66 results about "Data series" patented technology

The Marker Fingerprinting system provides a method for identifying and correlating serial or sequential data patterns across diverse domains such as geological, biological, and financial datasets. This innovation transforms single- or multi-attribute data series into feature matrices, generating unique hash tokens—or fingerprints—that encapsulate specific data patterns. Using advanced signal analysis and spectral transformations, it enables efficient processing and pattern recognition within complex datasets. Fingerprints from reference patterns are matched against target datasets, with quantitative confidence metrics derived from weighted algorithms assessing match accuracy. Iterative data conditioning enhances robustness by addressing noise and inconsistencies, ensuring reliability at scale. The invention improves decision-making by delivering rapid and accurate pattern identification with quantified reliability, making it particularly suited for applications like geological top picking, seismic data analysis, and other fields requiring precise data correlation

An anomaly cause estimation apparatus includes: an anomaly detection unit converts a data series acquired in a time series from a plurality of components provided in a target system into an anomaly level data series, and detects an anomaly based on the obtained anomaly level data series; and an anomaly propagation estimation unit inputs a target anomaly level data series, extracted from the anomaly level data series, for a period before a point in time at which the anomaly is detected, a target data series corresponding to the target anomaly level data series, and information indicating a causal relationship between the components to an anomaly propagation estimation model, and estimates an anomaly propagation likelihood of the anomaly propagating between the components.

A method for analyzing brain imaging data from a brain lesion patient and generating prognostic information is disclosed. The method includes obtaining imaging data of the brain of a patient from a scanner and classifying the data by acquisition plane and modality to select a data series of interest. The method further involves processing the data series of interest to generate brain masks and corresponding volumetric data. The brain masks and corresponding volumetric data are then co-registered to a common brain space, and registered volumetric data is generated. Lesion segmentation is performed to generate a lesion mask in the common brain space. The lesion mask data is applied to a trained prognostic model, which comprises a machine learning model configured to output a probability-based prognosis of the patient's brain lesion.

The invention discloses a residential charging facility load identification method and system, electronic equipment and a storage medium, and the method comprises the steps: firstly collecting a historical daily power utilization characteristic data sequence and a historical charging state data sequence of each residential charging facility; through calculation and analysis of correlation between a historical daily power utilization characteristic data sequence and a historical charging state data sequence, a deep association relationship between power utilization characteristic data and charging state data of different charging facilities can be mined. Taking the correlation sequence as a feature vector, adding a label according to the type of the residential charging facility, constructing to obtain a training data set corresponding to each type of residential charging facility, training the support vector machine model by using the training data set to obtain a load identification model, and finally identifying the load of the residential charging facility according to the load identification model. Real-time load identification can be carried out after the real-time power utilization characteristic data and the real-time charging state data of the charging facility to be identified are collected and the characteristics are extracted, so that the accuracy of load identification is greatly improved.

To realize non-teacher-type data classification in a more preferable aspect.SOLUTION: A calculation part 12 generates a similarity matrix whose elements are similarities between each of feature quantities extracted from each of a series of data to be classified. A correction part 13 corrects the similarity matrix by replacing at least some of the elements of the similarity matrix with the similarity to which conversion has been applied according to a degree of similarity corresponding to the elements. A classification part 14 classifies the series of data into one or more groups based on the similarity matrix after correction by the correction part 13.SELECTED DRAWING: Figure 1

Machine learning models for spatial-temporal forecasting systems based on a multi-layer perceptron (MLP) model or other feedforward network can incorporate one or more random projection layers. Such models need not compute or rely on information representing relationships between different spatial nodes. In addition, the model can include temporal mixer layers that process time series data in the frequency domain, thereby leveraging the periodicity of many spatial-temporal data series.

A plunger lift management system may measure a casing pressure data series of an annular space between a casing and a tubing. A plunger lift management system may measure a tubing pressure data series of the tubing. A plunger lift management system may generate a pressure differential data series based on the casing pressure data series and the tubing pressure data series. A plunger lift management system may, based on the pressure differential data series, a weight of a plunger, and a length of the tubing, identifying a weight of liquid lifted by the plunger.

The invention discloses a meteorological data extension method considering mean variance consistency, S1, grouping stations, and obtaining the initial data sequence of the reference station and the interpolation station; S2, obtaining the simple interpolation sequence of the interpolation station; S3, obtaining the correlation calculation sequence of the interpolation station and the reference station; S4, calculating the correlation coefficient between stations, and determining the interpolation reference station list of the interpolation station; S5, interpolating the interpolation station, obtaining the preliminary interpolation sequence of the interpolation station; S6, calculating the interpolation correction parameter based on the simple interpolation sequence and the preliminary interpolation sequence of the interpolation station; S7, correcting the preliminary interpolation sequence of the interpolation station, obtaining the corrected interpolation sequence of the interpolation station; S8, merging the corrected interpolation sequence and the simple interpolation sequence of the interpolation station, and obtaining the final interpolation station completed data sequence. The advantages are: making the mean and variance of the interpolation extension data series and the original data series at the same level or having a more reasonable change trend, avoiding obvious mutation or transition phenomenon, and improving the accuracy of interpolation data.

A method (200) for assessing the condition of a road (120) comprises steps of periodically acquiring (205) vertical velocity data on board a vehicle (105) traveling on the road (120); generating (215) several overlapping data series (405-450) of predetermined length from the acquired data; recreating (220) each data series (405-450) using a capsule autoencoder (138); determining (225) a mean absolute error between each data series (405-450) and its corresponding newly created data series (405-450); and detecting (230) an anomaly on the road (120) when the mean absolute error exceeds a predetermined threshold.

The present disclosure generally relates to apparatus, software and methods for detecting anomalous elements in data. For example, the data can be any time series, such as but not limited to radio frequency data, temperature data, stock data, or production data. Each type of data may be susceptible to repeating phenomena that produce recognizable features of anomalous elements. In some embodiments, the features can be characterized as known patterns and used to train a machine learning model via supervised learning to recognize those features in a new data series.

The invention discloses a multivariable flood design standard value measuring and calculating method and system based on a combination relation curve, and the method comprises the steps: firstly collecting the upstream multi-year hydrological data of a reservoir design object to be built, sorting out the data series of the flood peak of each year and the flood volume in different time periods, and then selecting the flood volume in the time periods to form a multivariable extreme value series; then carrying out variability detection on the selected multivariable extreme value series and obtaining a variability detection result; according to the method, the function of diagnosing the variability of the multivariable series is realized, and the multivariable dynamic joint distribution model can be constructed for the varied multivariable series; then a combination relation curve between the primary variables and the secondary variables is established through a condition most probable combination method, the combination relation curve is inquired on the basis of the design value of the primary variables under the non-consistency condition to obtain design standard values of the corresponding secondary variables, and therefore the multivariable flood design standard values of the given return period under the non-consistency condition are obtained through deduction, and measurement and calculation efficiency is high; and the measurement and calculation result is accurate, and the method is suitable for being widely popularized and used.

Disclosed concepts aim to provide schemes, solutions, concepts, designs, methods, and systems pertaining to improved prediction of gestational weight gain (GWG). Specifically, a data series describing weight of the pregnant subject at least twice per day (e.g., after waking up, and before going to sleep) during an early stage of pregnancy (e.g., during the first 30 days of pregnancy, or during the first trimester) is used to determine a historic GWG curve of the subject. As energy balance in pregnancy is defined as energy intake equal to energy expenditure plus dynamic energy storage, a specific GWG prediction model is used to generate the historic GWG curve, rather than a generic weight gain model. From the historic GWG curve, a future GWG value of the subject may be predicted. This future GWG value may be used to assess a pregnancy risk score, and / or to generate lifestyle recommendations for the subject.

This invention discloses a method and system for calculating the design standard value of multivariate floods based on a combination relationship curve. First, it collects multi-year hydrological data upstream of the proposed reservoir and compiles data series of flood peaks and flood volumes for each year and time period. Then, it selects time period flood volumes to form a multivariate extreme value series. Next, it performs variability detection on the selected multivariate extreme value series and obtains the variability detection results. This invention achieves the function of diagnosing the variability of multivariate series and can construct a multivariate dynamic joint distribution model for multivariate series with variability. Then, it establishes a combination relationship curve between the primary and secondary variables using the conditional most probable combination method and obtains the design standard value of the corresponding secondary variable by querying the combination relationship curve based on the design value of the primary variable under inconsistency. Thus, it derives the multivariate flood design standard value for a given return period under inconsistency. This method not only has high calculation efficiency but also provides relatively accurate results, making it suitable for widespread promotion and use.

The invention relates to a method for forming a continuous spatio-temporal data sequence based on a species distribution model and an environmental data supplementary time section, and relates to the technical field of fishery resource investigation and evaluation and ecological system modeling and management. The method comprises the following steps: collecting fixed-point survey data and environmental condition data; establishing a resource-environment relation model; acquiring environment data at a target time point and speculating a fishery resource distribution state based on the model; speculating resource distribution characteristics in the middle time period through interpolation between the two investigation time points; adjusting environmental adaptation feature optimization prediction based on the speculation result; and finally, integrating the speculated data and the measured data to generate a minute-scale, hour-scale or daily-scale continuous three-dimensional resource distribution data set. According to the method, the temporal-spatial resolution and continuity of fishery resource distribution data can be remarkably improved, the ecological mechanism support of prediction is enhanced, and the method is widely applied to fishery resource dynamic monitoring, ecological system evaluation, protection division formulation and fishery management based on an ecological system.

To make operation of generating training data more efficient in machine learning for events in data series. An information processing apparatus includes: a division section that divides, into a plurality of partial feature sets, a set of features constituting a feature series corresponding to each of a plurality of data series; a clustering section that clusters, into a plurality of clusters, a group of the plurality of partial feature sets which has been obtained from the plurality of data series; and a selection section that selects target data to be provided with a ground truth label, from a set of pieces of data which corresponds to at least one of the plurality of partial feature sets included in each of the plurality of clusters and which constitutes at least part of one of the plurality of data series.

The invention relates to the technical field of application program front ends, in particular to a 3D map multi-layer dynamic interaction and vector element control simulation method, device and equipment and a medium, and the method comprises the steps: receiving longitude and latitude data required by map vector elements, and configuring a setOption method of ECharts based on the received data; monitoring an interaction event of a map geographic coordinate system by utilizing a response type mechanism of Vue, and establishing a dynamic association relationship; according to the change of the scaling value, dynamically adjusting the configuration of the geographic coordinate system and the data series, and synchronously updating the position of each layer based on the association relationship; traversing vector element data in the data series, and calculating visual parameters of vector elements based on the scaling values; correcting the coordinates of the vector points in real time by adopting a boundary constraint algorithm; and automatically adjusting the icon size and the font size according to the zoom value, and hiding the secondary elements when the zoom level is lower than a threshold value. The position constraint of vector elements is realized, and the visual effect is improved.

The invention discloses an intelligent control algorithm for realizing precise fermentation, and relates to the field of organic compost fermentation control. The method comprises the following steps: collecting material characteristic parameters of compost materials and time series data of fermentation process parameters, extracting a local feature sequence of a data series by using a convolutional neural network, processing by taking the local feature sequence as input of a recurrent neural network, obtaining feature vector sequence data of the fermentation process parameters, and establishing a feature database; the method comprises the following steps: collecting fermentation process parameters of a newly added compost material in an initial decomposition stage with a time step length of lambda, extracting a feature vector sequence as a real-time sequence, calculating a dynamic time bending distance between the real-time sequence and a comparison sequence, and taking the type of the compost material corresponding to a minimum value in a distance calculation result as the type of the newly added compost material, and determining the material characteristic parameters according to the types of the newly added compost materials, and adjusting the control strategy of the fermentation process according to the determined material characteristic parameters of the newly added compost materials.

Described herein is a computer implemented method for generating a new chart based on a source chart and a destination chart. The method includes accessing source chart data in respect of the source chart, wherein the source chart data defines a set of source chart data series and a set of source chart colours, and wherein each source chart data series is associated with a source chart colour and accessing destination chart data in respect of the destination chart, wherein the destination chart data defines a set of destination chart data series and a set of destination chart colours, and wherein each destination chart data series is associated with a destination chart colour. The method further includes determining that the number of source chart colours is greater than the number of destination chart colours and, in response, generating one or more new chart colours. The method further includes generating the new chart to include the set of source chart data series, associating a first source chart data series with a destination chart colour and associating a second source chart data series with a new chart colour.

Embodiments include example systems, methods, and computer-accessible mediums for analysis and visualization of data associated with anatomical images. In some embodiments the anatomical images can be spinal images used for assessment of stenosis and disc degeneration. In some embodiments, systems, devices, and methods described herein include selecting a region of interest (ROI) in a three-dimensional (3D) volume of image data of a plurality of vertebra of a spine, identifying one or more anatomical parts in the ROI, determining one or more parameters of the one or more anatomical parts, and assessing a severity of a spinal deformity based on the one or more parameters.

A diagnostic method for the remaining service life of a switching device, wherein performance characteristics of the switching device (1) are obtained with a measuring unit (41, 42) and then used as historical condition value data relating to a deterioration state of the switching device (1), are estimated with a condition value estimation unit (51) on the basis of measurement data obtained by the measuring unit (41, 42); wherein, on the basis of the historical condition value data, a remaining service life estimation unit (53) generates two or more sets of data series, namely - data series in which the state values ​​are plotted, the abscissa indicating the elapsed time during an operating period of the switching device (1); - data series in which the state values ​​are plotted, the abscissa indicating the number of operations of the switching device (1) during the operating period of the switching device (1); - data series in which the state values ​​are plotted, the abscissa indicating the non-operative time of the switching device (1) during the operating period of the switching device (1); and - data series in which the state values ​​are plotted, the abscissa indicating the accumulated operating time of the switching device (1) during the operating time of the switching device (1); wherein, on the basis of the data series among the generated two or more data series sets for which the correlation between the abscissa values ​​of the generated data series sets and the state values ​​corresponding to the respective abscissa values ​​is the strongest, a first deterioration tendency of the switching device (1) is determined; wherein a first estimated value of the remaining service life of the switching device (1) is calculated on the basis of the first deterioration tendency; wherein the first deterioration trend is removed from the generated two or more data series sets; wherein a second deterioration tendency is determined on the basis of the data series from the two or more data series sets from which the first deterioration tendency has been removed, for which the correlation between the abscissa values ​​of the data series sets from which the first deterioration tendency has been removed and the condition values ​​corresponding to the respective abscissa values ​​is the strongest; wherein a second estimated value of the remaining service life of the switching device (1) is calculated on the basis of the second deterioration tendency; and wherein the remaining service life of the switching device (1) is then determined at least on the basis of the first estimated value and the second estimated value of the remaining service life.

Disclosed are a processing method, device, medium, and product for spatiotemporal data sequences. The method includes storing a plurality of points in a graph database, wherein each of the plurality of points has a corresponding point identifier and a point type, wherein the plurality of points include: a plurality of location points, each location point corresponding to its associated location information, a spatiotemporal data sequence point, the spatiotemporal data sequence point corresponding to a location point associated with the spatiotemporal data sequence point in the plurality of location points, and a plurality of index points, each index point corresponding to an attribute value of a corresponding attribute of the associated location point. The method also includes storing a plurality of edges in a graph database, wherein each of the plurality of edges has a corresponding endpoint identifier and an endpoint type, wherein the plurality of edges include: a plurality of first edges, each first edge pointing from the spatiotemporal data sequence point to a corresponding location point in the associated location points, and a plurality of second edges, each second edge coupling a corresponding index point to an object endpoint.

The invention provides a grassland recovery state dynamic monitoring system and method based on multi-scale fusion, and the system comprises a multi-scale data obtaining module which is used for obtaining macro monitoring data of a grassland through a satellite remote sensing technology, and obtaining micro monitoring data of the grassland through an unmanned plane; the long-time sequence data analysis module is used for collecting macroscopic monitoring data and microscopic monitoring data in a long time, forming a time sequence, performing fusion analysis, and determining an actual growth state and a recovery effect of the grassland; and the prediction and strategy adjustment module is used for predicting the grassland growth trend and adjusting the grassland recovery strategy based on the grassland actual growth and recovery effects in combination with the actual grassland environment data and the historical time sequence. A dynamic monitoring system is established by combining macro monitoring of satellite remote sensing and micro monitoring of an unmanned aerial vehicle, precise monitoring and prediction of the grassland growth trend are achieved, and timely and accurate data support is provided for management personnel to adjust a recovery strategy.

The present invention relates to the technical field of urban management, and discloses a city potential assessment method and system based on multi-indicator fusion. The method comprises the following steps: deploying multiple data source collection points for a target potential assessment city, preprocessing initial environmental indicator data, and determining target environmental indicator data; extracting target environmental indicator data of the same type, constructing a target environmental indicator data series, and calculating environmental indicator data pointing coefficients; performing set division of environmental indicator data pointing coefficients based on a preset environmental indicator data pointing coefficient series, and calculating initial potential assessment factors; generating potential assessment identifiers for data source collection points; counting positive and negative quantities, setting a potential assessment optimization coefficient, optimizing the initial potential assessment factor, and obtaining a target potential assessment factor. The method evaluates the city potential based on the multiple environmental indicator data, thereby ensuring the accuracy and comprehensiveness of the city potential assessment and providing a basis for comprehensive urban development and key city selection by operators.

The invention relates to the technical field of material detection, in particular to a method for detecting the performance of a heat stabilizer for a PVC (polyvinyl chloride) product, which comprises the following steps: acquiring a multi-dimensional data sequence formed by production data and test data of the PVC product and a standard sequence corresponding to the data sequence of each dimension; according to the difference distribution between the data sequences of different dimensions of any batch of PVC products and the corresponding standard sequences, the trend influence degree of the data sequences of the PVC products under each dimension is obtained; obtaining the environmental condition influence degree of each batch of PVC products according to the aggregation characteristics of the trend influence degrees of the corresponding data sequences of all batches of PVC products under all dimensions; and analyzing the influence degrees of all environmental conditions of the PVC product by using a neural network so as to evaluate the performance of the stabilizer in the PVC product. The accuracy of the performance evaluation result of the heat stabilizer in the PVC product is improved.

The invention provides a design method of a curve groove of a zoom cam lever and a zoom mechanism, and the method comprises the steps: obtaining data columns of the moving distances of a zoom lens group and a compensation lens group through optical software simulation, arranging the data columns, determining data and data serial numbers of a circle of rotation of the zoom cam lever, and calculating the curve groove of the zoom cam lever; and by adjusting the radius of the zoom cam lever or calculating the rotation angle of the corresponding point, it is ensured that all the pressure angles in the data column are not larger than the allowable pressure angle. According to the width of the curve groove and the minimum wall thickness of the curve groove, the minimum moving distance of one circle of curve winding is limited, so that the inner wall of the curve groove is smooth in the whole process and not prone to deformation, it is guaranteed that excellent imaging quality is obtained, smooth movement of the zoom guide pin can be guaranteed, a zoom mechanism is not prone to being blocked or even stuck, jumping of an optical axis is reduced, and the service life of the zoom mechanism is prolonged. And the driving torque of the motor for driving the zoom cam rod to rotate is reduced.

An approach for forecasting multiple related data series includes first determining individual forecasts for different items or groups of items and / or over different time sequences or granularities. These first forecasts are then reconciled to form second forecasts that satisfy relationships between the data series while best approximating the first forecasts.

This invention discloses a method for assessing the safety status of a material yard based on multi-source sensing data, belonging to the field of data processing technology. The method includes acquiring multi-source sensing data from various location units within a continuous sampling time and constructing a data time series; establishing adjacency relationships between location units based on spatial coordinates; correcting the data based on the differences between adjacent time points and the spatial differences between adjacent location units to obtain a target data series; calculating spatial difference indices for each location unit under various data types based on the target data series; determining weight values ​​based on the magnitude of the spatial difference index differences; weighted fusion of the spatial difference indices to obtain the overall spatial status value of the material yard; and performing spatial difference concentration analysis based on this spatial status value to determine the safety status level. This invention, through time and spatial consistency correction and multi-source fusion analysis, achieves a quantitative assessment and graded output of the overall safety status of the material yard, improving the ability to identify local spatial anomalies and the overall risk characterization capability.

The present invention relates to the field of data processing technology, and in particular to a key link management and control system and method for distribution network materials based on artificial intelligence. The method includes the steps of: collecting data of each dimension at each sampling moment, obtaining each dimension historical data sequence corresponding to each sampling moment; based on each dimension historical data sequence, obtaining the degree of correlation between all two dimensional historical data sequences corresponding to each sampling moment and obtaining the comprehensive synergy index between all dimensional historical data sequences corresponding to each sampling moment, correcting the initial smoothing parameter according to the degree of correlation between all two dimensional historical data sequences corresponding to each sampling moment and the comprehensive synergy index between all dimensional historical data sequences, obtaining the corrected value of the smoothing parameter at each sampling moment, and predicting the value of each dimensional data at the next moment of each sampling moment according to the corrected value of the smoothing parameter at each sampling moment. The present invention makes the prediction result more accurate.

The application discloses a bridge structure parameter correction model establishment and prediction method based on time domain data, which comprises the following steps: selecting at least one type of to-be-corrected parameter of a bridge structure; taking each type of to-be-corrected parameter as a training sample; obtaining a series of acceleration time history data of each type of to-be-corrected parameter corresponding to each measuring point position and taking the series as a sampling point; compressing and converting the series of acceleration time history data into accumulated intensity values and inputting data, so as to construct a training sample set; establishing a blind Kriging model; inputting the training sample set into the blind Kriging model; determining important variables by using a Bayesian variable selection algorithm; starting iteration from 0 by setting a parameter k in the blind Kriging model; finally finding an optimal value of k; finding other corresponding parameters of the blind Kriging model from the optimal value; substituting the parameters into the blind Kriging model; and obtaining a final blind Kriging model. The bridge structure parameter can be corrected based on the time domain data.

Method for checking and, if necessary, improving the setting of at least one parameter of a control unit monitoring function of a vehicle diagnostic system, taking into account at least one robustness indicator, in particular taking into account four robustness indicators, - where at least one robustness parameter R z [n] is calculated according to the following equation: R z [ n ] = 1 r max_pos / max_neg ⋅ N 0 ∑ i = n n+N 0 ri - where r max_pos / max_neg the largest positive or largest negative distance value when monitoring against a positive or a negative deviation is, - where N0 is the number of data points in the data series that represents the minimum time, in particular the debounce time, for error detection, - where n is an element of a data series of consecutive feature values, - where r ithe distance of a characteristic value from a positive or negative error threshold, determined on the basis of the raw distance, - where the setting of at least one parameter is retained if the calculated value R z or the calculated values ​​R z above a minimum robustness index R z,min lies / lie - and where the setting of at least one parameter is adjusted when the calculated value R z or the calculated values ​​R z below the minimum robustness index R z,min lies / lie or the calculated value R z or the calculated values ​​R z the minimum robustness index R z,min corresponds / correspond to, - wherein, in order to check the setting of at least one parameter, the results of the control unit monitoring function are calculated by inputting an input data set of a functioning system and an input data set of a non-functioning system into the control unit monitoring function, characterized in that - that, to check the setting of at least one parameter, the results determined by the control unit monitoring function are compared with certain values ​​of a characteristic of a functioning system, and, to monitor against a positive error threshold exceedance, a value R is calculated. z,max_threshold,False Fail to check whether a functioning system is incorrectly identified as non-functional, - that, in order to verify the setting of at least one parameter, the results obtained by the control unit monitoring function are compared with certain values ​​of a characteristic of a functioning system for monitoring against a negative error threshold undercutting by calculating a value R z,min_threshold,False Fail to check whether a functioning system is incorrectly identified as non-functional, - that, in order to verify the setting of at least one parameter, the results determined by the control unit monitoring function are compared with certain values ​​of a feature of a non-functional system for monitoring against a positive error threshold undercutting by calculating a value R z,max_threshold,False Pass to check whether a non-functional system is incorrectly identified as functional, - and that, to verify the setting of at least one parameter, the results obtained by the control unit monitoring function are compared with certain values ​​of a feature of a non-functional system for monitoring against a negative error threshold exceedance by calculating a value R z,min_threshold,False Pass It should be checked whether a non-functional system is incorrectly identified as functional.