公开(公告)号：US11650351B2

公开(公告)日：2023-05-16

申请号：US17165515

申请日：2021-02-02

Applicant: NEC Laboratories America, Inc.

Inventor： Yanchi Liu ,  Jingchao Ni ,  Bo Zong ,  Haifeng Chen ,  Zhengzhang Chen ,  Wei Cheng ,  Denghui Zhang

IPC: G01W1/00 ,  G06N3/08 ,  G06N3/02 ,  G01W1/10 ,  G06N20/00 ,  G01W1/02 ,  G06N3/04 ,  G06N5/00 ,  G06N3/088

CPC classification number: G01W1/00 ,  G06N3/0454 ,  G06N3/08 ,  G01W1/02 ,  G01W1/10 ,  G01W2001/003 ,  G06N3/02 ,  G06N3/0445 ,  G06N3/088 ,  G06N5/003 ,  G06N20/00

Abstract: A method for employing a unified semi-supervised deep learning (DL) framework for turbulence forecasting is presented. The method includes extracting historical and forecasted weather features of a spatial region, calculating turbulence indexes to fill feature cubes, each feature cube representing a grid-based 3D region, and building an encoder-decoder framework based on convolutional long short-term memory (ConvLSTM) to model spatio-temporal correlations or patterns causing turbulence. The method further includes employing a dual label guessing component to dynamically integrate complementary signals from a turbulence forecasting network and a turbulence detection network to generate pseudo-labels, reweighing the generated pseudo-labels by a heuristic label quality detector based on KL-Divergence, applying a hybrid loss function to predict turbulence conditions, and generating a turbulence dataset including the predicted turbulence conditions.

公开(公告)号：US11842271B2

公开(公告)日：2023-12-12

申请号：US17003112

申请日：2020-08-26

Applicant: NEC Laboratories America, Inc.

Inventor： Yanchi Liu ,  Wei Cheng ,  Bo Zong ,  LuAn Tang ,  Haifeng Chen ,  Denghui Zhang

IPC: G06N3/04 ,  G06N3/08 ,  G06N3/049

CPC classification number: G06N3/08 ,  G06N3/049

Abstract: Methods and systems for allocating network resources responsive to network traffic include modeling spatial correlations between fine spatial granularity traffic and coarse spatial granularity traffic for different sites and regions to determine spatial feature vectors for one or more sites in a network. Temporal correlations at a fine spatial granularity are modeled across multiple temporal scales, based on the spatial feature vectors. Temporal correlations at a coarse spatial granularity are modeled across multiple temporal scales, based on the spatial feature vectors. A traffic flow prediction is determined for the one or more sites in the network, based on the temporal correlations at the fine spatial granularity and the temporal correlations at the coarse spatial granularity. Network resources are provisioned at the one or more sites in accordance with the traffic flow prediction.

公开(公告)号：US20210255363A1

公开(公告)日：2021-08-19

申请号：US17165515

申请日：2021-02-02

Applicant: NEC Laboratories America, Inc.

Inventor： Yanchi Liu ,  Jingchao Ni ,  Bo Zong ,  Haifeng Chen ,  Zhengzhang Chen ,  Wei Cheng ,  Denghui Zhang

IPC: G01W1/00 ,  G06N3/04 ,  G06N3/08

Abstract: A method for employing a unified semi-supervised deep learning (DL) framework for turbulence forecasting is presented. The method includes extracting historical and forecasted weather features of a spatial region, calculating turbulence indexes to fill feature cubes, each feature cube representing a grid-based 3D region, and building an encoder-decoder framework based on convolutional long short-term memory (ConvLSTM) to model spatio-temporal correlations or patterns causing turbulence. The method further includes employing a dual label guessing component to dynamically integrate complementary signals from a turbulence forecasting network and a turbulence detection network to generate pseudo-labels, reweighing the generated pseudo-labels by a heuristic label quality detector based on KL-Divergence, applying a hybrid loss function to predict turbulence conditions, and generating a turbulence dataset including the predicted turbulence conditions.

公开(公告)号：US20210064999A1

公开(公告)日：2021-03-04

申请号：US17003112

申请日：2020-08-26

Applicant: NEC Laboratories America, Inc.

Inventor： Yanchi Liu ,  Wei Cheng ,  Bo Zong ,  LuAn Tang ,  Haifeng Chen ,  Denghui Zhang

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods and systems for allocating network resources responsive to network traffic include modeling spatial correlations between fine spatial granularity traffic and coarse spatial granularity traffic for different sites and regions to determine spatial feature vectors for one or more sites in a network. Temporal correlations at a fine spatial granularity are modeled across multiple temporal scales, based on the spatial feature vectors. Temporal correlations at a coarse spatial granularity are modeled across multiple temporal scales, based on the spatial feature vectors. A traffic flow prediction is determined for the one or more sites in the network, based on the temporal correlations at the fine spatial granularity and the temporal correlations at the coarse spatial granularity. Network resources are provisioned at the one or more sites in accordance with the traffic flow prediction.

公开(公告)号：US20220261551A1

公开(公告)日：2022-08-18

申请号：US17584638

申请日：2022-01-26

Applicant: NEC Laboratories America, Inc.

Inventor： Yanchi Liu ,  Bo Zong ,  Haifeng Chen ,  Xuchao Zhang ,  Denghui Zhang

IPC: G06F40/30 ,  G06F40/284

Abstract: A method for employing a knowledge-driven pre-training framework for learning product representation is presented. The method includes learning contextual semantics of a product domain by a language acquisition stage including a context encoder and two language acquisition tasks, obtaining multi-faceted product knowledge by a knowledge acquisition stage including a knowledge encoder, skeleton attention layers, and three heterogeneous embedding guided knowledge acquisition tasks, generating local product representations defined as knowledge copies (KC) each capturing one facet of the multi-faceted product knowledge, and generating final product representation during a fine-tuning stage by combining all the KCs through a gating network.