669results about How to "Fully excavated" patented technology

The invention discloses a big data based wireless real-time position positioning method. The big data based wireless real-time position positioning method comprises the following steps of gridding a positioned detection area, enabling a plurality of wireless routers which are arranged inside the detection area to transmit wireless signals, enabling a wireless signal receiver to collect wireless signal information of the wireless routers for a plurality of times in every grid of the area after gridding and forming collected wireless signal information into a big database wireless signal fingerprint database; performing signal preprocessing; performing parameter training; training DNN(Deep Neural Networks); performing signal character extraction and character classification based on the trained DNN; performing position estimation based on a HMM (Hidden Markov Model). The big data based wireless real-time position positioning method has the advantages of improving the accuracy of a positioning result under the condition that the real-time positioning speed is not influenced, successfully integrating positioning problems into the big data background and improving the performance of the real-time positioning system by effectively using advantages of the big data.

The invention discloses a convolutional neural network structure-based traffic flow prediction method. The method comprises the following steps of 1) establishing a traffic flow data set and preprocessing the data set: establishing the traffic flow data set according to obtained traffic flow data, preprocessing the data set, constructing a data set sample matrix, and dividing the data set into a training set and a test set; 2) establishing a single-layer conventional convolutional neural network, removing a pooling layer, constructing a feature extraction network of a road traffic flow matrix,adding a sigmoid nonlinear regression layer to a full connection layer, and constructing a road traffic flow nonlinear regression prediction network; and 3) training the convolutional neural networkand realizing real-time prediction of short-term traffic flow: defining a model objective function, taking the training set as an input of a convolutional neural network model, solving an optimal parameter of the model to finish model training, and performing real-time traffic flow prediction on the test set by utilizing the trained convolutional neural network model. The short-term prediction accuracy of the traffic flow is improved.

On the basis of analyzing the features of the electric transmission and transformation device multi-source state assessment data, an electric transmission and transformation device multi-source state assessment data processing method is provided. The method comprises: multi-source data obtaining, data cross-platform access, data preprocessing and preliminary cleaning, data quality assessment model, data standardization conversion and data output, and is applied on the big data platform. The electric transmission and transformation device multi-source state assessment data processing method and the application thereof are configured to provide service such as storage, retrieval and excavation for the main net electric transmission and transformation device multi-source data and provide data support for the high-grade service such as risk assessment and the like. The electric transmission and transformation device multi-source state assessment data processing method and the application thereof belong to the electric power informatization technology field.

The invention discloses a method for evaluating the reliability of a stepping stress quickened degradation experiment based on a time sequence. The method utilizes a correlation coefficient stationary sequence analytical method to describe non-equidistant stochastic information in stepping stress quickened degradation experiment data, establishes a regressive-non-equidistant autoregression degradation model on the basis of obtaining the respective advantages of a deterministic regression model and a stochastic correlation coefficient stationary sequence autoregression model, combines a grey theory to predict a product degradation trend and forms a function and a curve for predicting the life and evaluating the reliability of the stepping stress quickened degradation experiment based on the time sequence. The method obviously decreases the sample quantity of a product and shortens the time of the degradation experiment, thereby saving a large amount of expenses and resources, enhancing the fitting accuracy of the degradation model and enhancing the reliability of a reliability evaluating result.

The invention provides a decoding method for compression video based on a GPU. The method utilizes point graphic element to show video block instead of square and maps decoding segments to the GPU except variable length decoding, and then the GPU organizes video data into point collection and completes decoding process by drawing point collection. The invention has the advantages of a CPU and the GPU so that the two work in parallel accelerate video decoding process; the invention has high performance of hardware decoding and flexibility of software decoding at the same time, can handle a plurality of video compression format and standard, replace a special decoding hardware of personnel computer with the GPU, a game console, a handheld mobile device, etc, and improve the utilization of hardware resources and reduce cost.

The invention discloses a method for constructing a full-space three-dimensional digital earth model. The method includes that an ellipsoid earth space mathematical model is constructed based on a center of gravity control system (CGCS) 2000 China geodetic coordinate system; an earth surface dissection network is generated based on a fictitious graticule; an earth surface digital elevation model is generated in an insertion mode; a geometric structure module of earth space inner and outer ring layers is fitted by interpolations; a three-dimensional body element mesh of the earth space inner and outer ring layers is generated based in geological cells; an attribute element three-dimensional distribution model of the earth space inner and outer ring layers is fitted by the interpolations; a geographical coordinate is converted into a geocentric space three-dimensional rectangular coordinate; an earth space model multi-scale expression mechanism based on level of detail (LOD) is constructed; three-dimensional visualization is performed; earth space positions are checked; and three-dimensional analysis is performed. According to the method, the automaticity and the adaptability are high, and an earth space solid model containing the inner and outer ring layers can be rapidly and automatically reconstructed in three-dimensional space to be displayed on a computer display screen in a three-dimensional visualization mode to support space analysis of various professionals.

The invention discloses a text classification method based on feature information of characters and terms. The method comprises the steps that a neural network model is utilized to perform character and term vector joint pre-training, and initial term vector expression of the terms and initial character vector expression of Chinese characters are obtained; a short text is expressed to be a matrixcomposed of term vectors of all terms in the short text, a convolutional neural network is utilized to perform feature extraction, and term layer features are obtained; the short text is expressed tobe a matrix composed of character vectors of all Chinese characters in the short text, the convolutional neural network is utilized to perform feature extraction, and Chinese character layer featuresare obtained; the term layer features and the Chinese character layer features are connected, and feature vector expression of the short text is obtained; and a full-connection layer is utilized to classify the short text, a stochastic gradient descent method is adopted to perform model training, and a classification model is obtained. Through the method, character expression features and term expression features can be extracted, the problem that the short text has insufficient semantic information is relieved, the semantic information of the short text is fully mined, and classification of the short text is more accurate.

The invention discloses a vital sign parameter evaluation device on the basis of volume pulse wave detection, comprising an input module, a volume pulse wave collecting module, a main control module and a display; the input module is used for inputting the basis information of the user such as height HT, weight WT, systolic pressure Ps, and diastolic pressure pd; the input module, the volume pulse wave collecting module and the display are connected with the main control module; the main control module comprises a volume pulse wave characteristic point extractor and a vital sign parameter calculator; the vital sign parameter calculator comprises a pulse blood-ejection prophase PEP calculator; the blood-ejection prophase can be gained directly by the calculation of the volume pulse; one signal of the volume pulse wave can realize the innovative detection of main vital sign parameter; the volume pulse wave is generally measured at the finger end and the requirement on the position of the sensor is not high; furthermore, the detection and analysis speed is quick, the cost is low, the repeatability is good, and the stability is high.

The invention discloses a method for constructing a three-dimensional physical model of a sedimentary stratum system by using drilling data, which is used for processing stratum surface data detected through geological drilling and solving various problems encountered during discontinuous stratum surface data encryption interpolation reconstruction in the sedimentary stratum system and belongs to the technical application field of three-dimensional geological simulation in engineering science and technology. The method comprises the following steps of: defining a modeling field and extracting relevant drilling information; judging modeling field total stratum ordering and integrity; discretizing drilling data; defining a skeleton triangulation network; interpolating and fitting a stratum top and bottom interface; judging the lost stratum category; generating a lost stratum processing sequence; carrying out lost stratum control interface intersected processing and elevation adjustment; carrying out lost stratum and adjacent stratum interface consistency processing; generating a three-dimensional physical model; and carrying out three-dimensional visual analysis. Compared with the traditional method, the method provided by the invention can be used for automatically judging the geologic origin of the lost stratum and defining the lost boundary and has the advantages of high automaticity and strong adaptability. A reasonable modeling result and high model precision are obtained, and the generated stratum lost boundary is natural and reasonable and is quite close to a practical stratum distribution condition.

The invention relates to a spectral reflectance peak decomposition based quantitative inversion method of the hyperspectral remote sensing mineral content. The method comprises the seven steps of: 1. reading data in; 2. intercepting a reflection peak band; 3. converting a reflectance spectrum and an absorption spectrum; 4. carrying out continuum removal on the spectrums; 5. linearly decomposing the spectrums to obtain the mineral spectrum decomposition content; 6. establishing a statistical relationship between the mineral spectrum decomposition content and the real content; and 7. converting the calculated mineral spectrum decomposition content in the step 5 into the real mineral content according to the established statistical relationship in the step 6. The invention can not only be applied to hyperspectral data which is not covered by a mineral absorption spectrum band, but also can be used for hyperspectral data which is covered by the mineral absorption spectrum band in the spectrum band range, carries out quantitative mineral content inversion by comprehensively applying a spectral reflectance peak and an absorption spectrum band and improves the inversion precision and the inversion accuracy. The invention has practical value and broad application potential in the field of hyperspectral remote sensing mineral identification.

The invention relates to a peak shaving control method based on an air conditioner aggregation model. The peak shaving control method based on the air conditioner aggregation model is characterized in that the peak shaving control method comprises the following steps that (1) a load model of single air conditioner is built according to the energy conservation principle and air conditioner running characteristics; (2) unified dispatch and control are conducted on air conditioner groups through load aggregators, the aggregation model of the air conditioner groups is built, and peak shaving potential of an aggregated air conditioner load is evaluated; (3) in the current market, a minimum electric power company dispatching cost is taken as the objective function, and dispatching plans of next-day peak shaving time periods are made; and (4) in the process of real-time dispatching, the profits of the load aggregators and the comfort level of users are considered together as a whole to achieve optimized control of the aggregated air conditioner load. According to the peak shaving control method based on the air conditioner aggregation model, the technical scheme achieves centralized dispatching control over the air conditioner groups, load-side resources are exploited sufficiently, and the investment pressure of power network facilities is relieved.

The invention discloses an artificial intelligence call center system, comprising a communication network, an artificial intelligence server, an AI agent for performing incoming and outgoing call tasks, a manual agent, an intelligent quality inspection management system for performing a quality inspection task, and an intelligent management background CRM for performing data mining and analysis, wherein the communication network is connected with a user terminal and the artificial intelligence server, the artificial intelligence server is used for accessing the data in the communication network, the AI agent is used for performing the incoming and outgoing call tasks, the manual agent is used for performing a call request that cannot be processed by the AI agent, the intelligent quality inspection management system comprises a quality inspection rule management module and a quality inspection result management module, and the intelligent management background CRM serves as a carrier ofthe call data and a processing analyzer. The artificial intelligence call center system disclosed by the invention solves the problems of low calling, screening and service efficiency, increasing labor cost, difficulty of managing large-scale artificial agents, difficulty in mass call recording quality inspection and insufficient user data mining of the existing call centers.

The invention discloses a method for predicting the remaining service life of complex equipment based on a combined depth neural network. The main steps are as follows: acquiring multi-sensor data ofcomplex equipment; Obtaining effective measurement data by feature selection; obtaining A plurality of slice samples by preprocessing; Establishing the neural network regression model which combines the attention mechanism and depth neural network; The slice samples and their corresponding labels are inputted into the neural network regression model to train the neural network regression model offline. inputting The slice samples of multi-sensor data to be predicted into the trained neural network regression model, and the remaining service life of complex equipment is obtained. Considering the data characteristics of the multi-sensor signal, the invention fully excavates the local characteristics and the time sequence information in the data, has high prediction accuracy and wide applicability, and can be widely applied to various pieces of complex equipment.

The invention relates to a streetscape semantic annotation method based on a convolutional neural network and a semantic transfer conjunctive model. A device according to the streetscape semantic annotation method comprises a deep characteristic extracting part and a soft limited semantic transfer part. A more balanced training set is constructed, and furthermore a super-pixel classification deep model with prior information is trained. According to the streetscape semantic annotation method, the prior information of a scene can be sufficiently mined, and a characteristic expression with more remarkable difference is learned so that the annotation accuracy of a superpixel is greatly improved. Through a Markov random field model, an initial result is optimized and an unnecessary noise is eliminated so that an annotation result is further improved. Finally per-pixel annotation accuracy and average classification accuracy are respectively higher than 77% and 53%.

The invention discloses an heterogeneous information universality correlation analysis system and an analysis method thereof. A configurable correlation processing framework and an information collection and receiving module are used for loading different analysis algorithms, connecting different data sources and realizing heterogeneous data analysis; an information pre-processing module is used for loading different processing algorithms, carrying out data structuring processing on analyzed data in a memory and extracting correlation characteristics; an information correlation processing module is used for loading different knowledge and correlation rules, carrying out correlation processing according to information semantic content, and finding out a correlation relation hidden in the information; an interactive visualized module is used for loading different visualized models, and carrying out drawing and interactive analysis on the relation of correlation information; and aiming at the difference of concerned targets in input information, the configurable correlation processing framework is used for carrying out dynamic flow customization. By virtue of the isomerism information universality correlation analysis system and the analysis method thereof, the universal processing problem of heterogeneous multi-source information correlation analysis is solved.

The invention discloses an urban traffic illegal behavior detection method based on a video monitoring system. The urban traffic illegal behavior detection method based on the video monitoring system includes the following steps of trajectory extraction, trajectory structuring, trajectory similarity calculation, trajectory clustering and modeling and abnormality detection, wherein in the trajectory extraction step, a video movement target is detected and tracked to extract a target trajectory; in the trajectory structuring step, a trajectory section is segmented and structured, and the trajectory section is represented through four structural characteristics; in the trajectory similarity calculation step, the characteristic distances corresponding to the four structural characteristics of the trajectory section are calculated respectively, and the similarity between trajectories is calculated through weighing and calculation of the relative similarity between the trajectories; in the trajectory clustering and modeling step, a similarity matrix is structured according to the similarity between the trajectories, the trajectories are clustered, the clustered trajectories are built into Gaussian model sets, and the trajectories belonging to the same class are built into one same set of Gaussian models; in the abnormality detection step, the probability of a trajectory belonging to each model is calculated, and abnormality is judged according to whether the largest probability is larger than a preset threshold or not. According to the method, traffic illegal behaviors are detected based on the video monitoring system, and the efficiency and the accuracy of detection and the illegal behavior class are improved.

The invention provides a convolutional neural network power system intelligent fault detection method and system based on Spearman level correlation, and the method comprises the steps: setting a phasor measurement unit at a regional network node, and carrying out the measurement of data; performing Spearman correlation analysis on the acquired data, and proposing an image generation method basedon an analysis result; establishing an equivalent fault network, verifying the relation between the fault characteristics and the Spearman level correlation, and demonstrating the feasibility of the method; taking the generated image as an initial convolutional layer, and establishing a convolutional neural network architecture based on Spearman level correlation; and verifying the rationality andsuperiority of the method based on PSCAD / EMTDC according to the established architecture. A plurality of types of electric quantity data are comprehensively used for fault diagnosis, the position ofa fault in the power system can be quickly and accurately identified through the convolutional neural network, the problems that the power system has volatility and the traditional detection method isinaccurate due to addition of a distributed power supply and the like are solved, and the robustness and the self-adaptability of the power system are higher.

The present invention provides an infrared image and radar data-based night unmanned parking lot scene depth estimation method. According to the method, firstly, a night vision image data set is established, wherein the night vision image data set comprises original sample images and radar data obtained through pre-classifying the original sample images. The original sample images and the radar data are written into corresponding text files. Secondly, a depth convolution / reverse convolution neural network is constructed and trained by utilizing the night vision image data set. Thirdly, a to-be-processed image is acquired in real time, and the to-be-processed image is input into the depth convolution / reverse convolution neural network. Through the depth convolution neural network, a feature map is obtained. The feature map is input into the reverse convolution neural network, and then the category of each pixel point in the feature map can be obtained. After that, a probability map is outputted. Finally, the probability map is subjected to anti-log transformation to obtain the estimated depth of each pixel point. The test proves that the method provided by the invention can effectively estimate the depth of a night scene. Meanwhile, the estimation correctness and the estimation real-time performance are ensured.

The invention discloses a fall detection method based on a convolutional neural network and mobile phone sensor data. A convolutional neural network model is trained with mobile phone sensor data. The method comprises the following steps: acceleration and angular velocity data is collected through a smart phone carried by a human body, and the data is sorted and input to the convolutional neural network model, wherein the designed convolutional neural network model includes feature abstraction, identification, classification, and other task layers, and the parameters are adjusted gradually through stochastic gradient descent optimization; and in the real-time detection stage, the sorted mobile phone sensor data is input to the convolutional neural network model, and whether the human body falls down is predicted through model output. Compared with the traditional threshold detection and the general machine learning detection, the precision is improved. The method is especially suitable for daily safety monitoring of the elderly and the young children.

The invention discloses a personalized tourist track planning method based on group footprints. The personalized tourist track planning method includes the specific steps of collecting group footprint data through web spiders, extracting tour sites, type attributes of the tour sites, user objects and signature records of the user objects from the collected data, dividing one day into a plurality of time periods, building a site preference model and a site heat-degree model of users in the different time periods, determining preference alternative site sets of the users in the different time periods with the collaborative filtering method according to tour demands provided by the users, and selecting optimal sites from the alternative site sets in the different time periods through a Markov model according to space-time constraint and user preference to generate tourist tracks. According to the personalized tourist track planning method, the tourist tracks conforming to the preference are automatically customized for the users through the abundant user track data according to the tour demands of the users, tour information implied in the open and available group footprint data is sufficiently mined, the people can be assisted to make tour plans, and the tour experience can be improved.

The invention discloses a traffic control sub-area dividing method based on vehicle trajectory data. The method comprises the following steps of: numbering intersections of a certain area, and acquiring block port data, road section length data and a road network base map of the area; collecting the block port data, driving the travel chain of a single vehicle to trajectory data, and eliminating invalid tracks; performing repairing of the missing vehicle trajectory based on the shortest path principle; calculating the dual-direction flow between each intersection pair in a certain time frame to form an intersection pair flow matrix; taking the intersections as nodes and taking the dual-direction flow between the intersection pairs as the association degree of the node connection lines to establish a full-connected directed network diagram, and employing a random walk map algorithm to perform initial division of the network diagram; performing the connectivity inspection of the same type of intersections, and performing correction of the divided non-connection portions of the real road network; and finishing the division, and projecting the division result onto the real road network. The traffic control sub-area dividing method can more fully excavate the information in the traffic flow and can analyze the structure in the traffic network from the global angle.

The invention discloses a small target detection method based on combination of two-stage detection. The method includes: Sending the original image into a first detector to detect a first-stage target B1; Fusing the output features of the shallow CNN and the output features of the deep CNN to obtain M1 ', and selecting a corresponding feature map M2 from the M1' by using B1; taking the M2 as an input feature map and sending the M2 to an RPN module and a classification and regression module of a second-stage detector for detection and positioning of a second-stage target; And adding d loss obtained from two-stage detection as the total Loss of the whole network to obtain an end-to-end detection network model. According to the invention, a two-stage detection network is constructed; A largetarget is accurately detected firstly, then a small target is detected in a large target area, and a detection frame of the small target is limited in a local area which is most possible and most easily detected, namely the area where the large target is located, so that complex background interference is effectively removed, the false detection probability is reduced, and the detection precisionof the small target and the small target in the image is improved.

The embodiment of the invention discloses a video frame interpolation method, device and apparatus The scheme comprises the steps that a video frame training set is acquired, the video frame trainingset comprises an even number of continuous video frames and a first key frame, and the first key frame is an intermediate frame of the even number of continuous video frames; a pyramid deep learning model is constructed, wherein pyramid deep learning model comprises a plurality of convolutional neural network layers, and the convolutional neural network layers are used for generating intermediateframes with different resolutions; the even number of continuous video frames is input into a pyramid deep learning model to generate a second key frame; the pyramid deep learning model is corrected according to the second key frame and the first key frame; And then video frame interpolation is carried out according to the corrected pyramid deep learning model. According to the method, time-spacedomain information among multiple frames is fully mined, a pyramid refining strategy is adopted, motion information and a shielding area are effectively estimated, and the quality of an intermediate frame is greatly improved.

The invention discloses a deep neural network-based text consistency analysis method. After a section of text is input, a distributed method is adopted to translate each word in sentences into vectorsto form distributed sentence matrices, the words repeatedly appearing in the adjacent sentences are counted, and repeated information of the adjacent sentences is added through a manner of expandingdimensionality of the matrices; a convolutional neural network is utilized to learn distributed representations of the sentences, and important features of logic, semantics, syntax and the like in thesentences are extracted to form sentence vectors; and similarity degrees between the adjacent sentence vectors are calculated to add context association contents, finally, a neural network is continuously trained, and probability of text consistency is output. The method is characterized in that complex artificial feature extraction operations do not need to be carried out, external resources arealso not relied on, and compared with existing consistency analysis technology, the method provided by the invention has a great improvement in an accuracy rate, and has a better practical value.

The invention discloses an intelligent operation and maintenance statement similarity matching method based on a natural language processing technology. The method mainly comprises two parts of data processing in knowledge base construction and sentence similarity matching based on deep learning. Compared with the prior art, the method has the advantages that (1) the operation and maintenance management knowledge is subjected to word segmentation by utilizing the specific word library and the HMM to find the new word model, so that the text word segmentation accuracy is improved, and the moreperfect text word library is established; (2) word vectors are trained through a deep learning method, so that the phenomenon of'dimensionality disaster 'represented by the word vectors can be avoided, information of vocabulary contexts can be fully mined, and relations between words can be obtained; And (3) on the basis of the sentence vectors configured with the weights, not only can the importance measure of each word be obtained, but also the information of the sentence vectors can be richer through the combination of the word vectors, and the accuracy of matching on the basis of forming the sentence vectors can be guaranteed through a cosine similarity matching algorithm.

An automatic optimization dispatching system and a method of an iron and steel energy resource on the basis of integrated data source belonging to the data source field of information resource, which comprises a PCS layer which is constituted by a sensor, a PLC, and a DCS which are mounted on site, an in-site monitoring terminal HMI, a scheduling system data bank server, an ESP data bank server, an applied system server, a client end, a fire wall, an anti-virus server, an apparatus for connecting each computer, a controller, and a computer network of a sensor. The method can analyze energy supplying and allocation of businesses according to the specific energy utilizing condition of specific iron and steel businesses. The invention has the advantages that energy effective utilization rate of the iron and steel businesses can achieve the best effect.

The invention discloses a Contourlet domain multi-modal medical image fusion method based on statistical modeling, mainly for solving the problems of difficulty in balancing spatial resolution and spectrum information during medical image fusion. The realization steps comprise: 1), performing IHS transformation on an image to be fused, and obtaining brightness, tone and saturation; 2), respectively executing Contourlet transformation on a brightness component, and estimating the CHMM parameters of a context hidden Markov model of a high frequency sub-band by use of an EM algorithm; 3), a low frequency sub-band employing a fusion rule of taking the maximum from area absolute value sums, and the high frequency sub-band designing a fusion rule based on a CHMM and an improved pulse coupling nerve network M-PCNN; 4), a high frequency coefficient and a low frequency coefficient after fusion executing Contourlet inverse transformation to reconstruct a new brightness component; and 5), obtaining a fusion image by use of IHS inverse transformation. The method provided by the invention can fully integrate the structure and function information of a medical image, effectively protects image details, improves the visual effect, and compared to a conventional fusion method, greatly improves the quality of a fusion image.

The invention discloses an interactive attention emotion analysis method based on dependency syntax. According to the method, the overall mutual influence of a target set and an original sentence is considered by carrying out dependency syntactic analysis on the sentence and designing interaction attention; The problems that the given target contains limited information, the relation between the target and the context cannot be fully established based on a simple splicing mode, and the emotion polarity of the text comments cannot be accurately analyzed are solved. According to the invention, the interaction attention based on the dependency syntax is designed; the fine-grained emotion analysis accuracy can be further improved; The emotional tendency of the commodity comments in the e-commerce industry is accurately mined, more detailed and directional commodity evaluation information is provided for the user before the user purchases the commodity, and the merchant can more fully understand the comment tendency of the consumer to a certain commodity, so that the service quality is improved, and the method has very high practical value and practical significance.

The invention discloses a multi-feature extraction and fusion intelligent fault diagnosis method. The method comprises the following steps: firstly, acquiring data in the operation process of mechanical equipment by using a data acquisition system and a sensor; secondly, intercepting an original signal which is not processed according to the determined length, dividing the original signal into a training sample and a test sample, and performing frequency spectrum normalization on each section of signal; constructing a multi-feature extractor based on an auto-encoder, constructing a multi-feature fusion device based on a dynamic routing algorithm, and constructing a health state classifier based on softmax; then, using a training sample training model for extracting effective features for distinguishing various health states and a self-adaptive learning feature fusion method; and finally inputting the test sample into the model, and verifying the effectiveness of the model. According tothe invention, self-adaptive extraction of equipment fault characteristics and intelligent diagnosis of fault states under the condition of small samples are realized, the training time is short, andthe result is accurate and reliable.