-
公开(公告)号：US11341422B2
公开(公告)日：2022-05-24
申请号：US16106680
申请日：2018-08-21
Applicant: Shanghai Xiaoi Robot Technology Co., Ltd.
Inventor： Bo Li , Zhongqiu Jiang , Yongmei Zeng , Pinpin Zhu
Abstract: The present invention provides a multi-round questioning and answering method, a method for generating a multi-round questioning and answering system and a method for modifying a multi-round questioning and answering system. The multi-round questioning and answering method includes: acquisition initial request information, and matching the initial request information with a knowledge point in a knowledge base; if it is determined that the initial request information matches with a thematic question in a thematic knowledge point, triggering a root node of a multi-round questioning and answering flow module corresponding to the thematic knowledge point; and, performing, according to a first interaction node to which the multi-round questioning and answering flow module is proceeded currently, one or more knowledge points corresponding to the first interaction node stored in the knowledge base and user interaction information input by an interactive user, questioning and answering interaction with the interactive user.
-
12.发明申请公开(公告)号：US20190295533A1
公开(公告)日：2019-09-26
申请号：US16414293
申请日：2019-05-16
Applicant: Shanghai Xiaoi Robot Technology Co., Ltd.
Inventor： Hui Wang , Shijing Yu , Pinpin Zhu
Abstract: Embodiments of the present invention provide an intelligent interactive method and apparatus, a computer device and a computer readable storage medium, which solves problems that a deep intention of a user message cannot be analyzed in an intelligent interactive manner in the prior art and humanized interactive experiences cannot be provided. The intelligent interactive method includes: obtaining an emotion recognition result according to a user message, where the user message includes at least a user voice message; performing an intention analysis according to a text content of the user voice message to obtain corresponding basic intention information; and determining a corresponding interactive instruction according to the emotion recognition result and the basic intention information.
-
公开(公告)号：US20180357219A1
公开(公告)日：2018-12-13
申请号：US16004734
申请日：2018-06-11
Applicant: SHANGHAI XIAOI ROBOT TECHNOLOGY CO., LTD.
Inventor： Zhi Li , Pinpin Zhu
Abstract: The present invention provides a method for generating a semantic expression for a standard question in a knowledge base. The knowledge base includes multiple standard questions, each standard question has multiple associated similar questions, and the method includes: for each standard question, obtaining multiple similar question segmentation results corresponding to the multiple similar questions of the standard question, where each similar question segmentation result includes word classes to which respective words in a corresponding similar question belong; for each standard question, selecting a phrase from an intersection of multiple similar question segmentation results of the standard question based on phrase occurrence frequencies, to form at least one semantic expression of the standard question, where each phrase includes a predetermined quantity of word classes; for all similar questions of all standard questions, performing standard question matching processing; for each semantic expression created for each standard question, determining whether the semantic expression is matched to at least one similar question of the standard question; and if yes, marking the semantic expression as a first state; or otherwise, marking the semantic expression as a second state; and deleting all semantic expressions in the second state.
-
公开(公告)号：US11455472B2
公开(公告)日：2022-09-27
申请号：US16992284
申请日：2020-08-13
Applicant: Shanghai Xiaoi Robot Technology Co., Ltd.
Inventor： Hui Wang , Yuning Wang , Pinpin Zhu
IPC: G06F40/30 , G06F40/103 , G06F40/205 , G06F40/289
Abstract: 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：US11227118B2
公开(公告)日：2022-01-18
申请号：US16504546
申请日：2019-07-08
Applicant: SHANGHAI XIAOI ROBOT TECHNOLOGY CO., LTD.
Inventor： Yongmei Zeng , Bo Li , Gongzhi Yao , Pinpin Zhu
Abstract: 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.
-
Patent Agency Ranking
16.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
Applicant: SHANGHAI XIAOI ROBOT TECHNOLOGY CO., LTD.
Inventor： Siyuan Li , Pinpin Zhu
Abstract: 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
Applicant: SHANGHAI XIAOI ROBOT TECHNOLOGY CO., LTD.
Inventor： Yongmei Zeng , Bo Li , Gongzhi Yao , Pinpin Zhu
Abstract: 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
Applicant: Shanghai Xiaoi Robot Technology Co., Ltd.
Inventor： Bo Li , Zhongqiu Jiang , Yongmei Zeng , Pinpin Zhu
IPC: G06F16/00 , G06F16/332 , G06F9/46 , G06N5/02
Abstract: 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
Applicant: Shanghai Xiaoi Robot Technology Co., Ltd.
Inventor： Hui Wang , Yuning Wang , Pinpin Zhu
IPC: G10L15/22 , G10L17/22 , G06F40/30 , G06F40/103 , G06F40/205 , G06F40/289
Abstract: 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：US10726562B2
公开(公告)日：2020-07-28
申请号：US15909402
申请日：2018-03-01
Applicant: Shanghai Xiaoi Robot Technology Co., Ltd.
Inventor： Bo Zhang , Pinpin Zhu
Abstract: 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.
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.017 seconds)
