1165 results about "Incremental learning" patented technology

The invention discloses a multi-modal dynamic fusion and incremental learning fault diagnosis method for deep vertical shaft equipment, which belongs to the technical field of industrial equipment fault diagnosis, and comprises the following four steps of: constructing a pre-training large model to perform feature extraction, and relying on a multi-layer Transformer encoder and a dual loss function, establishing a multi-modal dynamic fusion and incremental learning fault diagnosis model; mining cross-modal universal fault features from vibration, temperature and current multi-modal time sequence data; according to the method, multi-modal features are fused, multi-modal association is constructed, modal weights are dynamically adjusted through a modal gating unit and a time delay compensation attention mechanism to adapt to signal quality changes, and meanwhile time sequence deviation is corrected to achieve accurate association; incremental learning is realized by using a decoupling projection layer, and a lightweight projection module is designed for a newly added fault task to suppress disastrous forgetting; network training is optimized, pre-training loss, incremental learning loss and attention regularization loss are integrated through a multi-objective loss function, and model stability and diagnosis precision are improved. The method has the advantage that the model stability and the diagnosis precision are improved.

The invention relates to a power distribution network data intelligent analysis method based on data consanguinity and multi-modal fusion learning. The method comprises the following steps: S1, constructing a dynamically evolved data consanguinity topological graph; s2, designing a label-guided graph neural network architecture, embedding historical abnormal knowledge into a graph learning process, and outputting a deep semantic feature vector; s3, constructing a multi-modal fusion analysis framework, performing multi-dimensional feature fusion and data quality analysis, and identifying abnormal nodes; s4, designing a semi-supervised and incremental learning combined mixed training normal form, and performing model training and strategy optimization; and S5, based on the dynamic consanguinity topology constructed in the step S1 and the identified abnormal nodes, constructing a probabilistic reasoning framework, and fusing the model parameters obtained by optimization in the step S4 to realize quality abnormality root positioning and full-link visualization so as to form a complete data intelligent analysis scheme. According to the invention, efficient and accurate management of the topological data quality of the power distribution network is realized.

The invention provides a server cluster operation and maintenance method based on multi-source heterogeneous data fusion and a dynamic knowledge graph, and the method comprises the following steps: collecting a performance index, a log text and topological structure data of a server cluster, splicing the performance data and the log data based on a unified time window, and generating a multi-modal feature sequence; and analyzing the sequence by using an unsupervised deep learning model, constructing a dynamic health baseline, and generating a health degree portrait through the deviation with real-time data. When an exception is detected, mapping an exception event into a dynamic topological graph constructed based on a topological structure; analyzing a fault propagation probability between nodes by using a graph neural network algorithm, positioning a root cause node, and generating a disposal strategy to execute disposal operation; and collecting the processed recovery data as a feedback signal, and updating the deep learning model by using incremental learning. The method has the beneficial effects that the fault discovery accuracy is improved, the alarm storm is effectively inhibited, the root cause is directly positioned, and the model self-iteration adaptability is higher.

The invention discloses an efficient processing method and system for online troubleshooting of the information department, and relates to the technical field of automatic operation and maintenance, and the system comprises a multi-modal data acquisition module, a dynamic knowledge graph construction module, a reinforcement learning driven self-healing module, an edge co-processing module and a cross-domain privacy calculation module. According to the method, the limitation of traditional single-dimensional monitoring is broken through, multi-source heterogeneous data such as server performance, container state and network flow are fused, a high-timeliness and high-consistency decision information base is constructed through unified time sequence alignment and semantic standardization, and a panoramic view is provided for dynamic analysis; based on an incremental learning mechanism and a causal inference engine, a service topology dependency relationship is updated in real time, a deep root cause is accurately positioned, and a cross-system and cross-level complex fault combination is solved.

The invention relates to the technical field of computer vision, in particular to a high-rise facility operation risk monitoring method based on deep learning and point cloud detection, and the method comprises the steps: collecting a three-dimensional point cloud in real time, and extracting a target point cloud through dynamic threshold denoising and template registration; performing joint coding on space geometry and time sequence motion by using a pre-trained space-time diagram network in combination with an attention mechanism; high-reflectivity beacon points are identified, and the change rate of displacement and angular velocity is calculated; constructing a gating fusion model, dynamically weighting and coupling semantic features and measurement data, and generating risk probability distribution through mutual information consistency check; a fuzzy logic classifier with membership degree optimization is used for mapping to four-level early warning, and grading response is triggered; after early warning, a key frame incremental learning fine tuning model is extracted, and preprocessing parameters are reversely optimized to form a closed loop. According to the method, through multi-source heterogeneous data fusion, dynamic adaptive weighting and a self-evolution mechanism, the real-time performance, accuracy and robustness of risk monitoring in a complex construction environment are remarkably improved.

A knowledge graph construction method based on active learning and incremental learning comprises the following steps: S1, preprocessing data from a plurality of heterogeneous data sources, and extracting entities, relationships and attributes to form an initial knowledge network; s2, vectorizing elements in the initial knowledge network by using a knowledge graph embedding model, and performing entity alignment based on vector similarity to obtain an initial knowledge graph; s3, screening out candidate knowledge triples with high uncertainty and / or high representativeness from the initial knowledge graph by adopting an active learning strategy, and obtaining user labeling information corresponding to the candidate knowledge triples; s4, performing iterative optimization on a knowledge extraction model and / or a knowledge graph embedding model according to the user labeling information; s5, new data are fused into the optimized knowledge graph in an incremental learning mode, and knowledge conflict detection and resolution are carried out in the fusion process; and S6, circularly executing the steps S3 to S5 until the knowledge graph meets a preset quality condition.

The invention provides a textile industry broken yarn identification method and system based on a neural network, and the method comprises the steps: collecting yarn multi-modal data, including a surface image, a fracture sound wave signal and tension change data; preprocessing the data, and extracting an image ROI region, sound wave spectrum features and a tension mutation sequence; performing space-time alignment and feature extraction on the extracted content to obtain a joint feature vector; inputting the broken yarn into a trained broken yarn identification model, wherein the model can identify broken yarn features; judging whether broken yarns exist or not according to the output result and outputting an identification result; and updating the model through online incremental learning. According to the method, multiple types of data are combined, the adaptive preprocessing and feature extraction technology is used, environmental noise is inhibited, key features are focused, and the problem of false alarm of a traditional sensor is solved; multi-modal features are fused through space-time alignment and a self-attention mechanism, and bidirectional LSTM modeling is combined, so that a broken yarn dynamic rule is accurately captured, and the problems of missing detection and delay of manual inspection are avoided.

The invention discloses a knowledge base knowledge association fusion method based on a knowledge graph, and the method comprises the steps: integrating structured, semi-structured and non-structured data through a cross-modal alignment technology, and constructing a multi-source heterogeneous data association network of a unified semantic space; newly added external data are fused to a multi-source heterogeneous data association network in real time by using a dynamic attention mechanism, and entity conflicts are eliminated by combining rule reasoning and a machine learning model; hidden association among entities in the multi-source heterogeneous data association network is mined based on the graph neural network, and a knowledge graph logic chain is complemented; based on the knowledge graph, intelligent question and answer and risk assessment decision scenes are supported through a hybrid retrieval architecture and an inference engine; and automatically updating and associating the knowledge base of the network extension knowledge graph by adopting an incremental learning technology. Natural language questions and answers are supported, accurate answers are generated through knowledge reasoning, and user experience is remarkably enhanced.

The invention relates to the technical field of intelligent teaching, and discloses an intelligent teaching system and method based on a large language model. The system comprises a teaching intention analysis module, a knowledge graph adaptation module, a dynamic reasoning engine module, a teaching strategy generation module and a feedback optimization module. The teaching intention analysis module is used for disassembling the teaching interaction instruction into a knowledge domain label and a teaching behavior sequence through a semantic segmentation engine; and the knowledge graph adaptation module is used for matching the subject knowledge graph and extracting an associated knowledge node set. The dynamic reasoning engine module inputs the node set into a large language model to complete multi-hop reasoning, and an intermediate state vector containing a reasoning path is generated; and the teaching strategy generation module generates a hierarchical teaching strategy in combination with the vector path weight and the behavior sequence timestamp. The feedback optimization module collects user behavior data, updates knowledge graph matching rules through incremental learning, and adapts to diversified teaching requirements.

The invention relates to the technical field of forestry environment monitoring, and discloses a forestry environment monitoring method and system based on big data analysis. The method comprises the following steps: acquiring multi-dimensional environmental parameters such as soil moisture content, vegetation coverage and meteorological factors through a distributed sensor network, and generating a real-time weight coefficient through a dynamic weight distribution engine; and completing anomaly detection by using the space-time correlation analysis model, and triggering a self-adaptive sampling strategy to perform high-density acquisition on an abnormal region. Real-time data and satellite remote sensing data are integrated through a multi-source data fusion algorithm, a forestry environment state matrix is generated, and a reference threshold is dynamically updated in combination with an incremental learning mechanism. And generating a regulation and control instruction set for soil improvement, vegetation maintenance and disaster early warning according to the updated threshold value, and executing and collecting feedback data by the edge computing node. And comparing feedback data with an expected index through a bidirectional verification mechanism, generating system optimization parameters, and returning the system optimization parameters to a dynamic weight distribution engine, thereby realizing accurate monitoring and efficient regulation and control of a forestry environment.

The invention relates to the technical field of network security and data processing, and discloses a violation short message recognition method and system based on deep semantic understanding, and the method comprises the steps: firstly cleaning an original short message, generating a mixed embedding vector through characters, sub-words and pinyin, and carrying out the recognition of the violation short message; then processing through a double-layer detection engine, wherein the first layer utilizes rules and a lightweight model for rapid preliminary screening; in the second layer, for suspected samples, a double-tower fusion neural network architecture is adopted, local and global features are combined, fusion is carried out through a gating unit, and a large language model is input to carry out deep semantic reasoning. The system executes strategies such as interception or flow limiting according to the risk score, and realizes model iteration through a dynamic knowledge base and incremental learning. According to the method, the resource consumption and the detection precision are balanced through the layered architecture, the antagonistic variants are effectively identified by utilizing multi-dimensional feature fusion, and the method has the adaptive evolution capability for a novel violation mode.

The invention discloses a new energy consumption multi-objective decision reasoning method and system based on a knowledge graph. The method comprises the following steps: completing data acquisition and preprocessing; extracting the relationship between the core entities and the entities to generate a structured triple, and further constructing an energy field knowledge graph; designing a loss function by taking economy and stability as optimization targets, training a GNN integrated with power grid topology perception in combination with historical scheduling data, and completing model construction; entity change and relation update in the new data are identified through an incremental learning method, and the energy field knowledge graph is automatically supplemented or corrected; according to a current scheduling demand, extracting a corresponding associated sub-graph from the updated knowledge graph, inputting the trained GNN model, and outputting a scheduling decision scheme; and accessing the scheduling decision scheme output by the GNN to a power grid digital twinborn simulation platform to complete analogue simulation and feedback regulation. And efficient and safe consumption of new energy in a dynamic environment is ensured.

The invention discloses an obstacle avoidance motion planning method and system for redundant drive of an intelligent process of a welding robot and computer equipment. According to the method, firstly, a motion path of a robot is planned based on welding process redundancy, then a sampling strategy that the position and posture of a welding gun are separated is adopted, then the sampled posture is mapped to a planar two-dimensional space, and the relevance between an obstacle collision boundary and the obstacle avoidance posture of the welding gun is constructed; an incremental extreme gradient lifting model is adopted to carry out probability modeling on the collision boundary and obstacle avoidance attitude relevance, nearest neighbor search and new planning node expansion are carried out based on target cost to obtain new planning nodes, collision detection is carried out on the new planning nodes, and the new planning nodes passing the collision detection are used for incremental learning of an obstacle avoidance model; and finally, an optimization strategy of spherical linear interpolation and cosine slow motion time mapping is adopted to ensure continuity and smoothness of a motion planning path trace. The problem that in the prior art, it is difficult to quickly calculate and generate a collision-free welding track is solved.

The invention discloses a network space security intelligent monitoring and analysis system, and relates to the technical field of network security monitoring and analysis, and the system comprises a multi-source data collection module which collects multi-dimensional data in a full-link manner, and the collection frequency is dynamically adjusted along with a network load; the data preprocessing module cleans the fused data and generates a standardized analysis data set; the AI intelligent risk identification module identifies various safety risks in real time through a mixed deep learning model; the real-time response processing module starts differential processing according to a three-level mechanism; the threat traceability analysis module traces an attack link and generates a report; the security situation visualization module displays the security state in multiple dimensions; the data encryption storage module encrypts and protects data and performs double backup; and the system self-optimization module dynamically optimizes the strategy through incremental learning. The method is accurate in risk identification, timely in response processing, reliable in traceability and evidence storage, and efficient in cross-domain cooperation; terminal protection and third-party access control are enhanced, and network space security and stable service operation are comprehensively guaranteed.

The invention discloses a robot language and intention interaction method and system and a computer readable storage medium, and the method comprises the steps: collecting voice information and / or gesture information, carrying out the feature extraction of the voice information and / or gesture information, obtaining semantic features and / or gesture semantic tags, and carrying out the recognition of the semantic features and / or gesture semantic tags; and based on the semantic features and / or the gesture semantic labels, through a dynamic classifier, intention category classification is realized, intention probability distribution is output, based on the probability distribution, a special encoder is selectively activated to extract domain-specific term features, and the dynamic classifier can also perform intention category expansion through an incremental learning mechanism, so that the domain-specific term features are extracted. And the semantic features and / or the gesture semantic tags are fused to calculate joint confidence, and an instruction execution module generates a robot executable instruction based on the joint confidence. According to the method, high-precision multi-modal interaction and intention understanding in a noise environment are realized, dynamic extension of intention categories is supported, and the accuracy and adaptability of robot interaction are improved.

The invention relates to the technical field of geological early warning, in particular to a dangerous rock mass instability analysis method, system and equipment based on a space-time diagram neural network, by fusing unmanned aerial vehicle LiDAR, multispectral data, meteorological radar data and the space-time diagram neural network (ST-GNN), the system realizes sub-meter spatial resolution and minute-level time response, and the stability of dangerous rock mass instability analysis is improved. The four-dimensional (time and space) analysis result of the instability probability of the dangerous rock mass is obtained through high-precision space-time modeling, the problems that a traditional geological disaster early warning system is low in resolution ratio, slow in response and high in misinformation are solved, the comprehensiveness, accuracy and reliability of instability prediction of the dangerous rock mass are improved, and the early warning effect is good. And full-chain intelligent closed-loop management of real-time data acquisition-dynamic prediction-early warning push-feedback optimization is supported, the emergency decision time is shortened by real-time rainfall superposition risk thermodynamic diagrams, and the attenuation rate of long-term prediction precision is reduced by dynamically fusing newly added geological data and instability events through incremental learning.

The invention provides an industrial anomaly detection and root localization method and system based on data driving, and the method comprises the steps: carrying out the cleaning, feature extraction and normalization processing of original data collected in an industrial production process, and constructing a feature space; based on a local anomaly factor LOF and a mahalanobis distance MD method, jointly detecting local anomaly and global anomaly, and identifying an abnormal working condition; extracting space and time correlation characteristics of the abnormal variables through Pearson correlation weighting and Granger causal test to form a space-time correlation matrix; constructing an abnormal causal network based on the matrix, and tracing an abnormal root and a propagation path through depth-first search and abnormal propagation intensity evaluation; and finally, dynamic optimization of the anomaly detection and diagnosis method is realized based on parameter self-adaption and model incremental learning. According to the method, the anomaly detection accuracy and the anomaly traceability interpretation capability can be effectively improved, and the intelligent level and the self-adaptive capability of data processing are enhanced.

The invention discloses an integrated circuit equipment data optimization monitoring system and method based on big data, and relates to the technical field of integrated circuit manufacturing. The method is used for solving the problems of insufficient multi-physical field monitoring, difficulty in abnormal traceability and lack of closed-loop control in plasma etching. A plasma sheath thickness inversion model and an etching selection ratio model are constructed by collecting radio frequency reflection phase, mass spectrum ion strength and wafer temperature data, and process parameter-plasma state dynamic coupling is established. Interference image distortion features and electron microscope size data are fused, micro-groove geometric parameters are analyzed, morphology instability risk indexes are generated, and nanoscale early warning is achieved. And designing a dual-channel fusion network, embedding a physical constraint attention mechanism, and generating an etching rate optimization instruction. On the basis of incremental learning, model parameters are updated online, a'monitoring-decision-feedback 'closed-loop system is formed, anomaly detection sensitivity and decision reliability are improved, and technical support is provided for intelligence of integrated circuit equipment.

The invention discloses an engineering vehicle safety simulation and prediction system based on digital twinning, and the system comprises a data collection layer which collects multi-source heterogeneous data in real time; in the knowledge graph layer, a streaming inference engine is constructed based on an Apache Jena graph database, and an entity-relationship-attribute triple dynamic graph structure is adopted; according to the AI model layer, a physical rule serves as a loss function constraint term to be embedded into a neural network through a physical information neural network, a digital organ model concept is combined to split a vehicle into key organs for heterogeneous modeling, a simplified physical model is adopted in the core physical process, and an LSTM-AI model is adopted in external behaviors; the explanatory analysis layer is used for integrating an SHAP / LIME explanatory tool to output a visual evidence chain during fault prediction, and deploying an online incremental learning framework to allow the model to learn from new data and dynamically adjust normal range definition; and the visualization and application layer is used for performing three-dimensional visualization rendering based on WebGL or Three.js, and ensuring data transmission security through block chain evidence storage and end-to-end encryption.

The invention discloses an abnormal data monitoring method and device based on artificial intelligence, and the method comprises the steps: 1, dividing an original data stream through a sliding window, extracting statistics, time sequence and change rate features, and dynamically screening features adaptive to data distribution based on an SHAP value; 2, constructing a double-flow model, capturing a global isolated mode by adopting an improved isolated forest in a static flow, capturing time sequence dependence on the basis of LSTM-AE in a dynamic flow, and fusing two-flow scores through performance-driven dynamic weight distribution; 3, combining a density peak value algorithm with historical density attenuation weighting, and dynamically adjusting an abnormal threshold value; 4, realizing low-delay incremental learning through a double-trigger mechanism and experience playback; 5, multi-granularity interpretation is generated, manual annotation feedback is supported, feature engineering and model training are integrated, and a'detection-interpretation-feedback-optimization 'closed loop is formed; high-adaptability anomaly monitoring is realized through dynamic feature screening, double-flow fusion detection, threshold value self-adaption and man-machine collaborative optimization.

The invention relates to the technical field of tunnel and underground engineering construction, and discloses an intelligent closed-loop control system and method for a tunnel construction section contour, and the method comprises the steps: collecting geological-geometric data through the fusion of a three-dimensional laser scanner and a geological radar before blasting; dynamically generating a theoretical blasting contour line and adaptive blasting parameters through a convolutional neural network; iMU positioning and a PID controller are combined to realize millimeter-level accurate control of the drill boom; generating a three-dimensional deviation field by adopting an iterative point cloud registration algorithm after blasting; when the deviation exceeds a threshold value, triggering incremental learning to optimize model parameters; and finally, closed-loop iteration is formed. Through multi-source data fusion, contour and parameter intelligent generation, precise execution control, three-dimensional deviation field feedback and an incremental learning mechanism, a complete intelligent closed-loop control system is constructed, the limitation of traditional blasting design depending on experience is broken through, and the precision, efficiency and economic benefits of tunnel construction are remarkably improved.

The invention belongs to the technical field of space intelligence, and relates to a dynamic obstacle intervention-oriented space intelligent scene self-reconstruction navigation system, which comprises a dynamic intervention sensing module, a dynamic obstacle intervention processing module, a dynamic obstacle intervention processing module, a dynamic obstacle intervention processing module, a dynamic obstacle intervention processing module and a dynamic obstacle intervention processing module, the spatial semantic topology reconstruction module is used for automatically updating a spatial semantic map and a topology connection relation according to the dynamic intervention event set; the local topology rapid recombination module is used for carrying out rapid recombination on the intervened and influenced local topology based on a topology incremental learning principle; and the perception and navigation bidirectional consistency optimization module is used for establishing a reverse feedback path between perception and navigation. According to the invention, the real-time response and structure-level self-adaption of the navigation system to environment change can be realized, so that the stability and consistency of navigation decisions can be maintained in changeable scenes. The invention further provides a space intelligent scene self-reconstruction navigation method oriented to dynamic obstacle intervention.

The invention relates to an animal wound multi-modal intelligent identification method based on artificial intelligence, and the method comprises the steps: carrying out the feature extraction and semantic constraint through multi-modal sample collection and metadata extraction, employing an image preprocessing and text natural language processing technology, and combining a mixed visual model of a convolutional neural network and a visual Transform, and a large language model. A cross-modal attention mechanism and a semantic trigger are utilized to realize feature reweighting, clinical standard soft boundary constraints are introduced, and fuzzy semantic rules are converted into learnable constraints in a feature space, so that the accuracy and consistency of model judgment are improved. The method has adaptive optimization and incremental learning capabilities, and is beneficial to improving generalization and clinical applicability of exposure level intelligent judgment under different animals and complex wound types.

The invention discloses a pressure sensor zero drift compensation method and system for a high-voltage direct-current converter valve cooling system, and relates to the technical field of monitoring and calibration of high-voltage direct-current transmission equipment. The method comprises the following steps: constructing a multi-factor coupling drift model taking temperature, vibration frequency and electromagnetic interference intensity as inputs; environment parameters and pressure signals are collected in real time, and reference pressure signals are collected regularly; short-term dynamic compensation is realized based on model prediction and reference deviation correction; updating the model through incremental learning according to the drift trend; and real-time monitoring and abnormal early warning are carried out. The system comprises a multi-parameter acquisition unit, a data processing unit, a reference pressure generation unit and a communication unit. According to the method, shutdown calibration is not needed, the compensation precision is improved by 75% or above, the calibration period is prolonged to 12 months, meanwhile, the method has the abnormal diagnosis and standby compensation functions, measurement continuity is guaranteed, compatibility is high, industrial popularization is easy, and the method is particularly suitable for being used in a complex environment.

The invention relates to the technical field of energy meteorology and intelligent power grids, in particular to a multi-extreme meteorological high-risk scene set generation method, system and equipment based on a joint training generative adversarial network. The method comprises the following steps: constructing a physical information generative adversarial network framework comprising a generator, a discriminator, a predictor and a physical constraint module; designing a multi-objective loss function fusing adversarial loss, prediction loss, physical consistency loss and task performance loss; adopting a training strategy combining meta-learning initialization and incremental learning to jointly optimize parameters of the generator and the discriminator in stages; extreme risk scene data of specified disaster types, seasons and intensity grades are generated through condition vector control, and the extreme risk scene data are stored in a high-risk scene library after physical consistency verification. Through the method, a multi-extreme-weather high-risk scene set with statistical authenticity, physical rationality and task correlation can be directly generated, and the risk identification, scheduling optimization and toughness evaluation capabilities of the clean energy base under extreme weather conditions are remarkably improved; the problems of sample scarcity, model overfitting and lack of physical constraints in scene generation in the prior art are solved, efficient and automatic generation of a high-risk scene is realized, and reliable data support is provided for power grid toughness evaluation and scheduling decision of a clean energy base.

The invention discloses a sawing machine saw blade vibration analysis method. Wavelet packet decomposition (WPD) is adopted to decompose a vibration signal into a plurality of equal-bandwidth sub-bands, energy entropy and kurtosis are extracted as features, a fault sensitive frequency band is screened out, a sensor spatial topological graph is constructed, a spatial dependency relationship is modeled by adopting a graph attention network (GAT), and a gradual change fault trend is captured in combination with slow feature analysis (SFA). And combining a bidirectional LSTM network to predict and reconstruct a residual error and calculate a health threshold, and finally realizing online updating of the model and adaptive adjustment of the health threshold through incremental learning (IL). According to the method, high-precision feature expression of complex vibration signals is realized, and the health state of the saw blade can be adaptively evaluated.

The invention relates to the field of electric power industry, and discloses a digital twinborn GIS partial discharge mode identification method, which comprises the following steps of S1, establishing a high-fidelity digital twinborn simulation model according to a typical structure, operating parameters and potential abnormal working conditions of GIS equipment; s2, in the simulation model, performing accurate modeling on a physical structure which may cause partial discharge, and simulating to generate a simulation data set containing common and rare partial discharge fault scenes; s3, extracting spatio-temporal features and constructing a fault diagnosis model based on spatio-temporal data collaborative learning; s4, combining laboratory GIS equipment and a digital twinborn model under laboratory conditions, refining spatial-temporal characteristics, and enriching a data set by continuously collecting data, so that the model learns more fault types in an incremental learning mode; and S5, integrating the model which is verified to be effective into an actual engineering scene monitoring system, and performing intelligent identification based on continuous fusion of simulation and actual data.

The invention discloses a post-stroke depression risk prediction system based on cerebral small vascular diseases and inflammatory markers, and relates to the technical field of computer-aided engineering, the post-stroke depression risk prediction system comprises: a data acquisition module acquires CSVD image data, serum inflammatory markers and clinical baseline information; the data preprocessing module processes image denoising registration, fills up marker missing values and encodes clinical information; the CSVD feature extraction module extracts image omics features and quantifies severity; the inflammation marker module calculates statistical characteristics and inflammation intensity; the multi-dimensional fusion module integrates features and eliminates redundancy; the risk prediction module is trained by using an improved attention CNN-LSTM model; the result output module visualizes risk and intervention suggestions; the model dynamic optimization module updates parameters by incremental learning. According to the method, multi-source key data are integrated, the prediction accuracy and generalization ability are improved, clinical interpretation and dynamic adaptability are achieved, early recognition of post-stroke depression is assisted, and patient prognosis is improved.

The invention provides a class incremental learning method based on prompt guidance and multi-modal fusion, and relates to the technical field of artificial intelligence and computer vision. The method comprises the following steps: firstly, performing semantic extension on a category label, and constructing semantic enhanced text representation through a text encoder; then block embedding and hierarchical feature extraction are carried out on the input image by using a pre-trained visual encoder, a cross-modal unified embedding space is constructed, a bimodal prompt gating fusion module is introduced into the unified embedding space, and adaptive weighting is carried out on text prompt and image prompt according to gating weight to generate fusion prompt; through a bimodal prompt collaborative filtering module, screening out a prompt set most relevant to the current task according to the similarity of the semantic features of the image and the text; the pre-training backbone network is frozen in the increment stage, only prompt parameters and fusion layer weights are optimized, a joint loss function is used for parameter updating, finally, image and text data are input in the reasoning stage, cross-modal similarity is calculated, and a classification prediction result is output.

The invention relates to the technical field of big data processing, and discloses a data extraction method and system for geological mineral exploration, and the method comprises the steps: carrying out the standardization preprocessing of original data containing space coordinates, lithology texts, mineral components, logging curves and mineralization labels; spatial, semantic, concentration and time sequence deep representations are extracted in parallel through a multi-modal geologic feature encoder and fused into high-dimensional vectors; applying structured sparse constraint to the features by using a graph attention mechanism guided by an expert knowledge graph, and strengthening a mineralization association dimension; a dynamic incremental learning engine is combined with an elastic weight solidification mechanism to realize local fine tuning of model parameters and historical knowledge retention; and finally outputting a mineralization potential score, a mineralization factor sequence and an abnormal element combination. According to the method, through triple mechanisms of multi-modal fusion, knowledge embedding and incremental evolution, the accuracy, interpretability and timeliness of data extraction are improved, and the real-time analysis requirement of large-scale mineral exploration is met.