370 results about "Hybrid data" patented technology

The invention discloses an intelligent fusion analysis system for multi-source heterogeneous data, and the system comprises a dynamic data collection module which is used for carrying out the data collection, and carrying out the processing of a collected mixed data flow; the semantic alignment module is used for constructing a domain ontology knowledge graph according to a preset scene target and carrying out semantic alignment and coordinate alignment on the collected data; the self-adaptive fusion engine module is used for fusing the collected multi-source heterogeneous data; the trusted computing module integrates a secure multi-party computing protocol and a homomorphic encryption algorithm to realize that data is available and invisible; and the intelligent decision-making module constructs a state action reward model based on reinforcement learning according to a preset scene target, and performs analysis and decision-making by using historical data and data acquired in real time. According to the invention, the capability and effect of data processing and decision support are improved.

The invention discloses a substation equipment rare defect simulation and identification method and system and a storage medium. The method comprises the following steps: constructing an equipment reference feature library; marking dynamic features of rare defects in historical inspection according to a spatial-temporal feature enhancement algorithm, generating a knowledge graph, and constructing a dynamic defect learning library; the method comprises the following steps: learning space association and environmental factor influence of defects and equipment through a bimodal generation network, and generating initial defect data matched with a weak area of the equipment; generating high-credibility defect fusion data through physical constraint-intelligent detection double screening; constructing a three-dimensional mixed data set, and screening high-quality training samples through a dynamic defect evolution algorithm and hierarchical cognitive evaluation; and constructing a multi-algorithm collaborative fine tuning network by using a federated learning framework, simulating and labeling defect information, and outputting a multi-dimensional identification prediction report. The method aims at solving the problems that the model is insufficient in rare defect recognition precision and lack of evolution prediction ability, and high-quality simulation of rare defect samples and high-precision recognition of the model are achieved.

The invention discloses a low-altitude unmanned aerial vehicle trajectory tracking and monitoring method based on a 5G-A communication sensing integrated base station, and relates to the technical field of low-altitude traffic management and communication sensing fusion, and the method comprises the steps: firstly collecting multi-source data such as a communication sensing fusion signal, environment interference and unmanned aerial vehicle attributes, and carrying out the alignment and packaging of a unified timestamp and a coordinate system into a synchronous data frame; then, deep fusion and anti-interference processing are carried out on the data frames, noise is filtered out, and pure fusion data is generated; and furthermore, real-time track calculation and motion trend prediction are carried out on pure data by utilizing multi-base-station cooperative calculation and prediction. Based on this, through a multi-target feature recognition and clustering separation mechanism, independent individual trajectories are accurately stripped from a complex mixed data stream, and compliance verification and anomaly judgment are performed on the trajectories in combination with an airspace rule base. In this way, the problems of signal interference and multi-target aliasing in a complex environment can be effectively solved, and therefore high-precision global tracking of the low-altitude unmanned aerial vehicle and real-time monitoring of abnormal behaviors are achieved.

The invention relates to the technical field of project intelligent management and control, and discloses a multi-agent power grid project intelligent monitoring, management and control and evaluation system and method, and the system comprises a mixed data resource library, a multi-agent system, an index calculation module and a process control module. The mixed data resource library stores structured business data and unstructured documents; the multi-agent system comprises an information extraction agent, an index design agent, a code generation and treatment agent and the like, works cooperatively, and converts a high-level natural language management and control rule into an executable code; the index calculation module is responsible for executing codes according to a scheduling strategy and calculating quantitative indexes; and the process control module automatically identifies risks and executes management and control operations such as process locking according to the index result and a preset threshold value. According to the invention, the complex business logic can be automated and coded, the accuracy and timeliness of risk identification are improved, and refined and prospective intelligent management and control of the power grid project are realized.

The invention discloses a mixed data encryption method and system based on multiple algorithm cores, and the method comprises the steps: receiving a mixed encryption request based on a first preset path, carrying out the encryption type analysis and data address analysis of the mixed encryption request, and determining a plurality of target encryption algorithm cores corresponding to an encryption type analysis result; sending a starting instruction to a plurality of target encryption algorithm cores based on a second preset path, and determining a multi-core encryption strategy corresponding to the hybrid encryption request; acquiring to-be-encrypted data based on a first preset path, a first preset data handling engine and the data address resolution result, and calling a plurality of target encryption algorithm cores to perform hybrid encryption processing on the to-be-encrypted data according to a multi-core encryption strategy to obtain a hybrid data encryption result, the delay of data encryption can be reduced, and the flexibility of a data encryption mode and the security of an encryption result can be improved.

A hybrid, redundant, fail-safe architecture provides a unified fail-operational framework for autonomous agents operating across physical and virtual domains. The system employs a multi-modal data source suite, an adaptive hybrid data fusion module, and an intelligent decision-making module. A novel closed-loop interaction enables a health monitoring module that detects an incipient fault in a data source by monitoring ancillary performance metrics. Upon detection, the module generates a fault signature, including a quantitative prognostic estimate of a future failure time, and transmits it to an adaptive data fusion module. The fusion module proactively reconfigures its state estimation algorithm by decreasing reliance on the degrading data source in proportion to the prognostic estimate. This preemptive compensation ensures the system maintains a high-integrity environmental model and achieves true fail-operational continuity. The architecture is applicable to numerous embodiments providing a universal solution for proactive fault management and system resilience.

The invention relates to the technical field of satellite communication networks and on-board buses, in particular to a data deterministic transmission scheduling method for a satellite-borne time-sensitive network. The method comprises the following steps: constructing a satellite-borne network architecture, connecting each terminal and a bus gateway by a TSN management node to form a unified data bus, distributing priority and monitoring link state; performing feature modeling on the data frames to define six-tuple parameters; designing a hierarchical queue architecture comprising a key task queue, a load data queue and a background traffic queue; a dynamic shaping mechanism is adopted, corresponding shaping devices are arranged for different queues, and parameters are set; the invention further provides an anti-disturbance scheduling strategy which comprises dynamic priority improvement and elastic bandwidth allocation. And finally, performing output scheduling according to a strict priority and a weighted fair queue rule. According to the method, by constructing a unified TSN bus and integrating heterogeneous subsystems, low-delay and low-jitter transmission of key task data is realized, the bandwidth utilization rate of scientific load data is improved, the network reconstruction time is shortened, the anti-interference capability is enhanced, and satellite-borne mixed data stream transmission in a high-dynamic and multi-task scene is effectively optimized.

The invention provides an abnormal sound detection method based on multi-scale time-frequency feature perception, and relates to the technical field of acoustic detection for industrial machine state monitoring, and the method comprises the steps: inputting an original sound signal, and carrying out the dual-branch feature extraction to generate a time domain coding spectrogram and a logarithmic Mel spectrogram; executing hybrid data enhancement; splicing the enhanced spectrogram and inputting the enhanced spectrogram into a dense encoder for compression modeling; extracting features through a two-stage multi-scale time-frequency sensing network, processing along a time dimension in the first stage, and processing along a frequency dimension in the second stage; inputting the high-order features into a lightweight classifier to output an abnormal score; and comparing the abnormal score with the gamma distribution threshold to judge abnormity. According to the method, the weak anomaly detection rate and the cross-equipment stability are remarkably improved, and the perception and discrimination capability of the model on the multi-scale time-frequency characteristics is effectively enhanced.

Embodiments of the present disclosure relate to synchronizing and managing data. A first event is received from a data source. The first event comprises an envelope comprising schema information associated with the first event. Schema drift is detected based at least in part on the schema information. A signal indicative of the schema drift is emitted to a mapping module. An activation ticket is received from the mapping module. The activation ticket corresponds to an updated mapping profile. The updated mapping profile is based at least in part on the signal. A second event is received from the data source. The second event is bound with the updated mapping profile.

The invention provides an automatic report generation method and system based on multi-source data integration and a medium, and relates to the technical field of data processing, cross-service-end redundancy check integration of a plurality of standardized data streams of a plurality of source service ends is received through a data integration cloud end, a uniform resource pool is output, and the report generation efficiency is improved. Dynamically extracting matched data in the uniform resource pool according to a real-time association label combination output by a user, and generating a temporary data set; and converting the temporary data set into a permission filtering report by taking the consulting permission of the user as a field filtering strategy. The technical problems that in the prior art, the mixed data storage precision is low, data redundancy is caused by lack of a conflict resolution mechanism, and then cross-system data calling response is delayed and the report error rate is high in subsequent practical application are solved. The technical effects of improving the data storage precision of multi-source heterogeneous data mixed storage, and improving the data calling speed and report output accuracy are achieved.

The invention relates to the technical field of intelligent manufacturing and reinforcement learning, and discloses a causal-driven intelligent manufacturing strategy optimization method and system, and a medium. Comprising the following steps: collecting state information of an intelligent agent and a production environment, and constructing an environment data set and a zero action data set; constructing a causal decoupling dynamic model comprising a causal intervention module and an environmental evolution module; mixing the environment data set and the zero action data set, and training a causal decoupling dynamic model by using a first mixed data set; performing intervention simulation on the environment data set by using the trained causal decoupling dynamic model to obtain a model data set; mixing the environment data set and the model data set, and training an unbiased strategy optimizer by using a second mixed data set; and deploying the trained unbiased strategy optimizer into a production system, and driving an intelligent agent to execute production operation according to the state information. Through causal-driven modeling and unbiased strategy optimization, high-precision and high-reliability decision control of the intelligent manufacturing system in a complex dynamic environment is realized.

This invention relates to the field of object detection technology, specifically to an improved YOLOv5 object detection method suitable for low-light environments. The method includes offline enhancement of the training set of a low-light dataset using an image enhancement algorithm to obtain an enhanced dataset; pairing and mixing the enhanced dataset with the original training set to obtain a mixed dataset; improving the baseline network to obtain an improved network model; training the improved network model using the mixed dataset to obtain an object detection network model; and inputting the image to be detected into the object detection network model for training to obtain the detection result. This invention, through a hybrid enhancement training method, enhances the low-light dataset using a GAN algorithm and then mixes it with the original training set, effectively suppressing the feature destruction problem caused by directly using enhancement algorithms, and solving the problem of low object detection accuracy in low-light environments in existing object detection methods.

The invention belongs to the related technical field of tool wear recognition, and discloses a low-quality image-oriented collaborative optimization tool wear recognition field generalization method, which comprises a mixed data enhancement strategy, an RSA embedded semantic segmentation network, geometric constraint loss, a field adversarial neural network and a multi-loss collaborative optimization strategy. The semantic segmentation network realizes effective suppression of a reflective region in a synthetic target domain low-quality image, geometric constraint loss improves coherence and marginal definition of wear region segmentation, and the domain adversarial neural network aligns feature distribution of a source domain high-quality image and the synthetic target domain low-quality image. And outputting an accurate wear region mask in the real target domain low-quality image through a multi-loss collaborative optimization strategy. According to the method, the robustness, the segmentation precision and the field generalization ability of tool wear identification are remarkably improved, the method is suitable for industrial automation quality control and predictive maintenance, and the technical problem of tool wear accurate identification under a low-quality image is solved.

The invention belongs to the technical field of partial discharge detection, and provides a switch cabinet partial discharge signal identification method and device. The method comprises the following steps: constructing a signal analysis model based on a multi-scale convolutional neural network, and carrying out data enhancement and expansion on a training data set of rare discharge type samples by adopting a mixed data enhancement strategy; constructing a complete network based on the signal analysis model and the partial discharge type identification model, and performing end-to-end training on the complete network by using the training data set after data enhancement and expansion; acquiring a traveling wave signal of the switch cabinet, and generating a corresponding traveling wave signal PRPD map; adopting the end-to-end trained signal analysis model to extract multi-scale features of the PRPD atlas in parallel, and fusing the multi-scale features to obtain fused features; and processing the fusion features by using the end-to-end trained partial discharge type identification model, and outputting a partial discharge type identification result. The method has higher recognition accuracy on rare discharge types.

The invention discloses a black-box watermark embedding method for a neural network text classification model, and the method comprises the steps: firstly constructing a watermark trigger set containing a semantic-level trigger and a character-level trigger at the same time, and then randomly mixing the constructed watermark trigger set with a common training sample to form a mixed data set; the classification model is trained based on the mixed data set, so that watermark information is encoded in the trained classification model, and the optimization target of training is to minimize an overall loss function; the method can effectively solve the problem that a trigger set sample destroys semantic discreteness and structure of a text, and meanwhile, due to the design of the double triggers, the intensity of a watermark signal is improved, it is ensured that when the trigger set is subjected to preprocessing operation such as text cleaning and the like and one type of triggers are missing, the text can still retain the other type of triggers, and the use experience of the user is improved. And through embedding at different levels, the robustness of the watermark for resisting attacks is obviously enhanced.

The application discloses a low-altitude unmanned aerial vehicle track tracking and monitoring method based on a 5G-A integrated base station, relates to the technical field of low-altitude traffic management and communication and perception fusion, and first collects multi-source data such as integrated perception and fusion signals, environmental interference and unmanned aerial vehicle attributes, and encapsulates the data into synchronous data frames through unified timestamp and coordinate system alignment. Then, the data frames are subjected to deep fusion and anti-interference processing, noise is filtered out, and pure fusion data is generated. Further, the pure data is subjected to real-time track solving and motion trend prediction by using multi-base-station cooperative solving and prediction. Based on this, independent individual tracks are accurately stripped from complex mixed data streams by using a multi-target feature recognition and clustering separation mechanism, and the tracks are subjected to compliance verification and abnormality determination in combination with a space domain rule library. In this way, the problems of signal interference and multi-target aliasing in a complex environment can be effectively overcome, so that high-precision global tracking of low-altitude unmanned aerial vehicles and real-time monitoring of abnormal behaviors are realized.

The invention discloses an overhead line foreign matter detection method and system based on a lightweight YOLO network, and relates to the technical field of power transmission lines. Multi-scene power transmission line images are collected through an unmanned aerial vehicle, a multi-scene power transmission line foreign matter data set is constructed, the images are amplified through a mixed data enhancement method, and a target image set is obtained; inputting the target image set into a preset target model to detect the foreign matter of the overhead line; if the foreign matter is detected, generating a foreign matter label; adding the foreign matter label into a preset 3D model diagram of the power transmission line; the foreign matter label comprises position coordinates and identification types of the foreign matters. The YOLOv5 model is improved to reduce the parameter quantity of the model, the performance improvement and real-time detection are realized, and the system can be carried on embedded equipment with limited storage space and calculation capability, such as a mobile terminal, so that the system can be deployed in an actual power transmission line inspection system to meet the actual application requirements.

The invention provides a building control collaborative optimization decision-making method fused with a lightweight AI inference engine. The method comprises the following steps: deploying an ultra-lightweight model on an edge side; collecting a mixed data set, and performing structured processing to obtain a standard time sequence matrix; feature extraction is carried out in a data dimension division mode, and a fused high-dimensional feature set is obtained; carrying out dimension reduction and activation, dimension raising reconstruction and feature fusion on the fused high-dimensional feature set to obtain an inference feature vector; and inputting the reasoning feature vector into the ultra-light model for intelligent reasoning to obtain a control suggestion, and completing a building collaborative optimization decision. According to the invention, the defects of insufficient intelligence, adjustment lag, poor adjustment precision and high cloud intelligent response delay of a traditional edge controller can be solved, and efficient, real-time and reliable building intelligent optimization control is realized.

The invention relates to the technical field of machine learning, and provides a trend prediction method and device based on intelligent question answering, equipment and a medium, and the method comprises the steps: collecting heterogeneous data of a plurality of data sources corresponding to a preset intelligent question answering platform through a hybrid data collector, and carrying out the weighted fusion of the heterogeneous data through a preset evaluation dimension, and obtaining the fusion data; constructing a semantic understanding model comprising a base layer, a logic layer and an interaction layer; constructing a dual-channel prediction architecture comprising a macroscopic channel and a microscopic channel, and completing the construction of a self-adaptive prediction model; and inputting the fusion data into the semantic understanding model to obtain a semantic analysis result, inputting the semantic analysis result into the adaptive prediction model, and outputting a trend prediction result. Through full-chain collaborative innovation of data, semantics and a prediction model, the technical bottleneck of function splitting of a traditional system is broken through, and an efficient, real-time and accurate intelligent solution is provided for complex scenes such as financial investment decision, medical health management and the like.

The application discloses a large-scale PDE neural operator pre-training method based on a high-frequency enhancement module, a partial differential equation (PDE) data set is composed into a mixed data set, a large-scale PDE neural operator is constructed, preprocessed PDE data is mapped to a latent representation space through a space-time encoder, a frequency decomposition module is used for frequency space mapping, the frequency decomposition module includes parallel high-frequency branches and low-frequency branches, and high-frequency features and low-frequency features are obtained respectively; a multi-frequency fusion module (GFM) adaptively fuses the high-frequency features and the low-frequency features through a gating mechanism; finally, a prediction head is used for processing the fused features, and final output features, i.e., predicted physical features of a next time step, are obtained. The application firstly introduces an explicit frequency division and a high-frequency enhancement mechanism, the input field is divided into low-frequency and high-frequency parts, the low-frequency branches / high-frequency branches are used for processing respectively, and thus the model can simultaneously consider global trend modeling and local gradient detail reconstruction.

The present invention relates to the field of time synchronization, and relates to a precise clock synchronization parameter tracking method based on an augmented Kalman neural network. In the method, for a multi-hop network scenario where an ambient temperature changes and a link transmission delay is asymmetric, taking into account the impact of an accumulated asymmetric link transmission delay in a multi-hop network on clock synchronization accuracy, a multi-hop network clock observation equation containing an accumulated asymmetric link delay is derived, and on the basis of a quadratic polynomial model of a temperature and a clock frequency offset, a recursive state equation of the clock frequency offset and a temperature change is established; the evolution processes of an accumulated asymmetric delay and an unknown temperature coefficient are modeled as a first-order linear difference equation, and the accumulated asymmetric delay and the unknown temperature coefficient are augmented to a clock parameter tracking state space model; and an augmented Kalman neural network algorithm is used to realize joint tracking of a clock phase offset and a clock frequency offset of a slave node. This method employs a hybrid data-model-driven approach to perform joint tracking of the clock phase offset and frequency offset, thereby improving accuracy and robustness of clock parameter tracking.

The invention provides a virtual power plant-power distribution network voltage dynamic cooperative control method and device, and the method comprises the steps: obtaining multi-source heterogeneous data to construct a mixed data set, and mapping the mixed data set to a quantum state space for feature extraction; fusing the quantum features, the satellite cloud picture and the voltage waveform data, and modeling by adopting quantum probability; generating a DERs output scene based on a quantum state superposition principle, searching and quantifying the voltage out-of-limit probability amplitude of each node, and generating a power distribution network risk thermodynamic diagram; constructing a hierarchical control decision; the hierarchical control decision is executed, then a causal logic chain of a voltage out-of-limit event is generated through an invariant graph reasoning network, the contribution degree of features to the control decision is quantified, and iterative optimization of model parameters is achieved in combination with a meta-learning mechanism. Based on the method, the invention further provides a voltage dynamic cooperative control device, self-adaptive response of distributed energy uncertainty is achieved, and a solution is provided for voltage stabilization of the power distribution network in a high-proportion new energy access scene.

The invention discloses a large model knowledge iterative enhancement method based on multi-dimensional reliability evaluation. According to the method, multi-dimensional reliability evaluation is carried out on a pre-enhancement model trained by a vertical field text data set. The test data samples are divided into correct answer samples, answer samples and illusion samples according to model responses. And counting the proportion of the number of various samples in the total number of test samples, and taking the proportion as the accuracy rate, the rejection rate and the illusion rate of the model. If the accuracy rate of the model is higher than a threshold value, taking the current model as a final knowledge enhancement model, if the accuracy rate is lower than the threshold value, constructing a mixed data set by a correct answer sample and an answer rejection sample, performing answer rejection capability enhancement fine adjustment on a pre-enhancement model, and then further using the answer rejection sample and an illusion sample to expand a knowledge boundary to obtain a knowledge enhancement model. And performing multi-dimensional reliability evaluation on the knowledge enhancement model until the accuracy of the current model is higher than a threshold value, and completing the iterative enhancement of the knowledge of the large model.

A distributed computing system and method for evaluating real estate agent performance through cryptographically secured, GPS-validated estimate submissions, scored by a machine learning-optimized algorithm with dynamically adjusted weightings. The Agent Competency and Credibility Score (ACCS) provides a transparent, technically verified trust metric combining price accuracy, geospatial expertise verification, property-type specialization, and statistical confidence calibration. The system implements a novel hybrid data architecture that maintains sensitive estimation data in secure encrypted databases while utilizing blockchain technology exclusively for transparent reward distribution, solving critical technical challenges in data security, computational efficiency, and incentive alignment.

The invention discloses a marine environment simulation and search and rescue formation method and system, and a computer program product, and belongs to the technical field of virtual reality technology and marine emergency rescue, and the method comprises the steps: designing a mixed data cleaning model of a space-time Kriging difference method and a long-short term memory network, and building a multi-modal dynamic environment database; establishing a marine meteorological data prediction model; combining the multi-modal dynamic environment database with the predicted marine meteorological data model to generate a dynamic marine environment; establishing a multi-agent training framework, and constructing a search and rescue formation strategy; and designing a hybrid planning model of a fast random tree algorithm and a long-short term memory network, realizing real-time path planning and path correction, and adjusting a search and rescue formation strategy according to the real-time path planning and path correction result. According to the invention, the problems of scene staticization and decision experience in traditional search and rescue training are solved, and the environment simulation precision, dynamics and decision accuracy are improved.

The invention discloses a safety reinforcement learning automatic driving decision-making method based on a behavior correction mechanism, and belongs to the technical field of automatic driving decision-making. Comprising the following steps: S1, collecting historical driving data to construct a mixed data set, and training a safety evaluation network according to the mixed data set; s2, calculating a safety score based on the trained safety evaluation network, and executing an action or triggering a correction mechanism according to the safety score and a dynamic safety threshold; s3, storing empirical data according to a security level by adopting a hierarchical empirical playback buffer area, and updating a strategy in combination with a constraint optimization and regularization method; s4, safety parameters are adjusted based on the real-time environment state, safety indexes are counted through a sliding window, and a basic safety threshold value is adjusted. By adopting the safety reinforcement learning automatic driving decision-making method based on the behavior correction mechanism, the safety violation frequency in the training process is reduced, the task completion efficiency is improved, and the method is suitable for automatic driving decision-making control in a complex traffic scene.

The invention discloses a control system and method based on a spiral screening and mixing device, and relates to the technical field of material mixing. The control system and method based on the spiral screening and mixing device comprises the following steps that S1, mixing full-process data and historical mixing data are preprocessed; s2, performing suppression type product fluctuation analysis, judging a mixed state, and linking layered dynamic adjustment, an abnormal region intervention process and a comprehensive compensation intervention process; s3, spatial distribution deviation analysis and deviation superposition are carried out, layered dynamic adjustment and an abnormal region intervention process are executed, and a comprehensive compensation intervention process is entered; s4, abnormal deviation aggregation and dynamic mapping analysis are carried out, a comprehensive compensation intervention process is executed based on a dynamic mapping analysis result, a stirring regulation and control instruction is converted, and stirring compensation measures are taken according to the regulation and control instruction. The problem that when an existing spiral screening and mixing device treats materials with different particle sizes, layering or segregation is prone to occurring in a mixture due to the mobility and the grading effect, and the component uniformity is affected is solved.

The invention discloses a vehicle-mounted Ethernet TSN network performance test system and method. The system comprises a plurality of vehicle-mounted Ethernet simulators, a passive TAP test tool, a flow generation module and a feature rule matching module. The plurality of vehicle-mounted Ethernet simulators are used for simulating a plurality of application vehicle-mounted terminals, the traffic generation module generates specific data streams and sends the specific data streams to the application vehicle-mounted terminals, and the specific data streams are forwarded to a target application vehicle-mounted terminal through a TSN network; the passive TAP test tool obtains a mixed data stream formed by the sent and received data streams; and the characteristic rule matching module is used for matching the specific data stream with the obtained mixed data stream to obtain time information of the specific data stream reaching the corresponding TAP test point location, and calculating to obtain a performance index of the TSN network by comparing the sending time of the specific data stream with the time of the specific data stream reaching the corresponding TAP test point location. According to the invention, the non-inductive test of the TSN network can be realized, and the network transmission performance of the TSN network can be accurately obtained.

The invention provides a DOA estimation confrontation and defense method based on Transform disturbance filtering, belongs to the technical field of array signal processing, and solves the problem that an existing DOA estimation mode is poor in robustness. The method comprises the following steps: preprocessing an array signal sample to obtain a standard signal sample; summarizing standard signal samples corresponding to the array signal samples and DOA angle labels, and constructing a data sample set; training and verifying the target model by using the data sample set; applying disturbance to the array signal sample to obtain an adversarial sample, and preprocessing to obtain a standard adversarial sample; combining the standard signal samples and the corresponding standard adversarial samples to construct a mixed data sample set; training a Transform network by using the mixed data sample set; the Transform network and the target model are connected in series, and a DOA estimation defense model is obtained; and performing DOA estimation on the real-time array signal by using the DOA estimation defense model.

The invention discloses a low-cost robot imitation learning method and system based on a human video. The method comprises the following steps: S1, data acquisition; s2, data extraction and physical alignment are carried out to eliminate man-machine physical differences; the step is divided into two parallel processing modules of action space alignment and visual space alignment; s3, data set construction: mixing the aligned human data with real robot teleoperation data, carrying out balanced sampling, and constructing a mixed data set Dmix; and S4, cooperative training: constructing a strategy network based on diffusion Transform for training. According to the method, data can be acquired only through the monocular RGB camera, expensive robot teleoperation data are replaced with cheap and easily available human videos, and the data acquisition threshold is greatly reduced. Through a visual alignment strategy of random color grid rendering, a network can learn neglect skin color textures and pay attention to geometric structures without a complex generative model, so that the robot can be seamlessly migrated to robots in different forms.