-
公开(公告)号：US11227118B2
公开(公告)日：2022-01-18
申请号：US16504546
申请日：2019-07-08
发明人： Yongmei Zeng , Bo Li , Gongzhi Yao , Pinpin Zhu
摘要： The present disclosure includes a device for constructing an intelligent knowledge base. The device comprises: a preset knowledge subject obtaining unit to obtain from a subject domain database preset knowledge subjects each comprising a standard question and an extended question; a receiving unit to receive an initial request message; a calculation unit to perform a semantic similarity calculation on the initial request message and the preset knowledge subjects to obtain a plurality of semantic similarity calculation results; a determination unit to determine whether a largest semantic similarity calculation result is greater than a similarity threshold value; and a storing unit to: when the largest semantic similarity calculation result is greater than the similarity threshold value, store into the intelligent knowledge base the initial request message, and a standard question and an extended question of a preset knowledge subject corresponding to the largest semantic similarity calculation result.
-
32.发明授权公开(公告)号：US11032419B2
公开(公告)日：2021-06-08
申请号：US16043415
申请日：2018-07-24
发明人： Siyuan Li , Pinpin Zhu
摘要： The present disclosure includes an intelligent customer service system comprising a customer end, a customer service robot, and a human customer-service end. The customer service robot is configured to: receive a session message from the customer end; identify content of the session message; determine whether it is capable of processing the session message based on the identified content; if so, obtain an answer message matching the identified content from pre-stored service resource and transmit the answer message to the customer end; or otherwise, set its state to a session suspended state, obtain a comforting answer message matching the session message from the pre-stored service resource, send the comforting answer message to the customer end, and transmit to the human customer-service end the session message that the customer service robot is not capable of processing or the content of which the customer service robot cannot identify.
-
公开(公告)号：US11017178B2
公开(公告)日：2021-05-25
申请号：US16504550
申请日：2019-07-08
发明人： Yongmei Zeng , Bo Li , Gongzhi Yao , Pinpin Zhu
摘要： A device for constructing an intelligent knowledge base, comprising an abstract semantic expression obtaining unit to obtain a plurality of abstract semantic expressions from an abstract semantic database, wherein each of the plurality of abstract semantic expressions comprises a semantic-lacking element; a receiving unit to receive an initial request message; an abstract semantic recommending module to obtain abstract semantic expressions corresponding to the initial request message by performing an abstract semantic recommending process on the initial request message based on the plurality of abstract semantic expressions; a filling unit to extract from the initial request message an element corresponding to a semantic-lacking element of the obtained abstract semantic expressions, and to fill the extracted element into the semantic-lacking element to obtain specific semantic expressions corresponding to the initial request message; and a storing unit to store the initial request message and the specific semantic expressions into the intelligent knowledge base.
-
公开(公告)号：US10942955B2
公开(公告)日：2021-03-09
申请号：US16103104
申请日：2018-08-14
发明人： Bo Li , Zhongqiu Jiang , Yongmei Zeng , Pinpin Zhu
IPC分类号： G06F16/00 , G06F16/332 , G06F9/46 , G06N5/02
摘要： According to a specific implementation manner that a questioning and answering system including a transaction node interacts with a user in the embodiments of the present invention, a quick call to an existing function or service can be realized, and by acquiring modification information for a set system component in the questioning and answering system, and correspondingly updating the questioning and answering system according to the modification information, the existing questioning and answering method based on a questioning and answering system, the existing method for generating the questioning and answering system, and the existing method for modifying the questioning and answering system are optimized, thereby improving efficiency and accuracy of questioning and answering, and improving generation efficiency and modification efficiency of the questioning and answering system.
-
公开(公告)号：US10783329B2
公开(公告)日：2020-09-22
申请号：US16052345
申请日：2018-08-01
发明人： Hui Wang , Yuning Wang , Pinpin Zhu
IPC分类号： G10L15/22 , G10L17/22 , G06F40/30 , G06F40/103 , G06F40/205 , G06F40/289
摘要： The present disclosure relates to a method, device and computer readable storage medium for presenting an emotion. The method for presenting the emotion includes obtaining a first emotion presentation instruction, wherein the first emotion presentation instruction includes at least one first emotion presentation modality and at least one emotional style, and the at least one first emotion presentation modality includes a text emotion presentation modality; and presenting an emotion corresponding to one or more of the at least one emotional style according to each of the at least one first emotion presentation modality. The present disclosure can realize text-based multi-modal emotion presentation modes, and thus user experience can be improved.
-
公开(公告)号：US20200273179A1
公开(公告)日：2020-08-27
申请号：US16871996
申请日：2020-05-11
发明人： Bo ZHANG , Pinpin ZHU
摘要： An object recognition device includes a memory, a processor and a computer program stored in the memory and executed by the processor. When the computer program is executed by the processor, the processor implements the following steps: extracting object recognition feature vectors based on at least one frame image of the video on the first tracking target; matching the extracted object recognition feature vectors with object feature vectors of registered objects in a registration object library, the registration object library being established based on pre-learning of the object feature vectors in images of the registered objects; and taking one of the registered objects as a recognition result if the extracted object recognition feature vectors match with the object feature vectors of the one of the registered objects.
-
公开(公告)号：US10726562B2
公开(公告)日：2020-07-28
申请号：US15909402
申请日：2018-03-01
发明人： Bo Zhang , Pinpin Zhu
摘要： A video tracking method comprises: determining a first tracking target in a video, and performing a video tracking process on the first tracking target based on the video; performing area overlap degree calculation on the first tracking target in a current image and the first tracking target in a past image during the video tracking process, the past image being an image obtained when the first tracking target was tracked last time in the video tracking process; extracting respective feature information of feature points of the first tracking target in the video during the video tracking process on the first tracking target; matching the extracted respective feature information of the feature points of the first tracking target in the current image with the respective feature information of corresponding feature points of the first tracking target in the past image if a result of the area overlap degree calculation is less than or equal to a preset threshold; and continuing the video tracking process on the first tracking target if the respective feature information of at least a preset number of feature points among the extracted feature points in the current image matches with the feature information of corresponding feature points of the first tracking target in the past image.
-
公开(公告)号：US20190332673A1
公开(公告)日：2019-10-31
申请号：US16504558
申请日：2019-07-08
发明人： Yongmei ZENG , Bo LI , Gongzhi YAO , Pinpin ZHU
摘要： An abstract semantic recommending device, comprising an abstract semantic expression obtaining unit to obtain a plurality of abstract semantic expressions; a receiving unit to receive an initial request message; a word segmentation unit to perform a word segmentation process on the initial request message to obtain one or more single words; a part-of-speech tagging unit to perform a part-of-speech tagging process on at least one of the one or more single words to obtain its part-of-speech information; a wordclass determination unit to perform a wordclass determination process on at least one of the one or more single words to obtain its wordclass information; a searching unit to acquire an abstract semantic candidate set relevant to the initial request message; and a matching unit to derive one or more abstract semantic expressions by performing a matching process on the several abstract semantic expressions in the abstract semantic candidate set.
-
公开(公告)号：US20190332672A1
公开(公告)日：2019-10-31
申请号：US16504550
申请日：2019-07-08
发明人： Yongmei ZENG , Bo LI , Gongzhi YAO , Pinpin ZHU
摘要： A device for constructing an intelligent knowledge base, comprising an abstract semantic expression obtaining unit to obtain a plurality of abstract semantic expressions from an abstract semantic database, wherein each of the plurality of abstract semantic expressions comprises a semantic-lacking element; a receiving unit to receive an initial request message; an abstract semantic recommending module to obtain abstract semantic expressions corresponding to the initial request message by performing an abstract semantic recommending process on the initial request message based on the plurality of abstract semantic expressions; a filling unit to extract from the initial request message an element corresponding to a semantic-lacking element of the obtained abstract semantic expressions, and to fill the extracted element into the semantic-lacking element to obtain specific semantic expressions corresponding to the initial request message; and a storing unit to store the initial request message and the specific semantic expressions into the intelligent knowledge base.
-
40.发明申请公开(公告)号：US20190164064A1
公开(公告)日：2019-05-30
申请号：US16052143
申请日：2018-08-01
发明人： Bo LI , Yongmei ZENG , Jie CHENG , Pinpin ZHU
摘要： A question and answer interaction method includes: receiving a question from a user, the question including at least one intention and at least one element related to each of the at least one intention; performing intention analysis on the question to obtain the at least one intention and the at least one element related to each of the at least one intention; obtaining an answer corresponding to the question according to the at least one intention and the at least one element related to each of the at least one intention; and sending the answer to the user.
-
-
-
-
-
-
-
-
-
搜索结果
43 条记录 (耗时 0.023 秒)
