-
公开(公告)号:US11827202B2
公开(公告)日:2023-11-28
申请号:US17189899
申请日:2021-03-02
Inventor: Yinong Tan , Xiao Cui , Dingfeng Guo , Zhenguang Zhu
CPC classification number: B60W30/02 , B60W10/04 , B60W10/18 , B60W40/10 , B60W2520/26 , B60W2530/20 , B60W2540/10 , B60W2540/12 , B60W2540/16 , B60W2540/18
Abstract: The disclosure discloses a method and an apparatus for simulating a vehicle. The detailed implementation includes: determining, by a tire dynamics module, a tire translational force at a current moment based on a control instruction issued by an upper planning module and motion data of a vehicle body and a tire normal load outputted by a vehicle body dynamics module at a previous moment; and determining, by the vehicle body dynamics module, motion data of the vehicle body and a tire normal load at the current moment based on the control instruction and the tire translational force at the current moment, the motion data of the vehicle body at the current moment being used for vehicle simulation, and the tire normal load at the current moment being used to determine a tire translational force at a next moment.
-
公开(公告)号:US11798193B2
公开(公告)日:2023-10-24
申请号:US17211001
申请日:2021-03-24
IPC: G06T7/90 , G06T7/00 , G06V10/80 , G06V10/82 , G06V20/10 , G06V40/16 , G06V10/25 , G06V10/56 , G06V10/98
CPC classification number: G06T7/90 , G06T7/97 , G06V10/809 , G06V10/82 , G06V20/10 , G06V40/162 , G06T2207/20081 , G06V10/25 , G06V10/56 , G06V10/993 , G06V40/161
Abstract: An image detection method and apparatus, an electronic device and a storage medium are provided, which relate to the fields of artificial intelligence, deep learning and image processing. The image detection method comprises: performing an acquisition processing on a to-be-detected imaging image to obtain an acquired image; extracting feature data of a target object in the acquired image through a preset image detection network in response to detection processing; performing a multi-dimensional detection comprising at least an imaging content indicator and a color bar indicator on the feature data of the target object according to the image detection network to obtain a detection result; wherein the target object includes imaging contents and color bars which are used to describe color information related to the imaging contents.
-
23.
公开(公告)号:US11797607B2
公开(公告)日:2023-10-24
申请号:US17211612
申请日:2021-03-24
Inventor: Huan Liu , Mingquan Cheng , Kunbin Chen , Zhun Liu , Bolei He , Wei He
IPC: G06F16/901 , G06F18/21 , G06F18/25 , G06F18/2132 , G06F40/30 , G06T7/00 , G06V30/413 , G06V30/40 , G06V30/18 , G06V30/19 , G06V10/82 , G06V30/10
CPC classification number: G06F16/901 , G06F18/217 , G06F18/253 , G06F40/30 , G06T7/0002 , G06V10/82 , G06V30/18057 , G06V30/19173 , G06V30/40 , G06V30/413 , G06F18/2132 , G06T2207/30168 , G06T2207/30176 , G06V30/10
Abstract: Embodiments of the present disclosure disclose a method and apparatus for constructing a quality evaluation model, an electronic device and a computer-readable storage medium. A specific implementation mode of the method comprises: acquiring samples of knowledge contents; extracting statistical features, semantic features, and image features respectively from the samples of knowledge contents; and constructing a quality evaluation model for knowledge according to the statistical features, the semantic features, and the image features. On the basis of the prior art, this implementation mode additionally uses semantic features and image features of knowledge contents to construct a more accurate quality evaluation model based on multi-dimensional features that characterize the actual quality of a knowledge, which may well discover some brief but very useful summary knowledge in an enterprise and may recommend high-quality knowledge more accurately for employees in the enterprise.
-
公开(公告)号:US11789985B2
公开(公告)日:2023-10-17
申请号:US17480780
申请日:2021-09-21
Inventor: Shuangli Li , Jingbo Zhou , Tong Xu , Hui Xiong
IPC: G06F16/29 , G06F16/9536
CPC classification number: G06F16/29 , G06F16/9536
Abstract: A method for determining a competitive relation of Points of Interest (POI), and a device are provided in the present disclosure. The specific implementation includes: determining POI representation data between two target POIs based on service-related data of the target POIs; and determining a competitive relation between the target POIs based on the POI representation data.
-
公开(公告)号:US11783570B2
公开(公告)日:2023-10-10
申请号:US17215563
申请日:2021-03-29
Inventor: Dayun Shen
IPC: B60W60/00 , G06V10/774 , G06V20/58 , G06V20/56 , G06V20/05
CPC classification number: G06V10/774 , B60W60/001 , G06V20/05 , G06V20/58 , G06V20/588 , B60W2420/403 , B60W2552/53
Abstract: Exemplary embodiments of the present disclosure provide a method and apparatus for determining road information data and a computer storage medium, which may be used for autonomous driving, road information prediction, and driving route planning. The method for determining road information data includes: determining, via a precision navigation device of a vehicle, a plurality of locations of the vehicle; acquiring, via a sensor of the vehicle, a plurality of image frames of a physical environment where the vehicle is located; determining, from the plurality of locations, a target location corresponding to at least one image frame among the plurality of image frames; and determining, based on the determined target location and a map related to the physical environment, road information data corresponding to the at least one image frame. According to the solution of the present disclosure, road information annotation data may be accurately and efficiently generated.
-
公开(公告)号:US11783227B2
公开(公告)日:2023-10-10
申请号:US16998616
申请日:2020-08-20
Inventor: Xingjian Li , Haoyi Xiong , Jun Huan
IPC: G06N20/00 , G06N3/08 , G06F11/34 , G05B13/04 , G06F18/214
CPC classification number: G06N20/00 , G05B13/042 , G06F11/3452 , G06F18/214 , G06N3/08
Abstract: A method, apparatus, device and readable medium for transfer learning in machine learning are provided. The method includes: constructing a target model according to the number of classes to be achieved by a target task and a duly-trained source model; obtaining a value of a regularized loss function of the corresponding target model and a value of a cross-entropy loss function of the target model, based on sets of training data in a training dataset of the target task; according to the value of the regularized loss function and the value of the cross-entropy loss function corresponding to each set of training data, updating parameters in the target model by a gradient descent method to implement the training of the target model. The above technical solution avoids excessive constraints on parameters in the prior art, thereby refraining from damaging the training effect of the source model on the target task.
-
公开(公告)号:US11781790B2
公开(公告)日:2023-10-10
申请号:US17206727
申请日:2021-03-19
Inventor: Zhiming Luo , Yiyi Duan , Bin Yi , Xiaozhong Li
Abstract: A refrigeration system is provided. The refrigeration system includes: an indoor heat exchange module configured for refrigerant to absorb heat; outdoor heat exchange modules for the refrigerant to dissipate heat. The outdoor heat exchange module includes a compression device and a condensing device; the outdoor heat exchange module is switchable between an active mode and a standby mode; in the active mode, the outdoor heat exchange module is connected to the indoor heat exchange module; in the standby mode, the outdoor heat exchange module is disconnected from the indoor heat exchange module, and the compression device of the outdoor heat exchange module is in an operation status.
-
公开(公告)号:US11775766B2
公开(公告)日:2023-10-03
申请号:US17249718
申请日:2021-03-10
Inventor: Xuyi Chen , Shiwei Huang
Abstract: Embodiments of a method and an apparatus for improving a model based on a pre-trained semantic model are provided. The method may include: based on the pre-trained semantic model, obtaining an initial improved model, where semantic result information of an input vector is determined in the initial improved model based on a hash search method; and based on a model distillation method, training the initial improved model to obtain an improved model. Some embodiments can obtain the semantic result information of the input vector by performing the hash search method on the input vector, replace the original complex iterative calculation process of a semantic model, and obtain the improved model with few model parameters and high compression ratio.
-
公开(公告)号:US11767029B2
公开(公告)日:2023-09-26
申请号:US17032090
申请日:2020-09-25
Inventor: Zhiyuan Chen , Xiaoxin Fu , Lin Ma , Xujian Li , Zhenguang Zhu
IPC: B60W30/095 , B60W60/00 , B60W30/09 , B60W40/072 , B60W40/12 , G06V20/58
CPC classification number: B60W60/0011 , B60W30/09 , B60W30/0953 , B60W40/072 , B60W40/12 , G06V20/58 , B60W2554/801
Abstract: Embodiments of the present disclosure provide a bend driving control method for an autonomous vehicle, a device and a storage medium, and relate to a field of perception and autonomous driving technologies. The method includes: obtaining an occupancy width of an autonomous vehicle on a target bend when the autonomous vehicle drives on the target bend; detecting location information of an obstacle on the target bend; and controlling a driving route of the autonomous vehicle on the target bend based on the occupancy width and the location information of the obstacle.
-
公开(公告)号:US20230290347A1
公开(公告)日:2023-09-14
申请号:US17622402
申请日:2021-06-02
Inventor: Jizhou HUANG , Shiqiang DING
IPC: G10L15/22 , G10L15/30 , G10L15/18 , G06F16/9032
CPC classification number: G10L15/22 , G10L15/30 , G10L15/1815 , G06F16/90332 , G10L2015/223
Abstract: Technical solutions relate to the fields of artificial intelligence technologies and voice technologies. A technical solution includes: performing voice recognition and demand analysis on a voice instruction input by a user; in response to an unknown demand obtained by the demand analysis, acquiring information of a query entity and query content using a result of the demand analysis, and acquiring reply information corresponding to the query content by communication with the query entity; and returning a first voice response to the user using the reply information.
-
-
-
-
-
-
-
-
-