12results about How to "Improve the determination accuracy" patented technology

The embodiment of the application discloses an image processing method, according to the classification label obtained by performing semantic segmentation on the to-be-processed image, determining the subject region, the edge undetermined region and the background region corresponding to the target object in the to-be-processed image, setting the identification value of the subject region as a first identification value, and setting the identification value of the background region as a second identification value. According to the pixel points adjacent to the edge undetermined region in the subject region and the background region, the pixel feature similarity between the pixel points in the edge undetermined region and the adjacent pixel points is calculated, and according to the similarity calculation result and the first and second identification values, the identification value of the pixel points in the edge undetermined region is determined. The closeness of the identification value to the first identification value and the second identification value can determine whether the pixel points belong to the target object, so that the edge part of the target object can be accurately determined, the determination accuracy of the region where the target object is located in the to-be-processed image is improved, and the image background removal scene with high precision requirement is suitable.

The application discloses a precoding matrix determination method, device and equipment and a storage medium. The method comprises the following steps: sending a first instruction to a terminal; the first instruction is used for instructing the terminal to report at least a first matrix; the first matrix is used for determining a precoding matrix; receiving a first uplink reference signal sent by the terminal; obtaining a prediction result by using the first uplink reference signal and a pre-trained neural network model; the prediction result comprises a first downlink channel matrix between a network device and the terminal; and determining the precoding matrix based on the first downlink channel matrix.

The invention discloses a nonmetal pipeline detection positioning device, method and system, and the positioning device integrates a sound generation device, a sound pickup, a main controller and the like through a detection box body, and an operator can carry one detection box body to carry out the detection work of a nonmetal pipeline. The sound generating device and the sound pick-up are used in cooperation, the position of the non-metal pipeline can be accurately determined by emitting the sound with the specific frequency and receiving the echo generated after the sound is transmitted in the non-metal pipeline, and the mode based on sound transmission is not limited by the non-conductive and non-magnetic characteristics of the non-metal pipeline; and the problem of non-metal pipeline detection can be effectively solved. The display device is installed on the detection box body and can display the position information of the nonmetal pipeline in real time. The main controller accurately analyzes and processes sound signals sent by the sound generating device and echo signals received by the sound pick-up, specific signals related to the non-metal pipeline are extracted, and the detection accuracy is improved.

The embodiment of the application provides a kind of target event determination method and device, storage medium, electronic equipment, wherein, the method comprises: abnormal detection is carried out to the index to be detected, determines the abnormal interval of the index to be detected, the first time series data of the index to be detected in abnormal interval, and further determine the second time series data of the multiple candidate root cause events of the index to be detected in abnormal interval, that is, abnormal interval can be used as the analysis center, and first time series data, second time series data are combined to carry out root cause analysis from multiple root cause analysis dimensions respectively, determine the analysis result of multiple candidate root cause events in multiple root cause analysis dimensions respectively, finally, target root cause event is determined by the analysis result of multiple root cause analysis dimensions, since root cause analysis focuses not only on abnormal interval, but also combines multiple root cause analysis dimensions, so as to effectively improve the determination accuracy of target root cause event.

The application discloses a parameter budget range determination method and device, a storage medium and computer equipment, relates to the high-resolution imaging system budget decomposition technical field, and is applied to a photoetching system. The method comprises the following steps: obtaining a test photoetching parameter, wherein the test photoetching parameter comprises a line width parameter and a period parameter; inputting the line width parameter and the period parameter into a pre-trained classification model; determining a target negative result farthest from a classification boundary of the classification model in negative results output by the classification model, and determining a line width parameter and the period parameter corresponding to the target negative result; and determining a parameter budget range of the photoetching system according to the line width parameter, the period parameter corresponding to the target negative result and the classification model. The above method can significantly improve the determination precision of the parameter budget range of the photoetching system.

This application provides a method, apparatus, device, and storage medium for determining inspection paths for devices. The method includes: determining alarm information and location information of alarm devices; wherein the alarm information characterizes the alarm status of the alarm devices; determining the inspection level of each alarm device based on its alarm information; wherein the inspection level characterizes the urgency of inspecting the alarm device; and determining an inspection path based on the location information and inspection level of each alarm device; wherein the inspection path characterizes the path taken from a preset starting point, passing through the alarm devices. This method, by combining the alarm information of each device, differentiates the urgency of inspecting these devices, thereby improving the accuracy of inspection path determination.

The invention provides a method and a device for determining mechanical parameters of a ceramic matrix composite material. The method comprises the following steps: acquiring a target genetic population of target mechanical parameters of a target material test piece; the target material test piece is a test piece prepared from a ceramic-based composite material; the target genetic population comprises a plurality of genetic individuals representing different candidate values of the target mechanical parameters respectively; for each genetic individual in the target genetic population, calculating a first resonant frequency of the target material test piece corresponding to the genetic individual based on the candidate value corresponding to the genetic individual by using the modal analysis model of the target material test piece; determining a target value of a target mechanical parameter of the target material test piece based on a target deviation between the first resonant frequency corresponding to each genetic individual and the second resonant frequency; the second resonance frequency is obtained by performing resonance test measurement on the target material test piece. The method can improve the determination precision of the mechanical parameters of the ceramic-based composite material.

The application relates to an aorta CT image center line determination method and system, electronic equipment and a computer readable storage medium, and relates to the field of CT image processing.The method comprises the following steps: inputting a three-dimensional aorta CT image to be detected into an aorta CT image key point detection model, and outputting a key point extraction result; the aorta CT image key point detection model is determined according to training of a U-Net network; the extracted key points are sequentially connected by using a progressive optimal fast random search tree algorithm; in the connecting process, a correction process is performed on sampling candidate points generated by random sampling; if the distance between the sampling candidate points located between two key points and any point outside the aorta is less than a set threshold value, an aorta inscribed sphere containing the sampling candidate points is formed, and the sphere center is taken as a connecting point between the two key points. The application improves the determination accuracy and efficiency of the aorta CT image center line.

This disclosure provides a method, apparatus, electronic device, and storage medium for detecting abnormal network behavior. The method includes: based on a target time period to be analyzed, determining a subset of group behavior features for each object group within the target object group during the target time period from a set of historical behavior features, wherein the set of historical behavior features characterizes the historical access behavior of objects in the target object group to at least one target system within a preset time interval; for any object group, determining candidate abnormal objects within the object group based on the subset of group behavior features of the object group; for any candidate abnormal object, determining a subset of object behavior features for the candidate abnormal object within the preset time interval from the set of historical behavior features; and determining a target abnormal object from at least one candidate abnormal object based on the subset of object behavior features of the at least one candidate abnormal object. This can improve the detection accuracy of abnormal network behavior.

The invention discloses a DEM-based determination method for design flood calculation parameters of a Huai Shanghai method, and the method comprises the steps: obtaining a target drainage basin and peripheral DEM data, calculating the water flow direction of each grid through a D8 algorithm, and generating a flow direction grid; determining a main stream position according to the flow direction grid; matching a net rain time period according to the drainage basin area A, and calculating net rain intensity i when net rain in the time period is 20mm; identifying the underlying surface type in combination with a satellite image, and matching the roughness values to form a roughness grid; estimating the flow velocity of each grid through a dynamic wave method; determining an isochrone; constructing an L-B curve and a tau-B curve; and determining core parameters of the Huai Shangshi method. The method has the advantages that the isochrone is determined based on the DEM, the isochrone calculation method is improved, the isochrone determination precision is improved, the L-B curve is reasonably determined, then standard, automatic and high-precision acquisition of seven core parameters of the Huai Shangzhou method is achieved, and the parameter determination efficiency and quality are improved.

The application provides a two-dimensional icon labeling method, system and device based on three-dimensional model feature recognition, which obtains model parameter information; extracts three-dimensional features of a target three-dimensional model in the model parameter information, determines the correlation of the three-dimensional features under multiple views based on a multiple view search method; selects an optimal projection direction according to the correlation to project the three-dimensional features to a virtual space plane, and determines shape information and size information of two-dimensional features; determines feature naming according to the matching relationship between the two-dimensional features and the counterpart information, and matches the two-dimensional features according to a preset industry rule to determine tolerance information; encapsulates the view position information, feature space position, tolerance information and feature naming corresponding to the two-dimensional features to generate a labeling data package; and optimizes the layout formed by the labeling data package to generate a two-dimensional icon. The application does not require manual intervention throughout, greatly reduces the labor cost and human error, and improves the labeling efficiency and quality.