238 results about "Network intelligence" patented technology

Systems and methods are described for optimizing network data transfers using multiple classes of network resources and network intelligence gathered and integrated by a multi-perspective network optimizer so as to maximize the performance, scalability and commercial controllability and minimize the cost of network data transfers in heterogeneous networks such as the internet.

A domain to be published to an enterprise ECDN is associated (either by static configuration or dynamically) with a set of one or more enterprise zones configurable in a hierarchy. When a DNS query arrives for a hostname known to be associated with given content within the control of the ECDN, a DNS server preferably responds in one of three (3) ways: (a) handing back an IP address, e.g., for an ECDN intelligent node that knows how to obtain the requested content from a surrogate or origin server; (b) executing a zone referral to a next (lower) level name server in a zone hierarchy, or (c) CNAMing to another hostname, thereby essentially restarting the lookup procedure. In the latter case, this new CNAME causes the resolution process to start back at the root and resolve a new path, probably along a different path in the hierarchy. At any particular level in the zone hierarchy, preferably there is an associated zone server. That server preferably executes logic that applies the requested hostname against a map, which, using known techniques, may be generated from given (static, dynamic, internally-generated or third party-sourced) performance metrics. Thus, a given name query to ECDN-managed content may be serviced in coordination with various sources of distributed network intelligence. As a result, the invention provides for a distributed, dynamic globally load balanced name service.

A system, method and computer program product are described, by which a user, through a control interface in a subscriber interface device, requests from network intelligence both transport network bandwidth and type of service line mode as part of call setup. An improved system by which requests to change access line mode and bandwidth are communicated over transmission facilities via D channels through local switch fabric to local or remote network intelligence is detailed. Connections over the transmission facilities, established between user B channels and B channels of transport bandwidth or between user B channels and the Stat Mux function, are described. An improved system is summarized, in which connections directly to transport bandwidth support point-to-point n B+D upstream and m B+D downstream service, and connections via stat mux allow connectionless traffic to share a portion of the transport bandwidth on an as needed basis. The ability to request and change access to available bit rate (ABR), variable bit rate (VBR) and constant bit rate (CBR) services, in a connection-oriented (CONS) or connectionless (CLNS) network, are described.

A role and entitlements mining system uses network intelligence to facilitate role definition. The system records traffic on a network. The traffic is analyzed to identify the user and application involved. The matched data is then provided to an analytics engine, which analyzes that data to attempt to derive an initial set of one or more roles and the application entitlements for each role. Each role derived by the analytics engine identifies one or more users who are identified as belonging to the role, as well as one or more application entitlements. Preferably, one or more directory services are then interrogated for known group and user relationships to detect whether the roles identified by the analytics engine can be modified or enriched. Evaluation of the known group and user relationships provides a way to identify a more granular set of role definitions. A role-based access control policy is then generated.

The invention discloses an adaptive access network selection device and an adaptive access network selection method, which belong to the technical field of communication. Own macro and micro characteristics of a terminal are sensed, a service sensitivity variable is determined according to a user application status and preference analysis, network application priorities and quality of service (QoS) sensitivity priorities are sequenced based on information such as the characteristics of the terminal, application needs, network statuses and the like, adaptive modeling is performed on different networks according to historical data, the QoS characteristics of a user terminal accessing the networks are acquired, an access network is judged according to the guidance information of an intelligent information management module and the actual output of an intelligent network simulation module and inter-network switching is performed. By the device and the method, heterogeneous networks are accessed adaptively optimally and selectively to effectively realize the user transparency orientation of heterogeneous properties of the access network and the terminal universality orientation of application service characteristics.

A telecommunications network includes a processor controlled switch and a network intelligence platform overload control function runs in the network intelligence layer. The overload control function measures the period of time taken to handle a call switching request and if the time taken exceeds a pre-determined quality of service threshold, it implements a call gapping function. The call gapping function modifies the gapping period such that requests to effect calls to particular destinations are spaced and any call arriving at a switching point prior to expiration of the gap period is automatically rejected by the local control processor. As the overload control function runs in a plurality of nodes, which may be file servers of the intelligence layer, the gapping period returned to the switch is dependent upon the perceived overload at the particular node. Traffic variations at the nodes may result in variations in the gapping period between nodes and therefore each node is arranged to communicate with other nodes to determine an average gapping period for the group of nodes and individual gapping periods in the nodes are relaxed towards the average value.

This invention discloses a method for intelligent patrol inspection by communication network including: executing said inspection task to an assigned NE by an intelligent patrol inspection server in the task, said NE feeds back the inspection state information in terms of the task to feed back the state information of said NE to said intelligent server, at the same time, this invention also discloses a device for patrol inspection in the communication network.

An embedded wireless sensing network intelligent platform comprises network nodes, a base station, a wireless gateway, and a central control computer, and carries out communication according to an IEEE802.15.4-based Zigbee communication protocol standard. The technique provides an intelligent platform for an embedded wireless sensing network, which can combine required different sensors according to practical control requirement to develop wireless sensing network systems meeting different requirements. The intelligent platform can thoroughly get rid of a wire access manner adopted in conventional sensing control system, and overcome disadvantages such as wiring difficulty, high cost, and maintenance / management difficulty caused by the wire control manner. The platform has high development flexibility, wide operation and application ranges, low cost of system construction and maintenance. Compared with other wireless control manners, the system networking manner has the advantages of combined short-range multihop and grid manner, high intellectualization and reliability, high stability, low power consumption, and long service life.

The invention is DCPL field bus of network intelligent meter gauge end. The host connects with several field slave machines which are several network intelligent water meter end, gas meter end and home distribution end respectively. Connects several field slave machines and addressing remote digital correspondence function through a twisted pair line, and provides the field bus of direct current power. The network prepaying bridge sets CPU, data storing chip, analog switch, displaying circuit, light coupler and correspondence chip connected through MODEM chip, the CPU also connects with radiofrequency read / write model, the user forms outdoor card brushing information interactive. The host of bridge connects with DCPL field bus ports of slave machines; connects with RS485 or CAN bus portsof housing estate managing computer. The IC card is brushed without contact through bridge, and the data are transmitted to user network intelligent meter gauge end through DPCL.

The invention discloses an intelligent reflection surface phase optimization method based on deep reinforcement learning. The method comprises the following steps: initializing an action network, an evaluation network, an intelligent reflection surface phase offset matrix and an experience pool in an intelligent reflection surface (intelligent agent); acquiring an initial state of the agent according to the user channel state information; storing the experience pool through interaction between the intelligent reflection surface and the wireless communication system; randomly sampling from theexperience pool to train the action network and the evaluation network so as to maximize the evaluation value output by the evaluation network, and then obtaining network model parameters after convergence; and outputting the optimal phase offset matrix coefficient of the intelligent reflecting surface, which maximizes the receiving signal-to-noise ratio of the user under the channel state information. According to the method, the time required for optimizing the phase offset matrix can be effectively reduced, the storage space of the sample is trained, and the robustness is better.

The invention provides a method for realizing a wireless network intelligent video monitoring system, which comprises the following steps: (1) real-time video acquisition; (2) video image coding and real-time transmission; (3) data forwarding; (4) video receiving, decompression and display; (5) motion object detection; and (6) optional angle adjustment of a camera. The invention can realize real time monitoring of a video monitoring system within a certain scope; the angle of the camera can be optionally adjusted according to the requirements of working personnel, thereby widening the video monitoring scope; and by adding the function of detecting and framing a motion object and the function of saving and recording a specific image, the intelligence of the monitoring system is enhanced, and the workload of the working personnel is reduced. In the invention, a video acquisition system is connected with a data forwarding module through wifi (wireless fidelity), and the data forwarding module is connected with the monitoring system through a public network, thereby simplifying the construction procedure of the system, lowering the construction cost of the system and improving the expandability of the system.

The present invention relates to a kind of solar street lamp networking monitoring system based on ZigBee wireless network, it is characterized in that: comprise and form ZigBee wireless network and be provided with plural solar street lamps of controller and the remote monitoring center connected with Internet; Described plural solar street lamps One of the street lights is provided with a first GPRS communication module; the remote monitoring center is provided with a second GPRS communication module. Through the rational design of each part of the system and its functional modules, the present invention provides a set of network intelligent solar street lamp lighting schemes, realizing the installation of a whole area (towns, campuses, streets, parks, squares, etc.) The solar street lights of the new controller, and wireless networking monitoring and centralized and convenient management of them.

An architecture for network layer mobility support, using always on broadband high speed access and a network-based mobility manager, termed as a network server or gateway is disclosed. The present invention obviates the need of MIP for IP mobility.

The invention provides a robot control method based on an off-line model pre-training learning DDPG algorithm, and the method comprises the following steps: collecting the training data of a 2D dummy in an off-line environment, and carrying out the preprocessing of the training data to obtain a training data set; constructing and initializing an artificial neural network and initializing parameters; pre-training the evaluation network and the action network offline by using the training data set; initializing a target network by using the pre-trained evaluation network, and storing state conversion data into a storage buffer by the intelligent agent to serve as an online data set for training an online network; training an online strategy network and an online Q network by using the online data set, and updating the online strategy network and the online Q network by using a DDQN structure; carrying out soft updating, and controlling the state of the 2D dummy. According to the method, the efficiency is higher, the generated Q value is more accurate, the average reward value is higher, the learning strategy is more stable and reliable, the convergence rate is increased, the obtained accumulated reward value reaches a higher level, and the robot can quickly arrive at the destination.

Methods, systems and computer products for notifying a customer if particular telephone numbers are in communication with the mobile network, when a status change has occurred, and the use of network intelligence to track the reason for the status change. Exemplary embodiments include a method for providing a mobile network status change notification service, including establishing a status change notification relationship between a device and the mobile network, monitoring the device for a status change on the network, detecting a reason for the change in state status and diagnosing the status change.

The invention belongs to the technical field of photoelectric tracking, precision measurement, navigation and location and particularly relates to a target tracking method based on intelligent IMM Kalman filter feedforward compensation and a system. A neural network intelligent target recognizer recognizes the type of a tracked target, state equation parameters of online operation of an improved intelligent IMM Kalman filter are adjusted, so that the filter is endowed with an adaptive characteristic, an online operating state model equation is matched with the tracked target, multiple filtersbased on different models are used for parallel work, speed and acceleration of the maneuvering target are estimated in real time accurately, estimation accuracy higher than that of traditional filtering is obtained, and a feedforward compensation controller constructed on the basis can obtain higher feedforward compensation precision and control performance.

The invention, related to information security field, discloses a method for improving network application security and a system thereof. The method comprises that client terminal application generates protocol message and disassembles the protocol message to plural IP packets and sends the plural IP packets; network filter driver receives and caches the plural IP packets and assembles the plural IP packets to obtain the protocol message and determines whether critical information is in the protocol message; if so, the network filter driver sends the protocol message to a smart key device; the smart key device analyzes the protocol message to obtain the critical information and sends the critical information to the user for confirming, if the user confirms that the critical information is correct, the network smart key device signs the protocol message and returns the signature data, the network filter driver generates new protocol message according to the signature data and the protocol message and disassembles the new protocol message to plural IP packets and sends the plural IP packets to the server via network card driver; if the user confirms that the critical information is not correct or no confirmation is received from user in predetermined time period, the smart key device performs exceptional operation. The system comprises a smart key device and network filter driver of client terminal computer. With compatibility and usability, the invention enhances network application security without modifying the client terminal.

Implementations described and claimed herein provide systems and methods for generating network intelligence based on network data. In one implementation, a network traffic dataset representative of network traffic across one or more ports of a primary network is obtained. The ports are associated with a secondary network in communication with the primary network. A content distribution network log associated with the secondary network is obtained. The content distribution log includes a history of content requests. A domain name system log associated with the secondary network is obtained. The domain name system log includes one or more Internet Protocol addresses. Network intelligence is generated based on the network traffic dataset, the content distribution network log, and the domain name system log. The network intelligence may be customer analytics, an aggregated data feed, and / or recommendations for inventory placement.

The invention relates to a mobile edge network intelligent resource allocation method capable of dividing tasks, which comprises the following steps of: dividing serial tasks generated by a terminal to obtain a plurality of subtasks, and establishing an unloading task model; respectively establishing a time delay model and an energy consumption model for the subtasks according to a local execution mode or an unloading execution mode, and defining an unloading joint target optimization function based on a multi-user serial dependent task; in a multi-server scene, establishing a Markov game model according to a cooperative competition relationship of multiple users to wireless communication and computing resources, and optimizing the unloading joint target optimization function; and in a time-varying environment, taking each terminal as an independent agent based on part of system state information to execute a reinforcement learning algorithm to solve the Markov game model, and determining an unloading strategy, sub-channel selection, transmitting power and resource allocation quantity. According to the mobile edge network intelligent resource allocation method, server resources can be reasonably allocated, fragmented resources can be fully used, the terminal user experience is ensured, and the network operation stability is improved.

The invention relates to a fault arc recognition method based on extraction current features. The fault arc recognition method based on extraction current features includes the steps: training a BP neural network by using the wavelet energy corresponding to the loop current in the normal state and the fault arc state to obtain a BP classification network based on current features, and performing fault arc recognition by using the BP classification network. The fault arc recognition method based on extraction current features effectively integrates the wavelet decomposition technology with theBP neural network intelligent algorithm, fully utilizes the advantages of wavelet decomposition to reflect the time-frequency domain change of the signal, and combines with the intelligent and accurate classification effect of the BP neural network to realize fast and accurate arc detection and improve the current fault arc detection level, so as to preferably guarantee the safe and reliable operation of power equipment, bring better benefits to the development of the power industry, and has very important practical significance for the safe, reliable and stable operation of the power grid.

The invention discloses an actively-homing network intelligent wireless control system which is based on a ZigBee network control technology and can realize remote automation control for such fields as family digitalization, industry and intelligent transportation; the system comprises a collector arranged in a user unit, a wireless signal transmitter connected to a control relay of the power switch of the collector, and a central base station that is arranged in a monitoring center and is connected to alarming units and mobile phone signals of users through a public mobile network; the protocol between the wireless signal transmitter and a signal transreceiver of the central base station is the ZigBee wireless protocol. The invention can not only realize the concentralized management of monitoring signals of the user unit, timely understand the conditions of the user unit and process the conditions in the first time, but also actively search the collector, electric appliances and a machine to realize trouble monitoring and remote control of various collectors and electric equipment; the system of the invention has the advantages of low operation cost, safe and reliable communication network, but no such phenomena as false alarm, seton or interference.

The present invention discloses a network real-time video collecting device based on FPGA chip and DSP chip development. The device of the invention comprises a video collecting module, a video signal processing module, a network control module, a handshake control module of press button switch and network protocol and an upper machine terminal alternation module. The device realizes the high-speed real-time collection and network transmission to analog video signal / analog television signal or high resolution computer signal. Based on the network handshake protocol between the upper machine and video collecting device which are developed independently on the video collection hardware platform, the specific data in the negotiation package can be flexibly set for controlling the working state of collecting device and realizing the network intelligent control of a plurality of video collecting devices. The device is composed of small-capability FPGA chip and intermediate-performance DSP chip, and can be widely used for the fields of enterprise / family guarding system, real-time video monitoring of operating interface of computer device, visual auxiliary drive of intelligent vehicle, etc.

The invention discloses a design and an implementation method for a user behavior analysis system based on Hadoop, the high speed catch package tool PF-RNG is used for catching the data of network inlet as the user behavior analysis data source and storing the data source in a distribution mode, adjusting the network security software development kit tool Libnids for recombining the data packet for realizing recombination for TCP / IP, reducing the application layer HTTP, using Hadoop cluster, using the distributed Mapreduce programme for analyzing the network behavior activity of the user application layer, analyzing from the physical layer to the application layer, positioning the user comprehensively for four-dimension, as search terms for user, shopping trend, website leave message and common website behavior for knowing the user behavior and demand in time, and strategy controlling the user behavior and optimizing the network service for realizing the network intelligence.

The invention discloses a network intelligent open fire detector control system which mainly comprises an open fire detector and a wireless gateway (base station) and so on. The core module group of the open fire detector comprises a central processor and a wireless module group unit and an ultraviolet flame detection system which are connected with the central processor. According to the system, the wireless module group unit performs data communication with the wireless gateway (base station), the wireless gateway (base station) is connected with a business engine, the business engine performs data interaction with a cloud side data server, and the cloud side data server is connected with multiple types of client sides through the network. With application of the system, the disadvantages that the ultraviolet flame detector has poor sensitivity and small detection distance and have no resistance to lightning interference and has certain rate of false alarm can be solved, and remote command deployment can be realized in case of emergency event so that unnecessary property loss can be reduced, and the powerful guarantee can be provided for the fire fighting force to quickly and effectively handle various fire accidents.

A network call center system is composed of multiple local call centers and an intelligent routing center connected between multiple local call centers for transferring the call between local call centers, so uniformly distributing network resources.

The invention relates to the field of power grid regulation and control, in particular to a regulation and control intelligent networked interaction system applied to an electric power company. The regulation and control intelligent networked interaction system comprises a network command sending center module, a management and report center module, an intelligent safety anti-misoperation center module, a publicity center module, a statistical query sharing center module and an auxiliary center module. The beneficial effects of the invention are that the system can improve the regulation and control management level of a power grid, and achieves the conversion of dispatching instruction interaction from a conventional telephone mode to a network intelligent mode through the technologies ofa computer network, network safety protection and artificial intelligence; the safety anti-error capability of the whole process of power grid dispatching network order sending is improved, safety anti-error of face recognition, order-receiving photographing file leaving, topological logic-based check, equipment real-time state check, dangerous point real-time reminding and the like is conductedto each link of the whole process of network order sending, and compared with a traditional telephone mode, the safety of power grid operation is greatly improved.

Network logistics and network business are mutually integrated. In order to realize the sharing of logistics information and logistics functions among logistics enterprises, industrial and commercialenterprises and logistics supervision government departments, the network logistics has to be interconnected, intercommunicated and interoperated with network government affairs. The problem of logistics information comprehensive integration among logistics enterprises, industrial and commercial enterprises, financial institutions and government supervision departments in logistics can be effectively solved by means of the government affairs. Network logistics systems are closely related to the network business, the network government affairs, network intelligent traffic systems and the like.The network logistics is based on the network business, the network government affairs, the network intelligent traffic systems and the like. A plurality of identification facilities and a general purpose calculator are mutually connected in a short distance through transmission media according to physical topological structures of a local area network (in a star shape, a ring shape, a tree shapeor a bus shape and the like) to form a logistics network unit. Each identification facility is fixedly distributed in a monitoring area and respectively takes an identification task of cargoes and thelike of the monitoring area in the logistics system.

The invention relates to a fire extinguishing system network intelligent control device, which can timely track monitoring management according to the running state of a fire extinguishing system, and can record the entire running process and state so as to realize remote monitoring and remote control. The device adopts PLC (Programmable Logic Controller)to detect the water outlet pressure of thefire extinguishing system, a fire activating signal and a manual activating signal of a fire alarm linkage control cabinet to automatically control a network intelligent control cabinet to be under afire-fighting state, and to start a fire pump to run. A pressure transmitter and an electric drain valve are arranged on a fire control outlet pipe and a return pipe on a fire control pipe network, the network intelligent control cabinet is connected with the fire alarm linkage control cabinet and a fire pump control cabinet on the fire control pipe network, and a network management monitoring center is respectively connected with the fire alarm linkage control cabinet and the network intelligent control cabinet. The invention can cause the fire extinguishing system to be under an ideal state, can find a fault timely, automatically records a working state, realizes centralized monitoring and management, and has important meaning for ensuring the stable running of the fire extinguishing system.

A network intelligence display control system comprises a first display control system and a second display control system. The first display control system comprises a first display screen, a first control mainframe controlling the first display screen to work and a first mobile terminal. The first control mainframe comprises a first memory module, a first display driving module and a communication module. The first mobile terminal comprises a first touch display screen and a communication module. The second display control system comprises a second display screen, a second control mainframe controlling the second display screen to work and a second mobile terminal. The second control mainframe comprises a second memory module, a second display driving module and a communication module. The second mobile terminal comprises a second touch display screen and a communication module. The first control mainframe is in local area network connection with the second control mainframe, and the first mobile terminal enables video images stored by the first memory module and the second memory module to be selectively displayed on the first display screen or the second display screen through local area network control.

The invention discloses an SD-WAN network intelligent link selection method based on cloud computing, and belongs to the technical field of networks. The method is applied to client equipment and comprises the following steps: S10, establishing a plurality of communication links between the client equipment and a plurality of edge routers deployed in a cloud environment; S20, detecting the networkcondition of each communication link; S30, evaluating the quality grade of each link according to the detected network condition; S40, according to the quality grade of each link, determining one link with the highest quality grade in each link as a main link and other links as standby links; and S50, setting the route of the client equipment according to the determined main link and standby links. According to the method, through periodic active detection, the network quality grade is evaluated in time, the relatively optimal link is intelligently selected for the network, and the actual usedemand of a user is fully considered.