147 results about "Network approach" patented technology

Social information, including computer communication information, is modeled according to a network approach, and users are provided with representations of patterns within their social spaces and graphical interface tools for navigating through the spaces. This can enhance the user's ability to seek out social information and manage their online social relationships. The social mapping includes automatically collecting computer communication information relating to multiple contacts who are in computer communication with each other, one of the multiple contacts being a selected user. The computer communication information is filtered according to one or more preselected criteria to maintain the number of contacts associated with the selected user at or below a selected threshold. The computer communication information is analyzed to determine extents of similarity between the multiple contacts. A visualization of a social map based upon the extents of similarity between the multiple contacts is rendered on a computer display screen so that a user can access and navigate information represented in the social map visualization.

The invention discloses a software package-based online automatic updating method for an open source operating system of a mobile terminal, which relates to the field of mobile terminal software and is applied to the open source operating system of the mobile terminal. By the method, the remote automatic updating of system software can be realized by taking a package as a unit, and convenience isbrought to the rehabilitation of security holes and the installation of the operating system. The method comprises the two aspects that: a server automatically finishes structuring and publishing thesoftware package, acquires all source codes of the operating system from an open source site, automatically divides and structures a proper software package, determines the updating information of the software package according to the version information and dependency of the source codes, and publishes the software package by utilizing a network; and the mobile terminal serving as a software package acquirer and user automatically checks the updating information by client software, and downloads and updates the system by taking the software package as the unit to fulfill the aim of automaticonline updating. The method has the characteristics of high degree of automation and the like, and is easy to deploy in large scale and use.

The invention relates to a spare part assembling demand forecasting information processing method applied to inventory management, comprising the following steps:1) take one part of historical sales data as method learning data and take the other part of the historical sales data as weight building data; 2) use the method learning data to practice an ARMA (Autoregression and Moving Average) method, a multiple linear regression method and a BP (Back Propagation) neural network approach respectively for each spare part; 3) apply the above three methods respectively by using the weight building data, so as to obtain forecasting relative error values for different methods; 4) calculate the weights of the above methods; 5)construct an assembling demand forecasting model; 6) forecast the future sales demands of all spare parts. Compared with the prior art, the method is suitable for the spare parts with different demand features, and has the advantages of strong objectivity, high forecasting precision, and can greatly reduce the inventory cost on the premise of having a certain service level and improves the supply chain management efficiency and customer satisfaction.

A rotary-table servo system neural network control method comprises (1) building a mechanical dynamic model of a permanent magnet synchronous motor rotary-table servo system, and initializing the system state, sampling time and relative control parameters; (2) according to the differential mean value theorem, enabling a non-linear input dead zone in the system to linearly approximate to a simple time-varying system, avoiding complex calculation of dead-zone inverse compensation, and finally inferring a rotary-table servo system model provided with an unknown dead zone; (3) at each sampling moment, calculating and controlling a system tracking error, a fast terminal sliding mode surface and a first-order derivative of the system; (4) based on the rotary-table servo system model provided with the unknown dead zone, selecting a neural network approaching unknown trend, designing an adaptive robust finite-time neural network controller according to the system tracking error, the fast terminal sliding mode surface and the first-order derivative of the system, and updating a neural network weight matrix; and (5) entering the next sampling moment, and repetitively executing the steps from (3) to (5).

A network approach for aided GPS broadcast positioning where A-GPS data is made available in the network and broadcast via cell broadcast servers to wireless devices in order to reduce the time required to determine the position of a wireless device.

The invention mainly relates to a design method of a reinforcement learning based optimal tracking controller for a model unknown servo system. The design method of the reinforcement learning based optimal tracking controller for the model unknown servo system is introduced mainly on the basis of a simplified reinforcement learning evaluation-execution structure with a high-order neural network approach method, and the optimal tracking control solution speed of a motor is increased. As for the model unknown servo system, firstly, homeostatic control is solved with a multilayer neutral networkintelligent identification system model; performance indexes are given, and a high-order neutral network approach optimal performance index function is applied; an HJB (Hamilton-Jacobi-Bellman) equation is established according to an approximate performance index function and the identification system model, and the optimal feedback control of the servo system is solved. The optimal tracking control is calculated according to the solved homeostatic control and optimal feedback control, so that tracking error accumulation values and system energy consumption are minimized simultaneously while load rotation angle and rotation speed rapidly track given signals.

The invention discloses a network expansion method and device. The method comprises the steps of in a pre-stored first correspondence relationship between a first user perception rate threshold and a first network expansion index threshold, obtaining a second correspondence relationship of a region to be evaluated between a second user perception rate threshold and a second network expansion index threshold; determining a current user perception rate and a current network expansion index of the region to be evaluated; comparing the current user perception rate and the current network expansion index with the second user perception rate threshold and the second network expansion index threshold in the second correspondence relationship; and carrying out carrier frequency expansion for cell to be expanded when the obtained comparison result conforms to a cell expansion condition. The invention is used for solving the problem that generally, an LTE network mode is based on the standard mainly from corresponding threshold requirements given by the LTE network load and network planning and design requirements and the limitation is high.

A method for embedding digital watermark of stream media includes selecting at least one key position requiring to embed digital watermark from frame of video stream media, simulating said watermark to be video frame of video stream media being embedded on selected key position, transmitting video stream media with embedded watermark to client end through network mode, collecting various information from client end by client end according to content and contained command of digital watermark and feeding collected various information back to relevant central server.

A linear array composed of N array elements with element position error is used as a receiving array to receive the original training data generated by the signal sources within the range of M groupsof training intervals. The training data of the input layer of the neural network are obtained by matrix operation and normalization from the original training data set. According to the dimension andprecision requirement of training data Rm and signal source arrival angle theta m, the number of hidden layers and the number of neurons in each hidden layer are set, and the dimension of weight matrix and threshold matrix of each layer are determined according to the number of neurons in input layer, hidden layer and output layer, so as to construct a neural network; M groups of training data are input to the input layer of the neural network, and the optimal weight matrix and the optimal threshold matrix reflecting the mapping relationship between the training data R and the angle of arrival of the signal source are obtained through the neural network training. The final output value of the neural network is the estimated value of the angle of arrival of the test signal by using the modified optimal weight matrix and the optimal threshold matrix to carry on the forward operation to the test data RC.

The invention discloses a network flow predicating system and flow predicating method based on a neural network, and belongs to the technical field of a computer. The network flow predicating system comprises a data collecting module, a data preprocessing module and a network flow predicating module, wherein a data collection sub module realizes real-time collection of various flow information in the network in a network mode based on port mirroring; the data preprocessing module respectively stores collected data and performs normalization processing on the collected data, so that the sample data value is between 0 and 1; pure data is provided for the predicating module. The flow predicating module determines the topological structure and the network parameter of a neural network for flow predication according to collected IP network flow data; a neural network method is used for predication; the predication result is obtained. The system and the method have the advantages that the monitoring detection and analysis can be performed on various backbone networks; network abnormal events in the network can be monitored and detected in real time; the advanced early warning on the network abnormal conditions is realized.

The invention provides a flexible satellite neural network backstepping sliding mode attitude control method, relates to a flexible spacecraft attitude control method, and aims at solving a problem of perturbation generated by plate flexible vibration and antenna rotation and a problem of enhancement of steady state precision and stability of existing attitude control methods. According to the method, a flexible satellite attitude kinetic model is established firstly according to a spacecraft, and then a model formula is processed; a sliding mode attitude controller (which is expressed in the specification) based on a backstepping method is designed; then an RBF neural network approach (eta+htau)sgn(sigma) is adopted; the controller (which is expressed in the specification) is designed; and finally a complete attitude controller (which is expressed in the specification) is obtained. A three-axis attitude controller is designed respectively according to the aforementioned process. The flexible satellite neural network backstepping sliding mode attitude control method is suitable for the field of flexible spacecraft attitude control.

Embodiments of the present invention provide an improvement to conventional machine model training techniques by providing an innovative system, method and computer program product for the generation of synthetic data using an iterative process that incorporates multiple machine learning models and neural network approaches. A collaborative system for receiving data and continuously analyzing the data to determine emerging patterns is provided. The proposed invention involves generating synthetic data clusters to be stored and used for retraining the main model as well as other models. In addition, the invention includes using one or more (subset) of the synthetic data clusters to train or retrain machine learning models, developing and training machine learning models that are trained with emerging synthetic data clusters, and ensembling machine learning models trained with emerging synthetic data clusters.

The invention discloses a dynamic code anti-counterfeiting method and a system, and the dynamic code anti-counterfeiting method is characterized by attaching a dynamic code anti-counterfeiting recognizer and a password lock on a commodity, leading each dynamic code anti-counterfeiting recognizer to have a unique machine code, leading the dynamic code anti-counterfeiting recognizer to generate cryptograph of an anti-counterfeiting code through an encryption formula based on the machine code, time and a key, leading a consumer to obtain the cryptograph through the recognizer, submitting the cryptograph to a server by using the telephone, the short message or the network way, leading the server to carry out decryption according to the cryptograph, the time of the server and the key, obtaining the machine code, further being in contrast with the machine code stored in a database, feeding back the authenticity and a password to the consumer, and leading the consumer to open the password lock attached on the commodity through the password, wherein the machine code which is inquired once can not be re-inquired. The system has simple structure, few elements, low production cost and good anti-counterfeiting effect, and can replace a traditional anti-counterfeiting label for use.

The invention relates to a network monitoring system for computer hardware processing parameters, belongs to the technical field of computers and aims to overcome a defect that existing computer room environment monitoring system cannot directly monitor computer hardware processing parameters and relative operation systems processing parameters. Accordingly, the invention provides the network monitoring system of computer hardware processing parameters. The network monitoring system comprises a client side and a server side. The client side and the server side are connected in a networking mode. The client side comprises hardware processing parameter acquiring unit, an operation system parameter acquiring unit and a client side network communicating unit. The server side comprises a user interface controlling unit, a parameter processing unit and a server side network communicating unit. The client side acquires various hardware processing parameters and processing parameters provided by an operation system of the computer in regular times, and transmits the parameters to the server side through the network; the server side receives the various parameters transmitted from the client side, determines processing state of the client side, saves the data, and further updates the user interface and displays the state of the client side.

Embodiments of the present invention provide an improvement to convention machine model training techniques by providing an innovative system, method and computer program product for the generation of synthetic data using an iterative process that incorporates multiple machine learning models and neural network approaches. A collaborative system for receiving data and continuously analyzing the data to determine emerging patterns is provided. Common characteristics of data from the identified emerging patterns are broadened in scope and used to generate a synthetic data set using a generative neural network approach. The resulting synthetic data set is narrowed based on analysis of the synthetic data as compared to the detected emerging patterns, and can then be used to further train one or more machine learning models for further pattern detection.

Disclosed are systems and methods which apply design criteria to beam forming network parameters to arrive at a passive beam forming network design. Preferably a beam forming network approach is implemented in two primary stages. Operation of the aforementioned first primary stage may provide a branching configuration which determines how the weights of a desired radiation pattern weight set are allocated in the beam forming network. Preferably, branching nodes are configured to substantially equally distribute power splitting/combining the branches of a node. The aforementioned second primary stage operates to determine the actual physical layout of the various components. Preferably, each branching node is analyzed to determine an optimal physical layout configuration with respect thereto.

The invention discloses a method for accessing a video monitoring system to front end equipment with different network modes in the technical field of video monitoring system control. The technical proposal comprises the following steps: establishing a center management server and a video transmission and distribution server in the video monitoring system for separating a control channel from a data channel of the video monitoring system; configuring fixed IP addresses for the center management server and the video transmission and distribution server; establishing connection between the front end equipment and the center management server and keeping the connection with the center management server all the time; and sending a request for watching the video of the front end equipment to the center management server by a user, and transmitting the video of the front end equipment to the user by the video transmission and distribution server. The method solves the problem that the front end equipment cannot be accessed when the IP address thereof is changed under an ADSL or a private address. Simultaneously, because the data channel is established dynamically as required according to the service condition of the user, the network bandwidth is saved to a large extent.

The invention relates to a multiple sectioned Bayesian network-based electronic circuit fault diagnosis method. Common electronic circuit fault diagnosis methods include a fuzzy set fault dictionary method, a neural network approach, a Bayesian network method and the like, and have low fault resolution, interpretability and real-time property. The method comprises the following steps of: setting two adjacent fault diagnosis reasoning credibility threshold parameters, and determining the number of intelligent agents; obtaining Bayesian subnetwork structures, mapping a fault cause source to each Bayesian subnetwork, and learning credibility condition probability parameters among nodes of a Bayesian subnetwork model by using an expectation-maximization (EM) algorithm; using nodes corresponding to overlapped signals as overlapped subareas of the network to form a complete multiple sectioned Bayesian network (MSBN) so as to construct a linked junction forest; and inputting respective k target characteristic signals serving as observation evidence into each Bayesian subnetwork. A spatial multi-source information fusion method is adopted, the fault diagnosis capacity of a system is improved, the method is suitable for complicated and uncertain systems, and the fault diagnosis accuracy and speed are greatly improved.

The invention provides an L1 adaptive ship power positioning double-loop control system based on a neural network. The control system comprises a marine ship, an outer ring position tracking loop controller, an L1 adaptive inner loop controller based on a neural network and a path generator. The outer ring position tracking loop controller can track a reference path of the system to obtain a virtual speed instruction; the L1 adaptive inner loop controller based on a neural network comprises an adaptive wavelet neural network approaching device, a state predictor, a parameter adaptive law and an L1 control law; the L1 control law comprises a filter; and the L1 adaptive inner loop controller based on a neural network solves the problem of uncertainty in the system, and approaches a coupling term in the system using a recursive wavelet neural network. The L1 controller introduces a low-pass filter into the feedback loop during feedback, thereby weakening the influence of unknown high-frequency noise in control signals on high-frequency noise. The control system can be applied to control of other ship power positioning systems.

The invention discloses an intelligent community medical management system. The system includes a smart health care community platform and a data management system, the smart health care community platform is composed of community hospitals, and medical institutions, regulatory agencies, pharmaceutical sales systems and home care system, and the medical institutions, the regulatory agencies, the pharmaceutical sales systems and the home care system are connected by a wireless network with the community hospitals. The data center management system includes a center management database, a hospital data management center, a data processing server, a shared server, a data management platform and a cloud storage center. The present disclosure uses modern electronic information technology and wireless sensor technology, the routine testing methods is applied to the patient, the patient is connected with the network, the establishment of patient pathology archives achieves patient care and service management, and patient information is provided to the hospital, the coordination mechanisms between hospital and the community is strengthened, the use of modern technology to enhance the ability of community hospitals and health services dan establish a national health service support system.

The invention is suitable for the technical field of communication, and provides a method and system for ensuring data transmission of a wireless sensor network. The method includes the steps of setting nodes, wherein a plurality of anchor nodes are arranged in an area where data need to be collected; authenticating the nodes, wherein security authentication is conducted on the ordinary nodes in the area through SINK ends of the wireless sensor network and the anchor nodes; transmitting the data, wherein each cluster head node transmits the data to the SINK ends in a preset multi-hop network mode after receiving the data transmitted by the ordinary nodes, passing the security authentication, in a cluster which the cluster head node belongs to. Thus, the problem of secret key hosting during WSN node security authentication is solved, and the secure data transmission of the WSN is achieved.

The invention discloses a design method for an unmanned surface vehicle tracking controller, and relates to the technical field of an unmanned surface vehicle tracking control technology. The method specifically comprises the following steps that: S1: according to unmanned surface vehicle tracking task requirements, firstly, designing a decision network, training to enable the decision network toobtain a decision capability, and designing an exploration function to explore an unmanned surface vehicle path tracking state; S2: designing a reward function, and obtaining the motion state of the unmanned surface vehicle through a state observation method. By use of the design method for the unmanned surface vehicle tracking controller, a deep reinforcement learning algorithm is adopted to train a deep convolutional neural network to serve as the unmanned surface vehicle tracking controller, the design process of the unmanned surface vehicle tracking controller is simplified, a neural network approaching form is favorably used for replacing mathematical derivation, in addition, the controller is automatically trained through a program, manual intervention is not required, calculation issimple, and transportability is high.

The invention provides a system for acquiring and distributing baseband data of a remote sensing satellite. The system comprises a task management device, a data acquiring device, a data storage device and a data distributing device. When detecting a data acquisition task list, the data acquiring device acquires baseband data of the remote sensing satellite and corresponding time code information thereof from the remote sensing satellite by a fully digital demodulator via the network. The data distributing device distributes the required baseband data of the remote sensing satellite to user equipment after receiving data distribution requests of the user equipment. By the aid of the system, the baseband data of the remote sensing satellite can be acquired in real time via the network, and meanwhile, uniform data distributing services can be provided to rear-end equipment via the network, and accordingly, limits of ECL (emitter-coupled logic) signal transmission distance and special acquisition cards are eliminated.