6 results about "Linear regression function" patented technology

The application relates to a key segmentation storage method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining an original key, encoding the original key to obtain a target value set; obtaining a target confusion factor and a target random number, and constructing a target linear regression function; sequentially selecting a current substitution value from the target value set, obtaining a current cycle number, analyzing the multiple relationship between the current cycle number and the target confusion factor to obtain a target analysis result; based on the target analysis result, substituting the current substitution value into the target linear regression function to obtain at least two current intermediate values; adding the at least two current intermediate values into a corresponding current intermediate value set to obtain at least two current intermediate value sets; repeating the operation of selecting the current substitution value until a termination condition is met, and obtaining at least two target result value sets; and sequentially splicing each value corresponding to the at least two target result value sets respectively to generate and store at least two final values. The method can improve the security of key storage.

This invention relates to the field of image processing technology, and in particular to an automated inspection method for the factory quality of liquid crystal screens based on image processing. The method acquires a grayscale image of the liquid crystal screen, divides the grayscale image into at least two window regions, merges the window regions according to their region type to obtain at least two target regions, marks the defect edge pixels in each target region, and further divides each target region based on the defect edge pixels to obtain multiple final divided regions. It then obtains the edge detection dual thresholds and region exposure coefficients of each final divided region and performs linear regression fitting to obtain the corresponding linear regression function. Using the linear regression function, it obtains adaptive edge detection dual thresholds for each final divided region, which are used to detect scratch defects on the liquid crystal screen. This achieves accurate calculation of adaptive edge detection thresholds for each region, effectively solving the problems of missed detections and false detections caused by traditional global thresholds.

The invention relates to a computer-implemented method (200) for training an artificial intelligence-based model (M) and to a computer-implemented method (600) for supporting an operation on a patient's eye, comprising such a model (M), which is used to calculate and / or provide refractive output data (933) on the basis of input data (931), and in particular to create nomograms. Nomograms from the prior art may either have an accuracy in need of improvement or, if the accuracy is improved, may generate implausible profiles of the nomogram. According to the invention, more accurate nomograms based on the output data (933) are made possible without implausible states. This is made possible by a cost function (915) which comprises a non-linear output value (917), representing a measure of the prediction error, of a univariate linear regression function and at least one non-linear penalty term (919). The invention further relates to a trained model (M) or a weighting matrix (923) of such a model (M), to a computer program product, to a data processing device (800), to a computer-readable medium, and to a laser therapy device.

A computer-implemented method (200) for training an artificial intelligence-based model (M) and a computer-implemented method (600) for supporting surgery on a patient's eye are provided, comprising such a model (M) which serves to calculate and / or provide refractive output data (933) based on input data (931), and in particular to generate nomograms. Prior art nomograms may either have insufficient accuracy or, if the accuracy is improved, generate implausible nomogram progressions. According to the invention, more accurate nomograms based on the output data (933) are enabled without implausible states.This is made possible by a cost function (915) comprising a nonlinear output value (917) of a univariate linear regression function representing a measure of the prediction error and at least one nonlinear penalty term (919). Furthermore, a trained model (M) or a weighting matrix (923) of such a model (M), as well as a computer program product, a data processing device (800), a computer-readable medium, and a laser therapy device are described.

The present disclosure relates to a method, device, medium, equipment and program for determining carbon emission abnormal data, and relates to the technical field of carbon emission monitoring. The method comprises: determining first data and second data, wherein the first data is a value of a specified category parameter in a first period, the specified category is selected from a plurality of categories including carbon dioxide emission, low calorific value of coal, etc., and the second data is a value of a second category parameter in the first period, the second category parameter being correlated with the specified category; substituting the second data into a preset linear regression function to obtain a predicted value of the first data; calculating a difference between the first data and the predicted value to obtain a prediction residual of the first data; and determining that the first data is carbon emission abnormal data in a case where the prediction residual of the first data exceeds a preset range. The method can improve the accuracy of carbon emission abnormal data diagnosis.

The application provides a distributed photovoltaic power station fault diagnosis method and device based on AMI data, wherein the method comprises the following steps: constructing a training sample library and a test sample library of the distributed photovoltaic power station; establishing a power generation operation model of the distributed photovoltaic power station according to the training sample library; calculating a linear regression function of the power generation operation model; identifying a fault power station in the test sample library according to the linear regression function; and diagnosing the fault power station by using AMI data. The application can realize rapid identification, accurate positioning and fault cause diagnosis of the distributed photovoltaic power station fault only by using AMI data, so that the efficiency of fault troubleshooting can be improved, and the influence of the power station fault on photovoltaic power generation efficiency can be reduced.