375 results about "Model configuration" patented technology

A method for accurately estimating a pose of the human head in natural scenes utilizing positions of the prominent facial features relative to the position of the head. A high-dimensional, randomly sparse representation of a human face, using a simplified facial feature model transforms a raw face image into sets of vectors representing the fits of the face to a random, sparse set of model configurations. The transformation collects salient features of the face image which are useful to estimate the pose, while suppressing irrelevant variations of face appearance. The relation between the sparse representation of the pose is learned using Support Vector Regression (SVR). The sparse representation, combined with the SVR learning is then used to estimate a pose of facial images.

In accordance with one embodiment, an article of manufacture embodied in a computer-readable medium for use in a processing system for modeling configurations of a wireless local area network is provided. The article of manufacture includes a characteristic and configurations receiving logic for causing the processing system to determine a set of original characteristics and configurations of the wireless local area network. As well, a simulation logic for causing the processing system to simulate an outcome based upon a set of configurations in accordance with a goal. In other embodiments, the goal may be user defined or based upon historical data. Further, a configuration creation logic for causing the processing system to create a set of new configurations based upon the outcome and a management logic for causing the processing system to apply the set of new configurations to the wireless local area network are provided.

The invention provides an OLAP multi-dimensional analysis and data mining system. The system comprises a data model, a distributed OLAP engine, an OLAP analysis engine, a multi-dimensional report analysis interface, a data mining interface and a data visualization tool; the data model is dragged by a user through a visual interface to finish data modeling, and has unified model configuration; thesystem automatically performs model adaptation and enables the data model to be called by cooperation with internal other engines or tools; the distributed OLAP engine provides a multi-dimensional data model preprocessing capability for the OLAP system; the OLAP analysis engine supports a multi-dimensional query analysis engine of a big data platform and a relational database, and analyzes an MDXstatement to obtain a standard SQL; the multi-dimensional report analysis interface and the data mining interface have multi-dimensional data analysis and data mining functions and provide a report analysis method and a data mining algorithm model; and the data visualization tool provides a visual service for report analysis and data mining in the multi-dimensional report analysis interface and the data mining interface, and provides visual result social sharing and chart management functions.

The invention discloses an internet live pornography detecting method based on a deep convolutional neural network. The detecting accuracy of the content of live pornography is greatly improved by means of a deep learning technology, a sample image data strengthening and preprocessing method based on convolutional neural network training model iteration, a model configuration and training method based on a deep learning convolutional neural network, an image combined testing method based on multi-tailoring and multi-models, an online image dynamic cutting method of internet live video supervision and other optimizing methods, thus the conversion of the supervision mode that the algorithm model pornographic content automatic detecting plays the principal role, and artificial real-time checking plays the subsidiary role is achieved, the supervision efficiency of a live platform is improved, the labor cost for operation is lowered, the work intensity of inspection personnel is reduced, and the high-speed increasing requirement of the live content is met.

The invention discloses an automated development platform based on model configuration, comprising a visualization work engine module and a database engine. For the visualization work engine module, the inside is divided according to system implementation functions, each divided part contains foreground and background related logics, the visualization work engine module works according to an agile developing model, and loose coupling is carried out among the parts; the database engine comprises a database connection manager, a sql manager, a things manager and an external interface, and is used for creating and managing database connections and maintaining data persistence; the sql manager is used for generating a corresponding sql object according to a data model configured by a user and transmitting the sql object to a tbl class in the visualization work engine module, and the tbl class executes the sql and makes corresponding response; and the platform automatically generates corresponding pages according to the configured data model, realizes insert, delete, update and select of simple functions, improves development efficiency and reduces workload of development.

The invention provides a graphical intelligent transformer substation pattern design method based on computer-aided design (CAD), which is characterized in that two functional modules including a graphical edit module and a model edit module are arranged in the CAD; the graphical edit module is used for drawing a conventional drawing and expanding attribute definition functions; the model edit module is used for finally generating a model file and supporting the high-order functions of importing, exporting, editing and verifying files and the like; and the graphical edit module and the model edit module carry out sharing operation on model information by accessing an extensive makeup language (XML) database interface. In the graphical intelligent transformer substation pattern design method based on the CAD provided by the invention, by developing graphical model design software based on the CAD, the design and the system of the intelligent transformer substation are integrated, thus not only realizing to carry out first and second wiring diagrams of the conventional transformer substation in the design, but also finishing the complete data model configuration of the whole substation and data stream connection of the transformer substation according to the interface control document (ICD) model files provided by equipment manufacturers and the configuration principle of the first and second equipment of the transformer substation.

In one aspect, a method and apparatus for determining a value for at least one parameter of a configuration of a model associated with structure of which view data has been obtained including detecting at least one feature in the view data, and determining the value for the at least one parameter of the configuration of the model based at least in part on the at least one feature. In another aspect, a method and apparatus for detecting at least one blood vessel from object view data obtained from a scan of the at least one blood vessel including generating a model of the at least one blood vessel, the model having a plurality of parameters describing a model configuration, determining a hypothesis for the model configuration based, at least in part, on at least one feature detected in the object view data, and updating the model configuration according to a comparison with the object view data to arrive at a final model configuration, so that the final model configuration represents the at least one blood vessel.

The invention discloses a deep learning-based electric power suspected complaint work order recognition method, and relates to complaint recognition method for electric power customer services. At present, electric power suspected complaint work orders are artificially recognized, so that the efficiency is low, the timeliness is bad and human resources are wasted. The method comprises the following steps of: 1) deep learning model configuration; 2) complaint feature label extraction; 3) complaint sample formatting; 4) model learning and training; 5) suspected complaint recognition; and 6) suspected complaint classification. According to the method, a series of work such as data cleaning and sorting, complaint tendency word extraction, data modeling and optimization, sample iterative learning and training, machine learning and prediction and the like can be carried out on complaint lists through a deep learning technology, so that deep learning-based intelligent recognition and classification of suspected complaint work orders are realized, the intelligent work experience is enhanced and the service quality control work efficiency is improved.

The invention discloses a method and system for analyzing and diagnosing an automobile fault. The method comprises the following steps of: acquiring the model configuration information and a fault code of a faulted automobile by using an automobile fault diagnostic instrument; analyzing the fault code to obtain a fault reason of the faulted automobile and automobile fittings influenced by the fault reason, and sending an analyzed result to a cloud server; enabling the cloud server to accumulate the number of generated times, stored in a database, of the fault reason of the faulted automobile so as to obtain the new number of generated times of the fault reason and generate a fault report of the faulted automobile; and sending the fault report to a smart terminal of a user of the faulted automobile. The method and the system obtain the fault reason of the faulted automobile and the automobile fittings possibly influenced by the fault reason in virtue of the analysis of the fault code, and generate the fault report in combination with the historical data of the automobile fault so as to contribute to the overall analysis of the automobile condition, and pushes the fault report to the smart terminal of the user in order that the user fast and easily knows the safety state of the automobile.

This invention allows users to build, manipulate, and finally deploy various model configurations with little performance overhead, better syntactic clarity and configuration flexibility.

The invention provides a method and device for accessing Internet of things equipment into an Internet of things platform and a server. The Internet of things platform comprises a connection adaptingsystem; and the connection adapting system comprises a connection public module and multiple type adapting modules respectively corresponding to different equipment types. The method comprises the following steps: when no brand model adapting module corresponding to a target brand model exists in the connection adapting system, acquiring brand model configuration data based on a target configuration template, wherein the target configuration template is a configuration template matched with a target equipment type; and establishing a brand model adapting module connected with a target type adapting module and corresponding to the target brand model in the connection adapting system on the basis of the brand model configuration data, so as to access the Internet of things equipment into theInternet of things platform by connecting the brand model adapting module. The method can realize the Internet of things platform compatible with all types of Internet of things equipment.

The invention discloses a system and a method for flexibly comparing and analyzing data. The system comprises a data source configuration module, a data table access module, a custom table data module, a comparison model configuration module, a correlation model configuration module, a comparison task management module, a comparison result early warning module, a comparison result statistic analysis module and a comparison result correlated query module; and the comparison model configuration module can be used for next configuration on comparison models on the basis of data information of comparison results, so that the data can be compared circularly.

The invention discloses a visual configuration method for index calculation. The visual configuration method for the index calculation includes following steps: S01, building models of business objects; S02, building a model of basic data: selecting attributes of the business objects in visualization mode from the models of the business objects, built in the step S01, in an FLEX environment, and connecting the business objects through operational characters so as to form a calculation link of basic data items; S03, building a model of the index calculation: resolving logic of the index calculation into the basic data items, weighting coefficients and the operational characters, and forming a topological graph model of the logic of the index calculation in the FLEX environment; S04, calculating an index: using numerical value of the basic data items and an algorithm described by the operational characters to calculate layer by layer so as to push deep into a root node, and finally obtaining an index value on the root node. The visual configuration method for the index calculation organically integrates technologies of concurrent calculation, memory calculation, visual index calculation model configuration together, and develops the advantages of being parallel in clustering of the concurrent calculation, being high in efficiency of the memory calculation and the like.

The invention discloses a method and system for arranging page contents of an intelligent television. The method comprises the steps: forming template data in advance in a server according to model configuration contents of templates, programs, recommend positions and resources in sequence; enabling an intelligent television to be connected to the server after the intelligent television is turned on to obtain the template data; establishing frames by the intelligent television according to the programs in the obtained template data, and default displaying one of the programs; gridding the program according to grid data of the program, obtaining a recommend position list in the program, and establishing a recommend position; and displaying resources of a resource list in the recommend position. Unified display networks can be obtained, contents of multiple programs can be displayed in the intelligent television, contents can be arranged according to obtained content data, and therefore flexible layout is achieved.

The embodiment of the invention discloses a vehicle terminal detection method and system and belongs to the technical field of vehicles. The method comprises the steps of a detection device receiving an input vehicle identification code and a vehicle model configuration code, the detection device sending an instruction of establishing communication connection to a server according to the input vehicle identification code, and the server sending an instruction of establishing communication connection to a vehicle terminal, the detection device determining the vehicle model configuration of the vehicle according to the vehicle model configuration code, and selecting corresponding detection items according to the model configuration, the detection device sending a detection instruction to the server according to the selected detection items, the server providing the detection instruction to the vehicle terminal, the vehicle terminal controlling the vehicle to perform the corresponding detection items according to the detection instruction and obtaining the execution result, and the vehicle terminal sending the execution result to the detection device through the server. The vehicle terminal detection method and the system have the advantages of simple operation and high efficiency, and can greatly reduce the detection cost.

An embodiment of the invention discloses a method and a system for binding a vehicle and a vehicle-mounted terminal, and the method and the system belong to the technical field of vehicles. The method comprises the steps that binding equipment receives an input vehicle identification code, an input vehicle-mounted terminal identification code and an input vehicle model configuration code; the binding equipment judges whether a vehicle of one vehicle model is configured with a vehicle-mounted terminal according to the input vehicle model configuration code; if so, the binding equipment verifies whether formats of the input vehicle identification code and the vehicle-mounted terminal identification code are correct or not; if the formats are correct, the binding equipment automatically binds the vehicle identification code and the vehicle-mounted terminal identification code, and sends binding information to a server; and the server receives the binding information sent by the binding equipment, and establishes a corresponding binding relationship between the vehicle identification code and the vehicle-mounted terminal identification code in a database. The method and the system for binding the vehicle and the vehicle-mounted terminal can perform automatic binding rapidly and accurately, thereby reducing the production cost and improving the production efficiency.

The invention discloses a method and system for discovering and deploying available resources in a power cloud data center. The method comprises the following steps: step one, carrying out available resource discovery; to be specific, initiatively discovering new available resources in a power cloud data center; step two, carrying out device resource agent communication; to be specific, establishing a communication mechanism with newly discovered available resources; step three, carrying out modeling configuration management; to be specific, analyzing the newly discovered available resource situation, providing a piece of deployment model advice, allowing confirmation and adjustment by a user, and then generating a resource configuration template; and step four, carrying out configurationdeployment; to be specific, carrying out modeling configuration on a resource configuration template and deploying the newly discovered available resources. In a cloud computing data center environment, when a new resource device is connected to a cloud computing data center management network, automatic discovery of a newly added physical device, information collection, communication establishment, resource analysis, modeling configuration, automatic mounting and deployment, and final new resource online realization are carried out.

The invention relates to a target detection method for feature extraction of images on the basis of a deep learning framework. The method is technically characterized in that the images are preprocessed on the basis of the MCG algorithm, and possible image blocks at target positions are extracted; the extracted image blocks are optimized on the basis of the MTSE algorithm; the obtained image blocks are iterated and adjusted to the size meeting the caffe framework input requirement through the superpixel optimization method; feature extraction is conducted on the image blocks through the caffe deep learning framework, and model configuration is finished through the R-CNN algorithm; obtained features are classified through the SVM algorithm to obtain a final result. The method is reasonable in design, the calculation quantity of the features is reduced by preprocessing the images, then deep features of the images are extracted through the caffe deep learning framework, objects can be represented better, the features are classified through the SVM classification algorithm, and a good detection result is obtained.