288 results about "Parallel search" patented technology

A system for real-time search, including: a set of partitions, each including a set of segments, each segment corresponding to a time slice of messages posted to the messaging platform, and a real-time search engine configured to receive a search term in parallel with other partitions in the set of partitions, and search at least one of the set of segments in reverse chronological order of the corresponding time slice to identify document identifiers of messages containing the search term; and a search fanout module configured to: receive a search query including the search term; send the search term to each of the set of partitions for parallel searching; and return, in response to the search query, at least one of the identified document identifiers of messages containing the search term.

The invention discloses a fast 3D face identifying method based on double-eye passive solid sight, which includes the following steps: 1) a non-contact short shaft parallel binocular stereo vision system is built by applying two high-definition digital cameras; 2) after system calibration is finished, face detection and collection based on a haar-AdaBoost sorting machine is carried out on a preview frame image for obtaining corresponding upper and lower stereoscopic vision graph pairs and estimating a sight difference; image correction is carried out on a face area for obtaining the upper and lower stereoscopic vision graph pairs vertical to the polar lines inside and outside the area; 3) the accurate location on the eyes and a spex nasi is captured by applying a Bayesian and the haar-AdaBoost sorting machines as well as point cloud 3D information for building a benchmark triangle; 4) the corresponding sub pixels in the middle and small areas are matched by applying the pyramidal parallel search solid graph of a phase relevant arithmetic based on a complex wavelet; 5) pose normalizing and hole filling are carried out on the faces under different poses by applying the built benchmark triangle; 6) expression normalization is carried out on different faces based on the suppose that the surface geodesic distance of the face is invariable; 7) the 3D faces after normalization are identified by utilizing the arithmetic. The method has the beneficial effects of: mainly solving the problems of being hard to fast and automatically obtain the passive stereoscopic vision and identifying the 3D point cloud information of the dense and accurate face under different poses and expressions, thus leading the 3D face identifying process to be faster, more hidden, safer and more reliable.

The present invention provides a technique for efficiently looking up address-routing information in an intermediate network node, such as a router. To that end, the node locates routing information stored in its memory using one or more “lookup” tables (LUT) which can be searched using a small, bounded number of dependent lookups, thereby reducing the number of dependent lookups conventionally performed. The LUTs are arranged so each table provides routing information for network addresses whose subnet mask lengths are within a different range (“stride”) of mask lengths. According to the technique, the node locates a network address's routing information by searching the LUTs, in order of decreasing prefix lengths, until the routing information is found. Preferably, several tables are searched in parallel. A match in a LUT may further point to a small MTRIE that enables the final bits of a prefix to be matched. That final MTRIE is searched using a relatively small, bounded number of dependent lookups.

A method and apparatus for communicating auxiliary information between a cellular telephone network and a GPS receiver positioned within a mobile station and identifying the location of the mobile station. A dedicated channel between the mobile station and the network is assigned by the network and uplink timing between the mobile station and the network is adjusted. The network requests auxiliary information and also requests the GPS receiver to perform a GPS code shift search at a common reference time. Upon receiving the auxiliary information, the network transmits the auxiliary information to the GPS receiver which then performs the GPS code shift search. The GPS receiver incorporates a bank of correlators and accumulators to perform multiple parallel searches for various Doppler frequency shifts resulting from a moving GPS receiver. The mobile station subsequently transmits the location information to the cellular telephone network.

Systems and methods are provided for scanning files and directories in a distributed file system on a network of nodes. The nodes include metadata with attribute information corresponding to files and directories distributed on the nodes. In one embodiment, the files and directories are scanned by commanding the nodes to search their respective metadata for a selected attribute. At least two of the nodes are capable of searching their respective metadata in parallel. In one embodiment, the distributed file system commands the nodes to search for metadata data structures having location information corresponding to a failed device on the network. The metadata data structures identified in the search may then be used to reconstruct lost data that was stored on the failed device.

The invention relates to a parallel search method and system of Openflow. According to the method and system, a compression storage mode through longitudinal segmentation of a rule table is proposed for multi-component and multi-list data search of the Openflow, so as to meet the requirement for storage space. A fast search and forwarding function is realized through parallel search of engines; a flow table in the Openflow is longitudinally segmented, compressed and stored, and the engines process respective header field parts, so that fast massage sorting and forwarding are achieved; and the problems of low table look-up efficiency due to complicated Openflow rules and large power consumption are solved.

The invention discloses a system and a method for supporting SDN multi-stage flow table parallel searching of a multi-core processor, and relates to the technical field of networks. The method comprises the following steps: adding a default table entry to the tail end of each multi-stage flow table; when a previous data stream enters a multi-stage flow table lookup, automatically establishing a data stream keyword-based quick table, recording the data stream and a table entry result matched with each stage of flow table, and directly associating the data stream with the table entries of the multi-stage flow tables in SDN equipment through the quick table; and directly obtaining forwarding rule information in the multi-stage flow tables from the quick table by a late data stream, directly finding out a to-be-matched table entry and an executed action from the multi-stage flow tables through the quick table, and converting matching for multiple times carried out in the SDN multi-stage flow tables into single matching in the quick table. According to the system and the method disclosed by the invention, the search efficiency can be improved; and the execution efficiency of the multi-core processor in the SDN multi-stage flow tables is improved.

An embodiment includes dividing a map into a first grid comprising a first plurality of cells with a first resolution and into a second grid comprising a second plurality of cells with a second resolution; determining that, because an initial portion of a key of a first cell of the second grid comprises a key of a first cell of the first grid, the first cell of the first grid comprises the first cell of the second grid; storing the first and the second grid in memories of distributed servers, wherein the first cell of the first grid and the first cell of the second grid are stored in a same one of the distributed servers or are stored in neighboring ones of the distributed servers; and directing respective processors of the distributed servers to perform a parallel search of the first grid and the second grid using the keys.

The invention discloses a method and a system for capturing a weak GNSS (Global Navigation Satellite System) signal under the condition of large-scale frequency deviation. The method comprises the following steps of: according to a pre-detection integration time, a carrier frequency and a sampling rate, determining a maximum carrier frequency searching step; dividing the whole frequency range to be searched into a plurality of carrier frequency units according to the maximum frequency searching step to realize rough search of the carrier frequency; mapping a received satellite signal onto each carrier frequency unit and regulating a local pseudo code rate according to the carrier frequency units so as to reduce the influence of code Doppler; calculating correlation in a flexible zero-padding mode through FFT (Fast Fourier Transform)/IFFT (Inverse Fast Fourier Transform) so as to realize code phase parallel search; and carrying out FFT operation on different correlation values corresponding to the same code phase so as to fulfill the aim of carrying out fine search on the carrier frequencies in the carrier frequency units. By the method and the system, a capturing speed and a capturing sensitivity of a receiver can be improved, so that the receiver completes the work of capturing a weak navigation signal pseudo code under the condition of the large-scale frequency deviation.

The invention discloses a multi-level acceleration method of flow-based biological sequence database search, which is to accelerate the search speed of a biological sequence database on the premise of ensuring search accuracy and relatively low cost. The technical proposal is that a cluster system composed of a plurality of personal computers shall be created firstly, and a master control node machine is assigned; the master control node machine distributes the database sequence and stores into each node machine in the cluster system, so as to fill and rearrange an inquiry sequence, and distribute the inquiry sequence to all the node machines in the cluster system; each node machine executes the search task in parallel, so as to be responsible for the completion of search tasks of the inquiry sequence in a local database sequence; the master control node machine collects, summarizes and outputs the results of parallel search tasks on all the node machines. The invention makes the search tasks be executed in parallel between the n node machines of the cluster, each node machine distributes the comparative calculation task of two sequences to p hardware calculation clusters to be conducted in parallel, thereby realizing the multi-level acceleration objective in parallel of three layers including a cluster node layer, a flow-level calculation layer, as well as a flow inner core command layer.

The invention discloses a full coherence accumulation time-frequency domain parallel capturing method based on FFT, in order to quickly capture a burst direct sequence spread spectrum signal with low signal to noise ratio and large frequency offset. The full coherence accumulation time-frequency domain parallel capturing method disclosed by the invention comprises two realization parts: pseudo code correlation based on FFT and full coherence accumulation based on FFT. Two methods of symbol correlation and zero complement FFT are used for further reducing the sinc loss in a pseudo code correlation process and the scallop loss in an accumulation process. The parallel capturing method is used for reducing the consumption of processing resources by the buffer of a large amount of intermediate data information and a parallel processing architecture based on FFT, obtaining a very high signal to noise ratio of a correlation peak within a short time, precisely evaluating Doppler frequency offset in a parallel search process of a pseudo code phase and reducing the average capturing time.

The invention discloses a convolution neural network structure searching method and a system based on an evolutionary algorithm. The method comprises the steps of inputting a data set and setting preset parameters to obtain an initial population. By the controller TC as the main thread popping the initial population into the queue q and opening the queue manager tq and the message manager tm, After the queue manager TQ is turned on, the untrained chromosomes in the queue Q are pop-up and decoded, and a worker manager TW as an independent temporary thread is started to calculate the fitness forthe training, Through the cooperation of controller TC, queue manager TQ, worker manager TW and message manager TM, the parallel search of convolution neural network structure based on evolutionary algorithm is completed and the best model is output. The invention can realize automatic modeling, parameter adjustment and training for a given data set, has the advantages of high performance, large-scale, flow-chart and good certainty, and is particularly suitable for deployment and implementation on a high-performance computer cluster.

The invention discloses a direct sequence spread spectrum (DSSS) communication pseudo code capture method used in a wireless sensor network (WSN). The method comprises the following steps: step 1. carrying out differential treatment to an input signal and a local pseudo code, using a circumferential related characteristic of FFT to perform parallel search pseudo code phase to the input signal and the local pseudo code after the differential treatment, adjusting the local pseudo code phase so that the local pseudo code phase is synchronized with the input signal pseudo code and completing the pseudo code phase capture; step 2. using the FFT to perform parallel search carrier frequency offset to the input signal and the local pseudo code after the pseudo code synchronization and completing frequency offset correction. By using the pseudo code capture method of the invention, search time can be shortened and a search speed can be increased. The capture time can not be increased as a length of the pseudo code is longer and carrier wave frequency offset is larger. A correlator does not needed during a capture process. Resource consumption is low. The method can be flexibly modified according to a requirement of a system to a signal to noise ratio.

One embodiment of the present invention provides a system for partitioning a graph representing customer purchases to facilitate parallel computations. During operation, the system initially receives graph data indicating vertices and edges of the graph, wherein the vertices represent customers and products and the edges represent purchases. Next, the system partitions edges of the graph to generate a partitioned graph such that each edge of the graph is a member of a respective partition. The system may then perform parallel computations on the graph data in one or more partitions to determine product recommendations.

The invention relates to a keyword-based RDF distributed semantic search method. The method comprises the steps of constructing a semantic feasible path of input query keywords based on an RDF ontology; performing score sorting according to semantic content and a semantic structure of query content in the construction stage; generating Top-k semantic feasible paths; and performing a parallel search by utilizing a MapReduce computing framework and returning Top-k query results. According to the keyword-based RDF distributed semantic search method proposed by the invention, the semantic feasible paths are constructed and searched for based on the ontology and interconnection paths among the query keywords are determined, so that time-consuming iterative computing directly on a large-scale RDF data map is avoided; and parallel computing is realized by utilizing a MapReduce computing model, so that the overall computing complexity is effectively lowered for improving query performance.

The invention provides a search method based on big data. The method comprises steps as follows: index data of images are stored by the aid of distributed files, all the index data are written into index data files, and then the index data files are distributed and stored in various nodes of a distributed file system; the index data are searched through a MapReduce parallel programming model, a search space is divided into multiple subspaces, then parallel searches are performed on the subspaces through task scheduling, and finally, a final search result is formed through summarizing. With the adoption of the search method based on the big data, processes for storing and searching the data of the images by the aid of the distributed system are optimized, the search efficiency is improved, and the performance bottleneck is overcome.

The invention discloses a method for raising ternary content-addressable memory (TCAM) -based message classifying and searching rate, applied to implement TCAM-based access control list (ACL) matching on network equipment, and characterized in that: it uses a method of trading space for time to raise TCAM message classifying and searching rate, concretely able to be implemented by keyword buffering technique, parallel searching technique and/or logic table splitting technique. And the method can largely raise the TCAM' rate of searching ACL/QoS, meeting the requirements for line rate of message classifying and multi-searching in high speed network. And the method is simple, reliable, flexible and easy to apply.

The invention discloses a two-directional pseudo code parallel search system which comprises a signal receiving device, a local PN (pseudo-noise) code generator, a signal acquiring module and a single processor; the local PN code generator and the signal acquiring module are connected with the signal processor respectively; and the local PN code generator is connected with the signal acquiring module. The two-directional pseudo code parallel search system further comprises a signal input device connected with the signal acquiring module, and enables the searches in phase direction and Doppler direction to be finished simultaneously within the related integral time, thereby shortening the search time, and improving the search efficiency. As all digital signal processing is realized on hardware in an assembly line manner, and the concurrency of the hardware is fully utilized for completing the whole search process, the speed of data processing on the hardware is greatly improved compared with the data processing on software, and the chip realization is benefited.

Receivers and reception methods conduct spread spectrum reception using the energy of multiple bits, preferably a substantial number of bits, in a packet for correct alignment of the spreading code at the receiver. Code acquisition, as well as packet detection and acquisition are provided by embodiments of the invention. Preferred embodiment receivers and reception methods provide packet detection at low SINR looking at energy of multiple bits of the packet, frame synchronization using short preamble, timing recovery at low SINR looking at energy of multiple bits of the packet, quick code acquisition using parallel search for all possible code phases, code acquisition at low SINR, and tracking of acquired timing and code phase. Preferred embodiment receivers and reception methods use the energy of multiple bits for making decisions.