27results about How to "Accurately get" patented technology

The invention discloses a drilling parameter optimization method and device and a storage medium, and relates to the technical field of parameter optimization, and the key points of the technical scheme are that the method comprises the following steps: establishing a drilling specific energy difference model and a mechanical drilling speed model; the drilling specific energy difference value is the difference value between the energy required for removing unit volume of rock and the pressure resistance degree of the rock lateral line; constraint conditions of the drilling parameters are determined, and a multi-objective optimization model is constructed according to the constraint conditions, the drilling specific energy difference model and the mechanical drilling speed model; and according to the multi-objective optimization model, well drilling parameters are optimized in real time, the optimal well drilling parameters of well drilling operation are determined, and the well drilling parameters of the well drilling operation are adjusted according to the optimal well drilling parameters. Through the optimization method, the multi-target optimization model can be formed by combining the mechanical drilling speed model and the drilling specific energy difference model, so that drilling parameters such as drilling pressure and rotating speed are realized under constraint conditions, optimization of the drilling parameters is realized, the drilling efficiency is improved, and the drilling cost is reduced.

The invention relates to the technical field of image processing, and discloses a container loading and unloading positioning identification method based on machine vision. The method comprises the following steps: firstly, obtaining a to-be-processed container image, and carrying out noise reduction processing, binarization processing and edge detection on the to-be-processed container image to obtain a processed container image; secondly, HOG features of the processed container image are extracted, and an HOG feature vector set is obtained; a final SVM classifier is obtained through training, the HOG feature vector set is input into the final SVM classifier for classification, and container recognition is completed. And after container identification is completed, obtaining a container top image, processing the container top image to obtain a container corner fitting lockhole image, and positioning the position of the container corner fitting lockhole by using a convolutional neural network to realize container loading and unloading identification and positioning. According to the method, the container image is processed, the purpose of container loading and unloading positioning identification is achieved, and the method is accurate and objective.

The utility model discloses an integrated guide rail type die special for an upper cover plate and a lower cover plate. Comprising a handle support, an upper pressing plate arranged at the bottom of the handle support and connected with the handle support, a grooving device arranged at the bottom of the upper pressing plate, an elastic pressing plate arranged on one side of the grooving device through an elastic device, and a mold pressing plate arranged on a fixed base corresponding to the grooving device. The multifunctional cover plate mold machining device is formed, the working efficiency is improved, and the use cost is reduced.

The utility model discloses an intelligent rotary butt joint equipment of special-shaped self-locking joint relates to self-locking joint technical field, including robot hoisting platform and special-shaped self-locking joint, the both sides of robot hoisting platform bottom are provided with truss, and the bottom of truss is equipped with fixed mount, and the fixed mount is equipped with the special-shaped self-locking joint. A quick-change tool fixing end is arranged in the fixing frame, the special-shaped self-locking connector is arranged in a truss bottom quick-change tool, a special-shaped self-locking connector male head is arranged on the outer surface of the top of the bottom testing table, and a quick-change tool is installed at the bottom of the quick-change tool fixing end. According to the equipment for intelligent rotary butt joint of the special-shaped self-locking connector, the problems of automatic tightening and separation of the special-shaped self-locking connector, tightening speed, tightening in-place judgment, random direction deviation of the quick change position of a female head after tightening and connector positioning precision are solved, the posture can be adjusted through five-axis wrist swing of a robot in the connector inserting and pulling process, and the positioning precision of the connector is improved. And the situation that the visually given coordinates are inaccurate after the special-shaped self-locking butt joint offset is large is avoided.

The invention provides a medical record text recommendation method and device, equipment and a storage medium, and belongs to the field of artificial intelligence. According to a sample data set and a preset knowledge database, a preset medical record text recommendation model is trained until convergence, and a medical record text is recognized based on the medical record text recommendation model; the recommended medical record text can be accurately obtained, and the efficiency and accuracy of medical record text recommendation are greatly improved. The invention further relates to the technical field of block chains, and the medical record text recommendation model can be stored in the block chain.

The utility model discloses a BMS system based on 4G monitoring. The BMS system comprises a BMS, a 4G transmission module and a monitoring platform. The BMS is connected with the 4G transmission module, and battery working information data collected by the BMS is sent to the monitoring platform through the 4G transmission module; and the monitoring platform is used for receiving and displaying the battery working information data sent by the 4G transmission module in real time. A GPS module is arranged in the 4G transmission module; the BMS and the GPS module are communicated through a UART (Universal Asynchronous Receiver / Transmitter) serial port, the BMS and the GPS module are connected through a flat cable interface, the flat cable interface comprises a communication interface arranged on the BMS, and the GPS module is provided with an interface matched with the communication interface. The Baud rate of the UART serial port communication bus is set to be 9600 bps, the communication data format is 8N1, and a full duplex mode is adopted in the serial communication direction. According to the device, a user can timely and accurately obtain the basic information of the battery pack, especially when the battery pack is in an abnormal state, the user is reminded of the situation needing to be noticed, and the effect of safety early warning is achieved.

This invention provides a repair mechanism for reducing the vibration level of a gas generator, relating to the field of gas generator technology. The invention includes a base with support rods evenly fixedly connected to its top. A semi-circular plate is fixedly connected to the top of each support rod. A centrifugal compressor shaft is mounted on the top of each semi-circular plate. When using the support device, the arc plate is manually rotated on the top of the semi-circular plate, thereby fitting the arc plate onto the surface of the centrifugal compressor shaft. Then, a fixing plate is manually slid along the inner wall of the connecting frame, sliding into the fixing groove. A first spring then pulls the fixing plate towards the semi-circular plate, effectively confining it within the fixing groove. This fixes the centrifugal compressor shaft to the top of the semi-circular plate. Other parts are supported by other staggered support rods and semi-circular plates, thus supporting all components of the gas generator on the surface of the base.

The present invention discloses a method and device for designing and evaluating a valve, the method comprising: obtaining a patient's coronary CTA image sequence, and constructing a physical model of the aortic root, aortic valve, and left ventricular outflow tract based on the CTA image sequence; determining different artificial valve physical models, blood flow related parameters, and the release position of the artificial valve; based on the physical model and blood flow related parameters, using a valve replacement model pre-trained based on the acquired real CTA image sequence to sequentially simulate the process of placing each artificial valve physical model in the release position to obtain corresponding simulation results; determining a valve implantation risk index based on the simulation results; and selecting the design parameters of the artificial valve based on the valve implantation risk index. Using the scheme of the present invention, individualized artificial valve data can be obtained efficiently, quickly, and accurately, providing an effective reference for clinical transcatheter aortic valve replacement surgery, and also providing an effective reference for the design of new valve models.

This invention provides a method, apparatus, device, and readable storage medium for detecting the stopping position of a glass rod, relating to the field of information technology. The method includes acquiring uploaded images and historical images of experimental exams; identifying the uploaded images based on a preset target detection model to obtain at least one frame of a filter paper image containing the complete filter paper; preprocessing the filter paper image to obtain a grayscale image, and then using Hough line detection to complete the contours of the grayscale image to obtain a three-layer filter paper region; identifying the uploaded images based on the target detection model to obtain at least one frame of a detection image containing the intersection of the glass rod and the funnel, and obtaining the detection result based on the three-layer filter paper region and the detection image. The beneficial effects of this invention are: by using Hough line detection for contour detection and completion, this invention not only filters out noise and interference points but also more accurately and quickly obtains the boundary line between the three-layer and single-layer filter paper, improving detection accuracy.

The application provides an electronic bidding file detection method and device, computer equipment and medium, wherein for each file picture in the electronic bidding file picture, the file picture is input into a file classification model to obtain a target file category of the file picture; the file picture is input into a target keyword extraction model to obtain at least one target keyword in the file picture; it is judged whether all keywords in at least one standard keyword are contained in the at least one target keyword; if all keywords in at least one standard keyword are contained in the at least one target keyword, the file picture is marked as a qualified picture; it is judged whether each file picture in the electronic bidding file picture is a qualified picture; if each file picture in the electronic bidding file picture is a qualified picture, the electronic bidding file to be detected is marked as a qualified file. The above method is used to improve the accuracy of detecting the electronic bidding file.

The invention provides a YOLO-BP network-based navigation impeding risk perception method for channel surface flow state characteristics, which extracts flow state characteristics based on YOLOV5s, evaluates risk grades of different flow state characteristics by using a BP neural network, recognizes channel surface flow states by using a machine learning mode instead of manual work, and timely discovers and evaluates flow state impeding risks. The method has the advantage that the target water area surface risk flow state characteristics can be efficiently and conveniently identified in real time, and a technical support is provided for preventing and eliminating navigation safety risks caused by navigation hindering flow states.

The embodiment of the invention discloses a lane recognition method, and belongs to the technical field of vehicles, and the method comprises the steps: determining a to-be-driven lane based on the driving data of a vehicle; target driving lane information is determined on the basis of preset lane passing condition information, a to-be-driven lane and current time, and the target driving lane information is used for indicating a lane where the vehicle can pass at the current time; and executing a target driving service according to the target driving lane information. According to the invention, the accuracy and efficiency of identifying the time-sharing lane can be improved.

The invention relates to the technical field of video recognition and echocardiogram video automatic analysis, and particularly provides an automatic spontaneous development recognition method based on an enhanced spatial-temporal feature network, and the method comprises the steps: carrying out the preprocessing of a to-be-recognized video, and obtaining a video frame set; wherein the video to be identified is a transesophageal echocardiogram video; inputting the video frame set into a trained automatic spontaneous development recognition model, and outputting a corresponding spontaneous development recognition result by using the automatic spontaneous development recognition model; wherein the automatic spontaneous development recognition model is obtained by training according to a plurality of training data, and the training data comprise transesophageal echocardiography videos; the automatic spontaneous development recognition model comprises an attention map creation module, a spatial-temporal feature extraction module and a classification module. According to the automatic spontaneous development recognition method based on the enhanced spatial-temporal feature network, the data cost can be effectively reduced, and the recognition accuracy is high.

The application provides a URL determination method and device, electronic equipment and a storage medium, relates to the technical field of networks, and solves the technical problem that all URLs corresponding to a web application cannot be accurately and completely determined in the related art. The method comprises the following steps: determining a physical position corresponding to each application in at least one application; obtaining a file name of an accessed file corresponding to each application based on the physical position corresponding to each application; and determining a URL corresponding to each application based on a position name of the physical position corresponding to each application and the file name of the accessed file corresponding to each application.

The invention provides an intelligent voice recognition method based on AI, and the method comprises the steps: monitoring a current hotspot in real time, generating a corresponding hotspot vocabulary, and adding the hotspot vocabulary into a hotspot data set; in the communication process with the outbound user, identifying the real-time voice content of the outbound user to obtain the real-time text content, judging whether the real-time text content has the real-time hot vocabularies in the hot data set or not, if so, obtaining the emotion tendency of the outbound user to the real-time hot vocabularies according to the emotion analysis of the real-time text content, and sending the emotion tendency of the outbound user to the real-time hot vocabularies. Performing hotspot interaction according to a preset verbal skill corresponding to the emotional tendency; and judging whether the current interaction is secondary flow interaction or not in real time, if yes, and the current interaction can be ended, returning to the preset main flow interaction through a replay skill so as to complete product promotion according to the main flow interaction. According to the invention, the response accuracy of the outbound user can be improved while the outbound efficiency is ensured.

This disclosure relates to an information processing method, apparatus, server, and storage medium, and pertains to the field of Internet technology. The method includes: a first server receiving an information processing request sent by a second server, the information processing request including an authorization token for first business data; determining first target information based on the authorization token for the first business data and a first correspondence relationship, the first correspondence relationship including multiple authorization tokens and target information corresponding to each of the multiple authorization tokens; performing preset processing on the first target information based on a first string to obtain the first business data; and sending the first business data to the second server. The technical solution provided by this disclosure can improve the accuracy of business data acquisition.

The invention discloses a meta-multi-graph assisted decoupling graph neurocognition diagnosis method, which comprises the following steps of: 1, constructing a student-exercise-concept interaction graph according to answer records of students and exercise concept information labeled by experts, 2, learning a graph neural network aggregation mode and updated representation in a differentiable mode through a one-element multi-graph aggregation module; 3, stripping an interaction graph from student nodes, decoupling a new exercise-concept dependency graph, and updating exercise characterization through an attention mechanism; 4, stripping the dependency graph from the exercise nodes again, decoupling the concept-concept relation graph, and updating the concept representation through the attention mechanism; and 5, after the representations of the three types of nodes are obtained, predicting the mastering degree of the knowledge concept by the students through a novel and highly explanatory diagnosis formula. According to the method, through a decoupling thought and a neural architecture search method, cognitive diagnosis can be carried out on the ability of students, and the robustness of the model can be ensured to a certain extent.

The invention belongs to the field of helicopters, and relates to a flight test method of a horizontal tail control strategy capable of rotating around a shaft. The method comprises the following steps: introducing a total distance and an air speed as control variables, carrying out test flight on the horizontal tail at different total distances and flight speeds, and adjusting a mounting angle to be optimal in the test flight process.

The invention provides an automatic generation method and device of a TCL command, electronic equipment and a storage medium, and belongs to the technical field of integrated circuit design, in the method, a user only needs to input own design requirements, the method can automatically generate a successfully verified target TCL command, the learning cost of the user is greatly reduced, the generation efficiency of the TCL command is improved, and the user experience is improved. When the target TCL command which is successfully verified is generated, not only is the design requirement of a user referred, but also the target TCL command Help information is referred, the target TCL command Help information is the TCL command Help information most related to the design requirement, finally, the target TCL command output by the TCL command large language model according to the design requirement and the target TCL command Help information is good in accuracy, the design requirement of the user can be met, and the user experience is improved. The generated target TCL command is verified, and the successfully verified target TCL command is more accurate, so that the user can be helped to quickly, conveniently and accurately obtain the TCL command (using the EDA tool) of the EDA tool, and the learning cost is reduced.

The invention discloses a large-inclination cable tower tensile stress control method which is used for regulating and controlling cable tower bottom tensile stress in real time and comprises the following steps that S1, a large-inclination cable tower comprises two symmetrically-arranged tower columns, and the two tower columns are constructed section by section at the same time; s2, the tower bottom tensile stress measured value of the large-inclination cable bent tower is detected in real time, and whether transverse supporting force needs to be applied between the two tower columns of the current section or not is judged according to the tower bottom tensile stress measured value; s3, if yes, skipping to execute the step S4; if not, skipping to execute the step S5; s4, calculating the size of the required transverse supporting force, carrying out transverse supporting between the two tower columns, and then skipping to execute the step S5; and S5, the next sections of the two tower columns continue to be built and constructed, the step S2 and the step S3 are executed again till construction of the large-inclination cable bent tower is completed, and all the transverse supporting force between the two tower columns is removed.

The invention discloses a point cloud rapid splicing method based on structured light three-dimensional reconstruction, and the method comprises the steps: obtaining and unfolding a wrapped phase, and the obtaining and unfolding of the wrapped phase comprise a four-step phase shift method and a three-frequency extrapolation principle; camera calibration, wherein the camera calibration comprises obtaining a coordinate mapping relation between camera image pixels and a three-dimensional space object; hand-eye calibration, wherein the hand-eye calibration comprises the step of obtaining a coordinate mapping relation between a coordinate system at the tail end of the mechanical arm and a three-dimensional space object; point cloud splicing, wherein the point cloud splicing comprises coarse point cloud splicing and fine point cloud splicing; according to the method provided by the invention, the surface information of the three-dimensional space object is measured through the structured light principle, and the surface information of the three-dimensional space object of a large scene can be quickly and effectively obtained through the point cloud rough splicing and fine splicing after hand-eye calibration.

The utility model discloses auxiliary equipment for lithotomy position surgery, which comprises a movable cart, the movable cart comprises a support plate, a fixed plate and a movable part, the bottom of the support plate is connected with the top of the fixed plate, and the movable part is connected with the bottom of the fixed plate and is used for driving the support plate and the fixed plate to move; the connecting assembly is arranged on the side wall of the fixed plate, the connecting assembly comprises an annular sleeve, a supporting rod and a fixed connecting frame, the first end of the annular sleeve penetrates through the fixed plate, the first end of the supporting rod is inserted into the annular sleeve and is in sliding connection with the annular sleeve, and the fixed connecting frame penetrates through the second end of the supporting rod; the filtering assembly is arranged on the side wall of the fixing plate. According to the utility model, the workload of medical workers and the loss of an operating bed are reduced, the operation turnover efficiency is ensured, the safety of a patient is effectively improved, and lavage fluid in the operation process can be collected and filtered, so that the operating bed and the ground are prevented from being polluted, and human tissue specimens are prevented from being lost.

According to the landslide risk intelligent evaluation method and system provided by the invention, a part of key landslide risk coefficients can be obtained from a key landslide risk coefficient set and determined as first undetermined landslide risk coefficients, and a part of non-landslide risk coefficients can be obtained from a non-key landslide risk coefficient set and determined as second undetermined landslide risk coefficients; and subsequently, according to a numerical difference relationship between a loss value to which the first undetermined landslide risk coefficient belongs and a loss value to which the second undetermined landslide risk coefficient belongs, an intelligent landslide risk evaluation result of the target landslide risk description information can be obtained. The loss values of all the landslide risk coefficients in the key landslide risk coefficient set and the non-key landslide risk coefficient set do not need to be calculated, so that the accuracy and reliability of the landslide risk intelligent evaluation result are improved.

The invention relates to the field of image processing, in particular to an image correction algorithm based on a text block angle and a dichotomy model. The method comprises the following steps: extracting a characteristic straight line representing the line direction of each line of characters in an image; removing abnormal feature straight lines; taking the average deviation angle of the characteristic straight line relative to the horizontal direction as the deviation angle of the image, and performing preliminary deviation correction on the image according to the deviation angle; using a pre-trained dichotomy model to judge whether the image is positive or reverse at the moment, and if the image is positive, completing image processing at the moment; if the image is reversed, the image is rotated by 180 degrees, and image processing is completed at the moment. Through the steps of the invention, the corrected image can be quickly and accurately obtained.

The application discloses a kind of cone barrel racecourse boundary classification method system, device and storage medium, wherein method includes: obtaining the cone barrel detection result based on laser point cloud;Wherein, the spatial coordinates of each cone barrel are cone barrel detection result;Cone barrel detection result is provided as input to pre-established classification model, and the spatial distribution interrelationship feature and intermediate layer feature of cone barrel are extracted;The spatial distribution interrelationship feature and intermediate feature of cone barrel are aggregated by the classification model, and the classification result is obtained according to the aggregation result;Wherein, classification result is used to indicate the boundary category of each cone barrel.The application can obtain more reliable, more accurate, more quickly cone barrel racecourse boundary information compared with the method of image and laser point cloud fusion in prior art for racecourse cone barrel detection, to solve the problem of unreliable, high complexity in the cone barrel racecourse boundary classification scheme of prior art.The application can be widely applied in the field of unmanned driving technology.

The invention provides an interface layout adaptation method and device, a terminal and a storage medium, and the method comprises the steps: obtaining a screen size and a screen resolution of a target platform, inputting the screen size, the screen resolution and to-be-adjusted user interface layout information into a trained interface adaptation model, obtaining target user interface layout information; generating a target user interface based on the target user interface layout information, and applying the target user interface to the target platform; wherein the interface adaptation model is used for adjusting user interface layout information according to the screen size and the screen resolution of the target platform. According to the embodiment of the invention, the to-be-adjusted user interface layout information is automatically adjusted according to the screen size and the screen resolution of the target platform by utilizing the trained interface adaptation model, and then the to-be-adjusted user interface layout information is applied to the target platform, so that manual adjustment by developers is not needed, and the adaptation efficiency and accuracy of the user interface are improved.

The invention provides a repairing mechanism for reducing the vibration level of a fuel gas generator, and relates to the technical field of fuel gas generators, the repairing mechanism comprises a base, supporting rods are uniformly and fixedly connected to the top of the base, semicircular plates are fixedly connected to the tops of the supporting rods, and a centrifugal compressor shaft is arranged at the tops of the semicircular plates; when the supporting device is used, an arc plate is manually controlled to rotate at the top of a semicircular plate, then the arc plate is arranged on the surface of a centrifugal compressor shaft in a sleeving mode, then a fixing plate is manually controlled to slide on the inner wall of a connecting frame, then the fixing plate slides into a fixing groove, and then the fixing plate is pulled in the direction close to the semicircular plate through a first spring; the fixing plate is arranged in the fixing groove, so that the fixing plate is well limited in the fixing groove, a centrifugal compressor shaft can be fixed to the top of the semicircular plate, other parts of the centrifugal compressor shaft are supported through other staggered supporting rods and the semicircular plate, and all parts of the fuel gas generator can be supported on the surface of the base.