-
公开(公告)号：US20200285698A1
公开(公告)日：2020-09-10
申请号：US16293860
申请日：2019-03-06
发明人： Leonardo Guerreiro Azevedo , Joel Luis Carbonera , Viviane Torres Da Silva , Maira Gatti De Bayser
摘要： A computer-implemented method for constructing an ontology includes using a chatbot program to elicit an utterance from a user. An utterance is received from the user. The received utterance is parsed to detect a concept/property/relationship therein. It is determined whether the identified concept/property/relationship is represented within an ontology and the identified concept/property/relationship is added to the ontology when it is determined that the it is not present therein. A response to the received utterance is generated using the ontology. The generated response is presented to the user using the chatbot.
-
公开(公告)号：US11048877B2
公开(公告)日：2021-06-29
申请号：US16293860
申请日：2019-03-06
发明人： Leonardo Guerreiro Azevedo , Joel Luis Carbonera , Viviane Torres Da Silva , Maira Gatti De Bayser
IPC分类号： G10L15/22 , G06F40/237 , G06F40/279 , G06F40/295 , H04L12/58 , G10L15/18 , G10L15/26
摘要： A computer-implemented method for constructing an ontology includes using a chatbot program to elicit an utterance from a user. An utterance is received from the user. The received utterance is parsed to detect a concept/property/relationship therein. It is determined whether the identified concept/property/relationship is represented within an ontology and the identified concept/property/relationship is added to the ontology when it is determined that the it is not present therein. A response to the received utterance is generated using the ontology. The generated response is presented to the user using the chatbot.
-
公开(公告)号：US10121096B2
公开(公告)日：2018-11-06
申请号：US15223777
申请日：2016-07-29
发明人： Alecio Pedro Delazari Binotto , Emilio Ashton Vital Brazil , Renato Fontoura De Gusmao Cerqueira , Rodrigo da Silva Ferreira , Michael Raghib Moreno , Vagner Figueredo De Santana , Viviane Torres Da Silva
摘要： A method is provided, the method including: displaying an image on a display; detect a user input corresponding to one or more portions of the image; analyzing the user input to determine at least one feature vector corresponding to the user input; and determining a classification for the one or more portions of the image based at least on the at least one feature vector.
-
公开(公告)号：US20180032839A1
公开(公告)日：2018-02-01
申请号：US15223777
申请日：2016-07-29
发明人： Alecio Pedro Delazari Binotto , Emilio Ashton Vital Brazil , Renato Fontoura De Gusmao Cerqueira , Rodrigo da Silva Ferreira , Michael Raghib Moreno , Vagner Figueredo De Santana , Viviane Torres Da Silva
CPC分类号： G06K9/627 , G01V1/30 , G01V1/306 , G01V99/005 , G01V2210/62 , G01V2210/64 , G06K9/00416 , G06T7/401 , G06T7/41 , G06T2207/20092 , G06T2207/30181
摘要： A method is provided, the method including: displaying an image on a display; detect a user input corresponding to one or more portions of the image; analyzing the user input to determine at least one feature vector corresponding to the user input; and determining a classification for the one or more portions of the image based at least on the at least one feature vector.
-
-
-
搜索结果
4 条记录 (耗时 0.012 秒)
