-
1.发明公开
公开(公告)号：EP4102498A1
公开(公告)日：2022-12-14
申请号：EP22164036.0
申请日：2022-03-24
发明人： ZHANG, Fuyu , LIU, Rong , WANG, Kun
摘要： Embodiments of the present disclosure provides a method and device for determining voice response speed, an electronic equipment, computer-readable storage medium, and computer program product, relate to the fields of artificial intelligence technology such as voice recognition, natural language processing, deep learning, and the like. The method comprises: reading a data stream constituting a test audio file, and determining a time point when a complete data stream is read as an interaction start time point; determining a voice instruction information contained in a complete data stream, and determining an execution time point of an action indicated by the voice instruction information as an interaction end time point; and determining the voice response speed based on the interaction start time point and the interaction end time point.
-
2.发明公开
公开(公告)号：EP4047583A2
公开(公告)日：2022-08-24
申请号：EP22180495.8
申请日：2022-06-22
发明人： YANG, Guoyi , ZHANG, Wen , YANG, Fan , WANG, Kun , HU, Maoyang
摘要： The present disclosure provides a method and an apparatus for controlling vehicle-infrastructure cooperated autonomous driving, an electronic device, a medium, a vehicle, and a cooperative vehicle-infrastructure system, and relates to the technical field of artificial intelligence, and in particular, to the technical field of autonomous driving and intelligent transportation. An implementation is: obtaining first detection information in a detectable range of a first vehicle; determining, based on the first detection information, that the first vehicle is in a jammed state on a current traveling lane; in response to determining that the first vehicle is in the jammed state on the current traveling lane, obtaining second detection information by using an infrastructure, where the second detection information includes information out of the detectable range of the first vehicle; and determining a control decision for the first vehicle at least based on the second detection information.
-
3.发明公开
公开(公告)号：EP3937125A2
公开(公告)日：2022-01-12
申请号：EP21204946.4
申请日：2021-10-27
发明人： MA, Wei , TAO, Ji , HU, Xing , WANG, Liqi , WANG, Kun
摘要： The present application discloses a method, an apparatus for superimposing laser point clouds and a high-precision map and an electronic device, and relates to the technical fields of artificial intelligence, autonomous driving, intelligent transportation, and computer vision. The specific implementation is: when superimposing the laser point clouds and the high-precision map for visualization, first performing dilution processing on non-road laser point clouds in the laser point clouds to be fused to obtain target non-road laser point clouds, which effectively reduces the amount of data of the laser point clouds to be fused; and performing segmentation processing on the map to be fused to obtain multi-level map data corresponding to the map to be fused, which effectively reduces the amount of data of the map to be fused. In this way, when superimposing the laser point clouds and the high-precision map for visualization, both non-road information may be visualized through the laser point clouds, and road information may be visualized through the high-precision map, not only digital city visualization is realized, but also the amount of visualized data is effectively reduced and the display effect of digital urbanization is improved.
-
公开(公告)号：EP3889545A2
公开(公告)日：2021-10-06
申请号：EP21183378.5
申请日：2021-07-02
发明人： WANG, Kun , RUI, Xiaofei , HU, Xing
摘要： The disclosure discloses a method and an apparatus for positioning a vehicle, a device, and a storage medium, and relates to a field of automatic driving and intelligent transportation. The method includes: obtaining a map related to a region, the region being a region where a positioning signal such as a GNSS signal is limited, such as a tunnel, the region including a plurality of positioning markers, and the map including positioning mark data corresponding to the plurality of positioning markers; capturing image data for the region when the vehicle travels through the region; and determining positioning information of the vehicle by matching the image data with the positioning mark data in the map based on an estimated posture of the vehicle. The map here can be a high-precision map. In this way, accurate positioning based on the positioning markers can be implemented, and the positioning accuracy can be improved.
-
5.发明公开
公开(公告)号：EP3937125A3
公开(公告)日：2022-06-08
申请号：EP21204946.4
申请日：2021-10-27
发明人： MA, Wei , TAO, Ji , HU, Xing , WANG, Liqi , WANG, Kun
摘要： The present application discloses a method, an apparatus for superimposing laser point clouds and a high-precision map and an electronic device, and relates to the technical fields of artificial intelligence, autonomous driving, intelligent transportation, and computer vision. The specific implementation is: when superimposing the laser point clouds and the high-precision map for visualization, first performing dilution processing on non-road laser point clouds in the laser point clouds to be fused to obtain target non-road laser point clouds, which effectively reduces the amount of data of the laser point clouds to be fused; and performing segmentation processing on the map to be fused to obtain multi-level map data corresponding to the map to be fused, which effectively reduces the amount of data of the map to be fused. In this way, when superimposing the laser point clouds and the high-precision map for visualization, both non-road information may be visualized through the laser point clouds, and road information may be visualized through the high-precision map, not only digital city visualization is realized, but also the amount of visualized data is effectively reduced and the display effect of digital urbanization is improved.
-
公开(公告)号：EP4198944A1
公开(公告)日：2023-06-21
申请号：EP22213481.9
申请日：2022-12-14
发明人： WANG, Kun
IPC分类号： G08G1/16 , G08G1/01 , G08G1/04 , G08G1/08 , G08G1/0965
摘要： The present disclosure provides a roadside sensing system and a traffic control method, relates to the technical field of artificial intelligence such as deep learning and intelligent transportation. An embodiment of the system includes: a basic supply facility, a roadside computing facility and a roadside sensing facility set on a target road section; the basic supply facility is connected to the roadside computing facility and the roadside sensing facility, and the basic supply facility is configured to provide basic supply to the roadside computing facility and the roadside sensing facility; the roadside sensing facility is configured to acquire roadside sensing information; and the roadside computing facility is configured to store and process the roadside sensing information to obtain sensing result information.
-
公开(公告)号：EP3889545A3
公开(公告)日：2022-05-18
申请号：EP21183378.5
申请日：2021-07-02
发明人： WANG, Kun , RUI, Xiaofei , HU, Xing
IPC分类号： G01C21/28 , G01C21/36 , G01C21/30 , G01C21/20 , G01C21/16 , G05D1/02 , G06T7/73 , G09B29/10 , B60W60/00
摘要： The disclosure discloses a method and an apparatus for positioning a vehicle, a device, and a storage medium, and relates to a field of automatic driving and intelligent transportation. The method includes: obtaining a map related to a region, the region being a region where a positioning signal such as a GNSS signal is limited, such as a tunnel, the region including a plurality of positioning markers, and the map including positioning mark data corresponding to the plurality of positioning markers; capturing image data for the region when the vehicle travels through the region; and determining positioning information of the vehicle by matching the image data with the positioning mark data in the map based on an estimated posture of the vehicle. The map here can be a high-precision map. In this way, accurate positioning based on the positioning markers can be implemented, and the positioning accuracy can be improved.
-
8.发明公开
公开(公告)号：EP3958256A2
公开(公告)日：2022-02-23
申请号：EP21213354.0
申请日：2021-12-09
发明人： WANG, Kun , HE, Xueyan , HE, Wence
IPC分类号： G10L15/32 , G06F3/16 , G10L15/30 , G10L15/183 , G10L15/22
摘要： The present application discloses a voice processing method for a vehicle-mounted device and relates to the voice technology, the vehicle networking technology and the intelligent vehicle technology in the field of artificial intelligence. The specific implementation is: acquiring a user voice; performing an offline recognition on the user voice to obtain an offline recognition text, and sending the user voice to a server for performing an online voice recognition and semantics parsing on the user voice; parsing, if there is a text matching the offline recognition text in a local text database, the offline recognition text to obtain an offline parsing result of the user voice; controlling the vehicle-mounted device according to the offline parsing result. Therefore, the present application improves the speech processing efficiency and ensures the accuracy of the speech processing of the vehicle-mounted device under the weak network scenario. The present application also discloses a voice processing apparatus, device and storage medium for a vehicle-mounted device.
-
9.发明公开
公开(公告)号：EP4047583A3
公开(公告)日：2022-12-07
申请号：EP22180495.8
申请日：2022-06-22
发明人： YANG, Guoyi , ZHANG, Wen , YANG, Fan , WANG, Kun , HU, Maoyang
IPC分类号： G08G1/01 , G08G1/04 , G08G1/0962 , G08G1/0967
摘要： The present disclosure provides a method and an apparatus for controlling vehicle-infrastructure cooperated autonomous driving, an electronic device, a medium, a vehicle, and a cooperative vehicle-infrastructure system, and relates to the technical field of artificial intelligence, and in particular, to the technical field of autonomous driving and intelligent transportation. An implementation is: obtaining first detection information in a detectable range of a first vehicle; determining, based on the first detection information, that the first vehicle is in a jammed state on a current traveling lane; in response to determining that the first vehicle is in the jammed state on the current traveling lane, obtaining second detection information by using an infrastructure, where the second detection information includes information out of the detectable range of the first vehicle; and determining a control decision for the first vehicle at least based on the second detection information.
-
10.发明公开
公开(公告)号：EP3958256A3
公开(公告)日：2022-06-15
申请号：EP21213354.0
申请日：2021-12-09
发明人： WANG, Kun , HE, Xueyan , HE, Wence
IPC分类号： G10L15/32 , G06F3/16 , H04W4/44 , G06F40/205 , G10L15/30 , G10L15/183 , G10L15/22
摘要： The present application discloses a voice processing method for a vehicle-mounted device and relates to the voice technology, the vehicle networking technology and the intelligent vehicle technology in the field of artificial intelligence. The specific implementation is: acquiring a user voice; performing an offline recognition on the user voice to obtain an offline recognition text, and sending the user voice to a server for performing an online voice recognition and semantics parsing on the user voice; parsing, if there is a text matching the offline recognition text in a local text database, the offline recognition text to obtain an offline parsing result of the user voice; controlling the vehicle-mounted device according to the offline parsing result. Therefore, the present application improves the speech processing efficiency and ensures the accuracy of the speech processing of the vehicle-mounted device under the weak network scenario. The present application also discloses a voice processing apparatus, device and storage medium for a vehicle-mounted device.
-
-
-
-
-
-
-
-
-
搜索结果
12 条记录 (耗时 0.015 秒)
