-way adversarial training of a GAN framework, and the method comprises the steps: constructing a data-driven prediction model and a mechanism-driven prediction model, executing the two-way adversarial training under a generative adversarial network framework, enabling the two models to take the roles of a generator and a discriminator in turn, and achieving the mutual game and collaborative optimization, the data driving model learns to generate parameters conforming to physical laws through physical constraint verification of the mechanism model, the mechanism driving model is fused into actual production optimal practice through historical experience verification of the data model, and a fusion optimization model is generated and applied to process parameter control of the regenerator of the catalytic cracking device. Efficient recovery of catalyst activity and effective reduction of regeneration energy consumption are achieved, and the technical problems that a traditional method depends on artificial experience, optimization precision is not high, a data model lacks physical constraints, and a mechanism model is difficult to adapt to complex working conditions are solved.

The present application relates to the technical field of aviation safety and artificial intelligence, in particular to an ADS-B time series data adversarial sample generation method based on improved WGAN-GP, comprising the following steps: obtaining ADS-B historical flight data, extracting the longitude, latitude, height, speed and heading five-dimensional features to construct a time series data set; building an adversarial sample generation model based on an improved Wasserstein distance generative adversarial network, and configuring a multi-objective composite loss function for the generator; the present application builds a generator and a discriminator based on LSTM, designs a composite loss function that integrates adversarial loss, concealment loss and time series smoothness loss, adopts gradient penalty and asymmetric update strategy to train the model, and the generated adversarial sample has high concealment and physical consistency, can effectively avoid various unsupervised anomaly detection models, the model training is stable, and technical support is provided for building a safer air traffic control defense mechanism.