Abstract: A query enhancement system for constructing an elastic field based on a time delay, including: dividing a network node to obtain a set of containers composed of several containers, wherein the containers are nested and each container includes a management node for performing node organization, neighbor maintenance and query services within the container. Further, a query enhancement method for constructing an elastic field based on a time delay includes: carrying out same-layer non-intersection full-coverage division on a network node to obtain a set of containers that are nested, and execute a query flow without a given low time delay requirement which uses an existing query technique and a nearby query flow with a given low time delay requirement which uses a distributed nearby querying method to carry out a nearby query; with an actual query time delay index Ti less than the requirement of an upper time delay limit Ts.

Abstract: A method for generating a nested container with no intersection and same layer full coverage, including: giving a right undirected graph G(V, E, W) and network measurement index set {Ti} for dividing nodes in G, each network measurement index Ti corresponding to a Ci layer container set {Ci k}; deleting an edge weighing greater than Ti, and segmenting G into subgraphs, each a connected component; setting all nodes in the subgraph Gcm not in the Ci layer container as set L; selecting one node from set L as current anchor aj; starting with anchor aj, performing breadth-first search on all nodes in L and Ci+1 layer container containing aj with the path communicated therewith less than Ti forming a Ci layer container with anchor aj; setting j?=j+1, determining whether L is a null set; setting m=m+1, determining whether all subgraphs are processed; setting i=i?1, and determining whether i=1 is satisfied.

Abstract: A big data processing method based on a deep learning model satisfying K-degree sparse constraints comprises: step 1), constructing a deep learning model satisfying K-degree sparse constraints using an un-marked training sample via a gradient pruning method, wherein the K-degree sparse constraints comprise a node K-degree sparse constraint and a level K-degree sparse constraint; step 2), inputting an updated training sample into the deep learning model satisfying the K-degree sparse constraints, and optimizing a weight parameter of each layer of the model, so as to obtain an optimized deep learning model satisfying the K-degree sparse constraint; and step 3), inputting big data to be processed into the optimized deep learning model satisfying the K-degree sparse constraints for processing, and finally outputting a processing result. The method in the present invention can reduce the difficulty of big data processing and increase the speed of big data processing.

Abstract: A method for generating a nested container with no intersection and same layer full coverage, including: giving a right undirected graph G(V, E, W) and network measurement index set {Ti} for dividing nodes in G, each network measurement index Ti corresponding to a Ci layer container set {Ci k}; deleting an edge weighing greater than Ti, and segmenting G into subgraphs, each a connected component; setting all nodes in the subgraph Gcm not in the Ci layer container as set L; selecting one node from set L as current anchor aj; starting with anchor aj, performing breadth-first search on all nodes in L and Ci+1 layer container containing aj with the path communicated therewith less than Ti forming a Ci layer container with anchor aj; setting j?=j+1, determining whether L is a null set; setting m=m+1, determining whether all subgraphs are processed; setting i=i-1, and determining whether i=1 is satisfied.

Abstract: A query enhancement system for constructing an elastic field based on a time delay, including: dividing a network node to obtain a set of containers composed of several containers, wherein the containers are nested and each container includes a management node for performing node organization, neighbor maintenance and query services within the container. Further, a query enhancement method for constructing an elastic field based on a time delay includes: carrying out same-layer non-intersection full-coverage division on a network node to obtain a set of containers that are nested, and execute a query flow without a given low time delay requirement which uses an existing query technique and a nearby query flow with a given low time delay requirement which uses a distributed nearby querying method to carry out a nearby query; with an actual query time delay index Ti less than the requirement of an upper time delay limit Ts.

Abstract: A big data processing method for a segment-based two-grade deep learning model. The method includes: step (1), constructing and training a segment-based two-grade deep learning model, wherein the model is divided into two grades in a longitudinal level: a first grade and a second grade, each layer of the first grade is divided into M segments in a horizontal direction, and the weight between neuron nodes of adjacent layers in different segments of the first grade is zero; step (2), dividing big data to be processed into M sub-sets according to the type of the data and respectively inputting same into M segments of a first layer of the segment-based two-grade deep learning model for processing; and step (3), outputting a big data processing result. The method of the present invention can increase the big data processing speed and shorten the processing time.

Abstract: A big data processing method based on a deep learning model satisfying K-degree sparse constraints comprises: step 1), constructing a deep learning model satisfying K-degree sparse constraints using an un-marked training sample via a gradient pruning method, wherein the K-degree sparse constraints comprise a node K-degree sparse constraint and a level K-degree sparse constraint; step 2), inputting an updated training sample into the deep learning model satisfying the K-degree sparse constraints, and optimizing a weight parameter of each layer of the model, so as to obtain an optimized deep learning model satisfying the K-degree sparse constraint; and step 3), inputting big data to be processed into the optimized deep learning model satisfying the K-degree sparse constraints for processing, and finally outputting a processing result. The method in the present invention can reduce the difficulty of big data processing and increase the speed of big data processing.