895 results about "Time series modeling" patented technology

The invention discloses a Transform-based cross-modal fusion multi-modal emotion recognition method and device, which are used for solving the problems of modal isomerism, difficulty in time alignment and insufficient dynamic emotion modeling in a multi-modal emotion recognition task, and the method takes the accuracy and robustness of emotion recognition as performance evaluation indexes. Firstly, feature information of three modes of vision, voice and text is obtained, feature extraction is performed on each mode through a deep learning model, then features of different modes are fused by using a cross-mode Transform module, and a complex dependency relationship between the modes is dynamically modeled through a multi-head self-attention mechanism, so that more accurate emotion recognition is realized, and the emotion recognition efficiency is improved. And finally, performing emotion prediction on the fused features based on time sequence modeling and an emotion classification module. According to the method, the problems of modal isomerism, difficulty in time alignment and insufficient dynamic emotion modeling in multi-modal emotion recognition can be effectively solved.

The invention discloses an informatization project management system based on big data analysis, which belongs to the field of big data and comprises a data acquisition module, a time sequence modeling module, a task coupling analysis module, a risk clustering identification module, a resource allocation prediction module and the like. The data acquisition module asynchronously and parallelly acquires structured and unstructured data and uniformly encodes the structured and unstructured data; the time sequence modeling module constructs a multi-dimensional time sequence based on an autoregressive residual network; the task coupling analysis module fuses the task trajectory and the dependency relationship to generate a task influence directed graph; the risk clustering identification module identifies risks through variational graph auto-encoder mapping; the resource allocation prediction module constructs a dynamic resource priority based on a graph attention mechanism; a progress deviation traceability module identifies a deviation causal chain; the knowledge graph decision-making module corrects resource priorities and path strategies in a cross-graph manner; and the project global control module dynamically adjusts key paths and resource configuration and performs closed-loop self-correction. The beneficial effect is that the intelligent level and the risk response capability of project management are improved.

The invention discloses a deep learning-based small target defect recognition model training method, relates to the technical field of defect recognition model training, and aims at meeting small defect detection requirements, starting with high-resolution diversified data construction and accurate labeling, highlighting weak targets through multi-scale feature fusion and spatial attention, and realizing high-resolution target defect recognition. A hard case scene is processed in cooperation with layer-by-layer screening and secondary intensified training, real-time iterative optimization is achieved through multi-model fusion and online dynamic adjustment and optimization, finally, multi-mode and time sequence dimensions are expanded to capture deeper and dynamic defect information, the missing detection and false detection rate is greatly reduced, and the detection efficiency is improved. The detection efficiency and adaptability of micron-sized defects under a complex process background are improved; furthermore, by means of multi-source data such as infrared, X-ray or 3D morphology and a time sequence modeling means, multiple dimensions are fused, and hidden or early cracks are brought into a detection and prediction range, so that a high-reliability and evolvable intelligent recognition system for the tiny target defects is constructed.

The invention discloses a fusion optimization method based on Kalman filtering and LSTM cascade. The fusion optimization method comprises three steps of dynamic state estimation, time sequence error modeling and closed-loop fusion optimization. IMU (Inertial Measurement Unit) data is used as input, dynamic state estimation is realized through Kalman filtering, modeling system errors are separated, an LSTM (Long Short Term Memory) network is used for carrying out time sequence modeling on a residual error sequence to capture nonlinear errors, and finally, a corrected state quantity is fed back to a Kalman filtering updating link through a closed-loop feedback mechanism. And collaborative optimization of error compensation and state estimation is realized. According to the method, IMU error accumulation is effectively inhibited through a dynamic-data dual-drive mechanism, the navigation precision and robustness in a complex scene are remarkably improved, and the requirements of high-dynamic applications such as intelligent driving and unmanned aerial vehicle navigation can be met. Finally, the optimized IMU data and the GNSS observation value are fused for integrated navigation, high-precision navigation solution is achieved through Kalman filtering, and indoor and outdoor seamless positioning and the all-attitude control requirement of a high-dynamic carrier are met.

The invention discloses a water supply pipe network water hammer control method and system based on multifunctional module fusion, and relates to the technical field of data identification. A time sequence diagram neural network prediction and traceability module which realizes water hammer risk prediction and propagation path traceability based on a causal constraint graph neural network model; the reinforcement learning intervention decision module is used for generating an active intervention strategy through a reinforcement learning agent, forming closed-loop control, abstracting a water supply pipe network into a graph structure, and modeling in combination with a time sequence, so that a propagation path of pressure waves can be comprehensively reflected, a blind area of traditional local modeling is overcome, and the comprehensiveness and accuracy of water hammer event detection are improved; and a causal analysis result is input as an adjacent matrix, so that the interference of irrelevant edges on prediction in topology is effectively eliminated, and the learning efficiency and causal traceability of the model are improved.

The invention relates to a higher education personalized hierarchical teaching method and system based on artificial intelligence, and the method comprises the steps: obtaining multi-dimensional learning data, carrying out the time-space alignment processing, and generating a synchronous multi-dimensional data set; performing spatial-temporal feature fusion and time sequence modeling on the data set by using a deep neural network, and constructing a dynamic student portrait; analyzing knowledge mastery degree features in the portrait through a semantic analysis model, and generating a personalized resource recommendation sequence in combination with the knowledge graph; based on the sequence and the portrait, planning a personalized learning path by using a path reasoning algorithm; and carrying out teaching hierarchy binding on the personalized resource recommendation sequence and the learning path to form a hierarchical teaching scheme. Accurate teaching support is provided for individual differences of students, and the teaching effect and learning experience are effectively improved.

The invention relates to the field of industrial robots, and discloses an industrial robot real-time maintenance system and method in combination with edge computing, and the method comprises the steps: obtaining the multi-source operation state data of an industrial robot, and constructing an operation feature data set of key parts of the robot in combination with a state coding mechanism of an edge end and a feature coupling analysis method; carrying out rapid distributed processing on the operation characteristic data set, constructing an equipment health state model based on a lightweight time sequence modeling algorithm, and introducing a multi-dimensional correlation analysis mechanism to carry out incremental learning on the model; judging whether the edge side state recognition result is stable or not based on the change trend of the trigger frequency; according to the corrected state mapping relation, performing response level division on the potential fault trend by applying a multi-scale fault prediction mechanism, and extracting matched maintenance plan parameters; and based on the maintenance scheduling plan, in combination with a preset fault handling knowledge base, performing automatic evaluation and optimization on the current maintenance strategy. The method has the advantage of improving the response speed.

The invention discloses a safety monitoring system of a liquid cooling over-charging pile, and relates to the technical field of over-charging pile monitoring, the system comprises a data acquisition module, a data processing and analysis module, a dynamic model construction module, a temperature prediction module and a safety early warning module; according to the method, the dynamic model is constructed through the long short-term memory network LSTM, the complex nonlinear relation and the time sequence dependence of the multi-dimensional data are mined by using the gating mechanism of the dynamic model, the accurate characterization of the operation state of the liquid cooling over-charging pile is realized, the actual operation state of the equipment can be accurately described, the temperature data time sequence modeling is performed through the LSTM, and the accuracy of the temperature data time sequence modeling is improved. Parameters such as multi-source temperature and cooling liquid flow are fused, real-time prediction of the temperature change trend is achieved, the defect that a traditional algorithm is insufficient in temperature time sequence dependence capture is overcome, temperature abnormity can be recognized in advance, a safety threshold value is dynamically adjusted through a fuzzy logic algorithm, and self-adaptive threshold value adjustment is achieved in combination with parameters such as charging power. The problem that a traditional fixed threshold value is poor in adaptability is solved, and the early warning accuracy is improved.

The invention discloses a multi-level feature fusion and time sequence modeling combined lithium battery life prediction method, and relates to the technical field of lithium ion battery health management and life prediction. The method comprises the steps of receiving time sequence observation data in a battery operation process, inputting the time sequence observation data into a pre-constructed local feature extraction model, and introducing a one-dimensional convolutional neural network into the local feature extraction model to perform feature extraction on the time sequence observation data to obtain local feature representation. According to the method, three structures of local feature extraction, global context modeling and bidirectional time sequence modeling are fused, and the battery degradation modeling capability and prediction precision are effectively improved. The TFN adopts an end-to-end architecture design, has good feature perception capability and time-dependent modeling capability, and can adapt to various degradation modes and complex time sequence environments. The method is suitable for life evaluation and health state monitoring in an intelligent battery management system, and has relatively high practical value and popularization prospect.

The invention provides a dam intelligent early warning method and system based on a depth time sequence attention network, and the method comprises the steps: carrying out the time alignment and sliding window segmentation of environment variables and historical displacement data of dam monitoring, extracting multi-scale statistical features, fusing the multi-scale statistical features with original features, carrying out the unified normalization processing of a spliced high-dimensional vector, and carrying out the calculation of the unified normalization processing; model input is generated; based on the constructed DSA-Net, carrying out local feature extraction, bidirectional time sequence modeling and key moment weighting on an input sequence, and jointly outputting horizontal and vertical displacement predicted values; fusing double deformation prediction results into a unified radial deformation index, and dynamically setting an early warning threshold value band according to a historical residual error to realize self-adaptive deformation early warning; quantitative evaluation is carried out on the model prediction precision, online prediction and threshold determination of real-time observation data are realized by using the qualified model and an adaptive threshold mechanism, abnormal early warning is triggered, and alarm information is recorded. According to the invention, deep coupling of deformation dimensions and dynamic threshold early warning are realized.

The invention relates to the technical field of automatic driving, and discloses an automatic driving lane changing trajectory planning method based on deep learning, and the method comprises the steps: carrying out the data collection and preprocessing of a multi-modal sensor; performing spatial feature extraction and time sequence modeling on the preprocessed multi-modal data by adopting a CNN-LSTM hybrid architecture, performing feature fusion through an attention mechanism, and outputting a first feature extraction vector; taking the detected vehicles as graph nodes to construct a traffic graph, learning an interaction relationship between the vehicles through a graph attention network and a message passing mechanism, and calculating a scene urgency score and a safety score; generating a lane changing decision based on the deep Q network and the strategy gradient; and generating a trajectory based on the generative adversarial network. The technical problems that an existing lane changing track planning method cannot adapt to the dynamic traffic environment, lacks the ability of understanding complex multi-vehicle interaction and is difficult to balance safety and urgent conflict requirements are solved, and intelligent, safe and efficient automatic driving lane changing track planning is achieved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a time series data processing method, device and equipment and a medium. Performing a data enhancement operation on the original time series data to generate enhanced time series data; training a feature encoder based on the enhanced time sequence data in a comparative learning mode to obtain a pre-trained feature encoder; connecting the pre-training feature encoder with a sparse attention mechanism module to construct a time sequence modeling network; target time series data is processed using the time series modeling network to generate a processing result. According to the method, the enhanced view is constructed on the unlabeled data and the contrast learning training feature encoder is introduced, so that the time sequence representation with generalization ability is obtained, effective modeling of the long dependency relationship is realized in combination with a sparse attention mechanism, and the accuracy of time sequence modeling is improved under the condition of not depending on a large amount of labeled data.

The invention discloses a double-flow time convolution enhanced interactive bearing life prediction method, which comprises the following steps of: acquiring original bearing vibration signal data, and processing and reconstructing the data; constructing a time flow feature extraction module by fusing the local time sequence modeling capability of the TCN and the multi-scale expansion attention, dynamically adjusting the expansion rate through the spectrum entropy, and capturing multi-scale local features by combining sparse multi-head attention; a spatial stream feature extraction module is constructed by fusing frequency sensing position coding and a layered sparse attention mechanism; designing a bidirectional cross-layer attention collaboration mechanism, performing feature interaction on the time flow feature extraction module and the spatial flow feature extraction module, enhancing the degradation characterization capability through hierarchical feature alignment and dynamic weight adjustment, and constructing a double-flow feature extraction layer; inputting the reconstructed signal into a double-flow feature extraction layer to extract features; inputting the extracted features into a multi-layer sensor to carry out RUL prediction; local-global feature complementation is realized; and prediction stability is improved.

The invention discloses a hybrid expert and KAN-based cyclic attention network time sequence prediction method. The method comprises the following steps: S100, inputting time sequence data needing to be predicted; s200, constructing a graph structure by using an attention mechanism, learning basic correlation characteristics among variables of the input time sequence data through an adaptive and learnable graph convolutional network, and then performing global averaging and maximum pooling on the basic correlation characteristics along a time dimension to obtain complementary time domain statistical information, so as to provide effective time-space correlation characteristics for the follow-up process; s300, after feature learning is completed, collaborative modeling of the KAN and an attention mechanism is brought into full play, rapid and efficient time sequence modeling is carried out on data by adopting a cyclic attention network embedded based on the KAN, and a foundation is laid for subsequent time sequence prediction; and S400, establishing a hybrid KAN expert-based time sequence prediction network, and adaptively fusing differentiation prediction results by a gating mechanism. The time sequence prediction method is designed from the three aspects of feature learning, time sequence modeling and time sequence prediction.

The invention relates to the technical field of power grid operation and maintenance, and discloses an AI-based reactive compensation optimization method and system, and the method comprises the following steps: integrating the four-dimensional characteristics of traffic flow, power grid load, user preference and equipment health degree, constructing a space-time correlation graph model, achieving the adaptive evolution of a topological structure through dynamic graph convolution and an attention mechanism, and obtaining a reactive compensation optimization model. The method comprises the following steps: fusing spatial-temporal features of a graph neural network with a BiGRU time sequence for modeling, injecting an equipment health degree attenuation factor, generating a charging demand prediction result with uncertainty quantification, expanding an intelligent agent state space, improving a reward function, and embedding equipment health degree constraints in a strategy network and near-end optimization. By sensing the degradation state of the equipment in real time and intelligently adjusting the reactive compensation strategy, the service life of the old equipment is prolonged while the voltage stability is guaranteed, the deviation accumulation effect is effectively inhibited through feedforward-feedback composite control and dynamic rescheduling, and accurate matching of a scheduling instruction and actual output is ensured.

The invention discloses a water quality time sequence prediction method of an SSA-VMD-LSTM-XGBoost hybrid model, and belongs to the technical field of water quality monitoring and prediction. Comprising the following steps: (1) data preparation and preprocessing; (2) optimizing the water quality time sequence decomposition of the VMD based on SSA: optimizing a penalty factor and a modal number of the VMD by adopting a sparrow search algorithm (SSA), and decomposing the water quality time sequence into a plurality of sub-components with high stability and low complexity by utilizing the optimized VMD; (3) construction and training of an LSTM-XGBoost hybrid prediction model: constructing a hybrid prediction model fusing long-short term memory (LSTM) and extreme gradient boost (XGBoost), inputting a high-frequency component into the LSTM model, inputting a low-frequency component into the XGBoost model, and finally performing superposition and integration on prediction results of the models; and (4) multi-component prediction result integration and performance verification. According to the method, adaptive optimization of VMD parameters is realized through SSA, the feature extraction and time sequence modeling capability is improved by combining the advantages of LSTM and XGBoost, and the prediction precision and stability of the water quality time sequence are effectively improved.

The invention relates to the technical field of people flow prediction, and discloses an urban people flow prediction method based on an urban point-of-interest spatio-temporal data set, which comprises the following steps: acquiring the urban point-of-interest spatio-temporal data set; performing multi-modal feature dynamic fusion by adopting a hierarchical perception attention fusion mechanism to obtain a point-of-interest feature vector; performing spherical spatial dependency modeling by adopting a regional adaptive spherical convolutional coding method to obtain a spatial coding vector; using a periodic mask generator to carry out business time constraint coding to obtain a time feature vector; and according to the interest point feature vector, the space coding vector and the time feature vector, space-time coupling features are extracted, regional perception time sequence modeling is performed on the space-time coupling features, and a people flow prediction value and crowding degree grade probability distribution are generated through multi-task sharing prediction. According to the urban people flow prediction method based on the urban interest point spatio-temporal data set, the urban people flow prediction performance is improved.

The invention relates to the field of recommendation systems, and particularly discloses a personalized recommendation method based on multi-modal behavior sequence modeling, which comprises the following steps of: acquiring multi-modal behavior data such as user text, image, time and place, preprocessing, and realizing dynamic fusion of the data by utilizing a multi-modal self-attention mechanism (MMSA) to obtain a multi-modal behavior sequence model; and the interest evolution of the user is accurately captured. An independent RNN module is adopted to model long-term and short-term interests of a user, and the long-term and short-term interests are combined through a self-learning weight coefficient, so that the change of the user interests is reflected more accurately. In addition, by introducing an online learning and incremental learning mechanism, model parameters are dynamically adjusted according to real-time feedback of the user, and it is ensured that a recommendation result can respond to user interest changes in time. According to the method, the defects of an existing recommendation system in the aspects of data fusion, time sequence modeling and real-time adaptability are effectively overcome, recommendation individuation and accuracy are improved, and the real-time updating capacity and scene adaptability of the system are enhanced.

The invention belongs to the technical field of geographic information data processing, and discloses a graph attention-based road slope surface displacement time sequence prediction method, which comprises the following steps of: obtaining surface displacement time sequence data of a plurality of monitoring stations and associated environmental influence data, and constructing a weighted adjacency matrix based on geographic positions of the monitoring stations, defining an initial spatial topological relation; carrying out feature fusion on the displacement data and the environment data, and constructing an attribute-enhanced feature matrix; respectively inputting the weighted adjacency matrix and the feature matrix into a graph convolutional network and a graph attention network for parallel processing; extracting structured spatial features by the GCN through a fixed topological structure, and generating a first feature representation; the GAT adaptively allocates a dynamic weight by using an attention mechanism, extracts a non-uniform spatial dependency feature, and generates a second feature representation; and fusing the two feature representations, inputting a time sequence modeling module to analyze time dependence, and finally outputting a surface displacement prediction result at a future moment. According to the method, the accuracy of surface displacement prediction is remarkably improved.

The invention provides an industrial fault feature adaptive extraction and multi-mode detection system and method, and belongs to the technical field of industrial fault detection. Comprising the steps of collecting multi-source data of industrial equipment, performing timestamp alignment and processing on the multi-source data to obtain a standardized feature sequence, inputting the standardized feature sequence into a dynamic convolutional neural network, extracting signal local features through a deformable convolution kernel, calculating feature weights in combination with a self-attention mechanism, and screening feature channels to obtain feature vectors of all modes; a graph structure with modals as nodes and correlation as edges is constructed, cross-modal features are aggregated through a graph attention network, and global state descriptors fused with spatio-temporal information are generated; and performing time sequence modeling on the global state descriptor through a bidirectional LSTM network, outputting fault type probability distribution, and completing industrial equipment fault detection. According to the method, the problems of insufficient single-modal information, fixed feature extraction, low efficiency of multi-modal correlation modeling and lagging model updating in traditional industrial fault detection are solved.

The invention relates to a multi-sensor fusion positioning method and device based on environmental characteristics. The method comprises the following steps: respectively acquiring RTK data, laser radar data and IMU data; converting the RTK data into RTK positioning data, converting the laser radar data into laser radar positioning data, and obtaining IMU positioning data according to IMU output; monitoring the quality state of the output signal of each sensor in the current environment, and calculating to obtain a corresponding quality score; constructing and forming an input matrix according to the quality score of each sensor, mapping the input matrix to a high-dimensional feature space through an embedded layer and adding a position code, inputting the input matrix into a Transform model for time sequence modeling and extracting environment dynamic features, and finally outputting a real-time fusion weight of each sensor; and performing weighted fusion by using the real-time fusion weight to obtain final pose output. The method has the advantages of being simple in implementation method, high in positioning precision and stability, high in environmental adaptability and robustness and the like.

The invention discloses an employment and entrepreneurship support system based on artificial intelligence, relates to the technical field of occupational planning, and aims to solve the problem that a traditional support mode is insufficient in individuation and accuracy. The system comprises a multi-modal data acquisition module used for acquiring facial expressions, whole body dynamics and voice data of a user in at least 30 minutes of video dialogue in real time; a dialogue text is processed through a large language model based on a Transform architecture, continuous time sequence modeling is carried out on multi-modal dynamic behaviors by applying a liquid time constant network, and deep fusion reasoning is carried out in combination with multiple groups of multi-head Transform attention mechanisms. The core analyzes the real thought, psychological state, behavior pattern and core ability of the user through consistency verification, generates a structured dynamic user insight abstract, and customizes personalized vocational development or entrepreneurship planning according to the structured dynamic user insight abstract. According to the method, the potential of the user can be deeply informed, high-precision personalized planning is provided, the decision-making quality and success rate are improved, and the method has dynamic adaptation and continuous learning capabilities.

The invention relates to a method for supervising intelligent classroom interaction. The method comprises the following steps: dividing a classroom into micro-interaction units, capturing behavior characteristics in each unit, establishing behavior vectors, and recording specific participants and interaction modes; constructing an interaction unit time sequence, forming a behavior log graph, and performing time sequence modeling on multi-unit behavior vectors; identifying a state evolution curve of an individual, establishing an interaction state map, and identifying a state mutation point or a continuous low value interval as a supervision trigger point; identifying the logic integrating degree of the behaviors through a context analysis model; based on a behavior intention reasoning module, judging whether the behavior is in cooperation, coping, interference or simulation; introducing a system to judge abnormal states of a high-frequency low-value behavior, a content-free but high-frequency behavior and a theme-deviating behavior; continuously observing the change of the state of the student after intervention, and performing associated learning on intervention measures and effects to form a teacher personal intervention model library; the system recommends the most effective supervision measures to assist teachers to make decisions.

The invention relates to the technical field of big data analysis, in particular to a geological disaster risk assessment platform and method based on big data, and the platform comprises a multi-source data collection module, a dynamic weight fusion module, a dual-channel time sequence modeling module, a risk probability dynamic deduction module, a multi-dimensional coupling assessment module and a three-dimensional visualization early warning module. Wherein the multi-source data acquisition module is used for acquiring multi-source data in real time; the dynamic weight fusion module is used for generating a fusion data set of time-space alignment; the dual-channel time sequence modeling module is used for outputting a coupling feature vector; and the risk probability dynamic deduction module is used for generating a regional geological risk probability distribution diagram. According to the geological disaster risk assessment system and method, accurate geological disaster risk prediction and assessment are provided by fusing multi-source data and adopting an advanced time sequence analysis and assessment technology, an interactive risk map can be generated in real time, graded early warning signals can be triggered, and data support is provided for disaster management and emergency response.

The invention provides a ship trajectory prediction method based on a graph attention mechanism and an electronic chart, and relates to the technical field of intelligent ships. By fusing dynamic AIS trajectory data and static navigation channel geographic information, high-precision modeling and prediction of the future motion trajectory of the ship are realized. According to the method, a traditional time sequence-based trajectory modeling mode is expanded into multi-modal joint modeling, channel structure vector representation is introduced for the first time, structural information of a channel environment is extracted on the basis of a graph neural network, and deep fusion is performed on the structural information and historical trajectory data of a ship; and constructing a trajectory expression mode containing time, space and environment triplex semantics at the same time. In the aspect of model architecture, a graph attention mechanism is adopted to enhance the node representation capability in a channel sub-graph, and meanwhile, a time sequence modeling module is introduced to model a trajectory evolution rule, so that the prediction precision and generalization capability of the model in a complex water area environment are effectively improved, and high-quality modeling, interpretable prediction and intelligent support of the ship trajectory are realized.

The invention relates to the technical field of image segmentation, in particular to a plant salt tolerance response modeling prediction method and system based on a time sequence image. The method comprises the following steps: preprocessing acquired plant sample image data; performing image segmentation on the preprocessed image data by using a plant semantic segmentation model based on U-Net; a plant salt tolerance response prediction model based on TimeSform is constructed; and predicting the plant salt tolerance response grade by using the plant salt tolerance response prediction model. According to the time sequence image-based plant salt tolerance response prediction modeling method provided by the invention, a prediction process integrating image acquisition, preprocessing, dynamic feature extraction and depth time sequence modeling is constructed, so that the efficiency, precision and automation level of plant salt tolerance phenotype recognition are remarkably improved.

The invention provides an adaptive time-frequency fusion sequence recommendation method based on a Mama framework, and relates to the technical field of sequence recommendation. Comprising the following steps: S1, carrying out embedding expansion processing on a user behavior sequence, and constructing a unified sequence input representation containing user embedding, article embedding and position embedding; s2, sending the sequence input representation into a frequency kernel guided filtering module, and extracting periodic preference features in the frequency domain representation; s3, inputting the extracted features into a selective state space module, constructing frequency modulation parameters, completing frequency domain state modeling, and generating frequency domain feature representation; s4, the sequence input representation is input into a Mamba module, time sequence modeling operation is executed, and time domain feature representation is generated; and S5, inputting the time-frequency feature representations obtained in S3 and S4 into an adaptive fusion module, calculating a fusion weight, completing feature fusion, and inputting the fused features into a prediction layer to generate a final recommendation result. The frequency domain and time domain features are modeled in a combined mode, and the accuracy of recommendation results is improved.

The invention discloses an intelligent construction site safety evaluation method and system based on data elements, and relates to the technical field of computer platform load balancing, and the method comprises the steps: collecting construction site multi-source heterogeneous data, and carrying out the preprocessing of the construction site multi-source heterogeneous data; constructing a safety evaluation model of time sequence modeling and graph structure fusion through combination of a long short-term memory network and a graph neural network, performing feature selection and dimension compression operation on the processed multi-source heterogeneous data of the construction site to obtain an input feature tensor, and inputting the input feature tensor into the safety evaluation model; and calculating a comprehensive score according to a model output result, and generating a classification result and data feedback through an edge node. According to the intelligent construction site safety evaluation method based on the data elements provided by the invention, combined modeling of time sequence dependence and space association is realized through a deep modeling structure fusing LSTM and GNN, and the risk identification precision under multi-source heterogeneous data is effectively improved.

The invention discloses a police affair studying and judging method based on behavior feature recognition, and relates to the technical field of intelligent police affair and behavior modeling, and the method comprises the steps: collecting dynamic behavior data of a target object, and constructing a dynamic behavior portrait map comprising a behavior event, a time node, a spatial position and an interaction object; time sequence modeling is carried out on the map, and individual behavior chain feature vectors are extracted; comparing the current behavior chain with the historical behavior chain and the group mean value model, and calculating the deviation degree; performing cross-regional universality evaluation on the deviation degree through a transfer learning model; if the deviation degree exceeds a preset threshold value, generating early warning information in combination with a regional safety rule and pushing the early warning information to a police research and judgment system; according to the method, accurate identification and hierarchical response of abnormal behaviors can be realized, and the method has high robustness, strong generalization ability and good actual combat adaptability.

The invention provides an earth and rockfill dam seepage pressure prediction method based on mechanism and data dual drive, and the method comprises the following steps: generating multi-working-condition seepage pressure data, optimizing a radial basis function neural network through an aurora optimization algorithm, and constructing an efficient proxy model; on the basis of a proxy model prediction result, fitting is carried out by combining measured data, and a seepage pressure prediction mechanism model based on a hysteresis effect function is established; with the predicted value of the mechanism model as a label, supervising the training model to learn the physical law of the seepage field; and freezing the physical feature extraction layer in the trained model, and finely adjusting the time sequence modeling layer by using actually measured data to realize approximation of an actually measured value. According to the method, mechanism driving and data driving are organically combined, the interpretability of a physical rule is reserved, complex factors which are not considered by a mechanism model are complemented by utilizing actually measured data, and the generalization ability of a deep learning model under extreme working conditions is remarkably improved while the prediction precision of the model is ensured.