公开(公告)号：US11802776B2

公开(公告)日：2023-10-31

申请号：US17212251

申请日：2021-03-25

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Hao Liu ,  Panpan Zhang ,  Jianguo Duan ,  Hui Xiong

IPC: G01C21/34 ,  G06Q10/02 ,  G06Q50/14

CPC classification number: G01C21/3484 ,  G01C21/343 ,  G01C21/3423 ,  G06Q10/02 ,  G06Q50/14

Abstract: A cross-regional travel recommendation method and apparatus, an electronic device and a storage medium are provided, which relates to the fields of intelligent transportation and deep learning. A specific implementation solution is: acquiring a travel request of a user, the travel request comprising a start point and an end point which are located in different regions; extracting user features according to the travel request of the user; and recommending at least one travel plan to the user according to the user features and a pre-trained cross-regional travel recommendation model. The technical solutions can make up for the deficiency of the existing technology, provide a cross-regional travel plan recommendation under a large-space scale and a multimodal environment through a pre-trained cross-regional travel recommendation model and user features extracted based on a travel request of a user, and can satisfy a cross-regional travel request of the user, and is highly practical.

公开(公告)号：US11790553B2

公开(公告)日：2023-10-17

申请号：US17355137

申请日：2021-06-22

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Yuchen Yuan

IPC: G06T7/73 ,  G06T7/77 ,  G06N3/04 ,  G06V20/40 ,  G06V20/52 ,  G06V10/764 ,  G06V10/82 ,  G06V40/10

CPC classification number: G06T7/73 ,  G06N3/04 ,  G06T7/77 ,  G06V10/764 ,  G06V10/82 ,  G06V20/46 ,  G06V20/52 ,  G06V40/103 ,  G06T2207/10016 ,  G06T2207/30241 ,  G06V2201/07

Abstract: Embodiments of the present disclosure provide a method and apparatus for detecting a target object, an electronic device, and a computer readable storage medium. The method may include: acquiring a to-be-detected image; processing the to-be-detected image using an object detection model including a deformable convolutional layer to obtain an offset prediction result of the deformable convolutional layer; and adjusting a size of an anchor point using the offset prediction result, and determining position information of the target object in the to-be-detected image using the anchor point of the adjusted size.

公开(公告)号：US11783565B2

公开(公告)日：2023-10-10

申请号：US17241191

申请日：2021-04-27

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Yuexiang Hu ,  Renyi Zhou ,  Junyu Han

IPC: G06K9/62 ,  G06V10/44 ,  G06F16/58 ,  G06V40/16 ,  G06V20/40

CPC classification number: G06V10/443 ,  G06F16/5866 ,  G06V20/46 ,  G06V40/166 ,  G06V40/169 ,  G06V40/172

Abstract: An image processing method, an electronic device and a readable storage medium, which relate to the technical field of computer vision, are disclosed. In an embodiment, a face recognition module and a service processing module maintains respectively an image buffer queue; the face recognition module maintains a face image buffer queue of face images, and the service processing module maintains a background image buffer queue of background images, i.e., first images; since the face recognition module only maintains the face image buffer queue, only a determined optimal face image, i.e., a face image to be matched, is transmitted to the service processing module, and then, the service processing module determines a background image matched with the optimal face image transmitted by the face recognition module from the maintained background image buffer queue, thus performing image recognition and image matching on a face appearing in a video source.

公开(公告)号：US11775845B2

公开(公告)日：2023-10-03

申请号：US17209380

申请日：2021-03-23

Applicant: Beijing Baidu Netcom Science and Technology Co., LTD

Inventor： Xiaoqiang Zhang ,  Chengquan Zhang ,  Shanshan Liu

IPC: G06N5/00 ,  G06N5/022 ,  G06V30/148 ,  G06V30/262 ,  G06V30/18 ,  G06V30/196 ,  G06V10/764 ,  G06V20/62 ,  G06V30/10

CPC classification number: G06N5/022 ,  G06V10/764 ,  G06V20/62 ,  G06V30/153 ,  G06V30/18181 ,  G06V30/1988 ,  G06V30/274 ,  G06V30/10

Abstract: A character recognition method, a character recognition apparatus, an electronic device and a computer readable storage medium are disclosed. The character recognition method includes: determining semantic information and first position information of each individual character recognized from an image; constructing a graph network according to the semantic information and the first position information of each individual character; and determining a character recognition result of the image according to a feature of each individual character calculated by the graph network.

公开(公告)号：US11775776B2

公开(公告)日：2023-10-03

申请号：US17147881

申请日：2021-01-13

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Shuangjie Li ,  Miao Yu ,  Yabing Shi ,  Xuefeng Hao ,  Xunchao Song ,  Ye Jiang ,  Yang Zhang ,  Yong Zhu

IPC: G06F40/40 ,  G06N20/00 ,  G06F40/289

CPC classification number: G06F40/40 ,  G06F40/289 ,  G06N20/00

Abstract: A method and an apparatus for processing information are provided. The method can include: acquiring a word sequence obtained by performing word segmentation on two paragraphs in a text; inputting the word sequence into a to-be-trained natural language processing model to generate a word vector corresponding to a word in the word sequence; inputting the word vector into a preset processing layer of the to-be-trained natural language processing model; predicting whether the two paragraphs are adjacent, and a replaced word in the two paragraphs; and acquiring reference information of the two paragraphs, and training the to-be-trained natural language processing model to obtain a trained natural language processing model, based on the prediction result and the reference information.

公开(公告)号：US11775309B2

公开(公告)日：2023-10-03

申请号：US17423144

申请日：2020-11-26

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Yang Peng ,  Hao Yang ,  Jing Zou ,  Lei Feng ,  Hongliang Sui

IPC: G06F9/44 ,  G06F9/38 ,  G06F9/54

CPC classification number: G06F9/3861 ,  G06F9/546 ,  G06F2209/547

Abstract: The present disclosure provides an exception stack handling method, system, electronic device and storage medium and relates to the field of mobile Internet. The method may include: at the level of any executor in a distributed stream-type processing system including at least two executors, performing the following processing of: obtaining at least one exception stack from a message middleware when the executor in an idle state each time, collected exception stacks generated by users being stored in the message middleware; as for any exception stack, obtaining an anti-obfuscation map file corresponding to the exception stack, and performing anti-obfuscation processing for the exception stack by using the anti-obfuscation map file. The solution of the present disclosure may be applied to improve the processing speed.

公开(公告)号：US11769480B2

公开(公告)日：2023-09-26

申请号：US17111238

申请日：2020-12-03

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Zhengkun Gao ,  Junteng Zhang ,  Wenfu Wang ,  Tao Sun

IPC: G10L13/00 ,  G10L13/047 ,  G10L13/06 ,  G10L13/10

CPC classification number: G10L13/047 ,  G10L13/06 ,  G10L13/10

Abstract: The present disclosure discloses a method and apparatus for training a model, a method and apparatus for synthesizing a speech, a device and a storage medium, and relates to the field of natural language processing and deep learning technology. The method for training a model may include: determining a phoneme feature and a prosodic word boundary feature of sample text data; inserting a pause character into the phoneme feature according to the prosodic word boundary feature to obtain a combined feature of the sample text data; and training an initial speech synthesis model according to the combined feature of the sample text data, to obtain a target speech synthesis model.

公开(公告)号：US11755940B2

公开(公告)日：2023-09-12

申请号：US17020527

申请日：2020-09-14

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Lijing Jin ,  Runyao Duan

IPC: G06N10/00 ,  H10N60/12 ,  H10N69/00

CPC classification number: G06N10/00 ,  H10N60/12 ,  H10N69/00

Abstract: A superconducting circuit structure, a superconducting quantum chip, and a superconducting quantum computer are provided, which relate to the field of quantum computing. The superconducting circuit structure includes: at least two qubits; a connector, coupled with the two qubits respectively, to realize transversal coupling with each of the two qubits; and a coupler, coupled with the two qubits respectively, to realize longitudinal coupling with each of the two qubits. Therefore, the σzσz parasitic coupling between the qubits is effectively removed, and a two-qubit gate with high fidelity is obtained.

公开(公告)号：US11748895B2

公开(公告)日：2023-09-05

申请号：US17184379

申请日：2021-02-24

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Tianwei Lin ,  Xin Li ,  Fu Li ,  Dongliang He ,  Hao Sun ,  Henan Zhang

IPC: G06K9/00 ,  G06T7/246 ,  G06N3/04 ,  G06V20/40 ,  G06F18/25

CPC classification number: G06T7/246 ,  G06F18/253 ,  G06N3/04 ,  G06V20/41 ,  G06V20/46

Abstract: A method and apparatus for processing a video frame are provided. The method may include: converting, using an optical flow generated based on a previous frame and a next frame of adjacent frames in a video, a feature map of the previous frame to obtain a converted feature map; determining, based on an error of the optical flow, a weight of the converted feature map, and obtaining a fused feature map based on a weighted result of a feature of the converted feature map and a feature of a feature map of the next frame; and updating the feature map of the next frame as the fused feature map.

公开(公告)号：US11743209B2

公开(公告)日：2023-08-29

申请号：US17792867

申请日：2021-08-05

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Xiaoping Yan

IPC: H04L49/9057 ,  G06F3/06 ,  H04L45/74 ,  H04L49/90

CPC classification number: H04L49/9057 ,  G06F3/061 ,  G06F3/0635 ,  G06F3/0679 ,  H04L45/74 ,  H04L49/9063

Abstract: A processor, processor implementation method, and a storage medium are disclosed, which relates to the field of artificial intelligence and deep learning. The processor includes: a system controller a data packing and unpacking module, a storage array module, and an operation module configured to perform operation processing on the acquired first packet, generate the second packet according to the operation result data, and return the second packet to the data packing and unpacking module. The storage array module comprises N1 storage units. The data packing and unpacking module comprises N2 data packing and unpacking units, each of the data packing and unpacking units is connected to the routing and switching module through a data channel. The universal operation module comprises M operation units. The activation operation module comprises P operation unit, each of the operation units is connected to the routing and switching module through a data channel.