345 results about "Continuous data" patented technology

The invention relates to a wind resource prediction method based on quality control assimilation of multi-source observation data, and the method comprises the steps: integrating the multi-source observation data, including a multi-band radar reflectivity factor, a radial speed, a ground observation station, and wind profile radar data; quality control processing such as mottle removal, data filling, speed folding removal and discontinuous data removal is carried out, so that the accuracy and continuity of the data are improved; then, through lattice point interpolation and three-dimensional variation assimilation technologies, the processed observation data are fused into an initial background field, and an analysis field closer to the actual atmospheric state is generated, so that the reliability of severe convective weather risk assessment is remarkably improved, and the accuracy of wind energy prediction is also enhanced; and more comprehensive, detailed and stable information support is provided for weather forecast and energy management.

The invention belongs to the technical field of Internet of Things prediction, and discloses a soil moisture content prediction method and system based on a BiLSTM-Transform dynamic weight hybrid architecture, and the method comprises the steps: collecting an observation data set of soil moisture content influence factors of an irrigation region, the observation data set comprising a meteorological element sequence and a soil parameter sequence; the method comprises the following steps: collecting time series data of soil moisture content influence factors, carrying out noise reduction processing on the time series data by adopting a wavelet noise reduction method to obtain noise reduction data, and filling missing values of the noise reduction data by adopting a linear interpolation method to obtain a continuous data set. According to the method, a feature fusion strategy is adaptively adjusted through a dynamic weight mechanism, the time sequence modeling capability of soil moisture content prediction is remarkably improved, parameter quantities are compressed while the prediction precision is kept, the feasibility of deployment on edge computing equipment is achieved, and the constructed framework has the advantages of improving the stability of a prediction result and improving the prediction efficiency. And the prediction result error of the soil moisture content can be effectively reduced.

The invention discloses a tunnel structure full life cycle damage detection and safety evaluation method, and belongs to the technical field of damage detection and safety evaluation. The method comprises the following steps: completing installation configuration of a mobile detection platform along the axial direction of a tunnel; generating a moving track and a detection point location distribution scheme of the mobile detection platform; controlling the mobile detection platform to sequentially move to each detection section position according to the detection path, and synchronously starting each detection module to perform continuous data acquisition in the moving process; generating a tunnel three-dimensional mathematical model, a lining structure thickness distribution diagram, a heat radiation anomaly distribution diagram and a crack damage distribution diagram; equally dividing the tunnel three-dimensional model into N detection segments according to a preset interval, and counting the lining thickness mean value, the number of heat radiation abnormal points, the crack length density and the damage level of each segment as safety evaluation indexes; statistical analysis and trend judgment are conducted on the safety indexes of all the segments, abnormal segments exceeding a safety threshold value are recognized, and the risk level of the abnormal segments is determined.

The invention provides a power system intrusion detection and defense method based on artificial intelligence, and belongs to the technical field of power system intelligent control, and the method comprises the steps: 1, collecting data based on a multi-dimensional data collection layer, and forming an original data flow containing a time-space synchronization mark; 2, dynamically segmenting the original data stream by adopting a self-adaptive sliding window mechanism, automatically adjusting the size of a window according to the arrival frequency of a data packet, and converting the continuous data stream into a final triple sequence; 3, extracting and analyzing the features of the final triple sequence, and determining an equipment behavior mode and sequential logic of power operation; 4, performing deviation analysis on the equipment behavior mode and the normal behavior mode, and generating a primary alarm signal when the deviation degree exceeds a dynamic threshold value; and 5, starting multi-stage interlocking verification based on the primary alarm signal to determine an intrusion type, and matching a preset response rule base according to the intrusion type. Intrusion behaviors in the power system are effectively detected and defended in real time.

The invention relates to the technical field of data acquisition, in particular to a large-scale node-oriented spectrum acquisition compression system, which is characterized in that the system acquires three types of sensor spectrum data characteristics, presets four types of alarm threshold generation configuration tables, and determines sampling periods of different load intervals according to the configuration tables and node real-time loads to generate scheduling schemes. According to the scheme, a sensor is controlled to collect data, compare a threshold, mark an alarm level and generate a data set, data which does not exceed the threshold is extracted, an amplitude difference is calculated, redundancy is judged, and different data are marked according to a redundancy result to generate a standardized compression format table. According to the method, multiple types of alarm thresholds are preset by obtaining spectrum data characteristics of multiple sensors, sampling periods of different load intervals are determined by combining real-time load data of monitoring nodes, data are collected according to a scheduling period, alarm levels are marked, continuous data which do not exceed the thresholds are extracted, amplitude difference values are calculated, redundancy is judged, and the reliability of the system is improved. Corresponding identifiers are added for different data to generate a standardized compression format, invalid sampling is reduced, redundancy is accurately judged, and the data transmission amount is reduced.

The invention discloses a mine pressure monitoring data optimization and feature extraction method, which comprises the following steps of: firstly, establishing a multi-channel and high-frequency original time sequence data set through continuous acquisition of underground multi-type sensors, and providing an input basis for subsequent fluctuation detection; and then, calculating the adjacent ratio of the data sequence point by point, and adaptively determining a threshold value in combination with a sliding window quantile statistical result, thereby realizing dynamic identification of high and low fluctuation points and providing a marking basis for an optimization strategy. And then, automatically matching a corresponding optimization strategy according to the distribution form of the fluctuation points, performing targeted smoothing and recovery on the abnormal data by means of point pair correlation correction, isolated point backtracking correction, continuous section batch correction, bottom backfilling and the like, and outputting an optimization sequence. And finally, taking the corrected data as new input, performing loop iterative calculation, and continuously optimizing parameters and strategies through correlation, smoothness and information entropy evaluation until indexes converge to obtain a final mine pressure monitoring data result with trend fidelity and noise suppression.

The invention relates to the field of data processing, and discloses a real-time data processing system and method, and the method comprises the steps: carrying out the real-time capturing of a continuous data flow from a multi-source collection end, and generating an initial data sequence with an emergency weight; carrying out cross-source interleaving processing on the initial data sequence, and forming a composite feature set with a time sequence hierarchy characteristic by combining an offset track of a historical data period, buffer areas of adjacent data channels and a conflict frequency of multi-source input; on the basis of the composite feature set, utilizing a partition aggregation deduction algorithm to extract a dynamic occupation path of the data event in a processing cycle, and marking potential abnormal candidate segments; performing re-grading labeling on the abnormal candidate segments, and constructing a local association network with a weight gradient; and according to the local association network, detecting and identifying the data processing units with resource mismatch in the target period, and deducing a corrected data processing sequence. The method has the advantage of improving the real-time performance of data processing.

The invention relates to a multi-scale ecological system carbon metering method, a metering model establishing method and system, equipment and a medium, and belongs to the technical field of ecological environment monitoring. The establishment method comprises the following steps: collecting continuous data of the carbon flux of the net ecosystem with different scales, and corresponding environmental factors and spatial heterogeneity parameters; performing data preprocessing on the continuous data of the carbon flux of the net ecosystem with different scales; performing feature construction on the continuous data of the carbon flux of the net ecosystem with different scales after data processing, the corresponding environmental factors and the spatial heterogeneity parameters; performing training data set construction on the data after feature construction; and based on the constructed training data set and the integrated learning model, completing the establishment of the multi-scale ecological system carbon measurement model. According to the invention, fusion of continuous data of the carbon flux of the net ecosystem with different scales is realized, and refined monitoring of the carbon of the ecosystem at different spatial positions is realized.

The invention relates to the technical field of medical data mining, in particular to a postoperative pulmonary infection prediction method and system.The postoperative pulmonary infection prediction method comprises the following steps that a continuous data set is formed by collecting breathing parameters and conducting alignment completion, tidal volume and blood oxygen response delay characteristics are extracted through sliding analysis, and a functional abnormal pulmonary segment is located through local anomaly recognition; and fusing physiological and anatomical features to establish a spatial probability map, extracting a respiratory variation coefficient and a risk feature regression analysis confidence index, and outputting an infection risk early warning list with anatomical positioning. According to the method, data faults are eliminated through timestamp alignment to improve the reliability of time sequence association, the breathing compensation capability is quantified through multi-scale window analysis dynamic coupling, lesion avoidance feature masking is accurately positioned through local anomaly detection, and the result interpretability is enhanced through combination of multi-modal feature fusion and space mapping. The three-stage progressive mechanism improves the prediction precision and timeliness, and provides a decision basis with both time sensitivity and anatomical orientation for clinic.

The invention discloses a method and system for measuring and identifying a high crack of a house wall, and belongs to the technical field of buildings, and the method comprises the steps: collecting complete wall crack point cloud data, carrying out the geometric feature extraction of the wall crack point cloud data, and dynamically adjusting the deployment density of an environment and a strain sensor. And completing the prediction of the future width of the crack through the prediction model, completing the classification of the crack risk level based on the predicted value and the structure standard, and generating a final maintenance strategy according to the crack dynamic expansion condition, the risk level and the construction resource configuration rule. According to the scheme, by introducing dynamic data fusion and prediction analysis, through continuous data collection and environment change analysis, pre-judgment and intelligent decision making of the future development trend of the crack are achieved, the damage level of the crack is evaluated through an automatic algorithm, the system can generate personalized repair plans under different crack conditions, and the repair efficiency of the crack is improved. The repairing efficiency is improved.

The invention relates to the technical field of industrial equipment control, and discloses an industrial equipment autonomous decision-making control method based on reinforcement learning, and the method comprises the steps: obtaining the time sequence data of a vibration sensor, the continuous data of a temperature transmitter and the discrete data of a pressure instrument of industrial equipment through a multi-mode sensing module; multi-modal data alignment is achieved through a feature space mapping algorithm, the thermal drift compensation amount is calculated in combination with a thermodynamic state model, self-adaptive threshold segmentation processing is conducted on pressure data, the processed data are input into a reinforcement learning decision model to generate a fusion decision result, exploration-utilization balance parameters are adjusted through a strategy updating mechanism, and the fusion decision result is obtained. And outputting the autonomous decision control scheme. The method solves the problems of poor adaptability, low decision-making efficiency and the like of a traditional control method, can improve the autonomous decision-making capability, the control precision and the operation stability of the equipment, reduces manual intervention, reduces the cost, and is suitable for intelligent control of the industrial equipment.

The invention relates to the technical field of medical equipment monitoring, in particular to an intelligent anesthesia atomization equipment state monitoring method and system. The method comprises the following steps: firstly, collecting atomization flow, particle size distribution, motor vibration frequency, liquid medicine temperature and pipeline pressure, and constructing an equipment state feature set; synchronously collecting electroencephalogram signals of a patient and constructing electroencephalogram state vectors; inputting the feature set into a support vector machine model to identify the running state of the equipment, and judging whether abnormity exists or not; when the equipment state is normal, an atomization efficiency attenuation equation is constructed based on continuous data, and the future efficiency trend is predicted; the prediction result and the electroencephalogram state are input into an anesthesia depth index dynamic balance model, and the adaptability of atomization output to the sedation reaction of the patient is evaluated; and when the efficiency attenuation rate is too high or the dynamic error exceeds a threshold value, generating a prompt signal and uploading the prompt signal to a remote platform. According to the invention, equipment state monitoring, efficiency prediction and neural feedback linkage control are realized, and intraoperative safety and postoperative evaluation precision are improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology, medical health and the like, and discloses an abnormity early warning method, device, equipment and medium based on stage penetration, and the method comprises the steps: collecting interaction whole-process behaviors to form a continuous data chain, and constructing a multi-dimensional dynamic portrait; establishing a stage penetration model, and defining progressive migration of three stages of service interaction, service use and exception occurrence; calculating the overlap ratio of the interactive and used feature identifiers at the first level, and calculating the difference degree of the used and abnormal feature identifiers at the second level; training an early warning model in combination with historical data; inputting the current state of the portrait, and outputting an abnormal level; and triggering an early warning signal according to the grade. According to the method, portraits and historical statistics are converted into calculable coincidence degree and difference degree indexes through staged modeling and hierarchical penetration, and the early warning model is formed by weights and threshold values, so that the abnormal level is judged in advance, the recognition accuracy and the response timeliness are improved, and preferential disposal of resources is facilitated.

A behavioral analysis platform is a comprehensive system designed to enhance the accuracy of polls and surveys. It utilizes an online or offline survey optimized through payload management and employs machines and deep learning models to analyze behavioral, haptic, or biometric data. The platform captures user behavior, including mouse movements, response times, and other haptic data, using custom APIs. It features a payload manager subsystem for campaign planning and execution, optimizing survey elements for behavioral analytics. The system establishes a behavioral baseline for each respondent, enabling precise analysis of survey responses in terms of conviction, veracity, and sentiment. Real-time adjustments to survey elements and continuous data capture contribute to improved predictive capabilities.

The invention discloses a seasonal frozen region salinization roadbed deformation monitoring and early warning method based on a neural network. Comprising the steps of static attribute data acquisition, dynamic monitoring data acquisition, action process data acquisition, data gridding fusion, construction and training of a first neural network model, construction and training of a second neural network model, regular monitoring and intelligent diagnosis and intelligent prediction and beforehand early warning. Data fusion is performed on spatial continuous data, investigation data, traffic load, freeze-thaw cycle and other action process data of a vertical deformation field and a salt concentration field of a roadbed, and then a serial neural network model is utilized to predict the disease type and severity of the roadbed under current and future working conditions. Full-chain intelligent analysis from multi-source data fusion, deformation prediction to disease identification is realized, the problems of monitoring fragmentation and early warning lag of a traditional method are solved, and the perception ability and the beforehand early warning level of the health state of the salinized roadbed in the seasonal frozen region are remarkably improved.

The invention provides a cross-platform data secure storage method and system based on a block chain. The method comprises the following steps: acquiring full-life-cycle operation trace data generated in a cross-platform data migration process, and constructing a life cycle event atlas based on time sequence characteristics of an operation timestamp; synchronously acquiring temperature monitoring data, and marking an operation timestamp corresponding to the physical tampering behavior and the temperature data as an abnormal event data set; performing joint coding with the life cycle event atlas according to an operation timestamp sequence to generate a space-time association evidence chain; and after the evidence chain is segmented into continuous data segments and the association marks of the adjacent segments are embedded, cross-platform storage is performed on the data segments and the association marks through the distributed characteristics of the block chain. According to the technical scheme provided by the invention, the efficiency and precision of cross-platform data secure storage can be improved.

The invention relates to a landslide hidden danger point land settlement prediction method and device based on multi-modal data, and the method considers a plurality of physical factors which greatly affect land settlement. The method comprises the following steps: firstly, dividing modal data of numerous physical factors into static data, time-varying continuous data and future predictable data according to trends of change, time, parameter types and the like, performing feature extraction on various types of data through a neural network, and capturing a complex nonlinear relationship among different modal data; the method comprises the following steps: firstly, performing feature enhancement on future predictable features of future predictable data and time-varying features of time-varying continuous data by using static features of static data, and finally, integrating the time-varying features and the future predictable features by using a multi-head attention mechanism so as to predict the land subsidence state of a rainfall-type landslide hidden danger point according to the integrated features. The accuracy of predicting the land settlement state of the landslide hidden danger point can be improved.

The invention provides a multi-parameter environment sensor chip data fusion method based on artificial intelligence, and belongs to the technical field of agricultural product growth environment monitoring. A continuous data sequence is constructed through a multi-parameter environment sensor chip, and the data quality is evaluated and preprocessed by using an abnormal jump matrix and an interference abnormal matrix; a multi-dimensional fusion algorithm is constructed to calculate a convergence index, a stability index and a disorder index to quantify a data fusion state, and a self-adaptive calibration algorithm is combined with a jump compensation matrix and an abnormal compensation matrix to carry out real-time dynamic compensation on sensor baseline drift and sensitivity attenuation phenomena. The number of attention approximation features is dynamically adjusted through a feature adjustment function, finally classification prediction and quality evaluation of the agricultural product growth environment are achieved, and the technical problem that in the long-term operation process of a multi-parameter environment sensor, baseline drift and sensitivity attenuation cause data fusion precision to be remarkably reduced along with time lapse is solved.

The invention relates to the technical field of tunnel settlement data acquisition and analysis, in particular to a tunnel settlement data acquisition method and system based on laser ranging, and the method comprises the following steps: S1, equipment is a monitoring device comprising a holder and two laser ranging sensors with a fixed included angle, the first sensor horizontally points to the side wall of a tunnel, and the second sensor horizontally points to the side wall of the tunnel; the second sensor points to the tunnel vault at an included angle theta; s2, point distribution and base point selection, wherein monitoring points are distributed in the tunnel according to a preset rule, and a zero reference point is arranged in a stable area of a tunnel portal; in the scheme, through integration of the double laser sensors and automatic holder scanning, high-density and high-precision automatic continuous data acquisition of the tunnel section is realized, and the defects of low efficiency and insufficient coverage of a traditional method are overcome; meanwhile, by means of intelligent coordinate transformation, a deformation calculation model and a multi-stage early warning mechanism, real-time calculation, trend prediction and graded automatic alarm of settlement and convergence parameters are achieved.

The invention relates to the technical field of equipment state monitoring, in particular to an electronic component monitoring system based on big data, which comprises a multi-frequency response analysis module, a frequency domain feature reconstruction module, a stress deviation trend module, a coupling correlation structure module and a grade mapping generation module. According to the invention, through continuous data acquisition and analysis based on multi-frequency response information, electrical parameter changes of components are tracked in real time, change trends under various frequencies are continuously monitored and accurately identified, and through analysis and extraction of frequency domain data features and combination of stress deviation trend analysis, tiny changes caused by external environment changes are identified. According to the electrical parameter change of different time slices, the long-term health state of the component is comprehensively reflected, a dynamic evolution model of the component is constructed, a multi-dimensional data association analysis method is adopted, and the component degradation process is accurately evaluated by judging the relevance among different electrical parameters. And scientific and accurate decision support is provided for component maintenance and replacement.

A behavioral analysis platform is a comprehensive system designed to enhance the accuracy of polls and surveys. It utilizes a web-based online survey optimized through payload management and employs machine and deep learning models to analyze behavioral data. The platform captures user behavior, including mouse movements, response times, and other haptic data, using custom APIs. It features a payload manager subsystem for campaign planning and execution, optimizing survey elements for behavioral analytics. The system establishes a behavioral baseline for each respondent, enabling precise analysis of survey responses in terms of conviction, veracity, and sentiment. Real-time adjustments to survey elements and continuous data capture contribute to improved predictive capabilities. The platform is applicable across various media types and is capable of monitoring and processing survey results dynamically. Overall, it offers a sophisticated approach to behavioral analysis for more accurately capturing end-user authentic sentiment.

The invention discloses a multi-sensor fusion road surface real-time detection method, system and device, and the method comprises the steps: carrying out the continuous data collection of a road surface through a laser radar in the advancing process of a construction machine, and obtaining the polar coordinate data; converting the polar coordinate data into rectangular coordinate data, and screening to obtain coordinate points consistent with a pavement coordinate system; correcting the coordinate points according to the height change of the laser radar; according to the angle data obtained through coordinate transformation and the laser radar attitude angle measurement data, cross section gradient data are obtained through calculation; acquiring height data according to the corrected coordinate points to calculate the flatness of the cross section; calculating a moving distance according to the laser radar GPS coordinate, constructing a pavement three-dimensional coordinate in combination with the corrected coordinate point, constructing an interpolation point by using an interpolation method, calculating to obtain an interpolation height, reconstructing the pavement three-dimensional coordinate by using the interpolation height, and calculating to obtain the flatness and gradient of a vertical section. According to the invention, efficient and real-time gradient and flatness detection can be realized, the measurement precision is improved, and the function dimension is expanded.

The invention discloses an electric energy meter data compression method and system, electronic equipment and a storage medium, and the method comprises the steps: carrying out the first-order differential processing of an electric quantity measurement data sequence, obtaining a residual data sequence, greatly reducing the value domain of the residual data sequence, greatly improving the repetition, and remarkably reducing the statistical entropy; low-entropy and high-redundancy ideal input is created for subsequent coding, and the compression ratio is integrally improved. According to the method, the residual data sequence is subjected to coding processing, positive and negative information is reserved, the problem that complement storage equivalent entropy is not reduced is avoided, bit column recombination processing or byte column recombination processing is performed on the residual coding sequence, and a large number of continuous data streams of local repeated fragments are generated, so that in an electric energy meter environment in which the MCU computing power and the RAM are limited subsequently, the residual data sequence is subjected to bit column recombination processing or byte column recombination processing. The lightweight compression algorithm can also quickly discover and reuse redundancy in an extremely short window, and the overall compression efficiency is remarkably improved.

The application discloses an electric energy meter data compression method and system, an electronic device and a storage medium. The method first performs first-order difference processing on an electric quantity measurement data sequence to obtain a residual data sequence. The value range of the residual data sequence is greatly reduced, the repetition degree is greatly increased, and the statistical entropy is significantly reduced, thus creating an ideal input with low entropy and high redundancy for subsequent coding, and improving the compression ratio as a whole. The residual data sequence is then coded, the positive and negative information is retained, and the problem of equivalent entropy not being reduced due to complement storage is avoided. The residual coded sequence is then subjected to bit column reorganization processing or byte column reorganization processing, and a continuous data stream with a large number of locally repeated segments is generated, so that in the subsequent electric energy meter environment with limited MCU computing power and RAM, a lightweight compression algorithm can also quickly find and reuse redundancy in a very short window, and the overall compression efficiency is significantly improved.

The present invention relates to the field of ecological monitoring technology, specifically to an agricultural ecological environment monitoring method and system based on digital twins, comprising the following steps: acquiring monitoring data within farmland, constructing a mapping relationship, performing time series arrangement, merging multi-source data, calling a virtual grid to update a three-dimensional model, generating mapping results, analyzing crop growth images, tracking environmental changes, comparing ecological stability intervals, extracting risk trends, calling a three-dimensional model, and generating a risk warning interface layer. In the present invention, by acquiring continuous data of the agricultural ecological environment and constructing a mapping relationship to arrange the information in time series, the response speed and processing accuracy to changes in the agricultural ecological environment are improved, the monitoring and management of the crop growth environment are optimized, and the real-time updated three-dimensional environmental model is used to intuitively display environmental changes. By comparing humidity and temperature changes, spatial fragments are screened, and detailed monitoring and accurate warning of environmental changes are strengthened.

A detection engine for detecting threats to a computing system is disclosed. The detection engine includes an interceptor that is positioned in a data path and configured to intercept IOs. The interceptor transmits a data stream, which may include data and / or metadata or the intercepted IOs, to a detector. The detector perform a detection analysis. When a threat is detected, a response may be initiated. The interceptor is configured to perform the response.

The invention discloses a distributed rock stress real-time inversion method and system, and the method comprises the steps: discretizing a target region rock structure through a discontinuous structure stress field model, collecting parameters, and constructing a geological-physical constraint inversion frame; initial stress tensor distribution is obtained by applying a seismic source mechanism solution and a stress tensor linear inversion algorithm, and optimization is carried out in combination with a constraint framework; distributed rock stress parameters are introduced to establish a mapping relation to invert initial distribution, and real-time updating is achieved through continuous data collection and repeated processing. The system comprises a plurality of association units which respectively execute the functions of discrete acquisition, framework construction, inversion optimization and the like. According to the method and the system, the geological-physical constraint quantification accuracy is improved, the problem that a real-time updating mechanism is incomplete is solved, the accuracy, comprehensiveness and efficiency of inversion are improved, and reliable technical support is provided for geological engineering, disaster early warning and the like.

The invention discloses a video analysis-based early warning and monitoring method for children hyperactivity behavior and a storage medium, and the method comprises the steps: firstly, guaranteeing the comprehensive monitoring of children behaviors through employing a multi-channel video collection device, and providing a sufficient continuous data source for subsequent analysis; furthermore, the quality of monitoring data is ensured through the use of image noise reduction and segmentation technologies, and accurate motion features are effectively extracted through the combination of an optical flow algorithm and a background subtraction algorithm; further, the movement behaviors of the children are comprehensively analyzed by calculating behavior parameters such as movement amplitude, movement direction change and continuous movement time, and potential behavior abnormity is revealed; the multi-dimensional behavior feature vector obtained through behavior parameter analysis is compared with the standard template, the behavior type of the child is automatically recognized, early-stage symptoms of abnormal behaviors such as hyperactivity and the like are found in time, and a basis for early diagnosis and intervention is provided for behavior problems such as hyperactivity and the like of the child.