-
公开(公告)号：US20230195988A1
公开(公告)日：2023-06-22
申请号：US18108585
申请日：2023-02-11
Inventor： Kehui YU , Lijing Jin
Abstract: A method is provided. The method includes: obtaining a parameter value of a determined dimension parameter, an initial parameter value of a dimension parameter to be optimized, and a target capacitance value of an interdigital capacitor; partitioning a geometric structure of the interdigital capacitor to obtain a plurality of sections of the interdigital capacitor, where the plurality of sections are in a one-to-one correspondence with a plurality of coplanar multiple-transmission line models; obtaining a capacitance value expression of the interdigital capacitor based on the plurality of coplanar multiple-transmission line models; determining, based on the parameter value of the determined dimension parameter, the target capacitance value, and the capacitance value expression of the interdigital capacitor, a loss function including the dimension parameter to be optimized; and optimizing, based on the initial parameter value by minimizing the loss function, the parameter value of the dimension parameter to be optimized.
-
公开(公告)号：US11682014B2
公开(公告)日：2023-06-20
申请号：US17806461
申请日：2022-06-10
Inventor： Chunhui Wan , Tong Jin
CPC classification number: G06Q20/401 , G06Q20/381 , G06Q20/389
Abstract: Provided are a method and apparatus for operating a blockchain system, a device and a storage medium. The method is described below. To-be-processed blockchain data is acquired through a kernel engine of the blockchain system. The to-be-processed blockchain data is processed through the kernel engine, a consensus component call request is generated according to a consensus component interface during a processing process of the to-be-processed blockchain data, and a corresponding consensus component is called according to the consensus component call request, where the corresponding consensus component is configured to execute a consensus mechanism between blockchain nodes.
-
公开(公告)号：US20230186536A1
公开(公告)日：2023-06-15
申请号：US17851484
申请日：2022-06-28
Inventor： Kailong YAN , Juntao TONG , Changjun SHENG , Yingjie NIU
CPC classification number: G06T11/60 , G01C21/3878 , G06F16/29
Abstract: The present disclosure provides a map data processing method, an electronic device and a storage medium, relates to a technical field of data processing, and in particular to the field of map data processing. A specific implementation solution is as follows: receiving first data encapsulated in a form of offline data, the first data being used to characterize low-frequency data in the map data; obtaining second data after initiating a first online request, the second data being used to characterize high-frequency data in the map data; and performing merging processing on the first data and the second data to obtain target data to be displayed in a map. By adopting the present disclosure, the timeliness of map data display may be improved.
-
公开(公告)号：US20230177821A1
公开(公告)日：2023-06-08
申请号：US18063564
申请日：2022-12-08
Inventor： Qiming PENG , Bin LUO , Yuhui CAO , Shikun FENG , Yongfeng CHEN
CPC classification number: G06V10/82 , G06V30/19147 , G06V30/1444
Abstract: A neural network training method and a document image understanding method is provided. The neural network training method includes: acquiring text comprehensive features of a plurality of first texts in an original image; replacing at least one original region in the original image to obtain a sample image including a plurality of first regions and a ground truth label for indicating whether each first region is a replaced region; acquiring image comprehensive features of the plurality of first regions; inputting the text comprehensive features of the plurality of first texts and the image comprehensive features of the plurality of first regions into a neural network model together to obtain text representation features of the plurality of first texts; determining a predicted label based on the text representation features of the plurality of first texts; and training the neural network model based on the ground truth label and the predicted label.
-
115.发明公开公开(公告)号：US20230177756A1
公开(公告)日：2023-06-08
申请号：US18075346
申请日：2022-12-05
Inventor： Zhe PENG , Yuqiang LIU , Fanyu GENG
CPC classification number: G06T13/40 , G06T7/20 , G10L25/57 , G10L15/063 , G10L15/02 , G10L15/16 , G06T2207/30201 , G06T2207/20084 , G06T2207/20081
Abstract: A method of generating a 3D video, a method of training a neural network model, an electronic device, and a storage medium, which relate to a field of image processing, and in particular to technical fields of computer vision, augmented/virtual reality and deep learning. The method includes: determining, based on an input speech feature, a principal component analysis (PCA) coefficient by using a first network, wherein the PCA coefficient is used to generate the 3D video; correcting the PCA coefficient by using a second network; generating a lip movement information based on the corrected PCA coefficient and a PCA parameter for a neural network model, wherein the neural network model includes the first network and the second network; and applying the lip movement information to a pre-constructed 3D basic avatar model to obtain a 3D video with a lip movement effect.
-
Patent Agency Ranking
公开(公告)号：US20230175859A1
公开(公告)日：2023-06-08
申请号：US18063705
申请日：2022-12-09
Inventor： Qiuyang Xu , Tingting Cao , Zhen Lu
CPC classification number: G01C21/3815 , G06V20/182 , G01C21/3837
Abstract: A method for discovering a newly added road, includes: determining trajectory data in a target area within a preset time period, in which the trajectory data includes a plurality of trajectories and attribute information of each trajectory point in respective trajectories; determining trajectory features of a plurality of grids in the target area, according to the plurality of trajectories, the attribute information of each trajectory point in respective trajectories, and position features of the plurality of grids; generating current grid portrait data of the target area, according to the position features and trajectory features of the plurality of grids; and determining newly added road information of the target area, according to the current grid portrait data and historical grid portrait data of the target area.
-
公开(公告)号：US11667285B2
公开(公告)日：2023-06-06
申请号：US17234644
申请日：2021-04-19
Inventor： Ruisuo Wang , Xiaobo Ma
IPC: B60W30/14
CPC classification number: B60W30/14 , B60W2520/10 , B60W2554/4041 , B60W2554/802 , B60W2555/20
Abstract: The present disclosure relates to adaptive cruise control in the field of automatic driving, and discloses a vehicle control method, an apparatus, an electronic device and a storage medium. A specific implementation is: firstly, determining a target travelling scenario according to real-time monitoring data upon fulfilment of a preset update condition; then, determining a target time headway according to the target travelling scenario, where the target time headway is used to dynamically adjust a relative motion state between an host vehicle and a surrounding vehicle; and finally, controlling a vehicle according to the target time headway. It solves the problem of the prior art in overemphasizing the state of the vehicle ahead for automatic driving control while overlooking the perception of the driver or passenger of the host vehicle in the travelling scenario can prompt the driver to manually intervene, compromising the experience of the automatic driving.
-
公开(公告)号：US20230161664A1
公开(公告)日：2023-05-25
申请号：US18157429
申请日：2023-01-20
Inventor： Zhigang ZENG , Zhenyuan SUN , Bingqing SHAO , Pengfei YAN , Shiyong LI , Yanpeng WANG
IPC: G06F11/07
CPC classification number: G06F11/0793 , G06F11/079 , G06F11/0709
Abstract: A method of responding to an operation, an electronic device and a storage medium are provided, which relate to a field of cloud computing, and in particular to a field of cluster technology. The specific implementation solution includes: performing, in response to determining that a target operation performed by a target client on a shared resource has timed out, a fault detection on the target client to obtain a fault detection result; and implementing, in response to determining that the fault detection result represents that the target client has a fault, an update operation to obtain a target authority identifier, so that the target client is prevent from continuing to perform the target operation by using the target authority identifier.
-
公开(公告)号：US20230154163A1
公开(公告)日：2023-05-18
申请号：US18151108
申请日：2023-01-06
Inventor： Zhuang Jia , Xiang Long , Yan Peng , Honghui Zheng , Bin Zhang , Yunhao Wang , Ying Xin , Chao Li , Xiaodi Wang , Song Xue , Yuan Feng , Shumin Han
IPC: G06V10/774 , G06V10/58 , G06V10/764 , G06V10/776 , G06V20/70 , G06V10/77
CPC classification number: G06V10/774 , G06V10/58 , G06V10/764 , G06V10/776 , G06V20/70 , G06V10/7715
Abstract: A method for recognizing a category of an image includes: acquiring a spectral image; training an image recognition model based on the spectral image, in which the image recognition model acquires a spectral semantic feature of each pixel, a minimum distance between each pixel and each category, and a spectral distance between a first spectrum of each pixel and a second spectrum of each category; splices them; and performs classification and recognition based on the spliced feature to output a recognition probability of each pixel under each category; determining a loss function of the image recognition model, adjusting the image recognition model based on the loss function, and returning to training the adjusted image recognition model based on the spectral image until training ends; recognizing a maximum recognition probability, output from a target image recognition model, and using a category corresponding to the maximum recognition probability as a target category.
-
120.发明公开公开(公告)号：US20230154077A1
公开(公告)日：2023-05-18
申请号：US17682295
申请日：2022-02-28
Inventor： Licheng TANG , Jiaming LIU
IPC: G06T11/20 , G06F40/109
CPC classification number: G06T11/203 , G06F40/109
Abstract: Provided is a training method for a character generation model. The training method for a character generation model includes: a first training sample is input into a target model to calculate a first loss, where the first training sample includes a first source domain sample word and a first target domain sample word, and content of the first source domain sample word is different from content of the first target domain sample word; a second training sample is input into the target model to calculate a second loss, where the second training sample includes a second source domain sample word and a second target domain sample word, content of the second source domain sample word is the same as content of the second target domain sample word; and a parameter of the character generation model is adjusted according to the first loss and the second loss.
-
-
-
-
-
-
-
-
-
Search Results
1470
records
(took 0.032 seconds)
