-
241.发明申请公开(公告)号：US20220148324A1
公开(公告)日：2022-05-12
申请号：US17581047
申请日：2022-01-21
Inventor： Xiameng QIN , Yulin Li , Ju Huang , Qunyi Xie , Chengquan Zhang , Kun Yao , Jingtuo Liu , Junyu Han
IPC: G06V30/18 , G06V30/24 , G06V30/148 , G06V30/19
Abstract: Provided are a method and apparatus for extracting information about a negotiable instrument, an electronic device and a storage medium. The method includes inputting a to-be-recognized negotiable instrument into a pretrained deep learning network and obtaining a visual image corresponding to the to-be-recognized negotiable instrument through the deep learning network;
matching the visual image corresponding to the to-be-recognized negotiable instrument with a visual image corresponding to each negotiable-instrument template in a preconstructed base template library; and in response to the visual image corresponding to the to-be-recognized negotiable instrument successfully matching a visual image corresponding to one negotiable-instrument template in the base template library, extracting structured information of the to-be-recognized negotiable instrument by using the negotiable-instrument template.-
公开(公告)号：US20220148190A1
公开(公告)日：2022-05-12
申请号：US17579425
申请日：2022-01-19
Inventor： Xiang LONG , Yan PENG , Honghui ZHENG , Zhuang JIA , Bin ZHANG , Xiaodi WANG , Pengcheng YUAN , Ying XIN , Yuan FENG , Shumin HAN
Abstract: The disclosure provides a method for detecting a change of a building, an apparatus for detecting a change of a building, an electronic device, a storage medium and a computer program product. The method includes: obtaining a remote-sensing image sequence of a to-be-detected region; obtaining a building probability map corresponding to each remote-sensing image in the remote-sensing image sequence; determining a sub-region located by each building in the to-be-detected region based on the building probability map corresponding to each remote-sensing image; for each building, determining an existence probability of the building in each remote-sensing image based on the sub-region located by the building and the building probability map corresponding to each remote-sensing image; and determining a change condition of the building based on the existence probability of the building in each remote-sensing image.
-
公开(公告)号：US20220147373A1
公开(公告)日：2022-05-12
申请号：US17580477
申请日：2022-01-20
Inventor： Tengfei Shan
IPC: G06F9/445
Abstract: Some embodiments of the present disclosure discloses a method and apparatus for acquiring information, relates to the technical field of information transmission and distributed network architecture. The method includes: determining, in response to receiving an instruction used to indicate to acquire configuration information, for each of a plurality of physical machines, a set of candidate processes of the physical machine; acquiring a first key value, and determining a target candidate process of the physical machine from the set of candidate processes based on the first key value; acquiring a second key value, and determining a target process from a plurality of target candidate processes determined based on the plurality of physical machines based on the second key value; and acquiring the configuration information using the target process.
-
公开(公告)号：US20220129966A1
公开(公告)日：2022-04-28
申请号：US17568886
申请日：2022-01-05
Inventor： Minfan LIN
IPC: G06Q30/06
Abstract: A method of transmitting a message, an electronic device, and a storage medium, which relate to a field of artificial intelligence technology, and in particular to an intelligent recommendation technology. The method includes: determining at least one object group corresponding to a target object from a plurality of object groups, based on at least one feature of the target object; acquiring at least one candidate message associated with the at least one object group within a predetermined time period, wherein each of the at least one candidate message indicates at least one candidate service to be recommended to an object in the at least one object group; selecting a target message from the at least one candidate message based on the at least one feature; and transmitting the target message to the target object, wherein the target message indicates at least one target service recommended to the target object.
-
公开(公告)号：US20220129768A1
公开(公告)日：2022-04-28
申请号：US17646851
申请日：2022-01-03
Inventor： Dongling XIAO , Yukun LI , Han ZHANG , Yu SUN , Hao TIAN , Hua WU , Haifeng WANG
IPC: G06N5/02
Abstract: The present disclosure provides a method and apparatus for training a model. The method can include: acquiring at least one paragraph text, each paragraph text comprising a plurality of fine-grained samples; processing a fine-grained sample in the each paragraph text to obtain a coarse-grained sample; annotating the coarse-grained sample in the each paragraph text and obscuring one coarse-grained sample using a mask of one fine-grained sample to obtain a training sample set, wherein the training sample set comprises a plurality of annotated texts, and each annotated text comprises at least one of a fine-grained sample or an annotated coarse-grained sample; and training a fine-grained model using the training sample set to obtain a trained fine-grained model, the fine-grained model being used to learn content of a previous fine grain size and predict content of an adjacent coarse grain size.
-
Patent Agency Ranking
公开(公告)号：US20220122338A1
公开(公告)日：2022-04-21
申请号：US17646319
申请日：2021-12-29
Inventor： Taotao Zhao
Abstract: A method for displaying a covering on a panoramic map image includes: acquiring covering information to be displayed, in which the covering information includes a plurality of coverings; acquiring a set of vertices of a maximum circumscribed polyhedron for each covering in a three-dimensional coordinate system of a panoramic scene; acquiring a mapped set of vertices of the maximum circumscribed polyhedron of each covering by mapping the set of vertices to a sphere; determining an overlapping result among the plurality of coverings based on the mapped set of vertices of each covering; and determining a target covering from the plurality of coverings based on the overlapping result, and displaying the target covering on the panoramic map image.
-
247.发明申请公开(公告)号：US20220114822A1
公开(公告)日：2022-04-14
申请号：US17559643
申请日：2021-12-22
Inventor： Chao MA , Jingshuai ZHANG , Qifan HUANG , Kaichun YAO , Peng WANG , Hengshu ZHU
IPC: G06V30/148 , G06V30/41 , G06V30/262 , G06V30/18
Abstract: A method, an apparatus, a device, a storage medium and a program product of performing a text matching are provided, which relate to a field of a computer technology, and in particular to natural language processing and deep learning technologies. The method includes: determining a word set and a plurality of semantic units from a text set, the word set is associated with a first predetermined attribute, and the text set contains a plurality of first texts indicating an object information and a plurality of second texts indicating an object demand information; generating a graph; and generating a final feature representation associated with the text set and the word set based on the graph and a graph convolution model, so as to perform the text matching.
-
公开(公告)号：US20220113793A1
公开(公告)日：2022-04-14
申请号：US17556564
申请日：2021-12-20
Inventor： Jingming WANG , Xiang GE , Xiantao CHEN , Meng XU
Abstract: The present disclosure provides a method for generating a reply message. The method includes: acquiring a current application scene of a user; acquiring a target object type in conversation with the user; generating at least one candidate reply content corresponding to the application scene and matching with the target object type in an expression style; and adjusting the expression style of the candidate reply content according to an expression style of the user on historical content, to generate at least one target reply content.
-
公开(公告)号：US20220113156A1
公开(公告)日：2022-04-14
申请号：US17560818
申请日：2021-12-23
Inventor： Lingguang WANG , Guocai BAI , Jiankang XIN
Abstract: The present disclosure relates to a method, an apparatus and a system for generating a real scene map. The method includes: performing recognition on an acquired panorama image to obtain a target frame for each point of interest in the panorama image, where the target frame is used for selecting a point of interest through a frame, and the target frame has a position attribute, determining relative position information of each target frame with respect to the panorama image according to the position attribute of each target frame, and embedding each target frame into a preset sphere model according to the relative position information of each target frame with respect to the panorama image to obtain a panorama sphere model, and rendering the panorama sphere model to obtain a real scene map.
-
250.发明申请公开(公告)号：US20220107791A1
公开(公告)日：2022-04-07
申请号：US17552151
申请日：2021-12-15
Inventor： Huanzhou WU , Huan WANG , Wei ZHOU , Tao LUO , Xiang LAN
Abstract: There is provided a method for compilation, an apparatus for compilation, an electronic device, a storage medium and a program product, which may be used in a field of source file compilation and a field of deep learning. The method includes: acquiring a source file set containing source files in a type; combining a plurality of source files in the source file set into at least one source file subset, based on a predetermined combination rule associated with the source file set; and compiling each source file subset of the at least one source file subset as a whole.
-
-
-
-
-
-
-
-
-
Search Results
1511
records
(took 0.041 seconds)
