91results about How to "Improve interpretation efficiency" patented technology

The invention provides an automatic fault interpretation device for a three-dimensional seismic data body. According to the automatic fault interpretation device for the three-dimensional seismic data body, a coherent body imaging module is used for detecting seismic faults, and outputting coherent bodies to depict the faults; an ant colony tracking module performs automatic three-dimensional fault tracking and judgment on the coherent bodies by using a directional ant colony algorithm, and outputs an automatic fault tracking result; an automatic fault separation module is used for judging and automatically separating each fault according to the automatic fault tracking result; and an automatic fault attribute calculation module measures and calculates geometric elements and dynamic attributes of the separated faults. The automatic fault interpretation device for the three-dimensional seismic data body can be used for automatically performing fault interpretation on various seismic data; the device has the advantages of high calculation efficiency, objectiveness and accuracy of fault interpretation results, and the like; and fault interpretation accuracy is effectively improved, and seismic interpretation efficiency is improved.

The invention provides a curve data automation interpretation method which is used for carrying out automation interpretation on correctness of a test curve generated during a satellite test process. The method comprises the following steps of extracting main characteristics of different types of curves generated during a curve satellite test process in advance and carrying out quantitative analysis on the main characteristics of the curves; arranging the different types of curves and finding a distribution scope of the main characteristics of the curves so as to make an interpretation criterion; using a predetermined scripting language to compile an algorithm used by a curve determination criterion and integrating to a ground automation test module so as to execute the interpretation; and through taking the curve ground automation test module, carrying out automatic interpretation on the curve to be tested. Therefore, by using the method, interpretation efficiency can be increased, an interpretation method is extendable, covering performance to different types of the tested curves is good, an advantage of the scripting language can be fully used, and the method is easy and simple and has good transportability. Besides, the method possesses good adaptability to the interpretation of the curve whose characteristic is not easy to extract.

In the medical image interpreting apparatus having a pointing device for moving a cursor, medical image, interpretation report, and cursor are displayed on a display screen, and initial movement information and information on the destination of movement of the cursor are linked and stored, via the pointing device when the cursor begins to move, said initial movement information relevant to the initial movement is retrieved to obtain the linked information on the destination of movement and the cursor is moved to the destination of movement indicated in the obtained information on the destination of movement. Due to this, just by slightly moving the cursor, the cursor jumps to the desired destination of movement, therefore, it becomes possible to omit an operation of the pointing device in between. Due to this, the operation load of the pointing device is reduced, thus preventing an operator's thought in creating an interpretation report from being destructed, and the enhancement in interpreting efficiency and the reduction of interpretation mistakes are achieved.

The invention provides a method for carrying out data interpretation on a plurality of signals, comprising the following steps: (1) loading data criterion which comprises analog signals, pulse counting signals and time sequence time string signal by interpreting control module; (2) interpreting upper bound and lower bound of the analog signal data; (3) interpreting whether the upper bound and the lower bound of pulses number of the pulse counting signals in a time range between interpretation starting and interpretation stopping is in the allowed range; (4) and interpreting whether on-off action of the timing sequence and series l data in a given channel in a certain time and a time deviation is normal. According to the invention, method for carrying out data interpretation on a plurality of signals has the advantage that transportability of criterion files is high due to criterion set by utilizing general text formatting. Criterion setting is flexible, and different types of criterion can be set according to different types of parameters. According to the invention, automatic interpretation and record are realized. The method solves a problem of right and wrong interpretation of the on-off action of the time sequence time string signal at a certain time, improves interpretation efficiency of mass data and greatly saves interpretation time and artificial cost.

A classification system and a classification method of the autoantibody immunofluorescence image are disclosed. The system includes an input device, a processor and an output device. The plurality of cell immunofluorescence images and the corresponded extractable nuclear antigen results are input through the input device. The processor conducts a plurality of convolution neural network calculation and output the classification based on the extractable nuclear antigen results, so as to obtain an extractable nuclear antigen classification model. When the autoantibody immunofluorescence image is input by the input device, the corresponded classification of the extractable nuclear antigen can be predicted. The classification result is output through the output device.

The invention relates to a flight malfunction determining method based on simulation. The method includes the following steps: a first step of establishing an aircraft simulation model which highly simulates malfunction and other special conditions; a second step of determining corresponding malfunction determination rules; a third step of making emergency handling methods for malfunction and other special conditions; a fourth step of performing flight simulation analysis based on real-time flight operation; a fifth step of comparing responding data of the model with remote-sensing data, and determining whether the aircraft is malfunctioned or at other special conditions; and a sixth step of providing emergency handling methods with respect to the malfunction and other special conditions, thus ensuring safe flight. Compared with manual interpretation, the method can process more data at the same time, and has efficient interpretation; and compared with the safety-boundary determination method, the method can determine the presence of malfunction in a plurality of abnormal data which are within the boundary, and can provide a conclusion earlier and accurately. The method can provide corresponding emergency handling methods with respect to specific malfunction, guides an aviator on how to conduct following operations, lowers risks in test flight, ensures safe flight, and also greatly increases test efficiency.

The invention relates to an aviation big data intelligent analysis method based on remote embedded data collection. According to the method, aviation big data is utilized to analyze and monitor the health condition of an aircraft and carry out fault diagnosis. Through the method, on the one hand, integration of multiple monitoring means such as onboard videos, audio, a warning system and a flightparameter system is realized, and a system can record and store more flight data; and on the other hand, aviation big data application software is embedded into an airborne computer system to realizereal-time monitoring of the aircraft, meanwhile, the application software is continuously upgraded according to the latest research achievement, and the data stored in the system also can be subjectedto trend analysis on the ground in combination with historical data and can be utilized again in teaching and scientific research work.

The embodiment of the invention provides a multi-person multi-dimensional remote sensing consultation collaborative studying and judging method and device. The multi-person multi-dimensional remote sensing consultation collaborative studying and judging method includes the steps that login requests of a plurality of clients are obtained, wherein each login request comprises a client application instruction; remote sensing images to be interpreted are pushed to the corresponding clients according to the client application instructions, and voice and video network communication is provided; data, edited by client users, of the remote sending images are obtained, and the edited data are synchronously arranged in the logged-in clients and displayed on user interfaces of the remote sensing images of the clients. The method allows professionals at different places to perform multi-directional, consultative, collaborative studying and judging interpretation on the remote sensing images through audio and video communication under the support of the WEB-GIS and WEB-RS technologies. According to the method, the interpretation efficiency of the remote sensing images under the condition that significant events and emergencies (such as geological disasters) occur is improved, and a supporting means is provided for emergency monitoring through remote sensing.

The invention discloses a chart display method and apparatus. The method comprises the steps of determining a to-be-selected chart in target charts, wherein the target charts include the to-be-selected chart and associated charts, and the associated charts are charts associated with the to-be-selected chart; selecting a first target part in the to-be-selected chart; analyzing contents in the first target part to obtain a first analysis result; and performing first filtration processing on the target charts by taking the first analysis result as a first filtration condition, and displaying the target charts subjected to the first filtration processing. Through the method and the apparatus, the problem of relatively poor user experience during operation of charts on interfaces in related technologies is solved.

The invention relates to an efficient seismic interpretation method through multi-window continuous sections. The method includes 1, fault interpretation, namely analyzing a planar structural pattern on coherence time slices, determining the corresponded section structural pattern on the sections, and considering the fault combination, observing the situation of a target fault on a first interpretation channel section, opening the section of the next interpretation channel, comparing the content, opening the isochronal coherence slices at the head and tail of the fault, confirming the connection relationship of the target fault and an adjacent fault, controlling the direction of the fault, and implementing the fault interpretation on the section; 2, horizon interpretation, namely avoiding the fault and establishing a backbone section on a time slice adjacent to a target horizon, interpreting the backbone section, opening the interpretation channel sections of two adjacent main lines, opening the interpretation channel sections of two adjacent cross lines at one end, and repeating the steps until the horizon interpretation of the region between the two main lines is completed. By the aid of the method, the accuracy of seismic data interpretation and interpretation efficiency can be improved.

The invention discloses an SHAP feature attribution method, device and equipment and a readable storage medium. The SHAP feature attribution method comprises the steps: obtaining data to be interpreted, distributing the to-be-interpreted data to an execution end associated with the driving end; broadcasting a preset to-be-interpreted model to the execution end, enabling the execution end to calculate marginal benefit expectations and label expected values corresponding to the sample features in the to-be-interpreted data in parallel based on the to-be-interpreted model; and receiving each marginal benefit expectation and the label expected value fed back by the execution end, and calculating an SHAP result corresponding to the to-be-interpreted data based on each marginal benefit expectation and the label expected value. The technical problem that the model interpretation efficiency based on the SHAP is low is solved.

The invention discloses a model interpretation method and device and a readable storage medium. The method comprises the steps: obtaining to-be-interpreted sample data, and distributing the sample data to all execution units in a cluster; broadcasting a to-be-interpreted model to each execution unit, so that each execution unit calculates the contribution degree of the target sample data to the prediction result of the to-be-interpreted model based on a preset model interpretation algorithm after receiving the to-be-interpreted target sample data. According to the method, the model interpretation efficiency is improved, and the method can be used for processing model interpretation tasks of more complex service scenes.

The present invention provides an SAR (Synthetic Aperture Radar) image automatic classification system. The system comprises an original image warehousing processing unit, which analyzes original SAR data to obtain basic information, generates an SAR image on the basis of a polarized mode included in the basic information, and enables the basic information and the SAR image to be associated and to be stored in an original image library; the original image library, which stores the SAR image and the basic information; a sample database, which stores a sample image and a sample configuration file; a sample database construction unit, which selects the SAR image from the original image library and makes the SAR image serve as a sample image, sets parameters of the sample image to generate a sample configuration file, and enables the sample image and the corresponding configuration file to be associated and stored in the sample database; and a classification unit, which obtains, from the sample database, a matched sample image and a corresponding configuration file according to the basic information of images to be classified, generates an automatic classification configuration file according to the sample configuration file, and classifies the images to be classified according to the automatic classification configuration file.

The invention discloses a method for interpreting telemetry data of a navigation satellite control system, which is used for extracting and judging telemetry data in a navigation satellite telemetry database, comprising: a step of connecting Matlab to the telemetry database; using Matlab to determine the telemetry data to be interpreted steps; steps for plotting telemetry data. The invention realizes the automatic interpretation of the remote measurement data.

The invention discloses a gene mutation pathogenicity detection method and system based on a neural network and a medium. The method comprises the steps of inputting a gene detection VCF file to be detected and an HPO phenotype; obtaining a characteristic value of each gene variation according to the to-be-detected gene detection VCF file and the HPO phenotype; for each gene variation, inputting the characteristic value of the gene variation into a trained neural network model to obtain a pathogenicity comprehensive analysis result of the gene variation, wherein the neural network model is pre-trained to establish a mapping relationship between the characteristic value of each gene variation and the pathogenicity comprehensive analysis result of each gene variation. According to the invention, the subjective defect of manual analysis is overcome, and various factors influencing the pathogenicity of gene mutation can be comprehensively considered, so that the comprehensive analysis result is more objective and effective, the accuracy of pathogenicity analysis of gene mutation is greatly improved, and the gene interpretation efficiency is improved.

The invention discloses a data burying point configuration method, a storage medium and equipment, and the method comprises the following steps: S1, setting a front end to record a behavior log of a user, comprehensively recording and reporting basic events such as page access and button click by adopting a comprehensive mode of full burying points and code burying points, and adding special burying points for functional events; s2, synchronizing various business data logs based on a back end, establishing a dimension information table, perfecting an EV event processing method, and ensuring the accuracy and comprehensiveness of data; and S3, carrying out buried point process management and data filtering management. According to the method, point burying process control and scheme compilation can be carried out based on point burying configuration, processing and a point burying system, the top design of a point burying technical scheme is perfected, understanding of event information and attribute information is increased through service mapping, the use condition is monitored, the problem that a triggering mechanism of point burying is not clear and unclear is solved, and the system reliability is improved. And the accuracy and comprehensiveness of burying point data are improved.

The invention relates to an aviation big data intelligent analysis system based on remote embedded data collection. Aviation big data is utilized to analyze and monitor the health condition of an aircraft and carry out fault diagnosis. Through the system, on the one hand, integration of multiple monitoring means, such as onboard videos and audio, an alarm system and a flight parameter system, is realized, and the system can record and store more flight data; and on the other hand, aviation big data application software is embedded into an airborne computer system to realize real-time monitoring of the aircraft, meanwhile, the application software is continuously upgraded according to the latest research achievement, and the data stored in the system can be subjected to trend analysis in combination with historical data on the ground and also can be utilized again in teaching and scientific research work.

The invention discloses a method and device for analyzing electronic fetal heart monitoring data based on artificial intelligence. The method comprises the steps of carrying out preprocessing according to initial EFM data so as to obtain EFM data, carrying out characteristic extraction on the EFM data, carrying out characteristic screening on initial EFM data characteristics according to a preset characteristic screening method so as to obtain EFM data characteristics, establishing an algorithmic model according to the EFM data characteristics, encapsulating the algorithmic model so as to obtain an encapsulated model, inputting continuous-acquired EFM data into the encapsulated model for training, outputting a probability value of EFM data prediction results, inputting the probability value into a preset regressive analysis equation for analysis, and outputting a probability value of acidosis and fetal distress of a fetus after combining sufferer's clinical features. Through extracting a plurality of characteristics from the EFM data, wrong clinical decisions caused by individual differences of manual reading of fetal heart monitoring data are reduced; and meanwhile, a direct relation between the fetal heart monitoring data and a fetus delivery outcome is mined through artificial intelligence algorithms, so that the efficiency of clinical decision making is increased.