795results about How to "Describe well" patented technology

A system and method of targeted marketing to consumers, including businesses and associates, based upon the financial characteristics of the consumer, type offer being made and the channel of communication for delivery of the offer. The consumer is characterized based upon financial, behavioral, and socioeconomic factors. The offer is characterized based upon the consumer and the potential for the consumer accepting the offer. The channel of communication for delivery of the offer is also characterized and combined with the consumer and consumer-offer characteristics to arrive at a net present value of the offer to be made. If the net present value is sufficient the offer is processed and presented to the consumer. If the net present value is not sufficient, the offer is revised to present a better value to the consumer (or discarded if the required offer value can not be created) thereby enhancing the chances that the consumer will accept the offer in question. In this way the system and method of the target marketing creates value in both releasing, and not releasing, specific offers.

The present invention is related generally to the method of customizing personal checks. More specifically, a method is provided herein to alter a personal check in such a way as to add selective artistic customization. Preferably, the enhancements are done with an ink stamp and colored pencils, or with adhesive stickers, wherein the user will be able to selectively alter the check. It is envisioned that the images will convey a mood, an emotion, a feeling, or represent an occasion, a cause, or a holiday.

Network traffic analysis is performed by deploying, across a network having a plurality of network nodes, at least one data collection agent, on at least two of the plurality of network nodes. Each data collection agent may monitor at each network node, a plurality of network connections instantiated during a monitoring time period. Data resulting from the monitoring is acquired from the data collection agents and an ontological description of the network is automatically created from the acquired data. The ontological description is dynamically updated and network traffic analysis is performed using the dynamically updating ontological description.

A method and system are disclosed for creating a real-time, high accuracy mosaic from an aerial video image stream by applying orthorectification of each original video image frame using known ground control points, utilizing a photogrammetric model resolving the object image into pixilation, applying shading to the pixellation, and mosaicking the shaded pixilation of several orthorectified images into a mosaicked image where the mosaicked image is then scaled to the known original image dimensions.

The invention discloses a depth convolution wavelet neural network expression identification method based on auxiliary tasks, and solves problems that an existing feature selection operator cannot efficiently learn expression features and cannot extract more image expression information classification features. The method comprises: establishing a depth convolution wavelet neural network; establishing a face expression set and a corresponding expression sensitive area image set; inputting a face expression image to the network; training the depth convolution wavelet neural network; propagating network errors in a back direction; updating each convolution kernel and bias vector of the network; inputting an expression sensitive area image to the trained network; learning weighting proportion of an auxiliary task; obtaining network global classification labels; and according to the global labels, counting identification accuracy rate. The method gives both considerations on abstractness and detail information of expression images, enhances influence of the expression sensitive area in expression feature learning, obviously improves accuracy rate of expression identification, and can be applied in expression identification of face expression images.

The invention provides a human body posture identification method based on multi-characteristic fusion of a key frame, comprising the following steps of: (1) extracting Hu invariant moment characteristics from a video image; calculating a covering rate of an image sequence; extracting the highest covering percentage of the covering rate as a candidate key frame; then calculating a distortion rate of the candidate key frame and extracting the minimum distortion percentage as the key frame; (2) carrying out extraction of a foreground image on the key frame to obtain the foreground image of a moving human body; (3) extracting characteristic information of the key frame, wherein the characteristic information comprises a six-planet model, a six-planet angle and eccentricity; obtaining a multi-characteristic fused image characteristic vector; and (4) utilizing a one-to-one trained classification model, wherein the classification model is a posture classifier based on an SVM (Secure Virtual Machine); and identifying a posture. The human body posture identification method has the advantages of simplified calculation, good stability and good robustness.

The invention discloses an electromyographic signal gesture recognition method based on a hidden markov model. The method comprises the following steps of: executing smoothing filtering for electromyographic signals; extracting a multi-feature feature set for each window data through a sliding window, and executing normalization and feature dimension reduction of minimum redundancy maximum correlation criterion for feature vectors; designing three classes of hidden markov model classifiers, and optimizing parameters of the hidden markov model classifiers; obtaining classifier models through training with hidden markov classifier model parameters and training data; inputting test data into the models trained well, and according to likelihood output by each class of hidden markov model, determining that the class corresponding to the maximum likelihood is the recognized class. According to the method provided by the invention, three classes of common hidden markov model classifiers are recognized based on a new feature set. By application of a classification method based on the hidden markov model, different gestures of the same testee can be recognized accurately, and gestures of different testees can be relatively recognized accurately.

The invention discloses a robot accuracy compensation method synthesizing a pose error model and rigidity compensation. The method comprises the following steps: step 1, establishing a robot motion model according to structural parameter of a robot; step 2, establishing a robot error model; step 3, in a robot working space, randomly giving a target pose point, and when a tail end of the robot moves a designated point, recording a joint angle at the moment; step 4, using a position measuring instrument to measure actual coordinates Pa of the given target pose point; step 5, using a least square method to recognize an error parameter; step 6, applying a load at the tail end of the robot, measuring the deformation amount of the robot, then returning to step 3, compensating a re-recognized structural error for the motion model again, thereby eliminating the pose error of the tail end due to the deformation caused by the load, and meanwhile, data of the deformation amount caused by the load is stored in a database for later accuracy compensation. According to the invention, the absolute positioning accuracy of the robot can be improved remarkably, and high simplicity and high efficiency are realized.

An insurance entity, organized as a stock, mutual or reciprocal company, offers claims paid property and causality insurance. This organization offers improvements over a risk-sharing vehicle such as MPT by removing unlimited liability and by capping annual assessments, while retaining the lower cost achievable by a claims-paid policy.

The invention relates to the technical field of biomedicine, and relates to a biomedicine event trigger word identification method based on characteristic automatic learning. The biomedicine event trigger word identification method comprises the following steps of 1, data pre-processing; 2, construction of an event trigger word dictionary; 3, construction of candidate trigger word examples; 4, characteristic learning by means of a convolutional neural network model; 5, training by means of a neural network model; and 6, classification of event trigger words. The biomedicine event trigger word identification method is advantaged in that 1, complex preprocessing to data is simplified, and tedious steps for carrying out a characteristic design by people are saved; 2, domain knowledge is introduced, and a lot of external resources such as unlabeled linguistic data are effectively utilized; 3, characteristic automatic learning is carried out by means of a convolutional neural network, manual intervention is reduced, sentence level characteristics in a deeper level can be excavated and explored, through the fusion of local characteristics, implicit global characteristics are discovered, and the category of trigger words can be identified; and 4, a better experiment result is obtained in MLEE linguistic data, and the whole performance on event trigger word detection is improved.

The invention discloses a camera motion and image brightness-based Kinect depth reconstruction algorithm. The algorithm comprises the steps of 1) uploading data collected by Kinect to a computer through a third-party interface under the condition that a Kinect depth camera and an RGB camera are calibrated and aligned; 2) recovering a three-dimensional scene structure and a motion track of the kinect RGB camera from an RGB video sequence, and obtaining a relationship between point cloud and a camera motion; and 3) reconstructing image depth by utilizing brightness status information of an image in combination with the relationship between the point cloud and the camera motion, obtained in the step 2). According to the algorithm, the depth camera does not need to be improved physically, a complex apparatus combination does not need to be designed, and an illumination calibration step which is often used in a conventional depth reconstruction method, generally only can be limited in laboratory conditions, does not have a practical application value and is complex and strict in condition is not needed, so that compared with the conventional method, the algorithm has higher practical application value and significance.

The invention relates to a workpiece recognition method based on a geometric shape feature and a device thereof. The method comprises the steps of (1) taking a two-dimensional image of a workpiece on a conveyor belt, carrying out difference operation on the two-dimensional image of the workpiece on the conveyor belt and a conveyor belt image, and obtaining a foreground area comprising the workpiece and the shadow of the workpiece, (2) using a shadow detection method to remove the shadow in the foreground area comprising the workpiece and the shadow of the workpiece to obtain the accurate area contour of the workpiece, (3) extracting the geometric feature for the accurate area contour of the workpiece so as to obtain the feature vector of the workpiece area contour, wherein the feature vector comprises a Hu moment and a Fourier operator, and (4) using a support vector machine SVM to train and classify the feature vector of the workpiece area contour. Through employing the above steps, the method and the device can be widely applied to the fields of workpiece grasp and transportation in a factory production line, circumferential welding manipulator, industrial painting and equipment assembly.

A method of processing stratigraphic data comprising a plurality of stratigraphic features, such as horizon surfaces, within a geological volume is provided. The method includes the steps of: extending a plurality of spaced sampling traces through the volume to traverse the stratigraphic features; and assigning the stratigraphic features respective relative geological ages. On each sampling trace, the relative geological age of each stratigraphic feature traversed by the sampling trace in the direction from geologically younger to geologically older stratigraphic features is increased in relation to the relative geological age of its preceding stratigraphic feature, under the condition that each stratigraphic feature takes the same relative geological age across all the sampling traces by which it is traversed.

The invention discloses a method, device and server for obtaining the similarity of key words, and belongs to the field of information technology. The method comprises the steps: obtaining key words of user labels and key words of interested classes; according to the key words of the user labels and the key words of the interested classes, looking for a preset database to obtain the word vector of each key word in the key words of the user labels and the word vector of each key word in the key words of the interested classes; computing a distance between the word vector of each key word in the key words of the user labels and the word vector of each key word in the key words of the interested classes according to the word vector of each key word in the key words of the user labels and the word vector of each key word in the key words of the interested classes; obtaining the distance between the word vector of a first key word and the word vector of a second key word to be used as the similarity of the first key word and the second key word. According to the invention, the word vectors are used for obtaining the similarity of the key words, so that the precision rate of recommended information is increased.

The invention discloses a device and a method for testing a low-permeability core starting pressure gradient at the high temperature and the high pressure with an unsteady state method. The method comprises steps as follows: a to-be-tested low-permeability core sample is prepared and placed in a core holder; an automatic water pump is used for providing required confining pressure and return pressure for the core holder; a third valve is closed, and a gas pressurization device is used for pressurizing a standard bottle; after a second pressure sensor stably reads, the third valve is opened, and gas in the standard bottle permeates an inlet of the core holder; a controller records a pressure value, changing over time, read by the second pressure sensor and stops recording until the change rate of a reading number of the second pressure sensor is lower than a threshold value; and the core starting pressure gradient is calculated according to the reading number, changing over time, of the second pressure sensor. According to the device and the method, all that is required is to add a high-precision pressure sensor at an outlet of the standard bottle for recording pressure of the outlet, the high-precision pressure sensor has characteristics of low cost, high test precision, large range and the like, and the measurement problem of low flow speed is solved.

The invention discloses a deep belief network image recognition method based on Bayesian regularization and belongs to the field of artificial intelligence and machine learning. The deep belief network plays a more and more important role in the field of digital detection and image recognition. The invention provides a deep belief network based on Bayesian regularization on the basis of the network sparsity characteristic and changes of connection weights to solve the problem of overfitting in the training process of the deep belief network. By applying Bayesian regularization to the network training process, balance between error decreasing and weight increasing is effectively adjusted. The classification experiment of a digital script database proves effectiveness of the improved algorithm. An experimental result shows that in the deep belief network, the deep belief network image recognition method can effectively overcome the overfitting phenomenon and improve accuracy of digital recognition.

A scrambling initial value is shared without deteriorating transmission efficiency. On the transmission side, a scrambling initial value is created based on a part of a physical layer header not scrambled, a transmission signal sequence scrambled is created by calculating an exclusive-OR operation between a scrambled sequence generated from the scrambling initial value and a transmission data sequence, and is transmitted. On the reception side, the same descrambling initial value as the scrambling initial value is created based on a part of a physical header of a reception frame, and a reception data sequence is descrambled by calculating an exclusive-OR operation between a descrambled sequence generated from this descrambling initial value and a reception signal sequence scrambled.

The invention discloses a wind and photovoltaic complementary power generation system reliability evaluation method based on a Copula theory. The method comprises the following steps of: (1) determining the power probability distribution of a wind power station and a photovoltaic plant; (2) respectively performing integral operation on the power probability distribution fWT(P1) and fPV(P2) of thewind power station and the photovoltaic plant, and calculating the accumulative power probability distribution of the wind power station and the photovoltaic plant; (3) calculating Kendall rank correlation coefficients of the power of the wind power station and the photovoltaic plant; (4) calculating a correlation parameter theta of a Frank Copula function; (5) forming a simultaneous equation through a formula (2) and a formula (4) to obtain the joint probability density of the random variables P1 and P2; and (6) acquiring the accumulative probability distribution of the wind and photovoltaiccomplementary power station through integral operation according to a joint probability density function of the power of the wind power station and the photovoltaic plant, forming an off-the-line table of the power of the wind and photovoltaic complementary power station through the accumulative power, and establishing a reliability model of the wind and photovoltaic complementary power station. According to the method, the reliability of the wind and photovoltaic complementary power generation system can be accurately evaluated.

The invention discloses a lithium-battery variable fractional order and equivalent circuit model and an identification method thereof. The lithium-battery variable fractional order and equivalent circuit comprises a run time circuit and a battery I-V characteristic circuit, wherein a capacitor in the battery I-V characteristic circuit is a variable fractional order capacitor. A second order RC circuit model is generalized to a non-integer order, and the model parameters and the number of fractional order of different SOC are identified based on a least square method, so that the fractional order and equivalent circuit varying order according to the SOC is obtained. The instruction of fractional order realizes the continuous change of the order number of the model, so that the model is relatively stable, good in dynamic property and high in precision. The variation of fractional order realizes more freedom and more flexibility and innovation of the model. As the number of RC networks is not increased, the fractional order model effectively solves the contradiction between the accuracy and practicality of the model, is suitable for various working conditions of batteries, and has high practical value. The invention provides a precise battery model easy to realize for precise estimation of SOC.

The invention provides a method and device for detecting video abnormal events. The method includes the steps that high-level expression information of a to-be-detected video stream with multiple images is extracted, wherein the high-level expression information comprises space-time information of the to-be-detected video stream; through a preset dictionary, reconstruction coefficients generated when bases with the minimum number in the dictionary are used for representing the high-level expression information of the to-be-detected video stream are calculated; according to the reconstruction coefficients, reconstruction cost values are calculated; when the reconstruction cost values are larger than a preset threshold value, it is confirmed that the abnormal events exist in the to-be-detected video stream; when the reconstruction cost values are smaller than or equal to the preset threshold value, it is confirmed that no abnormal events exist in the to-be-detected video stream. By the adoption of the method, the feature expression capacity is high, the abnormal events can be well described, and the detection efficiency and the detection accuracy of the video abnormal events are improved.

The invention discloses a linear prediction speech coding method and a speech synthesis method. The linear prediction speech coding method includes the following steps: speech is preprocessed; second-order backward linear prediction is carried out on the preprocessed speech, so that a residual signal is obtained; wavelet decomposition and compression are carried out on the residual signal, so that a wavelet coefficient is obtained, vector quantization is carried out on the wavelet coefficient, and meanwhile, the pitch period and gain parameters of the residual signal and the unvoicing and voicing characteristic of each sub-band are calculated and respectively and scalarly quantized. The speech synthesis method is based on the linear prediction speech coding method. After being adopted, the technical scheme of the invention can reduce the affection of noise on the quality of decoded speech, inhibit the deterioration of speech quality when unvoicing and voicing judgment is mistaken and improve the performance of coding unvoiced speech or background noise.

The invention discloses a facial expression recognition method based on random forests. The facial expression recognition method based on the random forests comprises the step of extraction of a displacement feature of an AAM, the step of extraction of AUs in a facial expression sequence, the step of training of a facial expression classification model and the step of facial expression recognition. According to the facial expression recognition method, the novel AAM displacement feature is provided to be used for training and learning the AUs, and finally facial expression recognition is carried out by depending on the AUs. Compared with other feature representations in identification of the same classification, the facial expression recognition method based on the random forests better describes expression information and changing process information contained in the expression sequence. The random forests are used for facial expression recognition for the first time, and the random forests in the method have a better classified recognition effect in the field compared with a frequently used support vector machine (SVM) method at present. For the aspect of CK and AU recognition of databases, the facial expression recognition method based on the random forests can achieve a perfect recognition effect.

The invention discloses a regional average value kernel density estimation-based moving target detecting method in a dynamic scene. The method comprises the following steps of: firstly, initializing a background model; secondly, building a time and space background model for describing the dynamic complex scene by using a training sample in a background modelling process and considering the time sequence characteristics of pixel points in a video frame and the space characteristics in the adjacent regions of the pixel points; thirdly, continuously updating the background model by using the new video frame sample in a moving target detecting process; fourthly, adapting to the instantaneous background change by the regional kernel density estimating method and adapting to the continuous background change by using single Gauss background model, wherein the combination of the two models can fast and accurately adapt to the continuous change of the background and increases the executing efficiency of the method at the same time; and finally performing a foreground detecting method by providing an adjacent region information amount-based method so as to further remove noise points and inanition of a moving target in the background region in the detecting process and more completely extract the moving object in the foreground. The method can be widely applied to alarming the suspicious moving target in an intelligent monitoring system in an outdoor scene or a prohibited military zone and has wide market prospect and application value.

The embodiment of the invention relates to the technical field of video images, in particular to a three-dimensional convolutional neutral network training method and a video anomalous event detection method and device based on a three-dimensional convolutional neutral network. The three-dimensional convolutional neutral network training method and the video anomalous event detection method and device based on the three-dimensional convolutional neutral network are used for detecting anomalous events occurring in a crowded situation. Each convolutional core on a convolutional layer of the Nth convolution and sampling layer convolves data of all characteristic patterns of all channels in a sampling layer of the Nth convolution and sampling layer in the forward transmission process of a three-dimensional convolutional neutral network, due to the fact that the last convolutional layer convolutes the data of all characteristic patterns of all the channels, characteristics with higher expressive ability can be extracted, and accordingly the anomalous events occurring in the crowd situation can be well described by means of the characteristics, and detection accuracy of the anomalous events can be improved.

The invention relates to a soft measurement method for the biochemical oxygen demand in sewage treatment, belonging to the sewage treatment technical field, while the sewage treatment has serious production conditions, serious random interference, strong nonlinearity, large time varying and serious delay, thus is hard to establish an accurate mathematic model via mechanism analysis, and the nerve network has advantages for controlling the system of high linearity and serious uncertainty. At the point of online detection of the key water quality parameter as the BOD (Biochemical Oxygen Demand) in the sewage treatment, the invention adopts a sewage water quality soft measurement modeling method based on neurocomputing and utilizes a delete-type nerve network to realize the biochemical oxygen demand BOD online soft measurement in sewage treatment, to obtain good effect, improve the quality and efficiency of sewage treatment, reduce sewage treatment cost, save investment and operation cost, and on-time detect water quality and parameters, to improve the efficiency and stability of sewage treatment plants.

The present invention provides a motion capturing system and method based on a CAN bus and an inertial sensor, for tracking and capturing motion information of a human body in a real-time manner. The system comprises an inertial sensing node combination, a data aggregation node, and a central computer. The inertial sensing node combination contains 18 inertial sensing nodes, collects an accelerated speed, an angular speed, and geomagnetic information data of each bone point part in a real-time manner, and performs attitude estimation by using a complementary integration filtering algorithm, so as to obtain data, such as a quaternion and an euler angle, of an three-dimensional attitude of the current bone point. The data aggregation node is connected to the 18 inertial sensing nodes, is configured to collect, in a time-sharing manner, three-dimensional attitude data of each bone point obtained by the 18 inertial sensing nodes, and send the collected data to the central computer by using a wireless wifi module. A main task of the central computer is to complete functions of collecting motion data transmitted from the data aggregation node and driving a virtual 3D person model by using the motion data.

This invention provides a system and method of Advanced Process Control for optimal operation of multi-unit plants in large scale processing and power generation industries. The invention framework includes the following components: continuous real time dynamic process simulation, automatic coefficient adjustment of dynamic and static process models, automatic construction of transfer functions, determination of globally optimal operating point specific to current conditions, provision of additional optimal operating scenarios through a variety of unit combinations, and calculation of operational forecasts in accordance with planned production.

This invention relates to a method for estimating movement using its vector site spacetime coherence based on searching mode including the following steps: determining a group of candidate vectors according to the movement vectors of several blocks near the present block to apply a renew structure based on the sequence of block matched search, computing pel block error of the same position in thepresent pel block and reference frame, determining the vector with the minimum error as the movement vector and carrying out mean value filter to the estimated movement vector for smoothing the vector site.

The invention discloses a pedestrian re-identification method based on depth learning joint optimization, which comprises the following steps: 1, collecting and screening positive and negative pedestrian sample pairs with balanced quantity to construct a data set; 2, constructing a deep-learning Siamese neural network structure model, comprising a two-way front-end convolution neural network and amulti-level feature fusion module, input positive and negative pedestrian samples into that model, and extracting the Hyper features of two different pedestrian; 3, sending the Hyper features of twodifferent pedestrian into a classification network and a verification network, combining the classification network and the verification network, combining the classification los function and the verification loss function, and optimizing the parameters of the neural network structure model. In the method, the depth convolution neural network and HyperNet network are combined to extract multi-scale features to enhance the detection ability of pedestrian target, and the verification model and classification model are combined to optimize the network structure, and the excellent pedestrian re-recognition neural network structure model is obtained.