-
公开(公告)号：US20210232765A1
公开(公告)日：2021-07-29
申请号：US16988907
申请日：2020-08-10
Inventor： Han Zhang , Dongling Xiao , Yukun Li , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang
IPC: G06F40/274 , G06F40/30 , G06F40/56 , G06K9/62
Abstract: The present disclosure discloses a method and an apparatus for generating a text based on a semantic representation and relates to a field of natural language processing (NLP) technologies. The method for generating the text includes: obtaining an input text, the input text comprising a source text; obtaining a placeholder of an ith word to be predicted in a target text; obtaining a vector representation of the ith word to be predicted, in which the vector representation of the ith word to be predicted is obtained by calculating the placeholder of the ith word to be predicted, the source text and 1st to (i−1)th predicted words by employing a self-attention mechanism; and generating an ith predicted word based on the vector representation of the ith word to be predicted, to obtain a target text.
-
公开(公告)号：US10896188B2
公开(公告)日：2021-01-19
申请号：US16278651
申请日：2019-02-18
Inventor： Jizhou Huang , Wei Zhang , Yaming Sun , Haifeng Wang
IPC: G06F16/2457 , G06F16/248 , G06N3/04 , G06N3/08
Abstract: The present disclosure provides a method and apparatus for determining search results, a device and a computer storage medium, wherein the method comprises: obtaining a current query, a historical query sequence of the current query and candidate search results of the current query; inputting the current query, the historical query sequence of the current query and candidate search results of the current query into a search result-sorting model, scoring the candidate search results according to the search result-sorting model, and determining search results corresponding to the current query; wherein the scores rendered by the search result-sorting model for the candidate search results are determined according to a similarity degree between an integrated vector representation of the current query and the historical query sequence of the current query and vector representations of the candidate search results. The present disclosure can provide the user with search results which more accurately reflect the user's demands.
-
公开(公告)号：US10609133B2
公开(公告)日：2020-03-31
申请号：US15410188
申请日：2017-01-19
Inventor： Haifeng Wang , Weide Zhang , Zhuo Chen , Wei He , Kaiwen Feng , Jingchao Feng
Abstract: The present application discloses a method and device for establishing communication connection. An embodiment of the method includes: selecting a predetermined number of servers from a server cluster to form a backup server cluster, the server cluster including at least one server adapted to implement a given service; obtaining communication information of each backup server in the backup server cluster, and selecting a backup server from the backup server cluster as a master server based on the communication information of the backup server; and sending the communication information of the master server to controlled equipment controlled by the server cluster to establish communication connection between the master server and the controlled equipment. The embodiment solves a problem of reliability raised when main server abnormally quits or restarts during the operation of a system.
-
公开(公告)号：US20180077230A1
公开(公告)日：2018-03-15
申请号：US15409753
申请日：2017-01-19
Inventor： Haifeng Wang , Wei He , Yu Ma , Weide Zhang , Zhuo Chen , Jingchao Feng
CPC classification number: H04L67/1029 , H04L41/0668 , H04L43/0817 , H04L43/10 , H04L67/1023 , H04L67/1034 , H04L67/1095
Abstract: The present application discloses a method and apparatus for switching between servers in a server cluster. The server cluster includes at least one server for implementing a given service. A specific implementation of the method includes: detecting a number of servers in a standby state in the server cluster; starting at least one server in the server cluster so that the number of servers in the standby state reaches a predetermined number, in response to detecting the number of servers in the standby state being less than the predetermined number; monitoring a master server for providing a service in the server cluster; and selecting a server from the servers in the standby state as a master server to continue to provide the service, in response to detecting the master server being abnormal. This implementation solves the data loss problem caused by an abnormal termination or restart of the master server.
-
公开(公告)号：US20180074176A1
公开(公告)日：2018-03-15
申请号：US15411927
申请日：2017-01-20
Inventor： Kaiwen Feng , Zhuo Chen , Bocong Liu , Chengliang Deng , Yibing Liang , Haifeng Wang
IPC: G01S7/497
CPC classification number: G01S7/497 , G01S7/4808 , G01S17/42 , G01S17/89 , G01S17/936
Abstract: A motion compensation method and apparatus applicable to laser point cloud data includes acquiring laser point cloud data of a frame; using an acquisition time of a start point as a target time; interpolating coordinate transformation relations and an end laser point, to obtain coordinate transformation relations of other laser points, and transforming coordinates of the other laser points to the coordinates at the target time. During motion compensation on each frame of laser point cloud data, the coordinate transformation relations corresponding to only the start and end laser points are obtained, and the coordinate transformation relations corresponding to the two points are interpolated to obtain transformation relations corresponding to other laser points, thus performing motion compensation. Therefore, the processing speed is improved and meets high real-time requirements on systems such as autopilot control systems.
-
Patent Agency Ranking
公开(公告)号：US20180065575A1
公开(公告)日：2018-03-08
申请号：US15410451
申请日：2017-01-19
Inventor： Wei He , Haifeng Wang , Yu Ma , Chengliang Deng , Weide Zhang , Zhuo Chen
IPC: B60R16/023 , G08B29/12 , G05D1/00 , G07C5/08 , G07C5/00
CPC classification number: B60R16/0232 , G05D1/0088 , G07C5/008 , G07C5/0841 , G08B29/12
Abstract: The present application discloses a monitoring method and apparatus. A specific implementation of the method comprises: reading information about monitoring data acquisition methods of monitored objects, the monitoring data acquisition method comprising an active acquisition method and a passive acquisition method; executing following steps for each of the monitored objects having the active acquisition method as the monitoring data acquisition method: generating a monitoring data acquisition task of the monitored object; determining a monitoring data acquisition frequency of the monitored object; and adding the monitoring data acquisition task to to-be-executed monitoring data acquisition task sets in a defined period corresponding to the monitoring data acquisition frequency; executing, in successive defined periods, monitoring data acquisition tasks in the corresponding to-be-executed monitoring data acquisition task sets; and parsing acquired monitoring data of the monitored objects to generate a monitoring result. The implementation solves the problem of high system resource occupation and waste of system resources during the monitoring process.
-
27.发明授权公开(公告)号：US11995405B2
公开(公告)日：2024-05-28
申请号：US17348104
申请日：2021-06-15
Inventor： Xuan Ouyang , Shuohuan Wang , Chao Pang , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang
Abstract: The present disclosure provides a multi-lingual model training method, apparatus, electronic device and readable storage medium and relates to the technical field of deep learning and natural language processing. A technical solution of the present disclosure when training the multi-lingual model is: obtaining training corpuses comprising a plurality of bilingual corpuses and a plurality of monolingual corpuses; training a multi-lingual model with a first training task by using the plurality of bilingual corpuses; training the multi-lingual model with a second training task by using the plurality of monolingual corpuses; and completing the training of the multi-lingual model in a case of determining that loss functions of the first training task and second training task converge. In the present disclosure, the multi-lingual model can be enabled to achieve semantic interaction between different languages and improve the accuracy of the multi-lingual model in learning the semantic representations of the multi-lingual model.
-
公开(公告)号：US11928432B2
公开(公告)日：2024-03-12
申请号：US17319189
申请日：2021-05-13
Inventor： Fei Yu , Jiji Tang , Weichong Yin , Yu Sun , Hao Tian , Hua Wu , Haifeng Wang
CPC classification number: G06F40/284 , G06F40/30 , G06N5/04 , G06N20/00 , G06V10/811 , G06V20/30
Abstract: A multi-modal pre-training model acquisition method, an electronic device and a storage medium, which relate to the fields of deep learning and natural language processing, are disclosed. The method may include: determining, for each image-text pair as training data, to-be-processed fine-grained semantic word in the text; masking the to-be-processed fine-grained semantic words; and training the multi-modal pre-training model using the training data with the fine-grained semantic words masked.
-
公开(公告)号：US11908219B2
公开(公告)日：2024-02-20
申请号：US17244291
申请日：2021-04-29
Inventor： Zihan Ni , Yipeng Sun , Kun Yao , Junyu Han , Errui Ding , Jingtuo Liu , Haifeng Wang
IPC: G06V30/413 , G06F40/30 , G06V30/414 , G06V10/70
CPC classification number: G06V30/413 , G06F40/30 , G06V10/70 , G06V30/414
Abstract: The disclosure provides a method and a device for processing information, an electronic device, and a storage medium, belonging to a field of artificial intelligence including computer vision, deep learning, and natural language processing. In the method, the computing device recognizes multiple text items in the image. The computing device classifies multiple text items into a first set of name text items and a second set of content text items based on semantics of the text items. The computing device performs a matching operation between the first set and the second set based on a layout of the text items in the image, and determines matched name-content text items. The matched name-content text items include a name text item in the first set and a content text item matching the name text item and in the second set. The computing device outputs the matched name-content text items.
-
公开(公告)号：US11727302B2
公开(公告)日：2023-08-15
申请号：US16006208
申请日：2018-06-12
Inventor： Ke Sun , Shiqi Zhao , Dianhai Yu , Haifeng Wang
Abstract: A method and apparatus for building a conversation understanding system based on artificial intelligence, a device and a computer-readable storage medium. In embodiments of the present disclosure, it is feasible to obtain the training feedback information provided by conversation service conducted by the user and the basic conversation understanding system, then according to the training feedback information, perform adjustment processing for a service state of the basic conversation understanding system, to obtain an adjustment state of the basic conversation understanding system. It is possible to perform data merging processing according to the training feedback information and the adjustment state of the basic conversation understanding system, to obtain model training data for building the model conversation understanding system. This method does not require persons to participate in annotation operations of the training data, exhibits simple operations and a high correctness rate, improving the efficiency and reliability of the conversation understanding system.
-
-
-
-
-
-
-
-
-
Search Results
80
records
(took 0.029 seconds)
