-
公开(公告)号：US20220023136A1
公开(公告)日：2022-01-27
申请号：US17492650
申请日：2021-10-03
Inventor： Lei XIA , Xi CHEN , Hailu JIA , Guangdi SHAN
Abstract: A method for guiding a blind, an electronic device, a storage medium and a blind guide product, and related to the technical field of navigation are provided. The method includes: acquiring Beidou satellite data and base station differential data, and determining location information of a user by using a carrier phase differential technology; in response to a blind guide request, generating a blind guide route according to current location information and destination information input by the user; and broadcasting a voice prompt based on the blind guide route. The location accuracy of a user is improved, and blind guide requirements for a complex road section can be met, thereby improving the travel safety for the user.
-
公开(公告)号：US20220020356A1
公开(公告)日：2022-01-20
申请号：US17489616
申请日：2021-09-29
Inventor： Wenfu WANG , Tao SUN , Xilei WANG , Junteng ZHANG , Zhengkun GAO , Lei JIA
Abstract: The present disclosure provides a method and apparatus of synthesizing a speech, a method and apparatus of training a speech synthesis model, an electronic device, and a storage medium. The method of synthesizing a speech includes acquiring a style information of a speech to be synthesized, a tone information of the speech to be synthesized, and a content information of a text to be processed; generating an acoustic feature information of the text to be processed, by using a pre-trained speech synthesis model, based on the style information, the tone information, and the content information of the text to be processed; and synthesizing the speech for the text to be processed, based on the acoustic feature information of the text to be processed.
-
公开(公告)号：US20220019592A1
公开(公告)日：2022-01-20
申请号：US17449752
申请日：2021-10-01
Inventor： Xue YANG
IPC: G06F16/2457 , G06F16/215 , G06F16/28 , G06F16/22
Abstract: Provided are a data annotation method and apparatus, an electronic device and a storage medium which relate to the technical field of artificial intelligence and further relate to a data annotation technology. The method includes: determining a data annotation factor, where the data annotation factor includes a data annotation element and an annotation operation matrix; acquiring to-be-annotated data according to the data annotation element; and annotating the to-be-annotated data according to the annotation operation matrix.
-
公开(公告)号：US20220012529A1
公开(公告)日：2022-01-13
申请号：US17485776
申请日：2021-09-27
Abstract: This application discloses a map display method and apparatus, where the method includes: obtaining an initial image, where a first road is included in the initial image. The initial image is divided into a first sub-image and a second sub-image, where the first road is not included in the first sub-image, and the first road is included in the second sub-image. The first sub-image is mapped to a first plane of a transition model, and the second sub-image is mapped to a second plane of the transition model, where there is an included angle between the first plane and the second plane, and the first plane is parallel to a screen of a display device. The second plane is controlled to move by means of the transition model, until the included angle is reduced from a first angle to a second angle, and a three-dimensional map display animation is obtained.
-
公开(公告)号：US20220011136A1
公开(公告)日：2022-01-13
申请号：US17487363
申请日：2021-09-28
Inventor： Yan Zeng , Junliang Deng , Xiuwei Lin , Shengfeng Liang , Gaopeng Mo , Geli Guo
Abstract: This application discloses a road data processing method, an apparatus, a device and a storage medium, and relates to the technical fields of intelligent traffic in data processing, big data and cloud computing. The specific implementation solution is: obtaining shape information of a target road and shape information of a reference road; generating a first segment sequence according to the shape information of the target road; generating a second segment sequence according to the shape information of the reference road; and recognizing parallel road segments in the target road and the reference road according to the first segment sequence and the second segment sequence. Thus, by converting the target road and the reference road into sequences of segments respectively, parallel road segments are recognized in the target road and the reference road based on the sequences of segments, the efficiency and accuracy are improved in recognizing parallel roads.
-
Patent Agency Ranking
276.发明申请公开(公告)号：US20220004930A1
公开(公告)日：2022-01-06
申请号：US17480292
申请日：2021-09-21
Inventor： Qingqing DANG , Kaipeng DENG , Lielin JIANG , Sheng GUO , Xiaoguang HU , Chunyu ZHANG , Yanjun MA , Tian WU , Haifeng WANG
Abstract: Embodiments of the present disclosure provide a method and apparatus of training a model, an electronic device, a storage medium and a development system, which relate to a field of deep learning. The method may include calling a training preparation component to set at least a loss function and an optimization function for training the model, in response to determining that a training preparation instruction is received. The method further includes calling a training component to set a first data reading component, in response to determining that a training instruction is received. The first data reading component is configured to load a training data set for training the model. In addition, the method may further include training the model based on the training data set from the first data reading component, by using the loss function and the optimization function through the training component.
-
公开(公告)号：US20220004811A1
公开(公告)日：2022-01-06
申请号：US17479061
申请日：2021-09-20
Inventor： Ruoyu GUO , Yuning DU , Weiwei LIU , Xiaoting YIN , Qiao ZHAO , Qiwen LIU , Ran BI , Xiaoguang HU , Dianhai YU , Yanjun MA
IPC: G06K9/62
Abstract: There is provided a method and apparatus of training a model, a device, and a medium, which relate to artificial intelligence, and in particular to a deep learning and image processing technology. The method may include: determining a plurality of augmented sample sets associated with a plurality of original samples; determining a first constraint according to a first model based on the plurality of augmented sample sets; determining a second constraint according to the first model and a second model based on the plurality of augmented sample sets, wherein the second constraint is associated with a difference between outputs of the first model and the second model for one augmented sample, and the first model has a complexity lower than that of the second model; training the first model based on at least the first constraint and the second constraint, so as to obtain a trained first model.
-
公开(公告)号：US20210406981A1
公开(公告)日：2021-12-30
申请号：US17036155
申请日：2020-09-29
Inventor： Jiamei KANG , Shengran CHE , Hanyao SHAO
Abstract: The present disclosure discloses a method and apparatus of determining a display page, an electronic device and a medium, which relates to a field of information recommendation and may be used in fields of deep learning, cloud computing and cloud service. The specific implementation scheme includes: acquiring attribute information of a user, wherein the attribute information includes position information; determining, based on the position information, at least one first information category for the user in a preset first information dimension; acquiring recommendation information classified into each first information category of the at least one first information category; and determining the display page for the user based on the preset first information dimension, the at least one first information category, and the recommendation information classified into the each first information category.
-
279.发明申请公开(公告)号：US20210406579A1
公开(公告)日：2021-12-30
申请号：US17468848
申请日：2021-09-08
Inventor： Tianwei Lin , Dongliang He , Fu Li
Abstract: The present disclosure provides a model training method, an identification method, device, storage medium and program product, relating to computer vision technology and deep learning technology. In the solution provided by the present application, the image is deformed by the means of deforming the first training image without label itself, and the first unsupervised identification result is obtained by using the first model to identify the image before deformation, and the second unsupervised identification result is obtained by using the second model to identify the image after deformation, and the first unsupervised identification result of the first model is deformed, thus a consistency loss function can be constructed according to the second unsupervised identification result and the scrambled identification result. In this way, it is able to enhance the constraint effect of the consistency loss function and avoid destroying the scene semantic information of the images used for training.
-
280.发明申请公开(公告)号：US20210406067A1
公开(公告)日：2021-12-30
申请号：US17184723
申请日：2021-02-25
Inventor： He QI , Yazhi WANG
Abstract: The present disclosure provides a distributed storage method, involving the technical fields of computer and cloud computing, and including: reading and sending data to an external shuffle service in response to a request of a task from a driver thread; modifying a state of the task to a waiting-for-completion state after finishing sending the data to the external shuffle service; and sending the waiting-for-completion state to the driver thread, to cause the driver thread to release an executor thread corresponding to the task. The distributed storage method can reduce the waste of the resources of the executor thread and improves the efficiency of task operations. The present disclosure also provides an electronic apparatus, and a non-transitory computer-readable storage medium.
-
-
-
-
-
-
-
-
-
Search Results
1522
records
(took 0.141 seconds)
