687 results about "Sequence model" patented technology

The invention relates to the technical field of artificial intelligence and health management, in particular to a health management method and system based on multi-dimensional data analysis, and the method comprises the steps: collecting the physiological, behavior, environment and psychological data of a user, and carrying out the modeling through a recurrent neural network, and generating health state data; extracting a key causal relationship of the health risk based on a causal analysis model of a Bayesian network; comprehensively analyzing health changes through the short-term time sequence model and the long-term trend prediction model, and generating health risk data; a personalized health intervention scheme is designed by using a conditional generative adversarial network, and safe sharing and dynamic management of the scheme are realized through a block chain technology. According to the method, the health risk can be accurately identified, scientific intervention measures can be designed, the health management process is dynamically optimized, powerful technical support is provided for an intelligent old-age nursing scene, and the health management efficiency and effect are improved.

The invention provides a construction scene prediction method and device fusing an image, a text and a BIM modal, and relates to the technical field of intelligent construction prediction management. According to the method, the BIM semantic graph is constructed by extracting the BIM semantic information of the BIM model, and the target detection recognition of the construction site video is carried out in combination with the YOLO model to obtain the target detection result; performing cross-modal alignment with the CLIP to realize deep fusion of the multi-modal data of the image, the text and the BIM to obtain a multi-modal heterogeneous graph; and inputting the multi-modal heterogeneous graph into a space-time sequence model for prediction, outputting prediction results of construction scenes at a plurality of moments in the future, and dynamically mapping the prediction results to a digital twinborn platform to realize risk early warning and visual display. The construction dynamic change can be captured in real time, the construction progress and risk can be accurately predicted, and the intelligent level of construction management is improved.

The invention discloses a fault early warning method and system based on an AI large model, and the method comprises the steps: obtaining multi-source heterogeneous data, and carrying out the denoising and standardization processing, and obtaining fusion data; inputting into a feature extraction model, and outputting a feature vector set; identifying the dynamic operation mode based on a K-means algorithm to obtain an operation mode baseline; inputting a feature sequence model, and outputting a precursor feature sequence; calculating an abnormal score according to the precursor feature sequence, marking as abnormal if the score is greater than or equal to a threshold value, otherwise, marking as normal, and obtaining an abnormal detection result; evaluating a risk level according to a detection result; inputting the risk level into a fault analysis model to obtain fault cause distribution; determining optimized operation mode parameters according to the fault cause distribution; and performing deviation analysis on the data and the optimized parameters, and if a deviation value is greater than a threshold value, triggering an early warning signal. The method can solve the problem of insufficient recognition capability in a scene with variable fault types.

The invention relates to a remote education data processing system which comprises the following steps: under a remote teaching task, pre-defining a task intention and a data expectation point; a semantic timestamp and a task binding label are printed on each data fragment; mapping the collected confusion data including silence, eye movement drift and prediction into a unified learning semantic vector; a micro-expression + interactive behavior + time sequence decision path ternary modeling mode is introduced, and a potential cognitive intention corresponding to the feature combination is recognized; teaching context information is fused; constructing a cognitive state mapping model; reasoning a current cognitive state label from multi-modal sensing data; searching intervention track VS effect feedback data in a historical database; generating a predicted intervention behavior sequence by using a sequence modeling algorithm; a dynamic combination suggestion chain including light prompt, content reconstruction, personalized practice and tutoring invitation is adopted; and superposing the cognitive state sequences of all students into a group cognitive trajectory map.

The invention discloses an intelligent bidding and tendering information identification method, which relates to the technical field of engineering management, and comprises the following steps: standardizing and preprocessing a bidding and tendering information document format; constructing a natural language processing model special for the bidding and tendering field; training a multi-level information extraction model based on deep learning; carrying out cross-document information integration and correlation analysis; performing anomaly detection and verification based on rules; semantic understanding and sentiment analysis; automatic subject matter description and technical specification extraction; a real-time dynamic monitoring and information updating mechanism; the invention discloses a graph-based decision support and recommendation system. According to the intelligent bidding and tendering information identification method, efficient and intelligent identification of bidding and tendering information is realized by constructing a natural language processing model specially aiming at the field of bidding and tendering. The bidirectional coding capability of BERT and the sequence modeling capability of LTM are combined, and a hierarchical attention mechanism is introduced, so that the model can accurately identify various key information in bidding and tendering documents.

The invention discloses an event analysis method, system and device based on task generation and multiple modes, which are used for quickly and accurately mastering the development trend of an event. The method comprises the steps that structured event information is generated through multi-modal data, and an event relation is obtained; constructing an event graph; extracting a multi-modal feature, and obtaining a multi-modal emotion relationship vector by using a cross-modal attention mechanism; based on a preset graph neural network, combining the event graph to obtain an emotion feature vector; calculating a comparative learning loss value, and obtaining a target emotion feature based on the comparative learning loss value; generating a target event atlas by using a cross-modal attention mechanism; extracting relation characteristics, and combining the attention weight and a preset time sequence model to obtain an event prediction map; extracting a causal chain and reasoning, and obtaining a trigger condition and an emotion factor after reasoning; and combining the event prediction map and the target event map with the node feature sequence, the trigger condition and the emotion factor to obtain an event analysis result.

The invention discloses a surveying and mapping geographic information data management method and system based on cloud computing, and relates to the field of geographic information, and the method comprises the steps: constructing a semantic segmentation model based on a convolutional neural network Deep Lab, and carrying out the feature extraction and semantic annotation of a surveying and mapping geographic data set through the semantic segmentation model, and obtaining a geographic element set; performing spatial division and indexing on the geographic element set by adopting an R tree spatial indexing method to obtain a hierarchically organized geographic element tree; constructing a graph neural network model based on a graph convolutional network GCN, and performing topological relation modeling on the geographic element tree by using the graph neural network model to obtain a time-space attribute graph containing geographic semantics and topological relations; and constructing a space-time prediction sequence model based on the space-time diagram neural network STGCN, and performing evolution trend prediction on the space-time attribute diagram by adopting the space-time prediction sequence model. Aiming at the problem that dynamic prediction of geographic elements is difficult to realize in the prior art, the spatial-temporal evolution trend of the geographic elements is predicted, and dynamic prediction is realized.

The invention relates to the technical field of artificial intelligence, in particular to an AI intelligent customer obtaining processing method and system, and the method comprises the following steps: collecting interaction data of a user and a platform, summarizing click, browsing duration and frequency information, extracting a user activity mode through an RNN and an LSTM network, analyzing the interest and behavior mode of the user, and generating a user behavior feature library. According to the method, the client acquisition process is optimized through data analysis and behavior prediction, the method does not depend on a traditional marketing means, user data are accurately analyzed through a sequence model, deep understanding of user behaviors is achieved, the accuracy of market segmentation is improved through refined analysis, it is ensured that marketing activities are matched with a target client group, and the marketing efficiency is improved. According to the method, the conversion rate is remarkably improved, the marketing means can be rapidly adjusted by means of intention recognition and real-time data analysis, synchronization with user requirements is ensured, the customer extension cost of the entity store is reduced by continuously integrating customer feedback and marketing data, and the problem that an entity store operator is difficult to obtain customers is solved.

The invention discloses a welded pipe conveying abnormity prediction method and system based on large model reasoning, and aims to solve the problems that multi-source data is difficult to align, cross-station false correlation is caused, prediction lacks executable positioning and time sequence, and linkage control reliability is insufficient. Event alignment is carried out by taking a controller edge signal and an encoder zero position as time anchor points, a production line topology semantic graph containing time delay, capacity and interlocking attributes is constructed, and topology reachability and physical time delay constraints are applied in a self-attention long sequence model to carry out multi-step rolling prediction. And outputting a risk probability, refining the risk probability to spatial positioning of a roller way section or a shaft and the minimum executable intervention time, and generating a risk interval in combination with uncertainty estimation and calibration so as to drive an upstream beat self-adaptive speed reduction, shunting or stopping strategy. The technical effects of improving accuracy and interpretability, reducing false alarm and missing alarm, ensuring that linkage can be executed in advance and meeting edge time delay budget are achieved.

The invention relates to the technical field of e-commerce, in particular to an e-commerce promotion method and system based on cloud computing, and the method comprises the following steps: building a user behavior sequence through log collection, extracting a sudden change point through dynamic time warping, generating a dynamic parameter through segmented integral, calculating a difference degree through gray correlation analysis, and reconstructing a weight set. And flexibly scheduling advertisement resource distribution, and generating a delivery instruction. According to the method, user click stream data is collected, a behavior sequence model is constructed, continuous dynamic characteristics of user browsing tracks are captured, time sequence relevance is analyzed, fluctuation peak points of user behavior paths are aligned, interest mutation nodes are captured, abnormal behavior modes are recognized, and implicit preferences and explicit feedback parameters in the interaction process are quantified. Establishing an associated feature analysis mechanism, resetting advertisement weight parameters, matching real-time requirements of users with putting strategies, mapping weights to distributed advertisement nodes, dynamically scheduling computing resources, adapting display requirements and resource allocation, and forming a closed-loop optimization link.

The invention discloses a composite structure damage form monitoring method and system based on deep learning, and the method comprises the following steps: collecting multi-source monitoring data of a composite structure in a loaded state, and carrying out the preprocessing; reconstructing a damage evolution trajectory in a high-dimensional phase space by adopting a delay coordinate embedding method, and executing dimension reduction to generate a chaotic dynamics low-dimensional trajectory; extracting singular attractor features, and generating a singular attractor feature set; carrying out sequence modeling through an improved Linformer damage identification network, and generating a prediction vector; training an improved Linformer damage identification network based on the prediction vector, and introducing nonlinear dynamic constraints to generate a damage identification network of the nonlinear dynamic constraints; and performing damage form classification and damage evolution prediction. According to the method, dynamics and deep learning are fused, composite structure damage monitoring is achieved, and the method has the advantages of being high in accuracy, high in stability and reliable in early warning.

The invention relates to the technical field of electric power engineering purchase demand prediction, in particular to an electric power engineering purchase demand prediction system based on machine learning, and the system comprises the steps: obtaining historical purchase data, construction progress information and electric power engineering design parameters, carrying out the standard stage division and time alignment, and constructing a stage sequence model reflecting the material use rhythm; and a coupling factor matrix is generated based on the material co-occurrence frequency and the stage position relationship, and the modeling capability of the model for the material cooperation relationship is enhanced. And the stage time sequence features, the coupling information and the structured engineering parameter vectors are fused and input into a regression prediction model, so that accurate mapping of material demands and multi-dimensional engineering features is realized, and the purchase prediction precision in a target period is improved. A deviation sequence is constructed based on historical prediction errors, and error correction is performed through a feedforward neural network, so that prediction accuracy and response capability are effectively improved, and resource waste and construction delay are reduced.

A process assessment platform for automatic query calibration in sequenced models can be used to generate system actions in management of process deployments. System actions can be generated by using a set of input data from one or more process management systems that define a workflow. The input data can include a set of observed task board information item properties for a particular structured process of the workflow. Using the set of input data, a first AI model can dynamically identify a set of actions from the structured process to be executed. Using the identified set of actions, a second AI model can dynamically classify particular dimensions of the set of task board information items and determine a degree of completion therefor.

The invention relates to the technical field of artificial intelligence, in particular to a charging pile construction planning method and system based on artificial intelligence. The method comprises the following steps: acquiring existing power infrastructure data and multi-source heterogeneous data, wherein the multi-source heterogeneous data comprises traffic data, geographic data, vehicle data and charging behavior data; performing time sequence feature extraction on the multi-source heterogeneous data, and performing cross-time scale fusion on different data source features by using a preset hierarchical attention network model to obtain factor weight data; and constructing a long-term charging demand prediction model through a sequence-to-sequence model according to the factor weight data and the multi-source heterogeneous data. According to the site selection method based on the risk minimum set coverage problem, initial site selection scheme data is generated by combining multi-objective optimization of the coverage rate, the service radius and the accessibility, and more scientific charging pile layout is achieved.

The invention discloses a water-cooling central air conditioner load management and control method based on artificial intelligence, and relates to the technical field of load management and control. Load prediction is carried out by combining a long and short-term memory time sequence model and a physical constraint neural network in a water chilling unit load prediction link and utilizing historical data; errors are corrected through an energy balance equation of the water chilling unit, and the prediction accuracy is improved; multi-objective optimization control is adopted, COP maximization of a water chilling unit, energy consumption minimization of a cooling tower fan and cooling water supply temperature stability serve as optimization objectives, environment temperature and humidity prediction is combined, and a cooling water supply temperature set point and a cooling tower fan start-stop strategy are dynamically calculated; based on a cooling water supply temperature set point and a fan start-stop strategy, a water chilling unit, a cooling tower fan and a water pump are dynamically adjusted, and the high-frequency operation phenomenon is reduced through fan start-stop optimization.

The invention discloses a high-voltage power distribution cabinet heat dissipation system based on big data, which relates to the technical field of heat dissipation of electrical equipment and comprises a data acquisition module, a processing analysis module, a man-machine interaction module and a data storage module. An existing heat dissipation mode usually depends on a static fan or air conditioning equipment, dynamic adjustment cannot be carried out according to environment changes and load conditions, and the problems of high energy consumption and slow response exist. The system processes data, eliminates abnormal values, fills missing data, calculates correlation among temperature, humidity, current and fan rotating speed, predicts change trends of the temperature, the humidity and the current through a time sequence model, and displays key data through a graphical interface by a man-machine interaction module, so that the equipment management efficiency is improved; and precious historical data is provided for subsequent fault analysis and tracking, so that optimization of a maintenance strategy of the system and reduction of potential operation risks are facilitated.

The invention relates to a lithium battery SOC estimation method based on a multi-scale physical information neural network, and belongs to the technical field of battery SOC estimation. The method comprises the steps that S1, a first-order RC equivalent circuit model is adopted to describe the dynamic characteristics of a battery, and electrical parameters in the first-order RC equivalent circuit model serve as Mama model output and serve as physical knowledge; s2, performing multi-scale fusion on the voltage features, the current features, the time features and the edge features to obtain new features, and taking the new features as input of a Mama model; s3, constructing a Mama model, wherein the Mama model comprises SSM, a convolutional layer, a linear layer and an element operator; the SSM represents a selective state space model and is formed by combining a structured state space sequence model with a selection mechanism and a scanning module; and S4, estimating the SOC of the lithium battery by using a Mamba model, and improving the model training efficiency by adopting an SPKF adaptive weight. According to the invention, the accuracy and reliability of SOC prediction are improved.

The invention provides a mediation document generation method and system, relates to the technical field of data processing, and comprises the step of forming structured case data through text preprocessing, named entity recognition and legal information association based on case text data and legal corpus information. Then, generating a preliminary mediation document with placeholders by utilizing case classification, semantic matching and a sequence-to-sequence model; after standard auditing and logic auditing are carried out on the documents, optimization is carried out based on reinforcement learning, language style migration and a text generative adversarial network, and the structural rationality, law term normativity and semantic integrity are improved. And finally, a mediator preference template is constructed through Few-shot Learning and meta learning, the format and language style of the document are adjusted in a personalized manner, and a mediation document conforming to the habits of a mediator is generated. According to the method, the intelligence and the accuracy of mediation document generation are improved, the law compliance and the logic preciseness are ensured, and the mediation working efficiency is improved.

The invention discloses a mine slope risk prediction method based on multi-modal deep learning, and relates to the technical field of mine slope risk prediction, and the method comprises the steps: Stepl: inputting multi-modal data, Step2: preprocessing effectiveness data, Step3: constructing a sample set, and Step4: realizing mine slope stability prediction based on a gating cycle unit GRU of a mutual information mechanism. According to the invention, a multi-modal data integration GRU network is adopted to carry out sequence modeling on fused data, more complex sequence features are extracted, slope safety event prediction analysis is completed, high-precision monitoring of a mine slope is realized, and the accuracy and comprehensiveness of a prediction result are improved; according to the method, the mutual information mechanism is applied to the GRU network to maximize the mutual information between the sample and the feature, the dependency between the feature and the label is improved, the prediction capability is guaranteed, and the generalization capability on new data is also guaranteed.

The invention discloses an airport hub construction intelligent regulation and control method and system based on BIM + 5G, and relates to the technical field of construction scheduling optimization, and the method comprises the steps: collecting on-site real-time data to construct a path construction sequence model, constructing a dynamic construction state set with consistent space and time sequence through component coding and semantic attribute mapping, and constructing a dynamic construction state set with consistent time sequence; and constructing a minimum disturbance optimization algorithm of four-dimensional disturbance cost based on the construction disturbance mapping graph, outputting procedure sequence adjustment, resource rearrangement, path decoupling and environment avoidance intervention suggestions, and tracking a construction response state in real time based on an intervention execution feedback mechanism. According to the method, unified modeling of construction plans, resource allocation and green indexes is achieved by constructing a ternary structure and a construction disturbance mapping graph, the field state is dynamically collected in combination with a 5G and edge sensing system, process abnormity and resource conflicts are accurately recognized, an efficient and executable regulation and control strategy is generated based on a multi-target disturbance optimization algorithm, and the efficiency and the reliability of the system are improved. And the intelligence, responsiveness and energy-saving level of the construction process are obviously improved.

The invention provides an intelligent customer service dynamic intention recognition system based on a semantic analysis model, and the system collects the multi-dimensional data of a user through a data collection module, constructs a user portrait through a feature extraction module, extracts the portrait features, carries out the semantic analysis of multiple rounds of historical dialogue data, and extracts preference features. And constructing a dynamic user-entity association graph to extract GNN node features. Multi-modal data of a user is analyzed through an emotion recognition module, emotion features are recognized, portrait features, preference features and emotion features are fused and analyzed based on an MLP model to obtain a final emotion state, and the portrait features, the preference features, GNN node features and the emotion features are fused through an intention recognition module to obtain a final emotion state. According to the method, dynamic intention analysis is carried out on the basis of the Transform sequence-to-sequence model, the current intention of the user is recognized, the recognition accuracy is high, the dynamically changing intention is adjusted in real time, and more accurate and targeted answers or services are provided for the user.

The invention discloses a railway bogie bearing fault diagnosis method and equipment based on a feature extraction network, and relates to the field of intelligent diagnosis and maintenance guarantee of urban rail trains. The method comprises the following steps: data acquisition: acquiring vibration signals of a bogie axle box bearing under the same rotation speed and load combination; performing data preprocessing: performing frequency spectrum adaptive decomposition on each section of signal based on improved empirical wavelet transform, introducing a Fisher score and frequency spectrum entropy joint scoring mechanism, screening out key modal signals, and then performing image mapping to reconstruct a diagnosis sequence; model construction: introducing a topology perception attention mechanism module on the basis of the lightweight convolutional neural network, and constructing a fault diagnosis model; model training: training the fault diagnosis model to obtain an optimized fault diagnosis model; and diagnosis result output: using the optimized fault diagnosis model to diagnose the fault signal of the bogie axle box bearing, and outputting the diagnosis result. The method can improve the accuracy of fault diagnosis.

The invention discloses an integrated airport foreign object detection system and method, and the system comprises a multi-source data collection module which is combined with a self-adaptive triggering mechanism, and dynamically adjusts the working mode of a sensor according to a flight timetable and meteorological data; the edge calculation processing module is used for extracting a foreign object candidate region by adopting a multi-modal data fusion technology, carrying out confidence coefficient weighted decision based on a D-S evidence theory and outputting accurate position and size information of a foreign object; the automatic submission module is used for establishing a grading alarm mechanism, pushing high-risk foreign objects to a control tower terminal in real time through a 5G / wireless private network, and synchronously generating an encrypted standardized report; and the intelligent analysis platform predicts a foreign object high-incidence area by using an LSTM time sequence model, traces foreign object causes in combination with a knowledge graph technology, and provides management decision support through a visual interface. According to the invention, full-process optimization is realized through a closed-loop architecture of multi-source data acquisition, edge calculation processing, automatic submission and intelligent analysis.

The invention discloses an island shoreline identification method and system based on artificial intelligence, and relates to the technical field of shoreline change monitoring. According to the invention, through fusion modeling of the optical image, the SAR image and the topographic data, the limitation of a single data source is broken through; a vegetation coverage area and a non-vegetation shoreline can be accurately distinguished through the multispectral characteristics of the optical image, and the problem of monitoring blind areas in scenes such as cloud and mist and nighttime is solved through the all-weather penetrating power of the SAR image; a random forest classifier can effectively distinguish bedrock steep cliff, sandy sand beach and the like in combination with superpixel unit feature vectors constructed by topographic data, and accurate partitioning of a target island shoreline is completed; moreover, a dynamic global correction mechanism further eliminates space-time error accumulation, a standard deviation mean value is calculated through cross-season historical data, accidental errors such as typhoon and rainstorm are filtered, a future global correction coefficient is predicted in combination with a time sequence model, and the reliability of long-term monitoring is remarkably improved.

The invention provides an industrial equipment residual service life prediction method based on a DMM-JA model, and relates to the technical field of industrial equipment predictive maintenance, and the DMM-JA model comprises a dynamic bimodal fusion and multi-scale feature extraction module DBF-MSFEModule, an LSTM-Mama mixed sequence modeling module, a jump perception attention module and an output layer. The method comprises the following steps: preprocessing bimodal sensing data of industrial equipment; the preprocessed bimodal sensing data is processed through a dynamic bimodal fusion and multi-scale feature extraction module DBF-MSFEModule, and multi-scale fusion features are obtained; the multi-scale fusion features are input into an LSTM-Mamba mixed sequence modeling module, and joint time sequence features are obtained; the joint time sequence features are corrected through a jump perception attention module, and robustness features are obtained; and inputting the robustness characteristics into an output layer to obtain an RUL prediction result of the industrial equipment. Key features in the equipment degradation process can be accurately captured, and the accuracy of residual service life prediction is improved.

The invention relates to the field of automatic crane control, in particular to a gantry crane remote control platform access system and method, and the system comprises a task prediction module, a task distribution module, a task execution module and an exception handling module. The task prediction module generates task prediction data by collecting the task pool and the equipment state data; the task allocation module dynamically generates a task allocation scheme by using a reinforcement learning optimization algorithm and a simulated annealing algorithm; the task execution module generates control path data through real-time data acquisition and multi-modal data fusion, and controls equipment to execute tasks; and the exception handling module predicts a fault through a time sequence model and implements a task relay and dynamic recovery mechanism. According to the method, the efficiency of task scheduling, the precision of a control path and the stability of system operation are improved, and the execution efficiency of a remote control task is remarkably improved.

The invention relates to the technical field of monitoring behavior analysis, and discloses an intelligent behavior analysis system and method for a monitoring camera. The system obtains video stream data through a video data acquisition module, extracts a video frame sequence and a timestamp, identifies a moving target and a position coordinate, associates behavior segments and calculates an active value, and generates a target behavior active set; a behavior sequence modeling module extracts active values and coordinates, sorts adjacent behavior segments and marks consistent and conflict sections to obtain a behavior consistency partition marking set; the environment mapping module obtains consistent section target behaviors, extracts illumination and shielding time sequences, evaluates the influence intensity of environment interference on the behaviors in combination with behavior types, and generates an overlay analysis result; the exception screening module recognizes exceptional points with response values larger than the average reference value and located in the conflict section, and a behavior exceptional point set is formed; and the risk output module obtains abnormal point information, marks diffusion risk point locations, and generates behavior detection and risk early warning results.

The embodiment of the invention discloses a traffic state prediction method based on multi-modal data and adaptive topology modeling. The method comprises the following steps: dynamically determining an adjacent matrix between roads according to the type and historical traffic flow of each road, and respectively inputting a GCN model and a GAT model according to an adjacent matrix dynamic traffic network diagram; extracting global spatial features by the GCN model according to the weight of each edge and the current feature representation of each node; strengthening the effect of a key node by the GAT model to obtain a local attention space feature; performing short-time timing sequence modeling and long-time timing sequence modeling on the time sequence of the multi-modal traffic data of each node in the latest period of time to obtain a short-time feature and a long-time feature respectively; and predicting a future traffic state according to the global spatial features, the local attention spatial features, the short-time features and the long-time features. According to the embodiment, the traffic state prediction accuracy is improved.

The invention relates to an event-based lip reading method and device, equipment and a storage medium. The method comprises the following steps: collecting an original event stream of a lip sequence image through an event camera; therefore, the brightness change of each pixel can be asynchronously recorded with microsecond-level time resolution, and ultra-low delay, high dynamic range and sparse data representation are realized. Converting the original event stream into a frame-shaped event tensor based on a voxel representation method to obtain a voxelized event body; performing spatial feature extraction on the voxelized event body through a front-end network in an event-based lip reading model to obtain multi-scale spatial features; performing time-dependent modeling on the multi-scale spatial features through a rear-end sequence model in an event-based lip reading model to obtain a sequence code; therefore, space and time features can be fused, and the accuracy and stability of sequence coding are improved. And determining the lip reading recognition content according to the sequence code. Therefore, stable recognition of lip movement can be realized, and lip reading accuracy is improved.

The invention discloses a multi-source heterogeneous engineering monitoring data fusion method based on deep learning, and relates to the technical field of engineering monitoring and artificial intelligence crossing. Collecting multi-source heterogeneous time series data; inputting the multi-source heterogeneous time sequence data into a dynamic space-time alignment module, performing time sequence alignment to obtain alignment data, and extracting time sequence characteristics of the alignment data through a sequence-to-sequence model; constructing a sensor topological graph through an adjacent matrix based on the sensor data, determining node features of the multi-source heterogeneous time series data through a statistical feature method, and inputting the sensor topological graph and the node features into a graph convolutional network for processing to obtain spatial features; inputting the structural crack image sequence data into the residual convolutional network to extract visual semantic features; and dynamically fusing the time sequence features, the spatial features and the visual semantic features through a space-time cross attention mechanism to obtain fused features. According to the method, the compatibility of engineering monitoring data fusion can be improved.