267 results about "Temporal correlation" patented technology

This invention relates to a gait emotion recognition method, system, storage medium, and computer device based on spatiotemporal graph convolution. The method includes the following steps: S1, data augmentation by reversing the temporal direction of gait; S2, obtaining deep emotion features and prior emotion features respectively through a spatiotemporal graph convolutional network and prior feature statistical methods; S3, performing nonlinear mapping on the prior emotion features using a feature mapping layer; S4, inputting the fused features of the deep emotion features and prior emotion features into an emotion classifier to obtain the emotion category. The feature mapping layer of this invention achieves more effective feature fusion by performing nonlinear mapping on prior features; it also introduces causal temporal convolution to replace general temporal convolution, effectively extracting fine-grained temporal features by enhancing temporal correlation and cross-period feature fusion. Furthermore, a walking direction recognition auxiliary task is designed to accelerate the training and convergence speed of the model, enhancing the ability to extract temporal-dependent features and the performance of emotion recognition.

The invention relates to the technical field of data processing, and discloses a comprehensive evaluation method and system for the health degree of a distribution network cable. The method comprises the following steps: collecting cable joint multi-source monitoring signals, normalizing the monitoring signals to obtain a degradation degree feature vector, correcting multi-physics field coupling model parameters, obtaining a recessive degradation index through finite element calculation to obtain an enhanced feature vector, and performing time-frequency domain decomposition to extract multi-scale feature parameters to obtain a comprehensive feature matrix; a double attention mechanism calculates a feature weight and a time sequence correlation degree to obtain a deterioration trend prediction value, and fuzzy integral is fused with a multi-classifier output probability to obtain a health degree evaluation grade and an early warning result. According to the invention, the early defect identification accuracy and the degradation trend prediction precision are improved.

The invention provides a vibration signal space-time reconstruction method based on a multi-modal condition diffusion model, and relates to the technical field of vibration signal reconstruction, and the method comprises the steps: firstly collecting structure vibration response through multiple sensors, constructing a multi-dimensional vibration signal matrix, and automatically recognizing a space continuous missing region and a time random missing region; performing coarse reconstruction on the missing region by adopting self-adaptive multi-scale interpolation so as to recover the basic trend and frequency band characteristics of the signal; a pseudo-missing mask is further applied to complete data, a training sample is constructed through a self-supervision strategy, and the model is guided to learn spatio-temporal correlation features and missing modes; in a training stage, a diffusion model is used as a generation framework, Gaussian noise disturbance is applied to a missing region, four types of condition embedding of time, space, trend and frequency domain are introduced in a denoising inversion process, signal periodicity, multi-sensor space coupling, low-frequency change and a physical frequency spectrum structure are respectively described, and the noise is reduced; and high-fidelity signal reconstruction under multi-modal information joint constraint is realized.

The invention discloses an artificial intelligence abnormity early warning diagnosis method for industrial equipment operation state monitoring, and belongs to the technical field of industrial equipment intelligent monitoring, and the method comprises the steps: collecting a multi-source heterogeneous signal of industrial equipment, and carrying out the time-frequency dual-domain feature extraction; constructing a multi-scale time window based on the time-frequency features, and executing self-supervised contrast learning by injecting a preset abnormal mode to obtain cross-scale contrast feature representation; constructing a dynamic adjacency matrix according to the comparison features, extracting space-time correlation features through a graph attention network, and determining an abnormal score based on joint evaluation; according to the method, a deep coupling closed-loop cooperative system is formed, multi-dimensional state characterization, adaptive anomaly detection and root cause diagnosis are realized, and the problems of single data source and lack of fault analysis capability in the prior art are effectively solved.

Systems and methods disclosed herein are enabled to dynamically generate structured documents using one or more artificial intelligence models. A computing device receives an output generation request and uses a first AI model to retrieve data chunks from source documents and applicable templates. A second AI model ranks the retrieved chunks based on one or more metrics, such as vector similarity, keyword density, and temporal relevance. A third AI model subsequently generates a response using the ranked chunks, templates, and predefined operational boundaries for each chunk. The generated response is tagged with source identifiers to enable the traceability of the response back to corresponding chunks. The system transmits, via the computing device, the response, the retrieved chunks, and / or the source identifiers.

The invention belongs to the technical field of tunnel engineering, and provides a multi-physics field real-time assimilation simulation and regulation method and system in a tunnel grouting process in order to solve the problem that real-time dynamic simulation and automatic regulation are lacked in existing tunnel construction, and the real-time assimilation simulation and regulation method and system in the tunnel grouting process are provided by utilizing ensemble Kalman filtering and combining real-time monitoring data in the tunnel grouting process. Dynamically correcting parameters of the multi-physical model; time correlation in the slurry condensation process is considered, a time-varying condensation model depicting physical property changes of slurry evolving along with time is integrated, the time-varying condensation model serves as an external function in the time step length to be embedded into the multi-physical field model in correction, and the slurry flowing state is adjusted in a self-adaptive mode through numerical simulation; and generating control parameters of tunnel grouting according to a dynamic simulation result, and realizing closed-loop regulation and control of tunnel grouting. Synchronous linkage of numerical simulation and on-site working conditions is realized.

The invention discloses a multi-source heterogeneous anomaly detection method based on time correlation, and belongs to the technical field of water diversion engineering, and the method comprises the steps: S1, obtaining multi-source sensor time sequence data in multi-source heterogeneous data, carrying out the preprocessing of the multi-source sensor time sequence data, and dividing a training set and a test set; s2, constructing a double-branch depth feature extraction network model, training by adopting the training set, and testing through the test set to obtain a trained double-branch depth feature extraction network model; the double-branch depth feature extraction network model comprises a double-branch unit, an attention feature fusion unit, a classifier unit and an output layer unit which are connected in sequence; and S3, inputting to-be-detected data into the trained double-branch depth feature extraction network model, and finally outputting an anomaly diagnosis result. A double-branch depth feature extraction network is constructed, adaptive fusion is realized through an attention mechanism, and the problem of poor modal adaptability of heterogeneous data is solved.

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 intelligent monitoring and early warning system and method for project progress and cost, and relates to the technical field of constructional engineering management. The streaming data fusion module adopts an Apache Flink engine and applies a dynamic time warping algorithm to carry out time alignment on multi-source asynchronous data to realize semantic unification; the space-time diagram neural network prediction module constructs a space-time association diagram, integrates global features such as weather and supply chain fluctuation, and adaptively learns an influence weight by using a graph attention mechanism; the self-adaptive early warning module adopts a Bayesian online learning framework, an early warning threshold value is dynamically adjusted according to a historical false alarm rate and a missing report rate, the method comprises the steps of data acquisition, fusion, mapping, joint prediction and self-adaptive early warning, the problem of data islands is solved, complex space-time association is accurately captured through a space-time diagram neural network, and real-time early warning is achieved. Joint prediction of progress and cost risk is realized, false report and missing report are reduced, and real-time performance, accuracy and decision-making efficiency of engineering management and control are improved.

The invention provides a multi-modal ecological environment monitoring element plug-in integration system and method based on unified objectification modeling. Firstly, an object model and an inheritance system of monitoring equipment, data and an algorithm are constructed; on the basis, a unified logic storage and metadata cataloguing mechanism oriented to heterogeneous databases such as relational databases, non-relational databases and file object databases is designed and realized; the plug-and-play and full-life-cycle management of equipment, data and algorithm models is further realized through a dynamic registration module; common APIs (Application Program Interface) such as object-level addition, deletion, modification and query, space-time association query, concurrent task scheduling and aggregation and the like are externally provided by relying on a unified service bus. And the hybrid storage engine cooperatively manages structured and unstructured data and maintains a topological relation between objects. According to the scheme, object dynamic integration and expansion are completed on the premise that operation is not interrupted, the multi-source heterogeneous data management and cross-modal analysis efficiency is remarkably improved, and the method is suitable for various ecological environment monitoring scenes such as natural reserve, drainage basin pollution supervision and disaster emergency response.

The invention discloses a traffic engineering multi-source monitoring data fusion intelligent management and control system, and the system comprises a multi-source data dynamic access module which is used for the access of multi-source heterogeneous data; a data processing module; the dynamic relation learning module is used for mining dynamic space-time association and potential laws in the multi-source data and establishing a time-varying mapping model among the data; the intelligent fusion decision module is used for generating a traffic control decision based on the processed multi-source data and an output result of the time-varying mapping model; an adaptive adjustment module; a data service module; through cooperation of the multi-source data dynamic access module, the data processing module, the dynamic relation learning module, the intelligent fusion decision-making module, the adaptive adjustment module and the data service module, full-process automation from multi-source data access to intelligent management and control decision-making can be realized, and self-adaption to changes of a complex traffic environment can be realized. And the fine management level of traffic engineering is improved.

The invention belongs to the cross technical field of hydrology and meteorology, data analysis and machine learning, and particularly discloses a soil humidity space-time multi-step prediction model construction method and a storage medium, and the method comprises the following steps: constructing a data set; a construction graph convolution module is used for constructing a connection matrix based on time sequence correlation of soil humidity data in a training data set, performing k-hop expansion and normalization processing on the connection matrix to obtain a k-hop normalized connection matrix, and extracting wide-area spatial features and remote heterogeneous dependence of soil humidity based on the construction graph convolution module; and a prediction model is constructed, the prediction model comprises GConvLSTM units and ConvLSTM units, the GConvLSTM units and the ConvLSTM units are crossed or stacked in sequence, a layer memory flow architecture is formed, and an initial KGCCLSTM prediction model is obtained. According to the invention, high-precision multi-step prediction of the soil humidity in a complex scene can be realized.

The invention relates to the technical field of artificial intelligence and data processing, in particular to a building energy consumption prediction model training method and equipment, and the method specifically comprises the following steps: obtaining building structure parameters through a building information model, deploying an Internet of Things sensor to collect dynamic data, integrating the data into a building energy consumption database, and carrying out the manual marking of the data; performing space-time alignment on the acquired data, and performing interpolation, noise reduction and normalization operation to obtain a space-time incidence matrix; constructing a building energy consumption prediction model based on a space-time diagram convolutional network, and inputting the space-time incidence matrix into the model for training; and newly collected data are transmitted to the trained model to obtain a classification result of the building energy consumption. According to the invention, the building energy consumption prediction model is trained to realize efficient processing and automatic tuning of the model on data, the accuracy of the prediction result is improved, the repeated development cost is reduced, and the method is suitable for energy management systems in intelligent buildings, green buildings and smart cities.

The invention discloses a safety risk assessment method and device for a transmission system of an offshore wind turbine generator and a storage medium. The method comprises the following steps: collecting multi-dimensional state data of the transmission system of the wind turbine generator; preprocessing the multi-dimensional state data, wherein the preprocessing comprises time synchronization, denoising, normalization and feature extraction; inputting the processed multi-modal data into a multi-modal fusion model for extracting spatio-temporal correlation characteristics and fusing the spatio-temporal correlation characteristics; inputting the trained artificial intelligence evaluation model based on the fusion features, and outputting the current safety and health score value and risk level of the target wind turbine generator; and carrying out structured output on the health score value and the risk level, and triggering alarming, recording and reporting operations of an edge side or a cloud end. And therefore, the fault monitoring precision and the early warning timeliness are improved, the adaptability and the expansibility of the system are enhanced, the cost is reduced, rapid judgment is facilitated, and the safety guarantee capability is improved.

The invention discloses an automobile cabin software control method and system based on multi-mode interaction, and relates to the field of multi-mode data, and the method comprises the steps: S1, multi-source signal synchronous collection and timestamp calibration; a user voice instruction, a gesture track and eye fixation point information are collected in real time through a distributed sensor array; according to sensor data, a three-level synchronization architecture is combined with a PTP precise time protocol to achieve microsecond-level clock synchronization, a unified time service timestamp is embedded in a data packet header, and the timestamp error is controlled within + / -0.5 ms; s2, dynamic environment interference compensation; the method comprises the following steps: constructing an environmental noise perception model; the construction of the environmental noise perception model comprises the following steps: starting a regional strong light suppression algorithm for a strong light scene with the illumination intensity greater than 10,000 lux; activating a motion compensation module for a bumpy scene with a vertical acceleration greater than 0.3 g, and outputting an environment compensation multi-modal data stream; s3, analyzing time-space association semantics; and S4, confidence decision and instruction execution.

The invention discloses a rainfall downscaling method and system based on a deep learning network model fusing rainfall priori knowledge, and the method comprises the steps: firstly collecting the topographic data and low-resolution day-by-day rainfall data of a target region, and taking the data as input data; a short-term high-resolution precipitation field generated in a mesoscale weather forecast WRF mode is used as training truth value data; according to the method, the function of accurately downscaling the rainfall data in combination with the convolutional neural network and the long and short term memory network is realized, the spatial-temporal correlation of rainfall is fully considered in the downscaling process, and meanwhile, a likelihood function combined with coupled censored data, Box-Cox conversion and time variation variance Gaussian distribution is adopted as a rainfall loss function; the method not only can represent zero expansibility, skewness and heterovariance characteristics of rainfall, but also can improve the rainfall downscaling precision and quantify the uncertainty of rainfall downscaling, and is suitable for wide popularization and use.

The invention discloses a power load prediction method of a multi-dimensional attention double-flow heterogeneous space-time diagram convolutional network considering multi-level influence factors, and the method comprises the steps: defining nodes and edges of a heterogeneous space-time diagram based on the type attributes of power load nodes and a power grid topological structure, and constructing a layered diagram structure according to the type attributes of the power load nodes; based on the hierarchical graph structure, generating a multi-dimensional adjacency matrix by using the feature set, the historical load and the geographic information; inputting the spatio-temporal information graph into a graph neural network to extract feature information of each dimension, and inputting the feature information into a multi-dimensional attention mechanism to obtain spatio-temporal feature representation; and inputting the spatial-temporal feature representation into the bidirectional gating time sequence convolutional network to obtain a power load prediction sequence. The problem of spatial-temporal correlation modeling of multiple types of loads in a complex power system is effectively solved, and the accuracy of power load prediction is further improved.

The invention relates to a water quality micro-station space-time correlation traceability analysis method based on multi-scale feature fusion. The method comprises the following steps: step (1), preprocessing and hierarchical dimensionality reduction of multi-source water quality data; step (2), measuring relevance of time-space fusion; and step (3), constructing and analyzing the space-time correlation network. According to the method, the association precision is improved through multi-scale feature fusion, the association deviation is reduced through spatial topology correction, the efficiency and the precision are considered through hierarchical dimensionality reduction, management and control are facilitated through structured network output, the precision and the practicability of water quality micro-station association mining are comprehensively improved, and a new breakthrough is brought to water quality monitoring traceability analysis.

The invention provides a network intrusion detection method and system based on artificial intelligence, and relates to the technical field of network intrusion detection, and the method comprises the steps: obtaining multi-dimensional behavior data of a terminal domain, a network link domain and an application layer domain, and employing a high-density or hierarchical collection strategy according to a network type; preprocessing the data through a standardization priority or coding priority scheme according to feature types; constructing a CNN-LSTM fusion model adaptive to network dynamics, and extracting space and time sequence correlation features; based on the sample condition, adopting full or incremental training to obtain a convergence model; a result is output through a high-precision or high-speed detection strategy in combination with scene requirements; and continuously iteratively optimizing the model based on the environmental change. The system correspondingly comprises a multi-domain data acquisition module, a data preprocessing module and the like. The method breaks through the limitation of single-domain detection, accurately recognizes cross-domain cooperative attacks, adapts to different network scenes, reduces the false alarm and missing alarm rate, improves the detection real-time performance and stability, and is suitable for various network environments such as enterprise intranets and hybrid clouds.

Certain aspects of the present disclosure provide techniques for opportunistic transmission of periodic reference signals. One example method performed at a user equipment (UE) includes receiving first signaling configuring the UE with a first set of reference signals (RSs) resources for periodically transmitting and at least a second set of periodic RS resources for opportunistic transmission of RSs; receiving a second signaling indicating when an RS is to be transmitted in the transmission opportunity of the second set of RS resources; calculating a temporal correlation metric based on measurements of RSs transmitted in the transmission opportunity of the second set of RS resources according to the second signaling and measurements of RSs transmitted in the transmission opportunity of the first set of RS resources; and sending a report indicating the temporal correlation metric.

The invention provides a high-precision map regionalization updating method and system based on space-time relevance, and relates to the technical field of high-precision maps, and the method comprises the steps: obtaining live-action image data and associated data of a shooting terminal, and binding the live-action image data and the associated data to form an image data unit with a space-time position mark; comparing the data with a pre-stored live-action three-dimensional map, determining satellite positioning information correction coordinates, identifying geographic element features and distributing the geographic element features to corresponding space-time grid units according to the correction coordinates; performing spatial clustering analysis according to space-time grid unit distribution, determining a key area needing to be backtracked, obtaining image data units and geographic element features at different historical times through time retrieval and spatial indexing, and reconstructing a time sequence change state; according to the difference between the time sequence change state and the pre-stored map, regionalized attribute updating is carried out on the live-action three-dimensional map, regionalized attribute updating of the high-precision map can be achieved, and the accuracy and pertinence of map updating are improved.

The invention relates to the technical field of artificial intelligence, can be applied to the fields of financial science and technology and medical science and technology, and discloses an intelligent decision-making method, device and equipment based on a graph structure and a medium. A visual encoding result and a language encoding result are obtained through encoding of the visual encoder and the language encoder respectively; a graph structure is constructed according to the coding result, nodes in a graph are visual feature vectors in the visual coding result and language feature vectors in the language coding result, and edges are dynamically established based on semantic, spatial or temporal relevance between the visual feature vectors and the language feature vectors; then, the graph structure is input into a large language model for reasoning to obtain feature representation, and finally, an action sequence of the intelligent agent is generated through decoding of an action decoder. According to the method, multi-modal information is fused through a graph structure, reasoning is performed by using a large language model, and more accurate and flexible agent decision is realized.

The invention relates to the technical field of deep learning, in particular to an intelligent prospecting model construction method based on a knowledge graph and data deep learning, which comprises the following steps: collecting multi-source geological data to perform time decomposition and spatial stratified sampling to extract features, calculating an attachment weight through semantic coding to construct a geological knowledge structure, and constructing a geological prospecting model; the method comprises the steps of extracting spatial-temporal features in a convolution mode, combining with semantic deviation degree weighted fusion to generate a hierarchical feature coupling result, carrying out aggregation analysis on spatial-temporal correlation to extract consistent components, judging a metallogenic response relation through conditional probability reasoning, fitting a model, calculating deviation, adjusting weights, analyzing semantic consistency, and carrying out classification and aggregation to generate an intelligent prospecting optimization result. The feature precision is improved through time decomposition and spatial stratified sampling of multi-source geological data, data association is enhanced through semantic coding, time-space consistency is enhanced through convolution extraction and semantic fusion, multi-scale features are balanced through hierarchical coupling, the ore-forming relation judgment accuracy is improved through probabilistic reasoning, and the result precision and stability are remarkably improved.

The invention belongs to the field of environment monitoring, and particularly relates to an environment monitoring method and system based on a large model, and the method comprises the steps: S1, collecting multi-source data which comprises environment monitoring data, geographic and spatio-temporal data and priori knowledge data; s2, carrying out preprocessing and non-uniform data interpolation on the multi-source data, and generating time-space aligned gridding feature data; a space-time attention mechanism is utilized to extract space-time correlation features from the gridding feature data, a pre-constructed environment knowledge graph is fused to perform knowledge enhancement, the features after knowledge enhancement are reused through a residual network, and depth features are output; dynamically adjusting the weight of the prediction layer based on the real-time monitoring data, and outputting an environment index prediction result of the target region in a future time period; and S3, generating an environment quality grade and early warning information according to an environment index prediction result, and generating a pollution cause traceability report based on a feature contribution degree analysis result. The problems of low prediction precision, poor interpretability and weak dynamic adaptability in environmental monitoring are solved.

The invention discloses a wavelength modulation spectral signal denoising method based on an unsupervised auto-encoder. The method comprises the following steps: step 1, constructing a WMS harmonic signal data set; step 2, training an HA-CAE denoising network model; 3, the HA-CAE denoising network model is evaluated and optimized, and an optimal HA-CAE denoising network model is obtained; and step 4, integrating the optimal HA-CAE denoising network model to a sensor system to realize real-time denoising processing of the signal. According to the method, a targeted data set and an improved HA-CAE denoising network model are constructed, three attention mechanisms are fused to accurately capture signal local details, time sequence association and global channel characteristics, non-stationary mixed noise characteristics are adapted, the denoising effect is improved, the generalization ability and the real-time processing ability of the model are guaranteed, and the method is suitable for popularization and application. The method is suitable for wavelength modulation spectrum signal processing in various complex scenes such as industrial leakage monitoring and atmospheric environment detection.

The invention relates to the technical field of electric power intelligent terminal equipment safety state detection, and provides an electric power intelligent terminal equipment safety state detection method and system, equipment and a medium, and the method comprises the steps: carrying out the preprocessing of equipment operation data obtained according to the equipment type of target intelligent terminal equipment, and obtaining to-be-analyzed equipment operation data; according to the to-be-analyzed equipment operation data, performing state identification based on an equipment security state detection model to obtain an equipment security state detection result; state recognition in the equipment security state detection model comprises the steps of performing modal feature extraction on to-be-analyzed equipment operation data, performing intra-modal feature enhancement, inter-modal semantic association and multi-modal adaptive dynamic fusion on multi-modal features in sequence, and performing state recognition on fused features. According to the method, the space-time relevance among the multi-modal data and the distribution difference of the equipment data can be effectively captured, the self-adaptive high-precision fusion of the multi-source data is realized, and the high efficiency and precision of safety state detection and anomaly positioning are effectively improved.

This invention discloses a traffic prediction method and system based on a spatiotemporal hierarchical network. The method includes: acquiring traffic data and preprocessing the data to construct a hierarchical regional augmentation network and a traffic feature matrix; using the hierarchical regional augmentation network and the traffic feature matrix as input to a prediction model, learning spatial and temporal correlations, and outputting prediction results; the prediction model includes a region-aware spatial correlation model and a region-aware temporal correlation model. The system includes a preprocessing module and a prediction module. By using this invention, the spatiotemporal correlations in traffic data are effectively captured, improving the accuracy of traffic flow prediction. This invention, as a traffic prediction method and system based on a spatiotemporal hierarchical network, can be widely applied in the field of traffic prediction.

This invention provides an emergency bionic robot collaborative method and multimodal rescue system with task and state collaborative perception, relating to the field of emergency bionic robot technology. It acquires environmental perception data streams through multi-source sensing acquisition devices deployed on each robot body in an emergency bionic robot cluster, covering panoramic vision, terrain stiffness distribution, gas composition concentration, and sound wave spectrum data. Each type of data stream is processed to obtain feature segments, and then visual and tactile, olfactory and auditory related segments are spatially superimposed to generate a collaborative scene map. The collaborative scene map undergoes physical field state interference deduction and cross-map temporal correlation fusion to generate a global collaborative perception situational deduction map. Based on this global collaborative perception situational deduction map, the coordinates of the disaster spread source, the leading edge of the spread path, and the robot's pose and state information are determined, generating a distributed rescue collaborative instruction set to achieve efficient robot collaborative rescue.

The invention provides a lightweight storage method and system for time series data of the Internet of Things, and relates to the technical field of data storage and compression of the Internet of Things, and the method comprises the steps: collecting multi-mode time series data and mechanical vibration energy data generated during the operation of equipment of the Internet of Things; extracting vibration frequency characteristics from the mechanical vibration energy data, and generating a time sequence vibration signal based on the vibration frequency characteristics; performing space-time correlation on the time sequence vibration signal and the multi-modal time sequence data to identify a data activeness level; according to the data activeness level, performing sparse representation processing on the multi-modal time series data to obtain sparse representation data; and carrying out dynamic dictionary construction and coding on the sparse representation data by adopting a self-adaptive dictionary coding algorithm to generate compressed coding data, and carrying out hierarchical storage management on the compressed coding data to realize lightweight storage. According to the invention, the storage efficiency and the processing capability of the time series data of the Internet of Things edge device are improved.

The application provides a high-precision map regionalization updating method and system based on space-time correlation, and relates to the technical field of high-precision maps. The application binds real scene image data and associated data of a shooting terminal to form an image data unit with a space-time position marker. The image data unit is compared with a pre-stored real scene three-dimensional map to determine satellite positioning information correction coordinates, identify geographical feature characteristics, and distribute the geographical feature characteristics to corresponding space-time grid units according to the correction coordinates. Spatial clustering analysis is performed according to the distribution of the space-time grid units to determine key areas that need to be traced back. Image data units and geographical feature characteristics at different historical times are obtained through time retrieval and spatial indexing to reconstruct a time sequence change state. According to the difference between the time sequence change state and the pre-stored map, the real scene three-dimensional map is updated in a regionalized attribute, which can realize regionalized attribute updating of a high-precision map and improve the accuracy and pertinence of map updating.