341results about How to "Accurate portrayal" patented technology

The invention discloses a day-dimension regional traffic index prediction method considering influences of multiple factors. The method comprises the steps that regions are divided and aggregated; regional traffic index original data preprocessing is carried out; the influences of multiple factors are considered, and regional traffic index prediction under the day dimension is carried out. According to the specific technical scheme of the method, on the basis of traffic cell division, traffic cells with the same aggregation property are aggregated, and regional traffic indexes are calculated;on the basis of road network operation early warning requirements, a prediction time period and a prediction cycle are determined; regional traffic data is extracted, made up for and removed, and preprocessing such as comprehensive building of a historical data factor attribute set from different angles is conducted on the data; on the basis of a decision tree theory, regional road network operation congestion state prediction is carried out; a final prediction result of the regional traffic indexes is determined by means of the square euclidean distance. By means of the method, on the one hand, monitoring and application of the urban road network operation state is deepened, and on the other hand, technical support is provided for early warning and forecasting work of the road network operation state.

The invention relates to an internet personalized recommendation technology and particularly relates to a modeling recommendation method based on user behavior data fragmentation cluster. According to the modeling recommendation method, the user behavior data is subjected to fragmentation cluster treatment, a user dynamic interest model is established, so that the personalized recommendation is realized. Compared with the existing personalized recommendation method, the modeling recommendation method has the following differences: the existing personalized recommendation method only considers user interest dynamic time-varying characteristics, while the modeling recommendation method not only considers user interest time-varying characteristics, and also excavates multi-dimensional discrete interest points from behavior data, so that a user interest model is depicted more accurately. According to the modeling recommendation method, aiming at the multi-dimensional discrete interest theme of target users, the concurrence of interest points of users is preliminarily recommended, and finally, the weight, memory and preliminary recommendation result of the interest points of the target user are predicted and scored to be finally recommended, so that the accuracy and the processing capability of the personalized recommendation result are improved.

The invention discloses a wavelet transformation and deep learning-based rolling bearing weak fault diagnosis method. The method comprises the following steps: a rolling bearing vibration signal is obtained, and the acquired vibration signal is subjected to continuous wavelet transformation to obtain a time-frequency diagram; autocorrelation operation is performed on wavelet coefficients corresponding to each frequency on the time-frequency diagram to filter out noise interference and extract periodic fault components; the Hilbert transformation is used to perform envelope demodulation to obtain a fault characteristic frequency; a processed time-frequency diagram is input as a feature diagram, and categories of early faults are determined by training a deep learning classification model. Theoretical and experimental results show that fault categories can be determined accurately at an early stage when weak fault of a rolling bearing occur based on an improved wavelet time-frequency diagram used as the classification model for input training, right determination results can be given when the method is applied to different bearings, high training speed can be realized, and high actual application value can be achieved.

The application discloses a role separation method based on voice, comprising the following steps: extracting feature vectors frame by frame from a voice signal to get a feature vector sequence; assigning role tags to the feature vectors; using the feature vectors with role tags to train a deep neural network DNN model; and judging a role sequence corresponding to the feature vector sequence according to the DNN model and a hidden Markov model HMM trained using the feature vectors, and outputting a role separation result, wherein the DNN model is used to output the probability of each role according to an input feature vector, and HMM is used to describe the jump relationship between roles. The invention further provides a role separation device based on voice. According to the method provided by the invention, as the DNN model with strong ability of feature extraction is used to model speaker roles, the method has stronger characterization ability than a traditional GMM (Gaussian Mixture Model), role characterization is more detailed and accurate, and therefore, a more accurate role separation result can be obtained.

Systems and methods for collecting gaming data from the play of a live table game and using the collected data to conduct and facilitate the remote play of the live table game and independent wagering games, including providing selectable features which enable remote players to, among other things, obtain unique access to the collected gaming data and customize the collected gaming data for use in remote play.

The invention relates to an intrusion alarm analyzing method based on relative entropy. According to massive alarm flow produced by an intrusion detection system, the macroscopic safety condition of a current network is evaluated and the attack condition on which the most attention should be paid is described. The intrusion alarm analyzing method comprises the steps of obtaining an alarm of the intrusion detection system; building a normal parameter base line with multiple characteristics and a tolerance range according to historical data and expert knowledge; adopting a threshold value detection method based on the relative entropy according to the five characteristics of intrusion alarm data, wherein the five characteristics include a source IP address, a target IP address, a source port, a target port and an alarm type; determining that abnormal flow exists once the alarm flow exceeds the tolerance range of the base line; helping a network manager position a network abnormity rapidly by excavating and analyzing abnormities and effectively recognizing and reporting types of the abnormities.

This invention provides accurate, high quality images for the identification of the surface characteristics of an object, that may be used as an input to suitable industrial process. It involves acquiring a first raw scan of a portion of a target object across a scan line in a scan zone with a first camera and simultaneously acquiring a second raw scan of the same portion of the target object across the scan line in the scan zone with a second camera. The raw scans are converted to digital and then processed with flattening coefficients derived from measurements of variations in illumination. The first and second cameras sets of flattened image data are then gridized to compensate for parallax, make them orthographic sets of image data that can be compared on a pixel-by-pixel basis with a known or measured geometric profile of the target. A selection of enhanced pixel value for a surface coordinate can then be made, based on both sets of data. The obscuring of surface features by specular reflection can thus be effectively eliminated.

The invention discloses an information push method based on internet-surfing log mining and user activity recognition.The method includes a data preprocessing stage, a potential pushing user screening stage and a timely push stage.The data preprocessing stage comprises a webpage portrait, webpage level classification and a user portrait.In the potential pushing user screening stage, similarity between new information and historical web pages which users have access to is solved through a method based on matrix decomposition, and potential pushing users who may be interested in the new information are screened out.The timely push stage includes situational information acquisition and activity recognition based on a mobile intelligent device, and information timely pushing adaptive to the activity situation.By mining internet-surfing log data, potential users interested in information are found, when new information is generated, the new information is pushed to the potential users in good time, and therefore information push efficiency is improved.

The invention belongs to the field of social network modeling and analysis, and particularly relates to a method for predicting the maximum information spreading range on the basis of a random model, and by means of the method, dynamic characteristics of a social network are explored. According to the method, a set of functions capable of describing the network information spreading dynamic characteristics are constructed, a dynamic information spreading model is built according to historical data of social network information spreading, a random model detector is used for predicting the possible maximum information spreading range through a verification and emulation technology, and the node set capable of maximizing the spreading range is found out, wherein information is spread through different node sets. Compared with a traditional spreading range maximization modeling method, the dynamic characteristics of the network can be modeled, so that the initial node set which is predicted out is higher in quality, and the success rate of a network marketing strategy is increased.

The invention discloses a multidisciplinary, long-periodic and reliable modeling method of a hydraulic servo mechanism based on a failure mechanism. The method is implemented by five stages: firstly, carrying out system modeling, namely carrying out dynamics mechanism modeling, dynamics mechanism parameterization and hydraulic system modeling; secondly, carrying out joint simulation, namely setting a joint simulation environment, building a joint simulation platform, selecting a joint simulation mode, setting a transfer function, and operating joint simulation; thirdly, injecting individual discipline failure mechanism and mode, namely injecting a failure mechanism of a dynamics mechanism and a hydraulic system failure mode; fourthly, injecting multidisciplinary failure mechanism and mode, thus injecting failure mechanism and modes into a hydraulic system and the dynamics mechanism; and fifthly, carrying out simulation analysis, analyzing single failure influence, finding out weak links and key parameters of a system, and depicting the degradation paths and performance degradation paths of the key parameters, thus obtaining reliable related data. According to the method, the multidisciplinary failure mechanism and mode injection is realized for the first time, and the long-periodic and reliable modeling method is perfected.

The present invention provides an enterprise portrait method and system based on a multi-index dimension model, wherein the method includes data source acquisition, and also includes the following steps: multi-dimensional index determination; multi-dimensional rule determination; multi-dimensional rule normalization processing; multi-dimensional Model determination; model parameter optimization adjustment. The enterprise portrait evaluation model and method disclosed in the present invention break through the problem of qualitative or one-sided description of enterprise characteristics, and establish a method for describing enterprise characteristics based on quantitative points, which can provide evidence for government supervision, credit investigation, finance, enterprises and institutions Comprehensive and accurate information support.

The invention discloses an infrared thermal image defect feature recognition method based on dynamic multi-objective optimization. The transient thermal response of a pixel point is selected by changing the step length of a thermal image sequence; FCM is used for classification. obtaining the category of the transient thermal response of each pixel point; the pixel value similarity of each type ofpixel points and the same type of pixel points is considered; the difference with different types of pixel points is realized; constructing a corresponding multi-objective function; meanwhile, afterthe environment is changed each time; Prediction mechanism, a guiding direction is provided for population evolution; a multi-objective optimization algorithm is helped to quickly respond to the new change; The method has the advantages that the dimension reduction result of the thermal image sequence is acquired by the aid of the feature extraction algorithm, the defect features of the infrared thermal image are extracted by the aid of the pulse coupling neural network, accordingly, accurate selection of transient heat representations (temperature points) can be realized, the accuracy of defect feature extraction can be guaranteed, and computing consumption of the transient heat representations for acquiring various types of information in dynamic environments can be reduced.

The invention discloses a shale gas volume fracturing micro-earthquake monitoring method, and belongs to the technical field of petroleum and natural gas production increasing. The method comprises the steps that a monitoring well is selected according to the maximized monitoring range, instrument deployment location cementing quality, background noise and actual construction requirements of a shale gas platform well; the liquid level of the monitoring well is reduced to a preset value below the ground; a high-sampling-rate detector is arranged at the vertical section of the monitoring well; an initial velocity model is established by utilizing a logging curve; the initial velocity model is calibrated and optimized according to a perforating event or a detonating cord and azimuth correction is performed on the high-sampling-rate detector; horizontal component rotation and filtering and other preprocessing are performed on original micro-earthquake signals; and micro-earthquake event information is computed and displayed by utilizing the calibrated and optimized initial velocity model according to micro-earthquake records received by the high-sampling-rate detector. Precision of shale gas platform well micro-earthquake monitoring can be greatly enhanced, and reasonable proposals can be timely put forward to onsite fracturing engineers.

The invention discloses a thermal image defect detection method of a pressure vessel based on line variable step size segmentation. The method comprises the following steps: selecting a maximum pixelvalue point from eddy current pulse thermal image, computing a related coefficient by utilizing a Pearson correlation coefficient method according to the maximum pixel value point, and then obtainingthe conversion step size; computing the transient thermal response of each pixel point by combining the conversion step size, and performing classification processing; and performing defuzzfication onall pixel points by utilizing the membership maximization principle to obtain the category of each pixel point; and finally performing feature extraction by adopting a Canny operator algorithm afterperforming dimension-reduction processing, thereby extracting the defect feature in the eddy current pulse thermal image.

The invention discloses a multi-viewing-angle face detection method based on skin color segmentation and machine learning. The method comprises the following steps: firstly, performing equalization processing on an original color image by adopting GrayWorld, and performing skin color detection by using an elliptic model; secondly, getting the minimum surrounding rectangle of a skin color connected region, appropriately expanding the minimum surrounding rectangle, and performing graying and median filtering processing on the minimum surrounding rectangle; and finally, performing multi-scale traversal search detection by using a multi-viewing-angle face detection device, and combining and outputting detection results. The multi-viewing-angle face detection device is formed by cascade classifiers which are corresponding to five viewing angles and are arranged in parallel, and the classifiers are trained by adopting a risk sensitive type continuous Adaboost algorithm. According to the method disclosed by the invention, the GrayWorld is adopted to perform equalization to effectively eliminate color offset, and the elliptic model is used for detecting the skin color, so that the subsequent search range is reduced and then the detection speed is accelerated; the risk sensitive type continuous Adaboost algorithm is used for constructing the multi-viewing-angle face detection device, the classification boundary can be portrayed more accurately, and a better classification effect on face samples can be achieved; and the method has a wide application prospect in the aspects of intelligent video monitoring and the like.

The invention discloses a rapid digital imaging fuzzy identification and restored image quality assessment method, and relates to a fuzzy identification and restored image quality assessment method, for solving the problems of poor real-time performance, incapability of effective identification of a blurred image and a clear image and effective assessment of an image restoration result, and instable output result after fuzzy restoration processing by use of a conventional method. The method is realized through the following steps: 1, obtaining a gradient image G (i, j); 2, calculating an average gray scale gradient value; 3, obtaining statistical distribution information of the gradient image; 4, performing threshold determining on BIM; 5, obtaining a restored image; 6, generating reference images F1 and D1; 7, calculating brightness similarities, contrast similarities and structural similarities between the reference images and an image to be assessed; 8, calculating g(F(i, j), F1) and g(D(i, j), D1); 9, obtaining a non-reference-image assessment index; 10, determining the non-reference-image assessment index; and the like. The rapid digital imaging fuzzy identification and restored image quality assessment method is applied to the field of fuzzy identification and restored image quality assessment.

The invention discloses a model-based automated test method for a spacecraft system and belongs to the field of system testing. The method comprises the steps of firstly building a window tree model of a tested spacecraft system through a formalization method, classifying behavior states of the tested spacecraft system during operation according to business processes, and constructing a system behavior state transition diagram; secondly traversing a window tree to generate a test case set, running the test case set in a tested spacecraft digital model and validation prototype system, setting tracking points, obtaining system behavior states and recording a state transition sequence; and finally checking whether the obtained state transition sequence obeys a state transition rule or not through a model detection algorithm, thereby automatically validating overall design of the tested spacecraft system and interface design among modules. According to the method, the test cost of the spacecraft system and the whole research and development cycle of the spacecraft system are reduced and shortened by adopting a model-based test technology; and the quality and accuracy of spacecraft system testing are improved by adopting the formalization method and the model detection algorithm.

The invention relates to a building method for an intelligent personalized service web site, which is a simple, easily used, highly efficient and general web site personalized service method. The method packages complex knowledge representation and knowledge acquisition processes and does not directly participate in 'personalized service', and the 'middleware' means is used for providing 'personality' of each client for an application program of the web site; the 'personality' of each client is abstracted into three aggregates which are respectively 'content preference', 'forecast preference' and 'access habit'; the data mining technology is utilized for continuous update of a knowledge base by means of establishment of a dynamic study; the 'personality' of each client is tracked and analyzed; the 'personality' of clients is provided to the application program of the web site by means of API; the application program of the web site can arrange web page contents according to the provided 'content preference' and the provided 'forecast preference' of the clients and arrange index links of web sites which can be next accessed by the clients according to the 'access habit' of the clients, thereby the aim of personalized service is achieved.

The invention discloses a multi-objective optimization infrared thermal image defect feature extraction method based on homogeneous evolution. The transient thermal response of a pixel point is selected by changing the step length of a thermal image sequence; FCM is used for classification. obtaining the category of the transient thermal response of each pixel point; secondly, considering the pixel value (temperature value) similarity of each type of pixel points and the same type of pixel points; meanwhile, considering the difference between the pixel point (temperature point) and different types of pixel points (temperature points), constructing a corresponding multi-objective function, obtaining a dimension reduction result of the thermal image sequence by utilizing a decomposition-based homoevolution multi-objective evolution algorithm, and finally, carrying out feature extraction by utilizing a pulse coupling neural network so as to extract defect features of the infrared thermalimage. Through the uniform evolution direction of the solution, the difference and the similarity are comprehensively considered, accurate selection of representative pixel points (temperature points)is realized, and the accuracy of defect feature extraction is ensured.

The invention relates to an attack detection method and device, computer equipment and a storage medium. The method comprises the steps of obtaining current flow information corresponding to current time; determining a target refining time period corresponding to the current time in a current flow period, wherein the current flow period is divided into a plurality of refining time periods according to a preset time granularity; obtaining target reference flow information corresponding to the target refining time period, wherein the target reference flow information is obtained through calculation according to target historical flow information of a plurality of target historical flow periods in the target refining time period, and dividing the target historical flow period is divided intoa plurality of refining time periods according to the preset time granularity; and performing attack detection according to the target reference flow information and the current flow information. Themethod is high in attack detection accuracy.

The invention discloses a personalized recommendation method based on multi-type academic achievement portraits and a mixed recommendation strategy. The personalized recommendation method comprises the following steps: adopting an appropriate recommendation strategy for users, academic achievements portraits and each academic achievement; wherein the user and academic achievement portraits comprise a user portrait, a paper portrait, a periodical portrait, a scholar portrait, a subject portrait and a fund portrait; and adopting appropriate recommendation strategies for each academic achievement, wherein the appropriate recommendation strategies comprise project-based collaborative filtering recommendation and content-based recommendation.