-
公开(公告)号:US20240046067A1
公开(公告)日:2024-02-08
申请号:US18380581
申请日:2023-10-16
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Junqiu WEI , Yi LIAO , Xin JIANG , Qun LIU , Li QIAN
IPC: G06N3/04
CPC classification number: G06N3/04
Abstract: A data processing method includes: obtaining a first embedding vector for indicating a known data unit and a position of the known data unit and a second embedding vector for indicating a position of a to-be-predicted data unit; processing the first embedding vector by using a target encoder, to obtain an output vector; and processing the output vector and the second embedding vector by using a target prediction network, to obtain a to-be-predicted data unit. According to the method, M pieces of additional position information do not need to be separately set as input of the target encoder, and a quantity of latent variables of intermediate output of the target encoder is also consistent with a quantity of input embedding vectors, thereby reducing a computation amount and memory consumption of the target encoder.
-
公开(公告)号:US20230020965A1
公开(公告)日:2023-01-19
申请号:US17951271
申请日:2022-09-23
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Jun YUE , Li QIAN , Songcen XU , Bin SHAO
IPC: G06V10/774 , G06V10/74 , G06V10/80 , G06V10/26 , G06V10/46 , G06V10/764
Abstract: This application provides a method and apparatus for updating an object recognition model in the field of artificial intelligence. In the technical solution provided in this application, a target image and first voice information of a user are obtained. The first voice information indicates a first category of a target object in the target image. A feature library of a first object recognition model is updated based on the target image and the first voice information. The updated first object recognition model includes a feature of the target object and a first label indicating the first category, and the feature of the target object corresponds to the first label. A recognition rate of an object recognition model can be improved more easily according to the technical solution provided in this application.
-
公开(公告)号:US20190327357A1
公开(公告)日:2019-10-24
申请号:US16404449
申请日:2019-05-06
Applicant: Huawei Technologies Co., Ltd.
Inventor: Li QIAN , Jie ZHANG , Kangmin HUANG
IPC: H04M1/725 , G06F16/9535 , G06K9/00
Abstract: Embodiments of the present invention provide an information presentation method and device. The method includes: receiving, by a mobile terminal, first information provided by a communications network; determining, by the mobile terminal, a presentation priority of the first information in a current situation of a user; and sending the first information to a wearable device when the presentation priority of the first information in the current situation is greater than or equal to a second preset value, so that the wearable device presents the first information to the user. According to the information presentation method and device provided by the embodiments of the present invention, information can be presented according to a scene of a user, so that a presentation effect is improved, and interference of information unrelated to a current situation with the user is reduced.
-
公开(公告)号:US20180299836A1
公开(公告)日:2018-10-18
申请号:US16016433
申请日:2018-06-22
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Li QIAN , Xueyan HUANG , Kangmin HUANG , Maosheng HUANG
Abstract: An embodiment of the present invention provides a method for presenting a watch face. The method includes: obtaining first context information and second context information, where the first context information is used to determine a watch face style of the smartwatch, and the second context information is used to indicate dressing information of a user; determining the watch face style of the smartwatch according to the first context information; and presenting a watch face pattern of the smartwatch according to the watch face style and the second context information.
-
公开(公告)号:US20170064070A1
公开(公告)日:2017-03-02
申请号:US15330850
申请日:2016-11-07
Applicant: Huawei Technologies Co., Ltd.
Inventor: Li QIAN , Jie ZHANG , Kangmin HUANG
CPC classification number: H04M1/72569 , G06F17/30867 , G06K9/00684 , H04M1/7253 , H04M1/72547 , H04M1/72552
Abstract: Embodiments of the present invention provide an information presentation method and device. The method includes: receiving, by a mobile terminal, first information provided by a communications network; determining, by the mobile terminal, a presentation priority of the first information in a current situation of a user; and sending the first information to a wearable device when the presentation priority of the first information in the current situation is greater than or equal to a second preset value, so that the wearable device presents the first information to the user. According to the information presentation method and device provided by the embodiments of the present invention, information can be presented according to a scene of a user, so that a presentation effect is improved, and interference of information unrelated to a current situation with the user is reduced.
Abstract translation: 本发明的实施例提供了一种信息呈现方法和装置。 该方法包括:由移动终端接收由通信网络提供的第一信息; 由所述移动终端确定所述第一信息在用户的当前情况下的呈现优先级; 并且当当前情况下的第一信息的呈现优先级大于或等于第二预设值时,将第一信息发送到可穿戴设备,使得可穿戴设备向用户呈现第一信息。 根据本发明实施例提供的信息呈现方法和装置,可以根据用户的场景呈现信息,从而提高呈现效果,并且与用户当前的情况无关的信息的干扰是 减少
-
公开(公告)号:US20250058804A1
公开(公告)日:2025-02-20
申请号:US18936090
申请日:2024-11-04
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Li QIAN , Siyuan CHENG
Abstract: A vehicle meeting method and a related apparatus are provided and relate to the field of intelligent driving. The method includes a vehicle switching from a first mode to a second mode operation, where the first mode is a mode in which a vehicle is controlled by the vehicle through autonomous decision-making, and the second mode is a mode in which the vehicle is remotely controlled by a roadside device through decision. The method also includes the vehicle receiving a vehicle meeting solution operation from the roadside device, where the vehicle meeting solution is used to schedule a plurality of vehicles that meet during vehicle meeting. Furthermore, the method includes the vehicle performs vehicle meeting operation based on the vehicle meeting solution.
-
7.
公开(公告)号:US20240184837A1
公开(公告)日:2024-06-06
申请号:US18441389
申请日:2024-02-14
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Jieming ZHU , Zhou ZHAO , Shengyu ZHANG , Xiuqiang HE , Li QIAN
IPC: G06F16/9535 , G06V10/40
CPC classification number: G06F16/9535 , G06V10/40
Abstract: Examples of recommendation methods and apparatus are described. In one example method, a plurality of images are obtained, where each image includes one candidate interface and one type of candidate content presented by using the candidate interface. Image feature data of each image is obtained, and input for a prediction model is determined based on user feature data of a target user and the image feature data. Then, a degree of preference of the target user for each image is predicted by using the prediction model. At least one of a candidate interface or candidate content that are included in the plurality of images is selected based on the degree of preference. Recommendation is then performed to the user based on the selected candidate content or candidate interface.
-
公开(公告)号:US20200327681A1
公开(公告)日:2020-10-15
申请号:US16913795
申请日:2020-06-26
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Zhigang LI , Jianzhuang LIU , Li QIAN
Abstract: In one embodiment, a target tracking method includes: receiving a current frame of picture including a target object; determining, based on a drift determining model, whether a tracker drifts for tracking of the target object in the current frame of picture, where the drift determining model is obtained through modeling based on largest values of responses values of a training sample used to train the drift determining model, where the training sample is collected from a training picture that includes the target object, where the response value of the sample is a value indicating a probability that the training sample is the target object in the training picture; and outputting a tracking drift result, where the tracking drift result includes: drift is generated for the tracking of the target object, or no drift is generated for the tracking of the target object.
-
公开(公告)号:US20180219967A1
公开(公告)日:2018-08-02
申请号:US15940182
申请日:2018-03-29
Applicant: Huawei Technologies Co., Ltd.
Inventor: Li QIAN , Maosheng HUANG
CPC classification number: H04L67/303 , G06F3/011 , H04B1/385 , H04L41/0803 , H04L41/16 , H04L67/12 , H04W4/80
Abstract: The present invention provides an interactive device selection method and apparatus. The method includes: determining, according to a usage scenario type of the user and a preset policy and from a wearable device set of the user, a first interactive device that matches the usage scenario type of the user; and sending attribute information of the first interactive device to all wearable devices in the wearable device set of the user, so that a wearable device in the wearable device set of the user performs information interaction with the first interactive device according to the attribute information of the first interactive device. Therefore, the user may obtain all required information in time.
-
公开(公告)号:US20170109339A1
公开(公告)日:2017-04-20
申请号:US15395325
申请日:2016-12-30
Applicant: Huawei Technologies Co., Ltd.
Inventor: Hongbo JIN , Zhuolin JIANG , Qiang YANG , Li QIAN
IPC: G06F17/24 , G06F3/0482
CPC classification number: G06F17/241 , G06F3/0482 , G06F9/445 , Y02D10/43
Abstract: An application program activation method is disclosed, the method includes: acquiring, by a user terminal, one or more pieces of annotation information of a current media object, and displaying the one or more pieces of annotation information (201), where the one or more pieces of annotation information are information obtained by annotating the current media object at a semantic layer; determining, by the user terminal, one or more application programs associated with the one or more pieces of annotation information (202); and responding, by the user terminal, to target annotation information selected by a user, and activating a target application program associated with the target annotation information (203), where the one or more application programs include the target application program, the one or more pieces of annotation information include the target annotation information, and the user is a user that operates the user terminal.
-
-
-
-
-
-
-
-
-