Abstract: A spectral clustering method and system based on unified anchor and subspace learning is provided. The spectral clustering method based on unified anchor and subspace learning includes: S1: acquiring a clustering task and a target data sample; S2: performing unified anchor learning on multi-view data corresponding to the acquired clustering task and the acquired target data sample, and adaptively constructing an objective function corresponding to an anchor graph according to a learned unified anchor; S3: optimizing the constructed objective function by using an alternating optimization method to obtain an optimized unified anchor graph; and S4: performing spectral clustering on the obtained optimized unified anchor graph to obtain a final clustering result.

Abstract: A consensus graph learning-based multi-view clustering method includes: S11, inputting an original data matrix to obtain a spectral embedding matrix; S12, calculating a similarity graph matrix and a Laplacian matrix based on the spectral embedding matrix; S13, applying spectral clustering to the calculated similarity graph matrix to obtain spectral embedding representations; S14, stacking inner products of the normalized spectral embedding representations into a third-order tensor and using low-rank tensor representation learning to obtain a consistent distance matrix; S15, integrating spectral embedding representation learning and low-rank tensor representation learning into a unified learning framework to obtain a objective function; S16, solving the obtained objective function through an alternative iterative optimization strategy; S17, constructing a consistent similarity graph based on the solved result; and S18, applying spectral clustering to the consistent similarity graph to obtain a clustering resul

Abstract: An unsupervised feature selection method based on latent space learning and manifold constraints includes: S11, inputting an original data matrix to obtain a feature selection model; S12, embedding latent space learning into the feature selection model to obtain a feature selection model with the latent space learning; S13, adding a graph Laplacian regularization term into the feature selection model with the latent space learning to obtain an objective function; S14, solving the objective function by adopting an alternative iterative optimization strategy; and S15, sequencing each feature in the original matrix, and selecting the first k features to obtain an optimal feature subset. Feature selection is performed in a learned potential latent space, and the space is robust to noise. The potential latent space is modeled by non-negative matrix decomposition of a similarity matrix, and the matrix decomposition can unambiguously reflect relationships between data instances.

Abstract: This application provides a communication method and apparatus. In the communication method, a first RLC entity is introduced to transmit a network-coded redundant packet, and a second RLC entity is introduced to transmit a network-coded original packet, so that requirement-based transmission of the network-coded redundant packet can be supported. The communication method includes: A terminal device receives scheduling information from an access network device, obtains a network-coded redundant packet through a first RLC entity, generates a first TB based on the network-coded redundant packet, and sends the first TB to the access network device, where the first TB includes the network-coded redundant packet. In this way, the access network device schedules the network-coded redundant packet by using the scheduling information only when the network-coded redundant packet needs to be scheduled, thereby avoiding a waste and reducing unnecessary redundant transmission.

Abstract: A multi-view clustering method and system based on matrix decomposition and multi-partition alignment are provided.

Abstract: A citation network graph representation learning system and method based on multi-view contrastive learning is provided. The citation network graph representation learning system involved in the present application comprises: a sample construction module, which is configured to construct a corresponding negative sample based on an original graph; a graph enhancement module, which is configured to obtain a positive sample graph and a negative sample graph; a fusion module, which is configured to obtain a consensus representation of the positive sample graph and the negative sample graph by means of a cross view concentration fusion layer; a mutual information estimation module, which is configured to compare learning representations of positive sample pairs and negative sample pairs by means of a discriminator; and a hard sample mining module, which is configured to represent the consistency between the negative sample pairs according to a pre-calculated affinity vector, and select and reserve nodes.

Abstract: A late fusion multi-view clustering method and system based on local maximum alignment are provided. The late fusion multi-view clustering method based on local maximum alignment includes the following steps: S1: acquiring a clustering task and a target data sample; S2: initializing a permutation matrix of each view and a combination coefficient of each view, and performing average partition of kernel k-means clustering on an average kernel to obtain a neighbor matrix of each view; S3: calculating basic partition of each view, and establishing a late fusion multi-view clustering objective function based on maximum alignment; S4: acquiring basic partition having local information, and establishing a late fusion multi-view clustering objective function based on local maximum alignment; S5: solving the established late fusion multi-view clustering objective function based on local maximum alignment in a cyclic manner to obtain optimal partition; and S6: performing k-means clustering on the optimal partition.

Abstract: A system for unsupervised deep representation learning based on image translation is provided. The system includes an image translation transformation module used for performing a random translation transformation on an image and generating an auxiliary label; an image mask module connected with the image translation transformation module and used for applying a mask to the image after translation transformation; a deep neural network connected with the image mask module and used for predicting an actual auxiliary label of the image after the mask is applied and learning the deep representation of the image; a regression loss function module connected with the deep neural network and used for updating parameters of the deep neural network based on a loss function; and a feature extraction module connected with the deep neural network and used for extracting the representation of the image.

Abstract: A multi-modal adaptive fusion deep clustering model based on an auto-encoder includes an encoder structure, a multi-modal adaptive fusion layer, a decoder structure and a deep embedding clustering layer. The encoder is configured to enable a dataset to be respectively subjected to three types of nonlinear mappings of the auto-encoder, a convolutional auto-encoder and a convolutional variational auto-encoder to obtain potential features, respectively. The multi-modal adaptive feature fusion layer is configured to fuse the potential features into a common subspace in an adaptive spatial feature fusion mode to obtain a fused feature. The decoder is configured to decode the fused feature by using a structure symmetrical to the encoder to obtain a decoded reconstructed dataset. The deep embedding clustering layer is configured to cluster the fused feature Z and obtain a final accuracy ACC by comparing a clustering result with a true label.

Abstract: A network device includes: a network interface configured to receive target data, a first processor configured to determine feature information of the target data, a second processor configured to perform preprocessing on the feature information, and a third processor configured to perform inference on a preprocessing result. In addition, the second processor is further configured to perform policy analysis based on an inference result.

Abstract: A data stream classification model updating method is disclosed. Determining, based on packet information of a current data stream and a behavior classification model, a first data stream class corresponding to the current data stream; determining, based on a target correspondence and a common feature of the current data stream, a second data stream class corresponding to the current data stream, where the target correspondence is a correspondence between a plurality of common features and a plurality of data stream classes; and if the first data stream class is different from the second data stream class, obtaining correction data corresponding to the current data stream, where the correction data includes the packet information of the current data stream and the second data stream class, and the correction data is used as a training sample to update the behavior classification model.

Abstract: A method, device, and system for multiplexing and mapping optical signals and demultiplexing and demapping optical signals are provided. The method for multiplexing and mapping optical signals includes the following steps: A label object that indicates a multiplexing and mapping relation is acquired. The label object includes a label and a label header. The label includes a type indication field and a TS indication field. The label object predefines a multiplexing and mapping policy about a first optical signal on a first optical channel and a second optical signal on a second optical channel. The first optical signal is multiplexed and mapped to the second optical signal according to the multiplexing and mapping policy. Therefore, when optical signals are multiplexed and mapped and are demultiplexed and demapped, so that an advantage of saving signaling overhead is realized.

Abstract: A method for realizing service protection in the automatically switched optical network includes following steps: after any defect occurs on the working paths that carry the service, the first node and the last node of the working paths sends the requests to restore the paths setup in opposite directions, respectively; at least one intermediate node in the restoration path establishes a connection according to the restoration path setup request, and forwards the restoration path setup request hop by hop, until the setup of the recovering path is finished; the service is switched from the working paths to the restoration paths. A system for realizing service protection and a node device in an ASON is also provided. The paths restoration process can be faster obviously using this invention, and the restoration time can be shortened, and the work efficiency and reliability can be improved, and the service can be ensured to be restored.

Abstract: A method, device, and system for multiplexing and mapping optical signals and demultiplexing and demapping optical signals are provided. The method for multiplexing and mapping optical signals includes the following steps: A label object that indicates a multiplexing and mapping relation is acquired. The label object includes a label and a label header. The label includes a type indication field and a TS indication field. The label object predefines a multiplexing and mapping policy about a first optical signal on a first optical channel and a second optical signal on a second optical channel. The first optical signal is multiplexed and mapped to the second optical signal according to the multiplexing and mapping policy. Therefore, when optical signals are multiplexed and mapped and are demultiplexed and demapped, so that an advantage of saving signaling overhead is realized.

Abstract: The present invention discloses a method for identifying node reachability, a method for identifying a link, a method for calculating a routing, and a method for disseminating node address information. In the method of the node address information dissemination, when the network is initiated, each node in the automatically switched optical network performs a node address aggregation process and an aggregation address dissemination process, and obtains and stores the aggregation address respectively. Therefore, any node in the network may judge whether the node and another node in the network are reachable to each other, and may further calculate the routing between the source and destination nodes pair. Moreover, the present invention also may determine whether any traffic engineering link in the multi-level ASON network is an external link or an internal link.

Abstract: A method, a system, and a device for setting up a wavelength connection are disclosed herein. The method includes obtaining a wavelength path from a source network node to a destination network node and wavelength impairment compensation information of the wavelength path; and setting up the wavelength connection from the source network node to the destination network node according to the wavelength path and performing impairment compensation for wavelength signals in an interface of each network node on the wavelength path according to the wavelength impairment compensation information during setting up the wavelength connection. The device disclosed herein includes a path calculation server, a network node device, and a control server. The system disclosed herein is a network communication system. The embodiments of the present disclosure set up an available wavelength connection efficiently, simply and quickly.

Abstract: A method and system for multi-domain route computation. In the invention, Path Computation Elements (PCEs) are placed in different layers and computation domains between upper and lower layer PCEs are mapped so that a computation task is divided into multiple computation tasks layer by layer and that the multi-domain route computation is finally fulfilled. The invention separates route computation from signaling and runs route computation tasks in parallel. Route establishment is done by signaling after route computation. The present invention may realize route computation based on complex Traffic Engineering (TE) constraints and enable end-to-end diverse route computation. The invention places PCEs in layers, allowing good scalability and high computation efficiency. The present invention is applicable to the Automatically Switched Optical Network (ASON) and the Multi-Protocol Label Switched Network Traffic Engineering (MPLS-TE) network.

Abstract: A method for realizing service protection in the automatically switched optical network includes following steps: after any defect occurs on the working paths that carry the service, the first node and the last node of the working paths sends the requests to restore the paths setup in opposite directions, respectively; at least one intermediate node in the restoration path establishes a connection according to the restoration path setup request, and forwards the restoration path setup request hop by hop, until the setup of the recovering path is finished; the service is switched from the working paths to the restoration paths. A system for realizing service protection and a node device in an ASON is also provided. The paths restoration process can be faster obviously using this invention, and the restoration time can be shortened, and the work efficiency and reliability can be improved, and the service can be ensured to be restored.

Abstract: A method for recovering from an inter-domain link failure includes: initiating a local recovery, by an upstream node of a failed inter-domain link, a local recovery from the link failure; performing the local recovery from the link failure with the upstream node of the failed inter-domain link as a source node and a downstream node of the failed inter-domain link as a destination node. A device for recovering from an inter-domain link failure includes: a link resource manager, adapted to detect an inter-domain link failure; a connection controller, adapted to inquire for a recovery path to a downstream node, and notifies a protocol controller to establish the recovery path; the protocol controller, adapted to establish the recovery path.

Abstract: A method and system for multi-domain route computation. In the invention, Path Computation Elements (PCEs) are placed in different layers and computation domains between upper and lower layer PCEs are mapped so that a computation task is divided into multiple computation tasks layer by layer and that the multi-domain route computation is finally fulfilled. The invention separates route computation from signaling and runs route computation tasks in parallel. Route establishment is done by signaling after route computation. The present invention may realize route computation based on complex Traffic Engineering (TE) constraints and enable end-to-end diverse route computation. The invention places PCEs in layers, allowing good scalability and high computation efficiency. The present invention is applicable to the Automatically Switched Optical Network (ASON) and the Multi-Protocol Label Switched Network Traffic Engineering (MPLS-TE) network.