-
公开(公告)号：US20180373692A1
公开(公告)日：2018-12-27
申请号：US15875453
申请日：2018-01-19
Inventor： Qiongqiong LIU
Abstract: A method for parsing a query based on artificial intelligence, a computer device and a computer program product are provided. The method may include: acquiring annotated data including an annotated search instance, an annotated template instance, a field of a search intent and a category in the field, an attribute of a term in the annotated search instance and a concrete term included in the attribute; performing a training on the annotated data so as to generate an instance dictionary, a template dictionary and an inverted index dictionary; acquiring a target query to be identified; and parsing the target query based on the instance dictionary, the template dictionary and the inverted index dictionary, so as to acquire a target parsing result corresponding to the target query.
-
362.发明申请公开(公告)号：US20180357571A1
公开(公告)日：2018-12-13
申请号：US16006213
申请日：2018-06-12
Inventor： Ke Sun , Shiqi Zhao , Dianhai Yu , Haifeng Wang
CPC classification number: G06N99/005 , G06F7/14 , G06F17/2785
Abstract: A conversation processing method and apparatus based on artificial intelligence, a device and a computer-readable storage medium. The disclosure embodiments, enable the user feedback information provided by conversation service conducted by the user to model conversation understanding system, then according to the user feedback information, perform adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system so that it is possible to execute the conversation service with the model conversation understanding system, based on the adjustment state. Since a fault-tolerant and fault-correcting mechanism is provided, it is possible to adjust the understanding capability of the model conversation understanding system in real time and thereby effectively improve the reliability of conversation by collecting the user's user feedback information, and then adjusting the service state of the model conversation understanding system in time based on the user feedback information.
-
公开(公告)号：US20180357570A1
公开(公告)日：2018-12-13
申请号：US16006208
申请日：2018-06-12
Inventor： Ke SUN , Shiqi ZHAO , Dianhai YU , Haifeng WANG
CPC classification number: G06N99/005 , G06F7/14 , G06F17/2785
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.
-
公开(公告)号：US20180352043A1
公开(公告)日：2018-12-06
申请号：US15942276
申请日：2018-03-30
Inventor： Hao LIU , Kai LIU , Yajuan LYU
Abstract: The present disclosure discloses an artificial intelligence based method and apparatus for pushing news. A specific embodiment of the method includes: determining at least one news subject from a news text of to-be-pushed news; extracting, from the news text, text fragments respectively associated with news subjects; generating, for each of the news subjects, a subject tag based on the extracted text fragment through a deep learning method; and pushing the to-be-pushed news based on the at least one news subject and the generated subject tag. This embodiment may improve the effectiveness of news pushing.
-
公开(公告)号：US20180349350A1
公开(公告)日：2018-12-06
申请号：US15921386
申请日：2018-03-14
Inventor： Zhifan ZHU , Shikun FENG , Kunsheng ZHOU , Jingzhou HE
Abstract: This disclosure discloses an artificial intelligence based method and apparatus for checking a text. An embodiment of the method comprises: lexing a first to-be-checked text and a second to-be-checked text respectively, determining word vectors of the lexed words to generate a first word vector sequence and a second word vector sequence; inputting the first word vector sequence and the second word vector sequence respectively into a pre-trained convolutional neural network containing at least one multi-scale convolutional layer, identifying vector sequences in a plurality of vector sequences outputted by a last multi-scale convolutional layer as eigenvector sequences, to obtain eigenvector sequence groups respectively corresponding to the texts; combining eigenvector sequences in each eigenvector sequence group to generate a combined eigenvector sequence; and analyzing the generated combined eigenvector sequences to determine whether the first text and the second text pass a similarity check. The embodiment improves the flexibility in checking a text.
-
Patent Agency Ranking
366.发明申请公开(公告)号：US20180342233A1
公开(公告)日：2018-11-29
申请号：US15986273
申请日：2018-05-22
Inventor： Hehan LI , Wensong HE
Abstract: The present disclosure provides a method and apparatus for correcting a speech recognition error based on artificial intelligence, and a storage medium, wherein the method comprises: obtaining a second speech recognition result of a second speech query input by the user; performing error-correcting intention recognition according to the second speech recognition result; extracting error-correcting information from the second speech recognition result when it is determined that the user has an error-correcting intention; screening error-correcting resources according to the error-correcting information, and using a selected best-matched error-correcting resource to perform error correction for the first speech recognition result, the first speech recognition result being a speech recognition result of a first speech query which is input before the second speech query. The solution of the present disclosure may be applied to improve accuracy of error-correcting results and reduce the error-correcting difficulty.
-
公开(公告)号：US20180276195A1
公开(公告)日：2018-09-27
申请号：US15922748
申请日：2018-03-15
Inventor： Ming MA , Tian QIN , Kefeng MENG
CPC classification number: G06F17/273 , G06F3/04883 , G06F17/24 , G06F17/276
Abstract: The present disclosure provides an error-correcting word displaying method and apparatus, a device and a storage medium, wherein the method comprises: obtaining a user-input input code; obtaining a discreteness evaluation result of the input code; determining an error-correcting adjustment policy according to the discreteness evaluation result; displaying the error-correcting word corresponding to the input code according to the error-correcting adjustment policy. The solution of the present disclosure may be used to improve the accuracy of display results.
-
368.发明申请公开(公告)号：US20180267487A1
公开(公告)日：2018-09-20
申请号：US15537389
申请日：2015-11-17
Inventor： Guang LI , Tian XIA , Chang HUANG
IPC: G05B15/02 , G05B19/418 , H04M11/00 , G10L15/08
CPC classification number: G05B15/02 , D06F21/00 , D06F33/02 , D06F39/005 , D06F2210/00 , D06F2216/00 , G05B19/042 , G05B19/418 , G05B2219/25168 , G05B2219/2633 , G05B2219/2642 , G10L15/08 , G10L15/22 , G10L2015/223 , H04M11/00 , H04M11/007
Abstract: The present disclosure provides a smart household equipment controlling method and apparatus, an apparatus and a non-volatile computer storage medium. In embodiments of the present disclosure, input information input by the user based on a natural dialog mode interface is obtained, then the control instruction of the smart household equipment is obtained according to the input information, so that the control instruction can be sent to the smart household equipment such that the smart household equipment executes an operation according to the control instruction. Since the natural dialog mode interface is used as an interaction mode with the user, it is unnecessary to display all operable controls of the smart household equipment provided by the application on the screen of the terminal. Therefore, this can avoid the problem in the prior art about increase of data interaction between the application and the processing engine used by the application due to a limited display area of the terminal, and thereby reduce the processing burden of the processing engine.
-
公开(公告)号：US20180262560A1
公开(公告)日：2018-09-13
申请号：US15534390
申请日：2015-12-03
Inventor： Zhenyi Peng , Yanfei Wang , Jiaoren Wu
CPC classification number: H04L67/1002 , G06F15/17331 , H04L67/1097 , H04L67/14 , H04L67/141 , H04L69/162 , H04L69/163
Abstract: The present application discloses a method and system for transmitting communication data. A specific implementation of the method comprises: receiving a connection request for transmitting communication data through a remote direct memory access network; determining a transmission type of the communication data according to the connection request; establishing a socket according to the transmission type; transmitting the communication data on the remote direct memory access network by using the socket; and deleting the socket when the transmission of the communication data is completed. This implementation improves the efficiency of transmitting communication data on a remote direct memory access (RDMA) network by a non-RDMA network.
-
公开(公告)号：US20180262418A1
公开(公告)日：2018-09-13
申请号：US15534395
申请日：2015-11-26
IPC: H04L12/755 , H04L12/741 , G06F9/455
Abstract: The present application discloses a method and apparatus for establishing a virtual network communication link. A specific implementation of the method includes: determining no flow table being detected; and determining sending of a data packet according to information about the data packet. This implementation implements automatic flow table repair, ensures an SLA for a virtual network communication link, and improves the disaster tolerance capability of the communication link.
-
-
-
-
-
-
-
-
-
Search Results
1985
records
(took 0.037 seconds)
