340results about How to "Strong data support" patented technology

The invention discloses a deep convolutional neural network-based lung cancer preventing self-service health cloud service system. The system comprises a convolutional neural network used for deep learning and training identification, a segmentation module which segments out a lung region from a CT image based on a full convolutional neural network, a deep convolutional neural network used for lung cancer diagnosis classification, and a self-service health cloud service platform used for performing early prevention and treatment according to an identified suspected lung cancer type. According to the system, the automation and intelligentization level of mobile internet-based lung cancer screening can be effectively improved, more citizens can know and participate in self-service health detection, assessment and guidance, the sensitivity, specificity and accuracy of early lung cancer screening and clinical diagnosis are improved, the lung cancer can be early discovered, early diagnosed and early treated, and the self-health management capability is enhanced.

The invention provides a method for replacing sensitive words in the call process of a mobile terminal. The method includes the steps that after a call instruction of a user is received, the mobile terminal is in a replacement mode; the mobile terminal records voice information of the user, semantic analysis and word segmentation processing are performed on the voice information so as to generate call words of the user, and the time point corresponding to each call word is recorded; the mobile terminal is used for analyzing the call words and judging whether the call words are the sensitive words or not; if the call words are the sensitive words, the mobile terminal replaces or eliminates the call words according to the time points corresponding to the call words. According to the method, the sensitive words are shielded through automatic processing of the voice information, therefore, call becomes more civilized, processing cost is low, the efficiency is high, and timeliness is good.

The invention provides a residual life prediction method for a non-stationary degradation process with uncertain impact and belongs to the technical field of reliability engineering. The impact effect is combined with a continuous degradation process, thereby more reasonably describing the actual degradation process. In a state estimation phase, a new online state estimation algorithm is provided to identify the real system state and to provide a necessary support for subsequent residual life prediction. In a parameter estimation stage, unknown parameters in a model are obtained by adopting an expectation maximization algorithm. For residual life production, the uncertainty of state estimation and the influence of the impact effect are considered at the same time, and an expression is analyzed to give a probability density function and a cumulative probability density function of residual life prediction distribution. The provided model meets the actual degradation condition, a more accurate residual life prediction result can be obtained, and the residual life prediction method is of great significance in fault prediction and health management in engineering.

The invention discloses a high-fidelity digital modeling method of terrain elevation, the steps are as follows: the first step is to carry out push-broom data acquisition; the second step is to carry out grid segmentation of the acquired vector terrain feature data; the third step is to carry out similar DEM grid data organization of PLA, organization management is carried out to the PLA data after the grid segmentation treatment according to grid data structure; the fourth step is to generate a new digital elevation model file to carry out the seamless embedding of the vector feature data; a feature embedded digital elevation model data structure is composed of three sub-files which comprise a grid file, a feature identification file and a feature file; the grid file is a regular grid data structure; the feature identification file is used for spatial data index of a vector grid integrated organization, the structure thereof is consistent with the current national DEM data structure and only records the grids with the features; the feature file records terrain feature information which is contained in one grid unit, and the information comprises feature points and feature lines.

The invention relates to an intelligent identification management and dynamic monitoring system and a method for fixed assets. The system comprises a data acquisition system, a gateway node and a management center connected in sequence. The system acquires real-time electrical parameter information, environment state information, basic asset information and asset position information through the data acquisition system, the information is wirelessly uploaded to the management center via the gateway node, the management center stores, analyzes and processes the received information, and the analysis result is checked through a management terminal of the management center. Manual inventory and manual two-dimensional code scanning are saved for asset management, periodical asset inventory and active asset inventory can be realized through the system, high efficiency of the work is realized, manual input is reduced, and happening of various error conditions of inaccurate asset inventory, extra inventory, missed inventory and the like caused by manual inventory can be reduced.

The invention discloses an operation monitoring system for an electricity consumption information acquisition system. The operation monitoring system comprises an abnormality data recognition module, a data statistics module and an application release service module. An electricity consumption information acquisition system operation abnormality recognition model is established in the abnormality data recognition module. The abnormality data recognition module calls data from an acquisition database of the electricity consumption information acquisition system; the electricity consumption information acquisition system operation abnormality recognition model analyzes the data to judge and recognize metering devices which are abnormal and inputs recognized abnormality results into the data statistics module; the data statistics module is used for pre-counting the recognized abnormality results and storing statistical results in an application release server; the application release service module displays the statistical results according to set query conditions. The invention further provides an operation monitoring method for the electricity consumption information acquisition system. The operation monitoring system and the operation monitoring method have the advantages that operation abnormalities of the electricity consumption information acquisition system can be discovered and recognized in time, and various abnormalities can be queried conveniently.

The invention discloses an urban traffic track data set generation method based on taxi data and an urban road network, and belongs to the field of traffic transportation. The model is composed of a preparation layer, a generation layer and a verification layer. Track data of private cars are generated based on taxi data and urban road network information for the first time, and meanwhile a complete verification method is provided for verifying the accuracy of a generated data set. The invention provides an urban functional region division method based on an adjacent road division method. Theurban functional region division method comprises the steps of dividing a city into different functional regions; meanwhile, providing a regional population weight opportunity model, and a populationmovement mode can be more accurately depicted. In order to verify the authenticity and the accuracy of the method, a macroscopic angle-based model and a microscopic angle-based model are respectivelyprovided on a verification layer to verify the authenticity and the accuracy of a data set generated by the model. Through verification of the verification layer, the track data of the private car generated according to the taxi GPS data and the urban vehicle network information are high in authenticity and accuracy.

The invention discloses a real-time performance test method which is applied to real-time performance tests of an embedded system. The real-time performance test method includes following steps: performing time characteristics modeling on application program source codes in an upper computer; using a time characteristics model obtained in the modeling process to complete instrumentation operation for the source codes; downloading the source codes onto a lower computer after the source codes are compiled and interlinked, and starting an application program through the upper computer; collecting test data during the running period of the application program, and returning data stored in a certain data container in real time to the upper computer according to preset transmission rules; obtaining a real-time performance test report of the application program after data analysis. The real-time performance test method achieves the real-time performance tests for the embedded real-time application program, and has the advantages of being fully automatic, small in error and detailed in result during the test process. The invention further discloses a system which uses the real-time performance test method.

The invention provides a satellite remote sensing monitoring method and a processing device for straw burning fire points in one embodiment and aims at solving the problems of high difficult of manual burning control and failure in guaranteeing the control efficiency and the control accuracy in the prior art. The method comprises the following steps: the processing device obtains the satellite remote sensing data of a region to be monitored obtained by a remote sensing monitoring device; for each pixel in the satellite remote sensing data, whether the brightness temperature value of the pixel is located within a preset fire point brightness temperature range is judged, and if so, the pixel is marked as the burning fire point; all the pixels marked as the burning fire points are marked in the region to be monitored, and the position information and attribute report form of the burning fire points in the region to be monitored are obtained statistically. The method is capable of remarkably improving the fire point monitoring efficiency and the monitoring accuracy, convenient to implement, and easy to popularize and apply.

The invention discloses an electric-transmission-and-transformation-equipment state monitoring data cleaning method based on time series analysis. The electric-transmission-and-transformation-equipment state monitoring data cleaning method includes the following steps: building an initial time series model of state data of electric transmission and transformation equipment, and estimating an initially-fit residual series and an initially-fit residual variance through the initial time series model; calculating the test statistics amounts of observing points through the initial time series model; judging whether the maximum value of the absolute values of the test statistics amounts is larger than a threshold value or not; calculating the test statistics amounts of the observing points through the modified model residual of the time series model, and judging whether new noise points exist or not by judging whether the maximum value of the absolute values of the test statistics amounts is larger than the threshold value or not till all the noise points are identified. The electric-transmission-and-transformation-equipment state monitoring data cleaning method has the advantages that the cleaning efficiency is high, the data integrity is kept, and the useful information of data is prevented from being lost.

The application provides an identification method, server and terminal for a webpage operation behavior. The identification method for the webpage operation behavior comprises the following steps: obtaining webpage operation behavior data to be processed; obtaining one or more class clusters corresponding to the webpage operation behavior data to be processed from the historical webpage operationbehavior information database pre-classified the class clusters based on the predetermined acquisition rules, wherein each of the class clusters in the historical webpage operation behavior information database is obtained by aggregating a plurality pieces of historical webpage operation behavior information based on predetermined clustering rules; and identifying whether the webpage operation behavior to be processed is a malicious operation behavior or not based on the pre-calculated aggregation degree of the corresponding one or more class clusters. According to the identification method, server and terminal for the webpage operation behavior, whether the webpage operation behavior is a malicious operation behavior or not can be effectively identified.

The invention discloses a ground testing device for an electrical element of a rail vehicle. The ground testing device comprises a frame, wherein an industrial personal computer is arranged in the frame; the industrial personal computer is respectively connected with a display, an I (input)/O (output) board card, a D (digital)/A (analogue) board card, an A/D board card and a printer; and the I/O board card, the D/A board card and the A/D board card are connected with a matrix unit circuit, and the matrix unit circuit is respectively connected with a program control multi-path constant current source, a program control voltage source, a voltmeter, an ampere meter and a tested experimental platform. The invention also discloses a method for testing an electric element by the testing device. More than 16 electric elements can be tested at the same time, and the testing process is automated. A configured test and control board card, a sensor and the like are high-speed and high-precision, high in reliability of tested data, can fast judge the condition of the tested object by matching with analysis software and artificial missing judgment or error judgment can be reduced, so that the test quality and labor productivity can be greatly improved, and the production cost can be reduced.

The invention relates to the field of real-time data acquisition and storage, in particular to a file management method of a real-time data acquisition and storage system, which solves the problems in file management in the existing environment without an operating system. Through the invention, effective file management is realized in the environment without an operating system through data storage, acquisition of historical data and acquisition of real-time data; and primarily, the environmental parameters are acquired and recorded for a long time to provide data to a fault diagnosis system, and the fault diagnosis system finishes the functions of real-time detection of parameters, early warning, fault diagnosis and the like together with a fault diagnosis computer. The file management method of a real-time data acquisition and storage system, provided by the invention, is mainly applied to the real-time monitoring and recording of the related parameters in the product development and using processes, brings convenience to the examination of the change rules of the parameters, and provides powerful data support for the product design and improvement.

The invention discloses a three-dimensional intelligent auxiliary evaluation system and method for a power transmission and transformation project. The system comprises the following parts: a two-dimensional evaluation system used for declaring design data and closing-in auditing, and a three-dimensional evaluation system which is used for three-dimensional process evaluation, wherein the two-dimensional evaluation system uses a Webster platform and comprises an evaluation plan management module, an evaluation data collection module, a pre-evaluation module, a formal evaluation module, a closing-in auditing module and other management modules, and the three-dimensional evaluation system is composed of a three-dimensional evaluation module and a plurality of evaluation clients. According to the system, the engineering data management capability is integrally improved, a three-dimensional design evaluation authority management mode of the power transmission and transformation engineering is created, and strong data support is provided for orderly development of engineering construction.

The invention provides a method for evaluating performances of servers, wherein performances of the servers are integrally evaluated by testing performances of sub-systems of various components from the sub-systems of the different components such as CPU (central processing unit), a memory, a disc and so on, so that performances of the servers are evaluated more specifically, and powerful foundation is provided for location of performance bottle-neck; test software related to the sub-systems of the various components is arranged on platforms of the servers, and performance test results of the sub-systems of the components are obtained finally by coding, installing and running so as to achieve the aim of integrally testing performances of the servers.

The invention relates to a quantitative analysis method of electrolyte consumption. The method comprises the following steps: selecting an internal standard substance; respectively carrying out a centrifuging method and a soaking method on two groups of parallel used batteries to obtain a first to-be-detected electrolyte and a second to-be-detected electrolyte; and detecting and calculating: respectively detecting the first to-be-detected electrolyte and the second to-be-detected electrolyte and then calculating respective consumption of all components of the electrolytes. The quantitative analysis method of electrolyte consumption is simple to operate and high in repeatability; the method can be used for obtaining the consumption of each component of electrolyte in a used battery, thereby providing a powerful support for injection of electrolyte in required amount during the process of battery preparation.

The invention discloses an industrial process abnormal condition prediction method based on operation parameter correlation analysis. The method can be applied to fault prediction and health management of an industrial process. The method starts from the relevance among industrial process operation parameters, and performs abnormal condition prediction based on relevance analysis of the operationparameters. In a single-parameter prediction stage, all operation parameters are predicted through an exponential smoothing method according to existing sensor data. In a correlation analysis stage, operation parameter correlation is calculated through known operation parameter values and parameter predicted values, and the parameter correlation is represented by similarity of a series of indexesrepresenting parameter curves. In a correlation trend prediction stage, a multivariate autoregression model is constructed to predict parameter correlation. According to the method, operation parameter relevance is considered, more complete equipment abnormal information and a more advanced prediction result can be obtained, and practical significance is achieved for fault prediction of industrialequipment.

The invention discloses an urban drainage pipe network operation and maintenance method based on a pipe network construction model and the Internet of Things. The method comprises the following stepsof: collecting urban drainage pipe network information; establishing the BIM model of the urban drainage network based on a BIM technology; establishing a B/S, M/S pipe network operation and maintenance platform based on a GIS technology; arranging the internet-of-Things intelligent sensing equipment at the front end of the pipe network through calculation of a pipeline hydraulic model so as to sense pipe network operation information; carrying out lightweight processing on the BIM model, uploading the BIM model to the B/S, M/S pipe network operation and maintenance platform, and superposing the BIM model into a GIS map; enabling the data obtained by the Internet-of-Things intelligent sensing equipment to be in one-to-one correspondence with the BIM model and the GIS map, and achieving thesharing and transmission of the data; performing drainage service workflow on a pipe network operation and maintenance platform, and performing pipe network operation and maintenance condition earlywarning and quality evaluation through Internet of Things monitoring and model calculation. The urban drainage pipe network operation and maintenance method based on the pipe network construction model and the Internet of Things is reasonable in arrangement, and refinement and scientization of drainage pipe network operation management and maintenance are achieved.

The invention discloses an industrial robot built-in wiring harness abrasion and accelerated abrasion test method and device. No method and no device specially aiming at the abrasion test of a built-in wiring harness of an industrial robot exist in the prior art. The device provided by the invention mainly consists of a plurality of wiring harnesses, a camera, a simulated mechanical arm, a wiringharness joint motor, a camera space position regulating device, a multi-wiring-harness bundling device, a swinging motor, an installing seat, a holding hoop, a swinging arm, a simulation board, a simulation board swinging rotation device, a simulation board moving platform, an industrial personnel computer, a motor movement controller, a swinging motor driver, a step motor driver and an image collection card. The plane abrasion test or joint constraint abrasion test can be selected; the swinging amplitude and the swinging period of the swinging motor are controlled according to the wiring harness abrasion mode or the wiring harness accelerated abrasion mode; next, an imaging recognition technology is used for recognizing the wiring harness abrasion region due to simulation; the wiring harness abrasion and accelerated abrasion detection intelligence is realized; and the image processing process is simple and efficient.