634 results about "Identification rate" patented technology

The invention discloses a dam measurement system and method based on multi-modal data processing, and relates to the technical field of dam measurement system data processing, a physical model is adopted to extract dam physical form change features in visual data, dam physical change associated sound features in audio data and micro-displacement features in radar point cloud data; according to the method, a three-dimensional monitoring network from macroscopic deformation to microcosmic displacement is constructed through cooperation of visual, audio and radar three-mode data, a monitoring blind area of a single sensor is broken through, and correlation analysis of dam body surface deformation and internal stress change is achieved. Feature fusion driven by physical constraints is carried out, finite element model constraints are embedded in a feature level fusion stage, radar point cloud displacement vectors need to conform to geological structure direction constraints, audio and voiceprint features need to be in space-time synchronization with visual crack expansion rates, and environmental noise interference is eliminated; the crack propagation early warning time is greatly shortened; the cavitation damage positioning is more accurate, and the abnormal working condition recognition rate is greatly improved.

The invention discloses a multi-source heterogeneous knowledge fusion question and answer solution system, which relates to the technical field of computers and comprises a knowledge base layer, a recall layer, an analysis and pruning layer and an answer generation layer. The knowledge base layer is used for constructing a dynamic heterogeneous entity fusion engine and a self-adaptive knowledge slice storage mechanism, and the dynamic heterogeneous entity fusion engine comprises a cross-modal entity alignment algorithm, relation topology completion and an incremental entity evolution model; the self-adaptive knowledge slice storage mechanism is used for performing semantic density perception slicing on the RAG document and constructing a three-level index tree; according to the method, through the technologies of cross-modal entity alignment, dynamic recall weight adjustment, context sensing entity priority correction, RAG cross-block reasoning enhancement, double-encoder conflict detection, knowledge graph guide generation and the like, knowledge fusion reasoning is achieved, the complex question answering accuracy is effectively improved, the conflict recognition rate is increased, and the manual maintenance cost is reduced.

The invention relates to the technical field of computer vision and deep learning, in particular to an aerial image target detection method based on frequency domain decoupling multi-scale feature fusion, which comprises the following steps of: acquiring an aerial image of an unmanned aerial vehicle, establishing a data set, and performing preprocessing and data division; an aerial image target detection network is constructed, and the aerial image target detection network receives an input image and outputs a target category and a bounding box position; loss functions are determined, wherein the loss functions comprise classification loss representing matching quality, coordinate loss representing prediction coordinate relevancy and bounding box regression loss representing bounding box positioning accuracy; training the aerial image target detection network based on the data set and the loss function; inputting a to-be-detected aerial image into the trained aerial image target detection network to obtain a to-be-detected target category and a bounding box position; the method can improve the feature fusion degree, retains high-frequency details, and enhances the small target recognition rate.

The invention belongs to the technical field of image processing, and discloses a frame image and event stream feature fusion-based target detection method, which comprises the following steps of: acquiring RGB (Red, Green, Blue) images and event stream data, and constructing a time-space synchronous multi-modal data pair; constructing a double-flow feature extraction backbone network to extract events and RGB features; based on a cross attention mechanism, multi-head attention is utilized to realize semantic alignment; the fusion weight is adaptively adjusted according to the statistical distribution; a multi-level fusion network is constructed, cross-scale fusion is performed by using an FPN pyramid, and target positioning and classification feature expression are cooperatively enhanced through a spatial semantic aggregation module. According to the target detection method based on frame image and event stream feature fusion, through a multi-modal data collaborative perception and self-adaptive feature optimization mechanism, the detection robustness in a complex scene is remarkably improved, the dynamic target omission ratio and the error recognition rate are effectively reduced, and the target detection efficiency is improved. And an all-weather high-precision environment perception capability is provided for an automatic driving system.

The invention discloses a cable tunnel fire risk feature identification system and identification method, and belongs to the technical field of cable tunnel safety monitoring. The whole stage of a fire is covered through multi-class cooperative detection, the target identification precision and scene adaptability are greatly improved, and the safety of the cable tunnel is improved. According to the whole system, a flame and smoke detection unit and a flame / smoke special detection unit are innovatively added to a detection engine module, an original heat source detection unit and an original human body detection unit are combined, a heat source-flame-smoke-human body four-category collaborative detection framework is formed, high-precision recognition is achieved on the basis of a YOLO model framework, and the detection efficiency is improved. Compared with the problems that a traditional system is high in single target detection omission ratio and cannot cover the whole stage of smoldering-initial open fire-violent combustion of a fire, the system has the advantages that the recognition rate of early flame and weak smoke is increased, the false alarm rate is greatly reduced, meanwhile, a heat source of operation and maintenance personnel is prevented from being misjudged as a fire hazard through human body detection, and the safety of the fire hazard is improved. And cable monitoring and personnel safety protection are both considered.

The invention provides a file uploading attack interception method based on semantic entropy enhancement, and aims at overcoming the defects of an existing file uploading security protection technology in the face of complex attacks. The method specifically comprises the steps that S1, file format analysis and content extraction are conducted, hidden scripts are mined through nested content recognition, and intermediate representation is generated through grammar cleaning and coding specifications; s2, constructing an abstract syntax tree and semantic entropy calculation, tracking a pollution chain, analyzing a high-risk function, identifying a high-entropy character string, modeling and controlling flow complexity, and generating a semantic entropy vector; s3, dynamic scoring and decision making are carried out, and accurate judgment is carried out in combination with white list perception, feature comparison, multi-modal model scoring, adaptive threshold and sandbox observation; and S4, carrying out real-time interception and feature synchronization, blocking malicious file landing, generating an attack log and synchronizing an attack fingerprint. The method takes the semantic entropy vector as a core, breaks through the limitation of static features, remarkably improves the recognition rate of complex attacks, reduces missed judgment, and guarantees the safety of Web applications.

The invention discloses an industrial surface defect image classification method based on hybrid query strategy active learning, and belongs to the technical field of computer image processing and machine learning. The invention aims to solve the technical problems of high cost, long period and low rare defect recognition rate caused by category imbalance due to dependence on large-scale manual labeling. The core of the method is to execute a hybrid query strategy in an iterative loop: firstly, screening out a candidate sample set of model cognitive ambiguity through uncertainty measurement of prediction entropy; secondly, in the candidate set, a core set and hierarchical thought diversity sampling method is adopted to select a final to-be-labeled sample with both characteristic representativeness and category balance. And the query batch is manually annotated and then is used for carrying out iterative updating and optimization on the model. According to the method, the recognition precision and generalization ability of the classification model on various defects can be remarkably improved with extremely low manual labeling cost, and the model development period is greatly shortened.

The invention discloses a PDF (Portable Document Format) drawing recognition and information structured extraction method. The method comprises the following steps: generating a high-resolution bitmap through image preprocessing; positioning and classifying a text region, a table region and a symbol region in the drawing based on a target detection model of transfer learning; hough transform is combined with SIFT feature matching to identify engineering symbols, and sub-pixel positioning is realized through an RANSAC algorithm; after the oblique text is corrected through affine transformation, the content is extracted through OCR; reconstructing a table structure based on OPTICS clustering and projection analysis; constructing an RDF knowledge graph according to a coordinate association rule; and using U-Net difference to detect and position an omission area and complementing the omission area. According to the method, deep learning and image processing technologies are fused, the problems of low rotating text recognition rate, table structure loss and semantic association deficiency in a traditional method are solved, through lightweight model compression and TensorRT acceleration, the analysis accuracy is remarkably superior to that of the traditional method, and the method can be widely applied to the fields of constructional engineering, petrochemical engineering and the like and has wide application prospects. And the drawing information processing efficiency and the data integrity are improved.

The invention relates to the technical field of block chain technology and asset transfer, in particular to a multi-risk interception and artificial intelligence error correction method in RWA asset cross-chain transfer, comprising the following steps: step 1, cross-chain transfer initialization and asset mapping verification; step 2, multi-level dynamic risk interception; step 3, an artificial intelligence error correction mechanism; step 4, asset right confirmation and log auditing after cross-chain completion; according to the method, technical risks (such as contract vulnerabilities), data risks (such as information inconsistency) and behavior risks (such as abnormal transactions) in RWA asset cross-chain transfer are covered through a multi-level interception system of "pre-transaction-in-process-contract layer" in combination with AI dynamic learning ability, the risk identification rate is greatly improved compared with a traditional method, and the risk identification efficiency is greatly improved. An artificial intelligence error correction mechanism is used for automatically classifying risk types and generating strategies, so that the average error correction time is shortened, and the error correction success rate is improved.

The invention discloses a radar communication radiation source identification method and system based on multi-modal feature alignment, and belongs to the technical field of electronic reconnaissance and signal processing. The method comprises the following steps: preprocessing a received radar signal to generate a standardized time-frequency graph; extracting a signal feature vector through a specially designed convolutional neural network encoder; extracting a text feature vector by using a Transform encoder; through joint optimization of cosine similarity loss and physical parameter constraint loss, alignment of signal-text features in a unified vector space is realized; and finally, zero sample identification of unknown radar signals is realized through vector similarity calculation. According to the method, the problems of low recognition rate and insufficient cross-modal information fusion in a low signal-to-noise ratio environment of a traditional method are effectively solved, and the recognition precision and the system robustness are remarkably improved.

The invention discloses a multi-scale convolution self-adaptive partial discharge fault type identification method based on characteristic parameters and moment characteristics, and relates to the field of discharge fault identification, and the method comprises the steps: obtaining a partial discharge phase three-dimensional statistical graph, and extracting a distribution relation to generate a statistical parameter graph; extracting statistical parameters based on the statistical parameter atlas, introducing preposed partial discharge occurrence judgment parameters to obtain statistical characteristic parameters, training a neural network, and constructing a statistical characteristic parameter model according to a training result; processing the statistical parameter atlas by using a multi-scale convolution technology to construct a moment characteristic model, and respectively deploying the statistical characteristic parameter model and the moment characteristic model to a partial discharge online monitoring and diagnosis platform; and obtaining a partial discharge fault type identification result based on the deployment result, analyzing the partial discharge fault type identification result by using an analytic hierarchy process, and evaluating the health state of the equipment. According to the method, the partial discharge fault type identification rate is improved, the anti-interference capability is improved, and the partial discharge type can be effectively and accurately identified.

The invention discloses a Web interface element recognition method, system and device and a medium, belongs to the technical field of artificial intelligence and Web interface development, and aims to solve the technical problem of how to improve the recognition rate of dynamic elements and CSS hidden elements so as to enable Web interface element positioning to be more accurate. Performing screenshot by using a playwright screenshot function, converting the screenshot into a Base64 coded character string by using a function after the screenshot is completed, inputting the character string and a url into an intelligent agent, calling a DeepSeek-VL2 visual model by the intelligent agent, analyzing the screenshot and outputting identified structured element data; dOM structure analysis: inputting a page url address, and generating DOM structure data by using a DOM analysis function; dOM tree analysis and visual element matching: calling an element matching function, performing visual element and DOM structure matching, and obtaining all successfully matched element data; interface element extraction and positioning generation; and element application.

The invention relates to the technical field of intelligent video monitoring, in particular to a park intelligent video monitoring system and method based on deep learning. The method comprises the following steps: collecting video monitoring deployment data of each camera in a park, and analyzing an overlapping area of a view field of a neighborhood camera pair on the ground and a shortest passable path length to obtain a park monitoring topological graph; performing space-time transition probability processing according to the park monitoring topological graph to construct a space-time trajectory prediction model; and capturing a monitoring target by using a camera, and carrying out intelligent video trajectory prediction by using the spatio-temporal trajectory prediction model to obtain a high-confidence monitoring trajectory. According to the method, high-precision target identity relay and automatic track correction are realized through a feature matching mechanism of a graph convolutional network and occlusion perception, so that the intelligent video monitoring recognition rate and track continuity in a complex environment are improved.

The invention relates to the technical field of environment monitoring and early warning, in particular to a forest fire monitoring and early warning system based on big data, which performs multi-period data superposition calculation in combination with a temperature change difference value, remarkably improves the recognition precision of a suspected point of a fire source, enhances the capture capability of dynamic change of forest environment temperature, and improves the accuracy of forest fire monitoring and early warning. According to the method, the identification rate of potential fire behavior is improved, difference analysis is performed by using a time period highly overlapped with humidity in a temperature trend curve, a high-risk section is accurately marked in combination with the temperature rise rate and the wind direction continuity, the judgment capability of a fire risk range is improved, and the judgment is matched with the change rate of a risk point through path overlapping number judgment. Quantitative control of trigger conditions is realized, so that a risk control decision has multiple response capabilities of spatial dimension, time dimension and dynamic evolution characteristics, and timeliness, spatial accuracy and risk response perspectiveness of forest fire prediction are improved.

The invention discloses a target tracking method and device based on a rolling and pitching type holder, and the method comprises the steps: building a polynomial response model through adaptive color calibration, and achieving the dynamic color correction; an improved YOLOv8 model is combined with a bidirectional feature pyramid network to carry out multi-scale target detection, and template matching is assisted to improve a low-confidence-coefficient scene recognition rate; predicting the position and the speed of the target by using Kalman filtering to cope with a shielding condition; and high-precision smooth rotation of the holder is realized through quaternion attitude solution in combination with PID (Proportion Integration Differentiation) and FOC (Fiber Operating Control) double-loop cooperative control. The device adopts a rolling and pitching type holder structure and comprises a main controller, an angle sensor, a visual sensor and a magnetic encoder, the mechanical structure is simplified, the weight is reduced, and higher response speed and higher control precision are achieved. The target tracking accuracy, stability and anti-interference capability of the intelligent mobile platform in a complex environment are remarkably improved, and the method is suitable for various dynamic scenes such as aerial photography and industrial inspection.

The invention relates to a ground penetrating radar parameter optimization and general survey method for highway subgrade condition detection. The method comprises four core modules: one is ground penetrating radar parameter optimization configuration, and automatic parameter correction during medium change is realized through static basic configuration and dynamic adaptive adjustment in combination with real-time sensing and PID (Proportion Integration Differentiation) control; the second method is rapid general survey execution, traffic flow, pavement vision and historical disease data are fused, a route is optimized through a Dijkstra algorithm, and abnormity is judged through multi-feature fusion; thirdly, imaging processing is optimized, multi-layer medium correction time delay imaging and complex disease classification imaging are provided, and the deep disease recognition rate is increased; and fourthly, maintenance decision linkage is realized, the disease level and priority are quantified, the maintenance scheme is automatically output, and the decision period is shortened. The method solves the problems of poor dynamic adaptation, difficulty in complex disease identification and disjunction in decision making in the prior art, has been verified in multiple sections, and is suitable for highway subgrade disease full-chain monitoring and maintenance.

The invention discloses a ground wire full life cycle management method, relates to the technical field of power equipment asset management, and aims to solve the problems that manual recording is easy to tamper, cloud diagnosis delay is high and an alarm mode is single and easy to neglect in traditional ground wire management. According to the method, operation fingerprints and spatio-temporal information during grounding wire hooking are recorded through the block chain technology, and it is ensured that data cannot be tampered; a built-in lightweight AI model of the edge computing unit is used for analyzing sensor data in real time to carry out localized fault diagnosis; and triggering a multi-mode sound-light alarm controlled by the PWM signal according to the diagnosis result grade. The system realizes full-life-cycle credible traceability, sub-second fault response and high-recognition-rate alarm of the state of the grounding wire, and is suitable for intelligent operation and maintenance of the grounding wire in the field of a transformer substation and the like.

The invention discloses an electroencephalogram signal recognition method based on a graph recurrent neural network, and the method specifically comprises the steps: carrying out the preprocessing of electroencephalogram signal data, and obtaining a data segment electroencephalogram signal; performing feature extraction and graph embedding processing on the data segment electroencephalogram signals, and dividing the data segment electroencephalogram signals into a training set and a test set; inputting the training set data into a diffusion convolution recurrent neural network for training; and inputting the test set data into the trained diffusion convolution recurrent neural network, if epilepsy detection is carried out, outputting a binary label and probability that whether the fragment contains the attack or not, and if epilepsy classification is carried out, outputting a label and probability distribution that the fragment belongs to four attack types. According to the method, the influence of the multi-channel space relation on prediction and classification of the electroencephalogram signal attack is deeply explored from three dimensions of time domain, frequency domain and space domain by taking the multi-channel space relation as an entry point, the problem of cross-domain feature deficiency in the prior art is effectively solved, the electroencephalogram signal attack mode can be more accurately recognized, and the recognition rate of the electroencephalogram signal is remarkably improved.

The invention relates to the technical field of payment security, and particularly discloses a security payment system and method based on biological recognition. The method is characterized by comprising the following steps: synchronously acquiring fingerprint, finger vein and pressure behavior characteristics through a coaxial integrated sensor; a dynamic encryption engine is adopted to bind the biological characteristics with the transaction parameters to generate a one-time payment token; living body verification is realized based on physiological synchronism of vein pulsation and pressure fluctuation; and establishing a user pressing behavior baseline model to identify abnormal operation. The terminal equipment is provided with a sapphire microlens array and a dynamic pressure-sensitive array. The problems of biological feature forgery, replay attack and living body cheating are solved, the forgery detection rate reaches 99.6%, and the false identification rate is smaller than or equal to 0.0001%.

According to the financial risk control risk assessment method based on the dynamic list library, the problems that a traditional method is poor in real-time performance, low in precision and insufficient in adaptability are solved through dynamic weight self-calibration list library construction, multi-model fusion of a self-adaptive scene, real-time assessment of dual-channel cross validation and a closed-loop self-adaptive response mechanism. The core innovation of the method lies in that a list library and model evaluation are deeply coupled, risk attenuation factors, dynamic weight adjustment and feedback closed loops are introduced, the fraud recognition rate is improved, the misjudgment rate is reduced, and the method can be widely applied to financial scenes such as banks and payment platforms.

The invention relates to the technical field of artificial intelligence and human resource informatization, in particular to an intelligent resume analysis method based on a large model, which comprises the following steps: constructing a multi-format analysis engine, constructing a hierarchical attention network by using the large model to extract resume feature information, generating text fingerprints by using an improved SimHash algorithm, and analyzing the text fingerprints. Establishing a multi-dimensional label knowledge base containing a three-level post classification system, and designing a three-dimensional talent cube data model; the method has the beneficial effects that the information extraction accuracy is remarkably improved compared with a traditional method; the semantic-level duplicate checking recognition rate is improved, and the false alarm rate is reduced; the post matching efficiency is improved through a dynamic label system; the quantitative evaluation model is used for providing an interpretable evaluation report; the data processing efficiency is obviously improved; and an enterprise exclusive talent map is established, and digital management of talent assets is realized.

The invention relates to the technical field of high-speed monitoring intelligent detection, in particular to a small target rapid enhancement detection method, device and equipment based on an image hot spot area and a medium. Intercepting an image slice through a hot spot region maintained by an asynchronous thread; forming an image array by the original image and the slice image, and inputting the image array into a target detection model supporting Batch reasoning for parallel detection; the slice detection result is mapped back to an original image coordinate system and then fused, and a final detection result is output; in the asynchronous thread, based on a detection result, screening a focused target, reversely calculating a candidate slice window and marking the candidate slice window to the difference graph; when conditions are met, the difference graph is constructed into an integral graph, the area with the highest heat degree is positioned as a new hot spot area, hot spot information is smoothly updated in combination with a sliding window mechanism, the optimal detection area can be accurately extracted, redundant calculation is reduced, the detection efficiency and the small target recognition rate are improved, and high-quality support is provided for follow-up tracking and analysis.

The invention discloses a multi-brand and multi-model automatic identification control method and system for an intelligent fixed-line telephone, and belongs to the technical field of plug and play of communication peripherals. The method comprises the following steps: after a USB plugging event is detected, extracting multi-dimensional features such as a manufacturer ID, a product ID, a USB serial number and a user-defined identifier of a fixed-line telephone in sequence to form a multi-dimensional feature vector with clear priority; then, through a multi-stage progressive matching strategy of first-stage (VI + PID accurate matching)-second-stage (self-defined identifier supplementary matching)-third-stage (serial number + descriptor fuzzy matching)-second-stage (self-defined identifier supplementary matching)-third-stage (serial number + descriptor fuzzy matching)-second-stage (self-defined identifier supplementary matching)-second-stage (self-defined identifier fuzzy matching)-second-stage (self-defined identifier fuzzy matching)-second-stage (self-defined identifier fuzzy matching)-second-stage And aiming at the scene of feature missing or VAD / PID conflict, a fault-tolerant mechanism is built in the system: when the scene is missing, the universal DLL is used for reverse query confirmation and identification, and when the scene is conflict, candidate DLLs are cyclically loaded according to a brand market share sequence until the communication verification succeeds. The method is high in accuracy, multi-stage progressive matching and confidence evaluation are combined, and the error recognition rate is lower than 0.1%; zero sample online: the new type number can be connected for the first time to complete the adaptation in the second level, and manual maintenance is not needed.

The invention discloses a method and system for processing unstructured monitoring information of an electric power centralized control system, and belongs to the technical field of electric power system automation, the method for processing the unstructured monitoring information of the electric power centralized control system comprises the following steps: inputting the unstructured monitoring information into a BERT embedding layer and an electric power professional vocabulary embedding module, generating two semantic vectors and splicing and outputting a label result of the entity; standardizing a device name in the monitoring information into a standard name in a centralized control system file; associating equipment in the structured monitoring information with equipment in a centralized control system file; and establishing association between the structured monitoring information and the feature tag of the event rule base by adopting a direct matching mode and an indirect matching mode, and analyzing a formula of the event rule base. The monitoring information of the centralized control system is processed through the artificial intelligence technology, the autonomous recognition rate of the event monitoring information can be remarkably improved, the entity extraction accuracy rate can reach 95% or above, and the event matching accuracy rate can reach 90% or above.

The invention discloses an access control authentication method based on multi-modal dynamic challenge and block chain auditing, and belongs to the technical field of access control authentication, and the access control authentication method comprises the following steps: collecting video, sound and motion data of a user, and carrying out dynamic living body detection; after detection is passed, face features, voiceprint features and gait features are extracted and subjected to fusion scoring, and after the score exceeds a threshold value, equipment trust chain verification is carried out according to a dynamic token generated after secret key exchange between the APP and the access control terminal; after the verification is passed, firstly performing deep counterfeiting detection on the whole face, and then performing deep counterfeiting detection on the details of the face; and finally, the authentication passing information is stored in the block chain, TxID verification is carried out when a receipt of certificate storage transaction success returned by the block chain is received, and the door is authorized to be opened after the verification is successful. According to the invention, forgery attacks can be effectively resisted, the false identification rate and the missed identification rate of the access control system are reduced, the auditing tracking and tamper-proof capabilities are greatly enhanced, and the identity authentication reliability in a high-security scene is guaranteed.

The invention relates to the technical field of network security, in particular to a network security situation awareness method based on artificial intelligence, which comprises the following steps: deploying probes on a plurality of key link nodes of a network, and acquiring a specific type of network basic maintenance message flowing through the node; based on the obtained message, microcosmic time sequence characteristics of the message are extracted, and a first time sequence signal is formed; comparing the first time sequence signal with a pre-stored node reference time sequence signal, executing collaborative deviation calculation, and generating a collaborative deviation coefficient; and based on the collaborative deviation coefficient, determining a local vibration intensity value of the node, converging local vibration intensity values of a plurality of nodes in the network, and executing spatial correlation fusion calculation. According to the method, anomaly detection is realized by analyzing the time sequence coordination rule of the network basic maintenance message, any abnormal condition damaging a normal coordination mode can be captured, and the recognition rate of unknown threats is improved.

The invention provides an unmanned aerial vehicle tracking system and method based on state space modeling and scale searching, and belongs to the technical field of artificial intelligence. The invention aims to solve the problems of low recognition rate and high false alarm rate when a traditional unmanned aerial vehicle tracking method is used for processing low-altitude complex backgrounds, illumination changes and multi-shielding scenes. The tracking system comprises a target detection module, a target tracking module and a dual-threshold closed-loop control module. The tracking method comprises the following steps: performing feature extraction and candidate target identification on an input video stream or image sequence through a target detection module, and outputting a detection result in the form of a coordinate frame and confidence; the target tracking module performs continuous frame association and real-time position updating on candidate unmanned aerial vehicle targets through a multi-scale twin convolutional network; and the double-threshold closed-loop control module receives an output result, automatically judges a current task state according to a detection confidence threshold and a tracking frame number threshold, and intelligently switches a tracking mode and a detection mode.

The invention discloses an end-to-end radar working mode identification method based on hierarchical density clustering and an encoder, and the method comprises the steps: firstly obtaining the pulse repetition interval PRI, PW pulse width and carrier frequency RF data of a radar pulse, and constructing a radar pulse sequence; and meanwhile, recording an initial working mode label corresponding to each pulse. Secondly, inputting a radar pulse sequence for preprocessing to obtain a preprocessed radar pulse sequence; and finally, performing working mode identification on the preprocessed radar pulse sequence through an encoder structure neural network model, and outputting a working mode corresponding to the radar. According to the method, the input sequence quality is remarkably improved, data interference is reduced, and the recognition rate of a complex radar working mode is improved.

The invention discloses a complex number network SAR (Synthetic Aperture Radar) identification method based on an improved rednet network, which relates to the technical field of SAR image processing and identification, and comprises the following steps: step 1, constructing a training set and a test set of complex number SAR images; 2, extracting multi-dimensional statistical characteristics and performing principal component analysis; step 3, constructing a CV-SE attention module, including amplitude operation, compression operation, activation operation and indexing; 4, constructing a fusion feature complex number recognition network, wherein the fusion feature complex number recognition network comprises two branches and a fusion module; 5, training the fusion feature complex number recognition network; step 6, testing the fusion feature complex number recognition network; the complex network SAR recognition method based on the improved rednet network solves the problems that in the prior art, it is difficult to directly extend a real value activation function to a complex domain, and the recognition rate is not high.