533 results about "Global information" patented technology

The invention belongs to the technical field of natural language processing and multi-modal information extraction, and particularly relates to a multi-modal named entity recognition method based on semantic alignment and cross-modal graph fusion, which comprises the following steps: S1, acquiring a data sample containing a text sequence and image content; s2, encoding the text and the image into vectors respectively; s3, similarity is calculated through a trainable bilinear function, and optimization is carried out through loss comparison; s4, cross-modal attention is used to enhance association information between modals; s5, determining the proportion of reserved image information through a modal matching module; s6, introducing a gating mechanism to dynamically fuse visual and text features; s7, realizing local and global information complementation by a cross-modal graph fusion model; and S8, inputting the fused representation into the CRF layer to predict the entity type. According to the method, fine semantic alignment can be realized in a weak image-text correlation context, and balance between local entity recognition and global semantic understanding can be achieved.

The invention provides a real-time command and control strategy optimization method and device based on multi-agent reinforcement learning, equipment and a storage medium, and the method comprises the steps: deploying a pre-trained cooperative intention network on edge equipment of each combat unit, and coding local observation data and a historical sequence thereof into a low-dimensional local cooperative intention vector; replacing original high-dimensional data as inter-unit communication content; whether broadcasting is carried out or not is dynamically determined according to observation uncertainty and a channel state by combining a self-adaptive intention broadcasting mechanism, and communication resources are distributed according to needs; after each unit receives an adjacent collaborative intention vector, a lightweight space-time attention module in a pre-trained local strategy execution network carries out space weighting on adjacent intentions and fuses time features of own historical intentions, and a collaborative and consistent real-time command and control instruction is generated under the condition that global information convergence is not needed.

The invention discloses a spine image key point detection algorithm based on multi-task learning. The algorithm comprises the following steps: constructing a multi-task deep learning network model comprising a segmentation branch and a key point positioning branch; a feature aggregation module based on multi-scale cavity convolution is embedded in the segmented branches, and the multi-scale cone feature extraction capability of the model is enhanced through splicing fusion of multiple cavity rate convolution branches and global pooling branches; a cross-task attention fusion module is introduced between the two branches, and bidirectional dynamic interaction and complementation between segmentation features and key point features are realized by generating and fusing first-order and second-order context attention maps; semantic alignment loss is designed in a training stage, collaborative optimization of two tasks is promoted by constraining the consistency of segmentation masks and key point heat maps in a high-level feature space, global information of segmentation and local information of key point detection are fully utilized, and the accuracy and stability of spine centrum key point positioning and the accuracy of a segmentation result are improved.

The invention discloses a formation riding danger information sharing method and system for intelligent riding helmets, and relates to the technical field of information sharing, and the method comprises the steps: carrying out the deep fusion of the adjacent beacons of all intelligent helmets, the state information of a vehicle, and the multi-source heterogeneous data of an external sensor, vehicle-road cooperation and the like; and constructing and dynamically maintaining a topological graph reflecting the space-time relationship among the formation members in real time. On the basis, intelligent source end propagation strategy decision is carried out on perceived semantic danger information, and topology-based directional relay and propagation are carried out. And finally, the decided propagable information is combined with the state of the rider, so that a highly personalized early warning instruction is generated. In this way, undifferentiated global information broadcast can be effectively converted into accurate risk announcement based on individual context, and the efficiency of dangerous information sharing in formation riding and the cooperative safety capability of the whole system are remarkably improved.

The invention discloses a multi-unmanned aerial vehicle cooperative inspection trajectory control method for optimizing medical area coverage and service efficiency. The method comprises the following steps: firstly, constructing a medical multi-unmanned aerial vehicle auxiliary inspection mobile edge computing system model, defining an unmanned aerial vehicle and mobile user set, and establishing a communication model containing A2G and A2A links, an unmanned aerial vehicle mobile model and an energy consumption model; then taking a joint function of a coverage score, a system throughput and an emergency task completion rate as an optimization target, under energy and communication connectivity constraints, proposing an LT-MADDPG algorithm, adopting a CTDE framework, processing a time sequence state by an actor network integrated with LSTM, fusing global information by a commentator network embedded with Transform through multi-head attention, and finally obtaining an emergency task. And modeling a cooperative relationship between the unmanned aerial vehicles and a medical task priority. Experiments show that the method is superior to a traditional algorithm in the aspects of coverage, service fairness and system throughput, and the medical inspection efficiency and reliability are effectively improved.

The invention discloses an FTU-based power distribution network fault positioning method and system, and belongs to the technical field of power distribution automation, and the method comprises the steps: constructing a space-time correlation feature matrix according to a transient current sequence and a voltage drop sequence during a fault period, and extracting the convolution features of a graph to obtain a fault feature graph containing the fault correlation degree between nodes; according to a static topological structure in the power distribution information model, virtual impedance is calculated based on the fault feature graph, and network equivalent topology is dynamically identified to obtain a dynamic virtual topological structure graph; and based on the dynamic virtual topological structure diagram structure and the fault feature diagram, performing fault section confidence competing decision through the intelligent agent unit corresponding to each FTU based on an incomplete information game, and outputting a fault section positioning result. The power distribution network fault positioning method solves the problems that a traditional power distribution network fault positioning method is insufficient in positioning accuracy and poor in fault tolerance and excessively depends on centralized processing and global information synchronization when information is incomplete, fault features are complex and network topology dynamically changes.

The invention discloses an edge computing node collaborative task unloading method for guaranteeing a low-delay service, and relates to the field of edge computing, each edge computing node generates a collaborative view comprising the edge computing node and a neighbor edge computing node through a local LSTM prediction model and federated learning, and the collaborative view comprises a predicted resource state and a predicted network state; according to the invention, the local LSTM prediction model and federated learning are combined to generate the collaborative view, so that accurate prediction and global information sharing of edge node resources and network states are realized, and the accuracy of decision making is improved; the tasks are analyzed into a dependency graph with key path marks, so that priority scheduling of the key tasks is ensured, and the overall task time delay is reduced; based on a weighted voting consensus mechanism of node credibility and resource adequacy, the efficiency and reliability of decision consensus among nodes are improved; the task unloading efficiency and the service quality of the low-delay service are effectively improved, and the stability and the reliability of the edge computing system are enhanced.

The invention discloses a low-voltage series arc fault detection method, system and device, and belongs to the technical field of low-voltage series arc fault detection, and the method comprises the steps: obtaining an original current signal, and carrying out the preprocessing through sliding window segmentation and instance normalization; performing multi-scale feature fusion on the preprocessed analysis unit, and generating fusion features through parallel feature extraction and an attention mechanism; performing context modeling on the fused features through an encoder, inputting a self-adaptive bottleneck layer containing an expert hybrid network, and routing the features to the most appropriate expert network by context sensing gating according to global information; the decoder reconstructs the signal and calculates an error, and generates a dense abnormal fraction sequence; gaussian position weighted aggregation abnormal scores are adopted, and fault judgment is carried out in combination with a self-adaptive threshold decision mechanism based on K-Means clustering. The method can be trained without a fault sample, can dynamically adapt to complex current modes under different loads, gets rid of dependence on the fault sample, and accurately detects the arc fault.

The invention discloses a local-global information aggregation remote sensing image change detection method based on Version Mama, and belongs to the technical field of remote sensing image change detection. The method adopts a Dual-LGNet network model for prediction, and comprises the following steps: inputting a dual-time-phase remote sensing image map before and after change into a twin encoder to obtain a feature map aggregating global features and local features; inputting the feature map aggregating the global features and the local features into a feature fusion module to obtain a fused difference feature map; and inputting the difference feature map into a progressive decoder to obtain a final prediction result. Wherein the LG-SS2D is introduced into the encoder to carry out feature extraction, and an LG-SS2D block comprises a parallel convolution branch and a Mama-based global branch. Through combination of local-global information aggregation and boundary enhancement, the recognition and detection precision of a remote sensing change area can be improved on the premise of keeping linear complexity, and especially the detection precision of a large building and a small target change area can be improved.

The invention discloses a storage robot cluster management system and method, and belongs to the technical field of robot scheduling. The system comprises a central management server and an autonomous mobile robot cluster. The central management server comprises a congestion prediction and global path planning module; the congestion prediction and global path planning module comprises a congestion prediction sub-module and an A * path planning sub-module with space-time cost; the autonomous mobile robot is internally provided with a multi-sensor sensing and communication module and a local decision module, and the off-line centralized training platform is used for optimizing the local decision module in each autonomous mobile robot through a centralized evaluation network with global information in a simulation environment. The invention provides a hybrid control architecture integrating global path planning, dynamic task allocation and local real-time decision based on multi-agent reinforcement learning, and efficient and smooth cluster collaborative operation can be realized.

The invention discloses an EAGLE-Net remote sensing image segmentation method, which comprises the steps of extracting multi-scale features of an input image, and obtaining low-level features of spatial details and high-level features of semantic information; the low-level features of the space details and the high-level features of the semantic information are input into an attention gating module, space-channel two-dimensional attention weights are generated, and weighting processing is conducted on the low-level features of the space details and the high-level features of the semantic information; inputting the weighted high-level features into a dynamic void space pyramid, predicting multiple groups of void rates based on global information, and generating enhanced semantic features through multi-scale void convolution fusion; splicing and decoding the weighted low-layer features and the enhanced semantic features to obtain a segmented prediction map; and performing edge detection on the segmented prediction map to generate an edge prediction map. According to the method, noise can be suppressed, key signals can be enhanced, large targets and small targets can be adaptively covered, and object boundaries can be accurately recovered by means of edge supervision.

The invention discloses a drainage basin monitoring network layout optimization method based on mutual information active learning. The method comprises the following steps: data processing; constructing an integrated learning prediction model composed of a plurality of LSTMs, initializing each LSTM model parameter by setting different random number seeds, and iteratively updating the model parameters; constructing a covariance matrix of prediction results of the potential monitoring points by using the trained integrated learning prediction model; on the basis of an active learning algorithm of mutual information maximization, mutual information gains of all candidate sites added into the current monitoring network are calculated, candidate points enabling the mutual information gains to be maximum are selected, and information value sorting is carried out on potential monitoring points according to the sizes of the mutual information gains; and outputting a monitoring station optimization suggestion list. According to the method, uncertainty is scientifically quantified by adopting an ensemble learning method, and global information value is evaluated by adopting a mutual information maximization strategy, so that point selection decision does not depend on subjective experience any more, but strict calculation based on data and information theory, and the scientificity of decision is remarkably improved.

The invention discloses a mooring type low-altitude monitoring countering unmanned system based on deep learning target recognition. The mooring type low-altitude monitoring countering unmanned system comprises a mooring unmanned aerial vehicle platform module, a multi-source sensing and data fusion module, a deep learning target recognition and classification module, a self-adaptive countering decision and execution module, a dynamic tracking and collaborative aiming module and a ground command and control module. The mooring unmanned aerial vehicle platform module forms a stable air monitoring and countering base point; the multi-source sensing and data fusion module provides high-quality input for system identification; the deep learning target recognition and classification module recognizes and predicts a target behavior through deep learning; the self-adaptive countering decision and execution module realizes precise countering; the dynamic tracking and collaborative aiming module applies counter energy to a dynamic target; the ground command and control module provides a human-computer interaction interface and displays global information. The low-altitude active defense system has the advantages that technologies such as multi-source fusion perception, deep learning AI recognition and self-adaptive precise countering are deeply fused, and the low-altitude active defense system is formed.

The invention discloses a remote computing power dynamic collaborative optimization method based on multi-agent reinforcement learning. The method comprises the following steps: constructing a resource topological graph; obtaining a node-level state feature vector and a system-level state feature vector based on the resource topological graph; constructing a multi-agent environment; inputting local observation, global information and an agent action set into an improved CTDE model, outputting strategy network parameters and value network parameters, and constructing a training batch; obtaining a converged strategy network parameter and a converged value network parameter based on the training batch; obtaining an execution result; dynamically updated strategy network parameters and dynamically updated value network parameters are obtained, and dynamic collaborative optimization of task acceptance, resource allocation, task migration, copy start and stop and bandwidth ratio is achieved.

The invention discloses a frequency modulation and wavelet sub-band guided double-domain collaborative Transformer X-ray image denoising method, which comprises the following steps of: acquiring a noise-containing digital ray original image and a corresponding clear reference image, and constructing a data set after preprocessing the noise-containing digital ray original image and the corresponding clear reference image; constructing a network model of a double-domain collaborative coding-decoding architecture; performing 3 * 3 deep convolution on an input image to extract shallow layer features; in the encoding stage, ETB and AFMB are alternately stacked to represent local and global information, a WB-LKED module is embedded to strengthen fine-grained features, and WDB executes down-sampling and transmits high-frequency features to a decoding end; in the decoding stage, the WUB recovers the resolution through double-path up-sampling, integrates the same-scale features of an encoder, enhances details by using high-frequency features, splices the features, then carries out ETB and AFMB refining, obtains output features through 3 * 3 deep convolution, and combines a global residual error connection optimization result; and training the model by using the data set, inputting a to-be-denoised image, and outputting a final result. According to the method, the problems of weak complex noise interference resistance, poor detail retention effect and limited CNR improvement can be solved.

The invention discloses a double-branch coding infrared visible light small target detection method based on improved vision RWKV. The method comprises the following steps: respectively forming a single-mode infrared small target image training set and a dual-mode infrared-visible light small target image training set; constructing an initial infrared-visible light small target detection network model; obtaining a trained infrared-visible light small target detection network model; and testing the model to obtain a small target detection result, and the like. The method comprises the following steps: respectively extracting a local feature map and a global feature map of an image by adopting a double-branch structure; an improved visual RWKV auxiliary encoder is used to carry out modeling on image global information, and a main encoder based on residual convolution is used to extract local detail information. A new multi-scale shift module is designed by combining wavelet transform according to the characteristics of a small target image, so that the multi-frequency feature expression capability of the model in global feature extraction is enhanced; the design of a feature fusion module is improved so as to realize deep interactive fusion of local-overall features.

The invention provides a multi-modal sentiment analysis model and method, electronic equipment and a medium, and the model comprises a feature enhancement module which is used for extracting original multi-modal data features through an exclusive tool, constructing a graph structure, and enhancing the graph structure through a graph convolutional network to obtain multi-modal enhanced features; the modal multi-stage balance module is used for processing enhanced features by using different multi-stage network structures and outputting multi-modal consistency representation; the modal noise reduction decoupling and specificity recombination module is used for obtaining low-noise representation through a modal noise reduction decomposer based on the global information and recombining the low-noise representation in a modal bank to generate low-noise multi-modal specificity representation; and the hierarchical fusion prediction module is used for fusing consistency and specificity representation according to single-peak, double-peak and three-peak modes, and outputting an emotion prediction result through a multi-layer perceptron.

The invention provides a point cloud key point generation method based on a key point detection network and a descriptor network, and the method comprises the steps: carrying out the random sampling of the key point detection network, obtaining candidate key points, carrying out the multi-level clustering with each candidate point as a center, expanding a sensing domain, and aggregating the neighborhood information, aggregated information is sent to a double-head attention mechanism to calculate a neighborhood point weight, and more representative key points are selected; the descriptor network receives the attention feature map of the detection network, carries out fusion learning on global information and local information of each key point, and calculates a descriptor and a direction vector for each key point. Secondary screening of the key points is carried out while the descriptors are optimized by using a joint matching loss function, and the key points with strong characteristic characterization force are obtained. Compared with the prior art, the time consumption is shortened by 90%, the key point repetition rate is 70%, the matching precision is 90% or above, and good robustness is achieved under different Gaussian noises.

The invention provides a resource scheduling method, electronic equipment, a storage medium and a computer program product. The method comprises: obtaining global information of a target computing power network, the target computing power network comprising a plurality of nodes, the plurality of nodes comprising a plurality of user nodes, a plurality of network nodes and a plurality of computing nodes, the global information at least comprising state information of the plurality of nodes and state information of a plurality of transmission paths, each transmission path comprises a user node and a computing node; constructing a resource scheduling model of the target computing power network based on the global information of the target computing power network; converting the resource scheduling model into a quantum computing model; constructing a quantum circuit based on the quantum calculation model; and determining a resource scheduling result of the target computing power network according to the measurement result of the quantum circuit. Through the scheme provided by the invention, the global resource scheduling strategy can be quickly obtained.

The invention provides an intelligent retrieval and reasoning generation method and system based on a knowledge graph and geoscience, and the method comprises the steps: firstly constructing a geoscience knowledge graph according to the information of a geoscience data set; secondly, identifying a key intention of the geographical question sentence; then, knowledge graph embedding work is carried out based on the entity relation structure of the knowledge graph, cross-entity potential relation and global information are captured, and reasoning from geoscience explicit data to deep knowledge is achieved; and finally, fusing a map result and a character result to carry out multi-domain retrieval so as to obtain an answer. Compared with an existing question answering system, the brand-new knowledge graph intelligent question answering system is constructed, the recall of answers can be improved, the knowledge reasoning ability is achieved, implicit internal association can be mined through explicit geoscience data, and geoscience experts can be helped to quickly and accurately find a target data set.

The invention discloses a lightweight sight line estimation method based on global information fusion, relates to the technical field of computer vision and intelligent driving, and solves the technical problems that an existing sight line estimation model is large in parameter quantity, is not adaptive to a vehicle-mounted multi-mode scene and is insufficient in robustness under a complex working condition. The method comprises the following steps: firstly, acquiring a driver image, an external scene image and vehicle running state data, and acquiring a target image through face and eye detection; based on a global information fusion module fusing CNN and Transform and a Res CBAM module, multi-modal global information features of vehicle state and driving behavior priori are obtained; deep modulation fusion of the local visual features and the global information features is completed through a double-stage fusion module, and finally the sight direction or the gazing area of the driver is output. The method realizes the unification of light weight and high precision of the model, is adaptive to vehicle-mounted complex working conditions, has both robustness and real-time performance, and can be widely applied to a vehicle-mounted driver monitoring system.

The invention, which relates to the edge computing field, discloses an inland ship overwater intelligent navigation aid and navigation information service system comprising: a system integration multi-source sensor for fusing and processing hydro meteorology and obstacle data under low visibility; the side cloud collaboration module processes real-time and global information in a labor division manner, analyzes a rule and optimizes a route; the channel modeling module constructs a real-time three-dimensional channel, and plans and dynamically adjusts an optimal path; the virtual navigation mark module dynamically deploys and manages navigation marks through AIS / Beidou; the information pushing module provides dynamic and static navigation data as required; the risk early warning module realizes graded warning and emergency linkage; the ship-shore cooperation module performs remote monitoring scheduling and channel analysis; the inland river adaptation module ensures that system parameters and algorithms are automatically matched with different river environments and rules. The method has the advantages that the multi-class perception and side cloud cooperation technology is fused, accurate navigation aiding, dynamic risk management and control and ship-shore efficient cooperation of the inland waterway are achieved, and intelligent upgrading of inland navigation is enabled in an all-around mode.

The invention discloses an antibacterial peptide prediction method based on dual-channel sparse attention. The method comprises the following specific steps: extracting initial embedding by using a protein language model; adaptively weighting the channel by using the channel attention enhanced convolutional neural network; capturing short-range interactions between amino acid residues using local sparse attention based on a sliding window; global sparse attention containing a scoring function is used for obtaining long-range interaction between key amino acid residues and the sequence, and local and global information is integrated so as to realize complete characterization of the peptide sequence; and predicting the final feature matrix by using a full connection layer. According to the method, the sequence information of the peptide is comprehensively modeled by using a simple and efficient training process, and a dual-channel sparse attention mechanism is introduced to effectively relieve the problems of representation redundancy and calculation complexity.

The invention relates to the technical field of glaucoma grading, and discloses a glaucoma grading system based on multi-modal conditional state space fusion, which comprises the following steps: acquiring a CFP image and an OCT image, and constructing a glaucoma grading network model which comprises a circular structure perception attention module, a layer prior enhancement axial attention module and a conditional state space fusion module; the circular structure perception attention module enhances the characterization capability of a circular key pathological change area in the CFP image, and the layer prior enhancement axial attention module enhances the utilization of key pathological change information in the OCT image; and the conditional state space fusion module dynamically modulates CFP spatial features through OCT global information, realizes cross-modal feature interaction, and performs glaucoma grading by using a trained network model. According to the method, multi-modal information can be effectively fused, the feature extraction capability of glaucoma related pathological features is enhanced, and the glaucoma grading performance is improved.

The invention discloses a sequence recommendation method and system based on a wavelet enhanced adaptive frequency filter, and the method comprises the steps: constructing a user behavior sequence according to the interaction between a user and an article, mapping the article in the user behavior sequence into an embedded vector, and processing the embedded vector to obtain a sequence embedded representation; the sequence is embedded and expressed, global features and fine-grained features are obtained through dynamic frequency filtering and wavelet feature enhancement, and fusion time domain features are obtained through feature integration; and processing the fused time domain feature to obtain a final time domain feature, performing probability prediction on an output vector of the last time step in the final time domain feature and transposition of an article embedding matrix to obtain a recommendation probability, and performing sorting to obtain a sequence recommendation result. According to the method, personalized global information is extracted and fuzzy non-stationary signals and short-term fluctuation are enhanced through dynamic frequency filtering and wavelet features, and performance and efficiency optimization is realized in a long-sequence recommendation scene through cooperative work of the two modules.

The invention relates to a real-time non-graphical robot autonomous navigation system, and belongs to the field of robots. The system comprises a main control module, an environment sensing module and a hybrid navigation module, the main control module is responsible for man-machine interaction, task flow control and cooperation of other modules, and storing and managing a visual semantic database; the environment sensing module is responsible for controlling the robot to collect image data and depth data under the condition of no prior map, identifying objects in a scene, extracting semantic information of the objects, and integrating identification results into a visual semantic database; and the hybrid navigation module analyzes the instruction sent by the main control module by using a large language model, matches visual memory, determines a navigation target, and completes autonomous navigation of the robot through a hybrid navigation strategy. According to the method, the problem of low navigation task accuracy caused by the sparsity of global information in map-free navigation is solved.

The invention relates to the technical field of image recognition, and discloses a lightweight system applied to label printing defect recognition. According to the system, the position of a target in a label printing image is recognized and a result is extracted by combining edge detection and a contour matching algorithm in a preprocessing stage, then, in order to improve the feature extraction efficiency and reduce the consumption of computing resources, a C-D-Conv module is constructed by using a mobile inverted residual bottleneck block, and the feature extraction efficiency is improved. In order to improve global information capture and local feature enhancement capability in image processing, an LA-LC-LM module mainly composed of self-attention, local convolution and MLP is constructed, in order to help a model to better process preliminarily extracted image low-level features in the later period, a dual-path collaborative hybrid attention mechanism DHAM is embedded in a network, and the algorithm is applied to image processing. According to the system provided by the invention, the Top-1 Acc and Param on a self-made data set Code-10 respectively reach 99.25% and 3.595 M, and the Top-1 accuracy on a public data set NEU-CLS-64 and the Top-1 accuracy on a reconstructed data set DAGM2007 * respectively reach 97.79% and 85.42%.

The invention discloses an image rain removal model, method and system, electronic equipment and a storage medium, and the image rain removal model employs a multi-output multi-scale architecture and has a plurality of scale branches operated under a plurality of resolutions; the encoder of each scale branch comprises a convolution layer which is used for receiving and extracting potential features of a to-be-processed rain image and obtaining a shallow feature map; the frequency feature enhancement unit is used for capturing multi-frequency information, acquiring context semantic information and acquiring a processing feature map; the multi-scale compensation Transform block is used for extracting global information and local detail features in each scale branch to obtain a deep feature map; a gating fusion module is arranged at the tail end of the encoder and is used for fusing depth features of all scale branches to obtain an enhanced feature map; a residual convolutional layer for outputting a residual image is arranged at the tail end of the decoder of each scale branch; the residual image is used for subtracting the received to-be-processed rain image to obtain a rain-removed image.

The invention discloses a building flexible load regulation and control method, equipment and a medium, relates to the technical field of Internet of Things and intelligent control, and solves the problems of high communication cost and low response speed of an existing regulation and control method. The method comprises the following steps: acquiring environmental parameters and equipment operation data in a building, and transmitting the environmental parameters and the equipment operation data to an edge computing node through a low-power wide area network; the environmental parameters and the equipment operation data are preprocessed, logic judgment is conducted on the preprocessed data through a machine learning model, and a preliminary regulation and control instruction is generated; performing load prediction on the global information of the building and the preprocessed data abstract, generating a load optimization strategy, and issuing the load optimization strategy to an edge computing node; and regulating and controlling the preliminary regulation and control instruction according to a load optimization strategy to generate a final regulation and control instruction. Through a hierarchical architecture of edge computing and cloud collaboration, dual effects of fast local response and high global efficiency are obtained, and at the same time, low-cost control equipment is used to reduce deployment and communication costs.

The invention relates to the technical field of data analysis, in particular to a data analysis processing method and system for processing a chromatographic system, and the method comprises the following steps: collecting a chromatographic matrix, calculating curvature change, constructing a piecewise function, mapping the piecewise function to a manifold space, screening drifting, reserving a trunk, calculating difference and variation rate, cutting a high variation region, constructing a three-dimensional tensor, and constructing a three-dimensional tensor; according to the method, a manifold space divided based on curvature abrupt change points is constructed, a gradient change rate is used for recognizing a signal trunk and screening out drift noise, and the identification identifier is generated. The method has the advantages that the manifold space divided based on the curvature abrupt change points is constructed, so that the accuracy of the identification identifier is improved, and the accuracy of the identification identifier is improved; according to the method, a high-gradient section of a signal response curved surface is constructed in combination with retention time difference and variation rate, a potential overlapping peak region in a complex structure is effectively positioned, local sub-sections are fitted through a least square method, peak shape moment characteristics are extracted, weighted reconstruction is executed in combination with global information, and refined expression of peak shape information and enhancement of recognition precision are realized.