936 results about "Data modeling" patented technology

The invention relates to the technical field of construction data modeling, in particular to a BIM (Building Information Modeling)-based construction progress dynamic optimization system, which comprises an abnormal event identification module used for detecting local abnormity based on multi-source data and marking an abnormal area; the local component reconstruction and dynamic fusion module is used for reconstructing an abnormal region component model and performing space mapping to obtain a global BIM model; the component-semantic double-layer graph modeling module is used for constructing a component topological dependency graph and a component semantic relation graph and jointly reasoning a state transition sequence of the component; the state recognition and self-adaptive classification module is used for fusing the geometric features of the component and the graph structure features and executing state recognition and judgment boundary adjustment; and the graph evolution calculation module is used for performing multi-round state propagation deduction to generate a component state evolution result. According to the method, in a heterogeneous information modeling environment, dynamic processing and state intelligent identification of component-level information are realized, and the data calculation precision and response capability under three-dimensional model driving are improved.

The invention relates to the technical field of building construction, in particular to a building construction safety intelligent early warning system based on multi-sensor fusion and deep learning. Comprising a multi-source sensing unit; an intelligent fusion unit; a depth analysis unit; and a dynamic response unit. According to the method, through a mixed deep learning model, personnel-equipment-environment space association in a 1m * 1m * 0.5 m space grid is extracted through an improved U-Net network, and a space risk association map is output; modeling data of 10 sampling periods by using a bidirectional LSTM network, and outputting a short-term prediction value; and carrying out weighted fusion through an attention mechanism to form a risk feature vector, and removing invalid anomalies in cooperation with parameter anomaly judgment and cross validation. And then a risk grade evaluation module introduces multiple coefficients to calculate a risk grade index, and a grid diffusion range is delimited according to grades, so that real-time identification, quantitative evaluation and range pre-judgment of construction safety risks are realized, and the problem that risk identification evaluation lacks scenarized accuracy and comprehensiveness is solved.

The invention relates to the field of wastewater treatment, and provides an industrial wastewater membrane process intelligent optimization method and system based on multi-dimensional data modeling. The method comprises the following steps: acquiring wastewater quality parameters of a target scene and a production line equipment state in real time through a multi-dimensional sensor network, and constructing a digital twinborn model of a wastewater treatment system in the target scene; the membrane surface pollution type of each node in the wastewater treatment system is identified through a digital twin model, and the inner membrane pollution evolution condition in the future preset duration is predicted; a multi-strategy evolutionary reinforcement learning algorithm is adopted, the wastewater quality parameters, the production line equipment state and the membrane pollution prediction result are combined, multi-target dynamic optimization is conducted on a wastewater treatment system through a multi-agent collaborative decision-making algorithm, an optimization strategy is generated based on the multi-target dynamic optimization result, and membrane process operation parameters and production control parameters are dynamically adjusted. According to the method, real-time intelligent adjustment of membrane process operation can be realized, the stability of membrane process operation is guaranteed, and the treatment efficiency of membrane process operation is improved.

The invention discloses a hardware fault real-time detection method and system based on cooperation of a CPU (Central Processing Unit) and a BMC (Baseboard Management Controller), and the method comprises the following steps: respectively collecting high-frequency state data and tendency indexes by establishing a communication mechanism between the CPU and the BMC; the processor uses a CUSUM algorithm to carry out abrupt change analysis on the periodically collected operation state to generate an abrupt change event; and the management controller uses an EWMA algorithm to model the trend data, and extracts abnormal changes. And the system performs fusion analysis on the mutation event and the trend anomaly to form a fusion anomaly vector. The risk assessment module calculates a risk score based on a preset rule, determines a fault level, positions a target component, and outputs a processing strategy. And triggering a response action according to the strategy and recording an execution state. And the fusion data and the response record are input into the adaptive module together for dynamically adjusting CUSUM and EWMA parameters, so that adaptive updating of the algorithm is realized, and finally a fault detection signal is generated.

The invention belongs to the technical field of robot learning, and particularly discloses a robot continuous imitation learning method and system based on a double diffusion model. Comprising the following steps: generating old task data in a submerged space by utilizing a pre-trained latent diffusion model, generating a model through guidance of a task identifier in combination with conditional diffusion, generating an image and state data related to an old task, modeling to construct a diffusion model, realizing multi-modal mapping from a state to an action, and generating a diversified action sequence; high-quality images and state data are generated through a pre-trained variational auto-encoder and a conditional diffusion model, and the consistency of the generated data in time and the accuracy of global semantics are ensured through time sequence continuity constraint and semantic consistency constraint; and performing feedback optimization training on the latent diffusion model. According to the method, the loss weight is dynamically adjusted, and the model is ensured to show good generalization ability and stability in a complex task in combination with collaborative training of an imitation learning strategy and a generator.

The invention discloses a storm surge water increase prediction method and device, electronic equipment and a storage medium, and relates to the technical field of seawater monitoring, and the method comprises the steps: obtaining multi-source observation data of a target sea area, the multi-source observation data comprising satellite remote sensing data, near-shore monitoring data, meteorological mode data and drainage basin data; performing space-time alignment and exception processing on the multi-source observation data to generate standardized space-time grid data; performing hybrid prediction modeling on the standardized space-time grid data through a physical data dual-drive modeling layer to obtain a target probability water increasing field; and dynamically correcting the target probability water increasing field by using real-time observation data to obtain a storm surge water increasing predicted value. A physical mechanism model and a probability generation model are combined, limitation of a single model is overcome, and the nonlinear evolution process of the storm surge is effectively captured; the time-space dual-drive architecture is adapted to complex coast terrains and changeable meteorological conditions, and the risk of missing report or false report is reduced.

The embodiment of the invention relates to the technical field of data modeling analysis, and discloses a tunnel rock stratum large deformation analysis method and system based on three-dimensional modeling, and the method comprises the steps: collecting initial three-dimensional point cloud data through three-dimensional laser scanning; constructing an initial three-dimensional geologic model containing spatial morphological characteristics and a rock stratum interface geometric topological relation through space coordinate matching and curved surface reconstruction; finite element unstructured mesh generation is carried out on the model, and a rock stratum mechanical analysis model is established in combination with physical and mechanical parameters; inputting construction parameters and process information, activating unit nodes in sequence, and solving a force balance equation to simulate stress distribution; identifying a potential deformation area through iterative calculation, and adjusting boundary conditions to predict a deformation trend; the three-dimensional space distribution cloud atlas, the time evolution curve and the position marks are fused to generate multi-view deformation early warning information, the accuracy and the visualization degree of tunnel rock stratum deformation analysis are improved, and support is provided for construction safety.

The invention relates to the technical field of electric energy meter metering, and discloses an electric energy meter metering anomaly analysis method and system, and the method comprises the steps: collecting data, such as voltage waveforms, to generate a metering feature vector set, and constructing an anomaly detection rule base; setting a scene parameter type set, and establishing an abnormal association judgment model; dynamically correcting the threshold value by combining the model, and generating an optimized error threshold value set and an abnormal triggering condition set; and updating a metering analysis strategy to generate an abnormal judgment scheme, and correcting data verification sequential logic. The system comprises a data acquisition module, an abnormal rule base construction module, a scene parameter configuration module, a correlation model training module, a dynamic threshold optimization module, a strategy updating module and a time sequence correction module. Through multi-dimensional data modeling, scene-based threshold configuration and dynamic time sequence calibration, the accuracy and adaptability of electric energy meter measurement anomaly detection are improved, and the method is suitable for measurement anomaly analysis of diversified power consumption scenes in a smart power grid.

The invention provides a pulse output sensor control system for an electromagnetic flowmeter, which relates to the technical field of electromagnetic flowmeters and comprises an acquisition module, a modeling module, a generation module, a judgment module and an output control module. The modeling module performs state vector construction and drift identification; the generation module generates control parameters based on state vectors and synthesizes pulse signals; the judgment module evaluates signal deviation and generates scores; the output control module dynamically updates the control parameters according to the scores and drift information; and real-time adaptive adjustment of pulse output is realized. The system can effectively improve the stability and accuracy of output signals of the electromagnetic flowmeter under complex working conditions.

The invention discloses a forward collision early warning device and method based on risk assessment, electronic equipment and a storage medium, and relates to the field of driving prediction, and the device comprises a sensing unit which is used for obtaining the relative position data of a detected object, and carrying out the modeling according to the relative position data of the recognized detected object; detecting a driving state of a driver; detecting the motion state of the vehicle in real time; the processing unit is used for processing the data of the sensing unit in real time, performing target classification, running a dynamic risk assessment algorithm and outputting an early warning level; the prompt unit is used for displaying prompt information on the instrument panel display module and the vehicle-mounted terminal; by means of the scheme, the problems that when a static vehicle or a low-speed obstacle is detected by an existing system, due to the conservative property of TTC calculation, the time window for triggering early warning is later, collision is difficult to avoid when the vehicle is close to the static vehicle, and potential safety hazards exist are solved.

The embodiment of the invention relates to the technical field of ground surveying and mapping data modeling, in particular to a ground surveying and mapping driven space-time evolution modeling method and system.The method comprises the steps that firstly, multi-dimensional correlation features of elevations, coverage types and deformation data in at least three continuous periods are integrated; the limitation of single time point or single parameter analysis is broken through, and the nonlinear space-time coupling rule in earth surface evolution can be accurately captured; secondly, a spatial-temporal model construction method based on dynamic parameter optimization effectively fuses geographic spatial correlation features and coverage evolution trends, so that the model has adaptive characterization capability for a complex geographic process; in addition, by establishing a closed-loop feedback mechanism of prediction results and model parameters, real-time iterative optimization of the model parameters is realized, and long-term prediction stability in different geographical scenes is remarkably improved.

The invention relates to the field of post data modeling, in particular to an enterprise cross-domain data modeling system and method based on data twinning, and the method comprises the following steps: obtaining an enterprise cross-modal real-time data flow, carrying out key service node identification and service load processing peak evaluation, and constructing a post workload peak datum line; the method comprises the following steps: collecting enterprise multi-post performance information, performing growth trend evolution analysis, performing dynamic post skill perception, and generating a skill assessment map of multiple posts; project processing logs are collected, organization communication association mining is carried out, organization topology association evolution is carried out, and an organization topology interaction visual network is constructed; carrying out multi-attribute evolution evaluation based on a post workload peak reference line and the skill evaluation map, carrying out accurate digital modeling on an organization topology interactive visual network, and constructing an adaptive synchronous optimization twin model; the enterprise operation efficiency is improved, and the post requirement is accurately recognized.

The invention discloses a wind field data modeling method and system for a small and medium-sized unmanned aerial vehicle wind resistance test, and the method comprises the steps: collecting the topographic data, wind speed data and fan data of a test wind field, and determining a preset region and an unmeasured region according to the preset trajectory of an unmanned aerial vehicle based on the test wind field; the method comprises the following steps: acquiring boundary conditions of an unmeasured area and disturbance grid wake flow through fluid simulation based on topographic data and a preset area, performing wind speed vector decomposition on a grid according to a preset wind field boundary condition, and acquiring a preset wind field model according to a disturbance time sequence, an unmanned aerial vehicle maneuvering weight and the disturbance grid wake flow, and obtaining a predicted wind field of the unmeasured area through Gaussian process regression according to the boundary condition of the unmeasured area based on a preset wind field model, and coupling the predicted wind field through a grid time sequence by using different unmanned aerial vehicle preset trajectories to obtain a target wind field model. According to the method, through space-time collaborative interpolation and fluid simulation of Gaussian process regression, the inlet boundary condition better conforms to the fluid mechanics law, and the physical consistency and reliability of the target wind field are improved.

The invention relates to the technical field of geographic space intelligence, and discloses a territorial space purpose control intelligent analysis system, which comprises the following modules: a multi-source data acquisition module, which is based on satellite remote sensing and an IoT sensor, plans vector data, adopts a spatio-temporal data fusion algorithm, and integrates territorial, ecological and economic field heterogeneous data through a distributed crawler technology; generating a territorial space total element data set; the multi-source data acquisition module comprises a remote sensing acquisition sub-module, an Internet of Things access sub-module and a planning data analysis sub-module. Through a distributed data crawling and real-time stream fusion technology and spatio-temporal data modeling, rapid integration of multi-source heterogeneous information is realized, low-efficiency delay of traditional manual acquisition is eliminated, high-precision deformation monitoring and land use change identification are synchronously completed, the violation behavior discovery timeliness is remarkably improved, and the method is suitable for large-scale popularization and application. The three-dimensional space analysis algorithm accurately quantifies the above-ground and underground space element interaction relation, and the engineering conflict risk is effectively avoided.

The invention discloses an industrial communication protocol conversion system and conversion method. The method comprises the following steps: acquiring data of an industrial communication source protocol; protocol conversion: converting the source protocol data into target protocol data according to a sequence of protocol analysis, standardized modeling and protocol repackaging; according to protocol analysis, original data transmitted from different hardware interfaces are analyzed according to corresponding industrial protocols; the standardized modeling parses the data into a data model in a unified format; protocol repackaging: recoding the data model into a data frame conforming to a communication specification according to a target protocol rule; and data output: pushing the obtained target protocol data to a third-party server through an MQTT protocol or directly storing the target protocol data in a database for a third-party system to access. Through three core technologies of protocol analysis, unified data modeling and protocol packaging, lossless conversion among different industrial protocols is realized, and an efficient and reliable data communication infrastructure is provided for an industrial automation system.

The invention relates to the technical field of atomic clock control, and discloses a punctuality type atomic clock control method based on a microwave frequency band. The method comprises the following steps: firstly, acquiring microwave frequency band signal data and atomic state data, and constructing a time calculation model in combination with historical operation data to output a theoretical time value; performing multi-dimensional difference analysis on the theoretical time value and the actual measurement time value to generate a time difference coefficient matrix; inputting the matrix into a spatial propagation analysis network, and combining atomic clock component parameters and environmental parameters to generate a time anomaly probability distribution diagram; and finally, configuring microwave control parameters according to the distribution diagram, including starting a high-frequency monitoring mode for a high-probability abnormal region and applying a disturbance test to adjacent frequency bands. According to the method, through multi-dimensional data modeling, difference analysis and dynamic parameter configuration, the accuracy and adaptability of atomic clock control are improved, and the operation stability of the atomic clock in a complex environment can be enhanced.

A computer-implemented method may comprise receiving a first user input from a computing device and identifying a plurality of data assets from a catalog of data assets based on the first user input, where each data asset in the catalog of data assets comprises a corresponding entity that comprises data. The method may further comprise causing the identified plurality of data assets to be displayed on the computing device, receiving a first user selection of one or more of the identified plurality of data assets from the computing device, obtaining a plurality of data models based on the one or more of the identified plurality of data assets using a large language model, and causing the plurality of data models to be displayed on the computing device.

The invention relates to the technical field of urban drainage management, and discloses a municipal sewage pipe network dynamic drainage system and a control method, and the system comprises a sewage pipe network, a central controller, a pump station, a valve and an edge control terminal; the control method comprises the following steps that real-time data are obtained from a plurality of sensors arranged in a sewage pipe network, the plurality of sensors comprise a flow sensor, a water level sensor, a pressure sensor and a rainfall sensor, and the obtained real-time data comprise the sewage flow, the water level, the pipeline pressure and the external rainfall inflow in the pipe network; based on the collected real-time data, dynamic hydraulic modeling is carried out on the sewage pipe network through a central controller, a mathematical model for describing the hydraulic state change of the pipe network is established, and the mathematical model comprises spatio-temporal evolution of flow, water level and pressure. According to the invention, by constructing a drainage scheduling mechanism based on real-time data modeling and edge control linkage, dynamic adjustment and stable control of the running state of the sewage pipe network are realized.

The invention discloses an automatic data modeling and optimizing system and method fusing a knowledge graph and ChatBI, and relates to the technical field of data analysis. In order to solve the problems of high interaction threshold and insufficient analysis depth of a traditional BI tool, the scheme adopted by the invention comprises a data layer which has the capabilities of multi-source data access, domain knowledge graph construction, intelligent mapping recommendation, federal calculation and data mild governance, and realizes data integration and semantic unification; the analysis layer realizes accurate conversion from a natural language to an SQL and semantic reasoning of a knowledge graph through graph vectorization, multi-model cooperation, natural language understanding, intelligent SQL generation and graph dynamic updating, and supports efficient data query and analysis; and the application layer has the functions of natural language interaction, visual recommendation and generation, root cause analysis and intelligent early warning, and provides a visual interaction interface and data display service for a user. According to the invention, intelligent data analysis and visualization based on natural language interaction can be realized.

The invention discloses a systemic lupus erythematosus interaction management method based on patient sign data modeling, and particularly relates to the field of lupus erythematosus interaction management, which comprises the following steps: collecting basic data and sign data of a patient, generating a standardized basic data set and an integrity sign data set, feature combination, feature correlation detection and factor extraction are executed, a potential feature space representing patient features is constructed, and static health behavior feature modeling is achieved; the method comprises the following steps: acquiring nurse-patient interaction behavior data, generating a preliminary interaction data set, executing interaction feature extraction and activeness judgment, and generating a standardized interaction feature matrix; a multi-dimensional feature vector and dynamic health behavior link is constructed based on patient sign data and interactive behavior features, and time sequence prediction and response feedback closed-loop optimization are combined, so that dynamic management and individualized intervention of active health behaviors of systemic lupus erythematosus patients are realized.

The invention relates to the technical field of intelligent clothing design, in particular to an artificial intelligence-based personalized clothing design scheme generation method, which comprises the following steps of S1, modeling and fusing multi-dimensional user portrait data; s2, generating a style evolution design engine; and S3, interactively feeding back the three-dimensional fitting in real time. According to the method, the accurate user portrait is constructed through multi-dimensional user portrait data modeling and fusion integration of information from different data sources, the environment context is acquired in real time in combination with a knowledge graph and a spatio-temporal data acquisition technology, personalized data support is provided for subsequent costume design, and the user experience is improved. The emotion analysis and natural language processing technology is applied to analyze the aesthetic tendency and style preference of a user, costume design meeting the user requirement is generated based on a deep learning model, it is ensured that each design meets the fashion trend and the user preference through real-time evaluation and optimization of a design sketch, and the user experience can be improved through personalized recommendation and diversified design. And the innovativeness and uniqueness of the design scheme are improved.

The invention relates to the technical field of slope catastrophe intelligent early warning and data modeling, and particularly discloses a strip mine high and steep slope multi-source monitoring and early warning method based on a graph neural network and Transform, and the method comprises the following steps: S01, carrying out the data preprocessing and disturbance variable construction of monitoring data; s02, constructing a heterogeneous space diagram structure by taking the monitoring points as nodes and taking geography, lithology and dynamic response relationships as edges; s03, constructing a space-time end-to-end multilayer coding framework based on the graph attention network and the integrated deep neural structure; s04, on the basis of graph coding and time sequence output, introducing a disturbance variable embedding mechanism, and designing a joint attention fusion structure; and S05, generating a deformation trend prediction value of the slope in a future period of time and performing corresponding risk grade judgment. The invention aims to solve the key technical problem of weak adaptability and interpretability of an early warning system.

The invention discloses a stainless steel single-core tube production method based on an improved population algorithm, which comprises the following steps: S1, collecting process parameters in a stainless steel single-core tube production process, and constructing a process parameter data set; s2, constructing a multi-objective decision network model, and generating a comprehensive performance score through conflict reconciliation between process objectives; s3, optimizing process parameters by adopting a particle swarm optimization algorithm; s4, performing target performance prediction on each particle position combination by using the comprehensive performance score, and iteratively updating the particle positions until an optimal process parameter combination is obtained; s5, the optimal process parameter combination is applied to each section of actual production of the stainless steel single-core pipe; and S6, collecting actual quality data of the stainless steel single-core tube generated under optimization control, calculating errors and feeding back the errors to the target weight channel. According to the method, the multi-objective decision network model, the particle swarm optimization algorithm and the industrial quality data modeling technology are combined, and stainless steel single-core pipe production based on the improved swarm algorithm is achieved.

The invention relates to the field of industrial equipment monitoring, and discloses a power plant steam-water system edge calculation monitoring terminal system, which comprises a data acquisition module used for performing real-time acquisition on temperature, pressure, flow and liquid level parameters of key parts such as a boiler, a steam turbine and a pipeline in a power plant steam-water system, an acquisition result is converted into a standard data format to be output; the edge calculation module is used for performing local processing on the data, including feature extraction, data modeling, anomaly recognition and operation state analysis, and the module establishes a state model based on historical data and outputs parameter optimization suggestions according to a set strategy; and the communication module is used for transmitting the processing result to a monitoring center and receiving an instruction issued by the monitoring center. Local modeling and recognition are carried out on collected data through the edge calculation module, delay caused by data return is avoided, an abnormal early warning mechanism of second-level response is achieved, and the fault handling capacity of the system is enhanced.

The invention discloses a well submersible pump hydraulic design data modeling method, which comprises five steps of sensing acquisition, hydraulic data enhancement, hydraulic performance prediction, intelligent material matching and modeling output, relates to the technical field of pump hydraulic modeling analysis, and particularly relates to a well submersible pump hydraulic design data modeling method and system. A physical information confrontation generative network is combined with a space-time Kriging interpolation algorithm to enhance three-dimensional flow field data; a multi-modal graph neural network fusing physical control loss is constructed, and dynamic prediction of performance indexes such as pump body efficiency, lift and net positive suction head is achieved; based on a corrosion-wear coupling model and a reinforcement learning algorithm, the service life, the cost and the machinability of candidate materials are evaluated, an optimal combination is intelligently recommended, and systematic support is provided for design of an efficient, low-cost and long-service-life submersible pump for a well.

The invention provides a dynamic risk prediction and optimization decision-making method and system for a deep foundation pit construction process. A deep foundation pit numerical simulation model is established, and the model is used for simulating soil mechanical behaviors and supporting system response parameters in the construction process; acquiring multi-dimensional real-time monitoring data of the foundation pit, comparing the monitoring data with a numerical simulation result, and calibrating parameters of the deep foundation pit numerical simulation model according to a comparison result; performing time series data modeling analysis on the real-time monitoring data by using a Transform algorithm, capturing possible risk modes in the construction process, and identifying potential risk signals in the data; on the basis of Transform algorithm analysis and numerical simulation feedback results, the foundation pit construction risk state is predicted in real time, and a real-time risk prediction result is obtained; and according to the prediction result, dynamically adjusting the construction scheme to complete decision optimization. According to the method, the risk management and control capability of the deep foundation pit construction process is remarkably improved, and the construction safety and efficiency are greatly improved.

The invention provides a time-space attention-driven soil humidity prediction method in a domestic supercomputing environment, and the method comprises the steps: constructing a time-space feature dynamic fusion soil humidity prediction network model based on attention guidance; the attention-guided spatio-temporal feature dynamic fusion soil humidity prediction network model comprises a convolutional long-short term memory network basic framework and a spatio-temporal attention mechanism module. The introduction of the ConvLSTM network effectively integrates the time sequence and space information of the soil humidity, the potential space-time dependence in the data is fully utilized, the space-time attention mechanism enables the model to adaptively pay attention to important time periods and space regions by dynamically adjusting the weight between time steps, and the accuracy of the model is improved. The limitation of fixed feature selection in a traditional method is avoided, so that the prediction precision is improved. The model can better capture space-time dynamic feature information, further identifies the relationship between the influence factor and the soil humidity, and especially shows unique advantages in complex space-time feature processing and modeling of long-time sequence data.

The invention discloses a marine meteorological observation data millisecond query system based on time sequence block indexing. The marine meteorological observation data millisecond query system comprises a data input module, a data preprocessing module, a data hierarchical modeling module, a data storage cluster, a data analysis engine, a data query engine and a data operation interface module. Based on data modeling, data thinning and data partitioning technologies, data preprocessing is carried out for different meteorological ocean space weather data, and distributed storage and access of mass data are achieved; the method comprises the following steps: inputting ocean actual observation data, forecast data or historical data, carrying out model construction and index design according to meteorological ocean space weather data characteristics, completing distributed storage, and applying a data query engine and a data analysis engine to realize rapid aggregation query of the meteorological ocean space weather data; storage and query of lattice point data are realized by using a distributed database, and the problems of scale and query performance of meteorological ocean space weather data are effectively solved.

The invention relates to the technical field of data modeling, in particular to an AI personalized tutoring method based on cognitive portraits. Through implicit feedback dynamic weighting driven by multi-modal emotions, behavior deviation caused by task errors and emotional fluctuation is effectively distinguished, and the input quality and recommendation matching degree of potential factorization are remarkably improved; structured modeling is carried out on multi-dimensional behavior indexes by using a graph convolutional network, and interaction association among the indexes is deeply captured, so that the system can sensitively recognize subtle state changes such as user attention distraction or strategy adjustment; through self-adaptive fusion of a historical portrait and new input information, it is ensured that portrait updating is stable and timely in the process from tension to adaptation or from fatigue to recovery of a user; and finally, reliable dynamic signals are provided for the whole system through a portrait-strategy-feedback-portrait closed-loop mechanism and robustness and interpretability of multi-modal emotion estimation, so that personalized tutoring can be continuously optimized along with data accumulation.

The invention discloses a load demand prediction method based on a multi-level space-time fusion feature, and the method comprises the following steps: constructing the topological graph structure data of a power distribution network, collecting the data of a load node, carrying out the preprocessing, and determining the feature vector of the load node; constructing a multi-level space-time fusion feature prediction model, carrying out learning training on the prediction model based on the feature vectors of the load nodes, and outputting a prediction result; and inputting the feature vectors of the load nodes in a plurality of time steps in the future into the prediction model, and predicting load demands in the plurality of time steps in the future. Through the effective heterogeneous multi-dimensional data modeling and load demand prediction technology, the prediction performance is improved, the prediction precision is improved, and data support is provided for efficient distribution and scheduling of electric power resources. According to the method, the topological structure and the time dynamic change of the power distribution network can be effectively fused, the characterization capability of the model on heterogeneous multi-dimensional data is remarkably improved, and the prediction precision of the future demand of the load node is further improved.