公开(公告)号：US20190337157A1

公开(公告)日：2019-11-07

申请号：US16457676

申请日：2019-06-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Wenhua SUN ,  Jiali FU ,  Heng LIAO ,  Huimin ZHANG

IPC: B25J11/00 ,  G06N20/00 ,  G09B5/06 ,  G10L25/63 ,  G06K9/00

Abstract: Embodiments of the present invention provide a human-machine interaction method, including: detecting and collecting, by a robot, sensing information of a companion object of a target object and emotion information of the target object that is obtained when the target object interacts with the companion object; extracting, by the robot, an emotion feature quantity based on the emotion information, determining, based on the emotion feature quantity, an emotional pattern used by the target object to interact with the companion object, determining, based on the emotional pattern, a degree of interest of the target object in the companion object, extracting behavioral data of the companion object from the sensing information based on the degree of interest, and screening the behavioral data to obtain simulated object data; and simulating, by the robot, the companion object based on the simulated object data.

公开(公告)号：US20170075358A1

公开(公告)日：2017-03-16

申请号：US15343603

申请日：2016-11-04

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Huimin ZHANG

IPC: G05D1/02 ,  G06Q10/10 ,  G08G1/127

CPC classification number: G05D1/0287 ,  G05D1/0027 ,  G05D1/0297 ,  G06Q10/047 ,  G06Q10/06 ,  G06Q10/1093 ,  G06Q50/26 ,  G06Q50/30 ,  G08G1/202 ,  H04W4/024

Abstract: The present invention belongs to the field of computer technologies, and discloses a self-driving car scheduling method, a car scheduling server, and a self-driving car. The method includes: receiving a ride request; determining, according to the ride request and driving information of self-driving cars within a management range, at least one first candidate car from the multiple self-driving cars; calculating a first time required by each first candidate car to arrive at a ride destination according to current location information, current road status information, and planned route information of each first candidate car; determining a final candidate car from the at least one first candidate car according to the first time corresponding to each first candidate car, where the final candidate car at least meets an expected destination arrival time; and delivering the ride request to the final candidate car.

Abstract translation: 本发明属于计算机技术领域，并且公开了一种自驾车调度方法，汽车调度服务器和自驾车。 该方法包括：接收骑乘请求; 根据驾驶汽车在管理范围内的乘坐要求和驾驶信息，确定来自多个自驾车厢的至少一个第一候选车辆; 根据当前位置信息，当前道路状态信息以及每个第一候选车辆的规划路线信息，计算每个第一候选车辆所要求的第一时间到达乘坐目的地; 根据对应于每个第一候选车的第一时间从至少一个第一候选车确定最终候选车，其中最终候选车至少满足预期的目的地到达时间; 并将乘车要求交给最终候选车。

公开(公告)号：US20230360254A1

公开(公告)日：2023-11-09

申请号：US18344208

申请日：2023-06-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Chang LIU ,  Chuangchuang LIU ,  Baoyang CHEN ,  Yuntan FANG ,  Siwei DONG ,  Shu FANG ,  Huimin ZHANG

IPC: G06T7/20 ,  G06T7/70

CPC classification number: G06T7/70 ,  G06T7/20 ,  G06T2207/30241

Abstract: A pose estimation method and an apparatus are provided, to obtain a more accurate pose estimation result. The method includes: obtaining a first event image and a first target image, where the first event image is aligned with the first target image in time sequence, the first target image includes an RGB image or a depth image, and the first event image includes an image indicating a movement trajectory that is of a target object and that is generated when the target object moves in a detection range of a motion sensor; determining integration time of the first event image; if the integration time is less than a first threshold, determining that the first target image is not for performing pose estimation; and performing pose estimation based on the first event image.

公开(公告)号：US20230335101A1

公开(公告)日：2023-10-19

申请号：US18338851

申请日：2023-06-21

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Libin ZHANG ,  Tingqiu YUAN ,  Huimin ZHANG

IPC: G10K11/178

CPC classification number: G10K11/17827 ,  G10K11/17823 ,  G10K11/17881

Abstract: The present discloser relates to a method for active noise cancellation. An example method includes: capturing an ambient sound to determine an ambient audio signal; and determining a working status, determining at least one corresponding wanted signal based on the working status, and then removing the at least one wanted signal from the ambient audio signal, to obtain a reference signal, where the wanted signal includes content of interest. The example method further includes determining a to-be-played signal based on the reference signal.

公开(公告)号：US20230275962A1

公开(公告)日：2023-08-31

申请号：US18314342

申请日：2023-05-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Feilong TANG ,  Xu LI ,  Haibo ZHANG ,  Huimin ZHANG

IPC: H04L67/1074 ,  H04L67/1061 ,  H04L67/62

CPC classification number: H04L67/1078 ,  H04L67/1061 ,  H04L67/62

Abstract: Embodiments of this application disclose a data transmission method and a communication apparatus. The method may be applied to a data transmission or data distribution scenario in a peer-to-peer P2P network. The method includes: A first end node sends delayed transmission information to a second end node, where the delayed transmission information indicates time information at which the first end node delays sending first data to the second end node. When determining that the second end node accepts the delayed transmission information, the first end node delays sending the first data to the second end node, to alleviate a load of the first end node, so that a network congestion problem caused by a large-scale concurrent data request can be resolved.

公开(公告)号：US20230076085A1

公开(公告)日：2023-03-09

申请号：US17985322

申请日：2022-11-11

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Tingqiu YUAN ,  Libin ZHANG ,  Chang LIU ,  Huimin ZHANG

IPC: G06F21/32

Abstract: A device enabling method and apparatus, and a storage medium relate to: collecting at least two types of biometric feature information of a user; performing identity authentication on the user based on the at least two types of biometric feature information; and if identity authentication succeeds, enabling at least one of a wearable device and a smart device, where the wearable device is communicatively connected to the smart device. This disclosure helps ensure information security of a device.

公开(公告)号：US20220335923A1

公开(公告)日：2022-10-20

申请号：US17852980

申请日：2022-06-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Tingqiu YUAN ,  Libin ZHANG ,  Huimin ZHANG ,  Chang LIU

IPC: G10K11/178

Abstract: A signal processing apparatus is configured to preprocess a sound wave signal and output a processed audio signal through an electromagnetic wave. The signal processing apparatus includes: a receiving unit, configured to receive at least one sound wave signal; a conversion unit, configured to convert the at least one sound wave signal to at least one audio signal; a positioning unit, configured to determine position information related to the at least one sound wave signal; a processing unit, configured to determine a sending time point of at least one audio signal based on the position information and a first time point, where the first time point is a time point at which the receiving unit receives the at least one sound wave signal; and a sending unit, configured to send the at least one audio signal through the electromagnetic wave.

公开(公告)号：US20190318245A1

公开(公告)日：2019-10-17

申请号：US16452290

申请日：2019-06-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Fenglong SONG ,  Wulong LIU ,  Xijun XUE ,  Huimin ZHANG

IPC: G06N3/08 ,  G06N3/063 ,  G06F9/50

Abstract: This application provides a method, a terminal-side device, and a cloud-side device for data processing and a terminal-cloud collaboration system. The method includes: sending, by the terminal-side device, a request message to the cloud-side device; receiving, by the terminal-side device, a second neural network model that is obtained by compressing a first neural network model and that is sent by the cloud-side device, where the first neural network model is a neural network model on the cloud-side device that is used to process the cognitive computing task, and a hardware resource required when the second neural network model runs on the terminal-side device is within an available hardware resource capability range of the terminal-side device; and processing, by the terminal-side device, the cognitive computing task based on the second neural network model.