956 results about "Data filtering" patented technology

The invention relates to the technical field of agricultural internet of things and environment intelligent control, in particular to a greenhouse environment adaptive regulation and control system based on artificial intelligence, which comprises an environment acquisition module used for acquiring multi-dimensional environment data in real time through a distributed multi-source sensor; the central controller is used for generating an optimized regulation and control strategy; the regulation and control execution module is used for driving execution equipment to carry out regulation; the central controller comprises a multi-source data fusion unit, an AI decision-making unit and a dynamic optimization engine which are respectively responsible for data filtering and fusion, generating an initial regulation and control strategy based on a space-time joint AI model, and reconstructing and optimizing the initial regulation and control strategy through a multi-target optimization algorithm. According to the method, the response real-time performance is improved through multi-source sensing and data fusion, predictive regulation and control and multi-parameter cooperation are achieved through the AI model, balance of energy consumption, growth and carbon emission is achieved in combination with multi-target optimization, and long-term self-adaption and strategy iteration of the system are supported.

The invention discloses a three-dimensional point cloud data filtering method and system based on adaptive clustering segmentation and gradient compensation, and the method comprises the steps: carrying out the data preprocessing of three-dimensional point cloud data through employing a statistical filtering method, obtaining the preprocessed point cloud data, extracting the point cloud features in the preprocessed point cloud data, and obtaining the point cloud feature data; according to the invention, a function of establishing multi-dimensional features including point cloud density, spatial autocorrelation and local curvature features by using an adaptive clustering segmentation algorithm based on density spatial distribution and carrying out dynamic clustering segmentation on a ground feature-ground cluster is realized; and residual mixed point clouds can be further separated through a coarse-fine granularity grid grading processing strategy, so that ground point clouds are separated, and the technical limitations of high parameter dependence, insufficient terrain adaptability and poor real-time performance in the prior art are broken through; and the filtering precision and robustness in a complex scene are remarkably improved through multi-dimensional collaborative optimization, and the method is suitable for being widely popularized and used.

The invention discloses a data filtering and noise reduction method based on laser point cloud. According to the method, the multi-scale features are intelligently screened through the random forest algorithm, and the system can automatically generate the optimal filtering rule according to the local geometric characteristics of the point cloud without depending on manual parameter presetting. In a complex urban scene, a fine structure of a high-rise vertical face can be accurately reserved through curvature features, and sparse noise of a vegetation area is rapidly eliminated through a density threshold value. The data-driven adaptive mechanism not only reduces the manual intervention cost, but also greatly improves the scene generalization ability of the filtering strategy, so that the filtering strategy can still keep stable output in a dynamic environment. The dynamic interference is accurately positioned by combining the consistency verification of the motion trails of the multi-frame point clouds and utilizing the time sequence correlation analysis, so that the data reliability in a complex dynamic scene is remarkably improved, and a solid foundation is provided for high-precision three-dimensional reconstruction and real-time perception.

The invention relates to an alarm event root cause analysis method, device and equipment based on a large language model and business topology, and the method comprises the steps: based on an analysis engine, according to an alarm event sent by an alarm system, obtaining an association node set, collecting multi-source data, generating a preliminary context packet, carrying out the extraction of abnormal information according to the preliminary context packet, and carrying out the analysis of the abnormal information. And generating a refined context package by removing irrelevant node information, and generating an interpretable root cause analysis report through large language model constraint and reasoning based on the constructed large language cue word template. According to the method, the initial context packet covering the fault propagation link is constructed based on the service topological graph, rapid modeling of the context is achieved, the high-frequency error mode template is generated through clustering, irrelevant nodes are dynamically pruned to generate the refined context packet, accurate focusing and data filtering are achieved, and the fault propagation efficiency is improved. And embedding the refined evidence chain through a structured cue word template, and driving the large language model to output an interpretable root cause report.

The invention belongs to the technical field of data management, and discloses a research and development data traceability and collaborative management system based on a block chain, and the system comprises a sensing layer which is used for collecting multi-source research and development data on various research and development tool chains through a multi-protocol collection agent, carrying out the structural packaging of the data to generate metadata, and embedding a data blood relationship tracking mark in the metadata; false data filtering is carried out on the metadata by deploying a trusted execution environment; the chain network layer is used for dividing the filtered metadata into data fragments and respectively storing the data fragments in a distributed storage platform; applying a Hash algorithm to each data fragment to generate a corresponding Hash value; taking the hash values corresponding to all the data fragments as leaf nodes, constructing a fragment hash tree, and further obtaining global root hash; the security of research and development data is ensured, and the cooperation efficiency is improved.

The invention discloses a power distribution network first-aid repair operation safety check scheme generation method and system and a related device. The method comprises the steps that a power distribution network first-aid repair operation safety check document is read and subjected to segmentation processing to form a plurality of text blocks; converting the text blocks into vectors through an embedded model, and storing the vectors into a power distribution network emergency repair operation safety inspection knowledge base; obtaining an input query problem, converting a query problem text into a problem vector through an embedded model, filtering and screening the problem vector by using the power distribution network metadata, and calculating the similarity between the filtered and screened problem vector and a vector in a power distribution network emergency repair operation safety inspection knowledge base by using a similarity measurement method; selecting a target vector construction prompt word from the power distribution network first-aid repair operation safety inspection knowledge base; and splicing the input query question and the prompt word as the previous text by using the large language model, and generating an answer. According to the method, retrieval and generation are combined, the retrieval data correlation is improved through power distribution network metadata filtering, and the effect of a large language model in scheme generation is enhanced.

The invention discloses a fault diagnosis and remote monitoring system and method for a solar power supply system, and relates to the technical field of fault diagnosis of a solar system, and the system comprises a heterogeneous multi-mode sensing module which collects the multi-dimensional information of an assembly through a plurality of sensors; the memristor storage and calculation integrated unit is used for realizing data filtering and feature extraction; the multi-scale causal diagnosis engine is used for diagnosing faults by fusing deep learning and causal diagrams; a self-adaptive topology communication network ensures data transmission; a digital twinborn monitoring platform and visual operation and maintenance are adopted, and in addition, an intelligent evolution decision and self-reconfiguration sensor network module is further arranged, so that the intelligence and reliability of the system are improved. Through cooperation of multiple modules, accurate fault diagnosis and positioning are realized, the diagnosis time is shortened, stable data transmission is ensured, self-repairing and autonomous learning capabilities are provided, the operation and maintenance cost can be reduced, the power generation efficiency can be improved, and the reliability and economic benefits of a solar power supply system can be enhanced.

A data processing method, an electronic device, and a storage medium. The method comprises: receiving a query request, wherein the query request comprises a target data table participating in a join operation; on the basis of the query request, executing a logical plan, wherein the execution of the logical plan comprises: constructing a data filtering condition corresponding to column statistical information, the column statistical information being information obtained by means of compiling statistics in advance on a column value range of columns included in the target data table; and executing a physical plan corresponding to the logical plan, wherein the execution of the physical plan comprises: performing partition pruning and / or dynamic filtering on the target data table on the basis of the data filtering condition, so as to generate a processed target data table, and executing the join operation on the processed target data table, so as to obtain an execution result.

The invention relates to the technical field of power transmission line monitoring, and discloses a power transmission line monitoring data transmission method based on Lora and 5G hybrid networking, and the method comprises the steps: determining a network access mode through a hybrid networking selection algorithm, and generating a communication link through dual-module networking configuration; original monitoring data are processed by using a data framing compression algorithm, and a path is selected and verified through dynamic routing optimization; the modulation format is adjusted through the space-time alignment data of the multi-modal data fusion model and the adaptive modulation technology; optimizing transmission by using an abnormal data filtering algorithm and a dynamic priority scheduling program; and feedback learning mechanism evaluation performance and updating algorithm parameters. According to the invention, network adaptability, data transmission efficiency and reliability are improved, data fusion processing is optimized, adaptive optimization of transmission performance is realized, operation and maintenance cost is reduced, and safe and stable operation of a power system is guaranteed.

The invention relates to the field of meteorological observation management, and discloses a low-altitude meteorological observation equipment operation and maintenance management method and system based on the Internet of Things, and the system comprises a meteorological sensor array module which is used for collecting low-altitude atmospheric environment parameters as observation data, including temperature, humidity, air pressure, wind speed, wind direction and particle concentration; the Internet of Things communication module is used for transmitting observation data to the edge computing node module in real time; the edge computing node module is used for performing local preprocessing on original observation data, including data filtering, abnormal value elimination and compression; the cloud operation and maintenance management platform is used for storing and analyzing the preprocessed observation data, judging an equipment state according to an analysis result, and generating an operation and maintenance instruction according to the equipment state; and the control module is used for receiving the alarm information and remotely controlling start and stop of equipment. According to the technical scheme, the safety of the low-altitude meteorological observation equipment can be improved.

The invention provides a recruitment patient determination method and device for a clinical test, a computer program product and electronic equipment, and relates to the technical field of medical big data, and the method comprises the steps: obtaining medical data of a plurality of patients, and converting the medical data into structured data; performing natural language analysis on the group entering standard information of the clinical test according to a large language model to generate a structured screening condition; performing data filtering on the structured data based on the structured screening condition through intelligent agents corresponding to a plurality of accommodating and arranging conditions of a clinical test to determine a recall result, matching the recall result based on the plurality of accommodating and arranging conditions, and determining an accommodating and arranging score of the medical data of each patient according to a plurality of matching results; and determining a target recruitment patient corresponding to the clinical test based on the recruitment score. According to the invention, the patient recruitment efficiency and accuracy can be improved.

The invention relates to the technical field of ocean remote sensing and satellite monitoring, in particular to a satellite-borne laser radar ocean water color product quality evaluation and calibration method, system and program, and particularly aims at improving the inversion precision of laser radar ocean water body parameters. The method comprises the steps of multi-source data acquisition and standardization, dynamic space-time matching window optimization, abnormal data filtering, seasonal conversion factor dynamic calculation, multi-source cross validation, consistency analysis, regional interpolation modeling, full-link uncertainty quantification, day and night difference correction and dynamic feedback optimization. By constructing a self-adaptive calibration mechanism and an error control process, the inversion precision and stability of a laser radar water color product are remarkably improved, and high-credibility data support is provided for marine ecological monitoring and carbon flux evaluation.

The invention relates to the technical field of battery temperature control, and discloses a new energy automobile power battery temperature adjusting method, system and equipment, and the method comprises the following steps: synchronously collecting vehicle operation data, traffic information, charging pile state and battery aging parameters, and carrying out timestamp alignment and abnormal data filtering; converting the road test data into a vehicle coordinate system, predicting an aging trend in combination with LSTM, and generating a cross-domain feature vector through feature coding and tensor fusion; and generating a basic temperature control strategy based on reinforcement learning, predicting SOH deviation in combination with digital twinning, dynamically calculating an aging compensation coefficient, and synthesizing an anti-aging enhancement strategy. According to the invention, the maximum temperature is controlled within a safety threshold value by constructing a full-link cooperative temperature control system, so that the effectiveness of a thermal management strategy in a full life cycle is ensured.

The invention relates to the technical field of water quality detection, in particular to a water quality detection method, device and system based on a spectrum technology, and the method comprises the following steps: obtaining spectrum data of a detected sample at a plurality of positions in a water quality detection process; extracting a characteristic peak of the spectral data of each position, and obtaining an abnormal offset coefficient of each characteristic peak; dividing the wave band of each characteristic peak into a rising part and a falling part, calculating the projection distortion coefficient of each part of the characteristic peak, obtaining the distortion index of each characteristic peak with projection and noise in combination with the signal-to-noise ratio of each characteristic peak, and further obtaining the waveform abnormal value of each characteristic peak. On the basis, the influence coefficient of uneven component distribution on the spectral data of each position of the detected sample is calculated, so that the step length factor of the spectral data filtering process of each position is adjusted, the spectral correction data of each position is obtained, and the COD concentration of the detected sample is detected. The accuracy of water quality detection can be improved.

The embodiment of the invention provides a multi-mode unmanned material checking method based on combination of RFID and machine vision, the method is applied to a mobile module and a camera module, an RFID read-write module is arranged on a mobile trolley, and the method comprises the following steps: in response to movement of the mobile module, the RFID read-write module scans a target material to obtain RFID identification data, and filters and de-duplicates the RFID identification data to obtain a target material; an RFID identification result is determined; dividing a shooting range of the camera module based on a scanning area of the RFID read-write module, and detecting a material box and a material surface sheet label in video image data when the video image data is shot; and identifying the material surface sheet label to obtain material data information, and matching the material data information with the RFID identification result to obtain a multi-modal material matching result.

The invention relates to the technical field of intelligent traffic systems, in particular to a linear intelligent monitoring system for a bridge fabrication machine, which comprises a multi-source sensing module, a data processing module, a data processing module, a data processing module, a data processing module, a data processing module and a data processing module, and is characterized in that the multi-source sensing module comprises strain sensors, inclinometers, GPS positioning units and machine vision units; the edge computing node is internally provided with a self-adaptive data fusion algorithm and is used for denoising sensor data in real time; the cloud digital twin platform is used for synchronizing the BIM design model and generating a millimeter-level linear deviation early warning signal; the PLC control interface is used for receiving the early warning signal and automatically adjusting parameters of the template system and the walking mechanism; according to the method, environmental noise interference is effectively eliminated through multi-source sensor fusion and a self-adaptive data filtering technology, the monitoring precision is improved to a millimeter level, real-time comparison of construction data and a design model is realized based on a BIM and digital twinning dynamic interaction system, and the timeliness and accuracy of linear control are remarkably improved.

The invention provides a structure health early warning method and system based on space-time correlation characteristics and digital twinning, and relates to the technical field of data processing. The method comprises the following steps: acquiring multi-source heterogeneous data of a target structure; performing dynamic sampling alignment and wavelet packet decomposition on the multi-source heterogeneous data to extract energy features to obtain synchronous data, and performing abnormal data filtering on the synchronous data to obtain cleaned fusion data; performing wavelet decomposition on a high-frequency vibration signal in the fused data to obtain a damage impact feature, performing time sequence processing on low-frequency temperature data in the fused data to obtain a temperature time feature, and performing dynamic graph convolutional network processing on strain data in the fused data to obtain a spatial correlation feature; constructing an input vector; calculating a damage degree index; and according to the damage degree indexes, early warning grades are divided, and corresponding control instructions are triggered for different early warning grades. By implementing the technical scheme provided by the invention, the accuracy of structural health early warning can be improved.

The invention discloses a carbon emission prediction method and system, and belongs to the technical field of carbon emission prediction, and the method specifically comprises the steps: collecting multi-source data, carrying out the preprocessing of the multi-source data, constructing a hierarchical federated block chain architecture, dividing a target area into block chain nodes, and carrying out the prediction of the multi-source data, each node deploys a lightweight sub-chain, generates a hash abstract with a timestamp and carries out chaining storage, data intercommunication is carried out between the sub-chains through a cross-chain interaction mechanism, the confidence degree of multi-source data is dynamically evaluated based on a data quality scoring model, the confidence degree is screened by using an intelligent contract, and the data quality is evaluated. Training a carbon emission prediction model by each district node by using local data, predicting the carbon emission of the district nodes, and generating a regional carbon quota allocation scheme according to a prediction result; according to the invention, the data is screened twice, so that the data quality and the accuracy of carbon emission prediction are effectively improved.

The invention provides a data processing method, electronic equipment and a storage medium, and the method comprises the steps: receiving a query request which comprises a target data table participating in a connection operation; executing a logic plan according to the query request, wherein the execution of the logic plan comprises the following steps: constructing a data filtering condition corresponding to the column statistical information; wherein the column statistical information is information obtained by performing statistics on a column value range of columns contained in the target data table in advance; in the execution process of a physical plan corresponding to the logic plan, partition cutting and / or dynamic filtering are / is conducted on the target data table according to the data filtering condition, a processed target data table is generated, connection operation is conducted on the processed target data table, and an execution result is obtained. According to the method, the data processing efficiency can be improved, and the query performance is improved.

The invention discloses an embedded platform-oriented lightweight multi-sensor data accurate and real-time fusion method, which comprises the following steps of: establishing a double-ring buffer area based on DMA (Direct Memory Access) to realize real-time acquisition of multi-sensor data; aligning multi-sensor data based on hardware timestamps and dynamic drift compensation; carrying out filtering processing on multi-sensor data by adopting dynamic cascade filtering, sliding window rapid sorting, segmented self-adaptive loss filtering and robust iterative estimation based on noise confidence; performing data fusion on the filtered multi-sensor data by compressing state dimensions and simplifying covariance matrix operation; the priority of multi-sensor data acquisition, multi-sensor data filtering and multi-sensor data fusion is distributed through a real-time operating system, and task scheduling is carried out. According to the method provided by the invention, the dynamic cascade filtering for lightweight data processing is combined with the lightweight dynamic weight anti-interference fusion algorithm, so that the real-time responsiveness and the data accuracy of the system can be improved.

The invention relates to a point cloud data filtering method and system based on a progressive triangulation network, and a medium, and belongs to the technical field of point cloud data processing. The method comprises the following steps: projecting point cloud data to the same plane; moving the rectangular window to enable the rectangular window to traverse all the point cloud data so as to extract undetermined ground seed points; screening to-be-determined ground seed points through curved surface fitting, removing non-ground seed points, and obtaining final ground seed points; and establishing an initial triangulation network, calculating a repeated distance and a repeated angle between the unclassified points and the initial triangulation network, determining an encrypted triangulation network, and obtaining ground points. According to the method, more to-be-determined ground seed points are extracted by sliding the rectangular window, the ground points are prevented from being mistakenly rejected through multiple times of curved surface fitting and seed point screening, the noise point rejection effect is improved, the method adapts to complex terrains, and the filtering precision is improved by encrypting the initial triangulation network.

Methods, apparatuses, and computer readable media are configured to perform operations comprising: obtaining, by a data management system (DMS), a first snapshot of a computing system, wherein the first snapshot comprises data associated with a set of files; determining, by the DMS, from among the set of files, a first subset of files or portions of files that comprise sensitive information; generating, by the DMS, one or more vectors based at least in part on data associated with a second subset of files or portions of files from among the set of files, the second subset of files or portions of files exclusive of files from the first subset of files or portions of files; and adding, by the DMS, the one or more vectors to a vector database along with metadata or a pointer to the metadata.

The invention discloses a data filtering method and system for a digital twin industrial control safety target range. The method comprises the following steps: firstly, marking an IP address of an industrial control system network in a segmented manner; feature extraction is carried out on the network behavior data of each IP segment, and splicing is carried out on the IP segment label to serve as a feature sample for constructing an industrial control network security identification model; a plurality of inverted residual modules with the same structure are adopted as core construction units, network behavior features in the feature samples are extracted and learned, and classification training is carried out; deploying the trained industrial control network security identification model to a pre-filtering module of a digital twin industrial control security target range, and carrying out classification, identification and filtering on network behavior data flowing in each IP segment in real time; and the misjudged sample is subjected to backtracking analysis, and the IP marking rule is updated. According to the technical scheme, the accuracy of network behavior data identification can be improved, so that the effectiveness of industrial control system simulation is improved.

The embodiment of the invention provides a fault diagnosis method and system for a thermal power plant auxiliary engine system based on a neural network, and the method comprises the steps: firstly extracting pressure data and flow data of an outlet pipeline of a water feed pump system from an edge side, and removing noise interference in the pressure data and the flow data through data filtering processing; a data processing technology based on deep learning is introduced to carry out multi-scale time sequence analysis on pressure data and flow data of the feed pump system so as to capture time sequence change characteristics of the pressure data and the flow data, and then bidirectional interaction analysis is carried out on the pressure time sequence characteristics and the flow time sequence characteristics so as to obtain the time sequence change characteristics of the feed pump system. The dynamic response relation of the outlet pipeline pressure relative to the flow change is excavated, and whether the feed pump system breaks down or not is intelligently recognized according to the dynamic response relation. Therefore, real-time monitoring and accurate diagnosis of the feed pump system can be realized, the accuracy and timeliness of fault diagnosis are improved, and meanwhile, the intelligent level of fault identification is improved.

The invention belongs to the field of data processing, and discloses a real-time data processing system and method for the Internet of Things. Comprising a long-tail device, data of a long-tail device end is transmitted to an edge layer through a communication protocol, an edge gateway in the edge layer is used for receiving the data, the edge layer further comprises a data filter, and the data filter discards useless data based on a filtering rule and retains value data; performing normal data and potential anomaly marking on the data based on a filtering rule, and finally outputting high-value data through an anomaly confirmation mechanism; the event detector performs anomaly detection on the value data through a model rule, if the data is abnormal, the data is divided into a high-priority queue, otherwise, the data is a low-priority queue, the high-priority data is transmitted to the cloud for application preferentially, and the low-priority data is subjected to settlement processing; and the cloud is used for receiving the high-priority data and triggering an alarm notification, thereby realizing high-efficiency and high-quality processing of real-time data oriented to the Internet of Things.

The invention discloses an early warning method for thermal runaway of an energy storage system. The early warning method comprises the following steps that a detection unit is installed on each unit of the energy storage system and connected with an upper computer; setting data processing and early warning judgment related parameters; acquiring electrochemical impedance spectroscopy data of the energy storage system in real time; performing optimization processing on the electrochemical impedance spectroscopy data by using a data filtering algorithm; and calculating an impedance change rate based on the electrochemical impedance spectrum data, and if the impedance change rate is greater than a set threshold value, sending an alarm signal and taking emergency measures. According to the thermal runaway early warning method of the energy storage system, the abnormal state of the battery, especially the early signal of thermal runaway, can be sensitively monitored through real part and phase angle changes under different frequencies, and higher-precision early warning is provided.

The invention discloses an SLAM-oriented multi-sensor space-time synchronization and online calibration method, and relates to the technical field of computer vision and robot perception. Comprising the steps that S100, initialization is carried out, and an initial pose and an external parameter transformation matrix initial value are obtained through coarse alignment; s200, data acquisition and preprocessing: acquiring IMU data, LiDAR data and Odom data in real time, and performing data filtering, distortion removal, time sequence correction and point cloud downsampling processing on the acquired data; and S300, performing time synchronization processing, estimating the time offset of the LiDAR and Odom data in real time, and performing unified correction to generate a unified timestamp. According to the method, an online time offset estimation and compensation mechanism with an IMU as a main clock is established, accurate synchronization of sensor data of different frequencies is achieved, and the problem of data alignment caused by sampling frequency difference and clock drift is effectively solved; and meanwhile, tight coupling fusion is realized by using an IMU pre-integration factor, a LiDAR residual factor and an Odom constraint factor, so that the space-time consistency of multi-sensor data is remarkably improved.

The invention relates to the technical field of network security operation and maintenance, in particular to a multi-mode network security operation and maintenance method and system driven by big data analysis, and the method comprises the steps: obtaining an operation state and network flow data to generate a comprehensive trigger signal, dividing a behavior feature section set, and extracting a main behavior feature region; and constructing a multi-modal behavior vector set, executing clustering analysis, and outputting a classification result. According to the method, through the steps of double-feature screening, mutation point division, weighted fusion, similarity screening and the like, the data filtering precision and the boundary recognition capability are improved, salient region extraction and cross-modal consistency expression are enhanced, adaptive aggregation and accurate classification of threat attributes in a complex scene are realized, and the stability and the recognition rate of network security operation and maintenance are guaranteed.

The invention relates to the technical field of radiation dose monitoring, in particular to a radiation dose monitoring method, device and system, and the method comprises the steps: obtaining the radiation dose data of a flaw detection room, and the temperature and humidity data in the environment; obtaining an influence coefficient of a linear fluctuation degree of radiation dose data caused by environment temperature change and humidity change, and further obtaining an influence coefficient of radiation dose monitoring caused by environment temperature and humidity change; the radiation dose irregular fluctuation change degree caused by equipment operation is calculated, the influence coefficient of the start-stop frequency and the time interval of the equipment is obtained, and the comprehensive influence significance value of the radiation dose monitoring by the environment change and the equipment operation state is obtained by combining the dispersion degree of all radiation dose data. And adjusting the step length factor in the radiation dose monitoring data filtering process to obtain a radiation dose monitoring result. According to the invention, the radiation dose data monitoring precision can be improved.

The invention provides a time series data acquisition method, system and device based on a large model and a medium, and belongs to the technical field of data acquisition. The method comprises the following steps: collecting time sequence data from a plurality of data sources, and sending the time sequence data to an edge computing node for data filtering, protocol conversion and time synchronization processing to generate structured time sequence data; preprocessing the structured time sequence data, and generating standardized time sequence data after time sequence segmentation processing; reading the standardized time series data, respectively extracting signal features and deep features in the standardized time series data, fusing the signal features and the deep features, and screening feature vectors from the signal features and the deep features; selecting a neural network model according to the task type, performing distributed training of the model by using the feature vector, optimizing and adjusting hyper-parameters of the model, and generating a target model; and deploying the target model in a production environment, collecting time sequence data in real time, preprocessing the time sequence data, inputting the preprocessed time sequence data into the target model for reasoning, and optimizing the target model according to a reasoning result.