-
公开(公告)号：US11314534B2
公开(公告)日：2022-04-26
申请号：US16777430
申请日：2020-01-30
IPC分类号： G06F17/00 , G06F9/451 , G06F40/30 , G06F16/9032 , G06N3/04
摘要： An intelligent question and answer (Q&A) system and method for interactively guiding users through a procedure is disclosed. The intelligent Q&A system can dynamically generate process trees (or procedural trees) from the content or procedures presented in a raw document, such as a reference manual. The intelligent Q&A system can include a virtual agent that uses the dynamically generated process trees for interactive conversation with a user. Using the system, the virtual agent can interactively guide users through completing tasks such as updating software or connecting an IoT device to an existing system.
-
公开(公告)号：US20210240503A1
公开(公告)日：2021-08-05
申请号：US16777430
申请日：2020-01-30
IPC分类号： G06F9/451 , G06N3/04 , G06F16/9032 , G06F40/30
摘要： An intelligent question and answer (Q&A) system and method for interactively guiding users through a procedure is disclosed. The intelligent Q&A system can dynamically generate process trees (or procedural trees) from the content or procedures presented in a raw document, such as a reference manual. The intelligent Q&A system can include a virtual agent that uses the dynamically generated process trees for interactive conversation with a user. Using the system, the virtual agent can interactively guide users through completing tasks such as updating software or connecting an IoT device to an existing system.
-
公开(公告)号：US10963043B2
公开(公告)日：2021-03-30
申请号：US16661306
申请日：2019-10-23
摘要： A device may receive human-related data associated with a surveyor and a surveyed person participating in an interview, and may receive environmental data. The device may determine, based on rules, that first portions of the human-related data and environmental data are more reliable than second portions, and may process the first portions of the human-related data and the environmental data, with a first model, to determine high-reliability context data. The device may process the second portions of the human-related data and the environmental data, with a second model, to determine low-reliability context data, and may process the high-reliability context data and the low-reliability context data, with a third model, to generate weighted context data. The device may process the weighted context data, with a fourth model, to calculate a total stress factor, and may perform actions based on the total stress factor.
-
公开(公告)号：US10324969B2
公开(公告)日：2019-06-18
申请号：US15046032
申请日：2016-02-17
发明人： Anutosh Maitra , Shubhashis Sengupta , Tom Geo Jain , Roshni Ramesh Ramnani , Hitanshu Rakeshkumar Tiwari
摘要： A device may receive a first textual document and a set of second textual documents. The first textual document may identify parameters. The device may process the first textual document, based on a natural language processing algorithm, to identify first values corresponding to the parameters. The device may process the plurality of second textual documents, based on the natural language processing algorithm, to identify second values corresponding to the parameters. Each of the plurality of second textual documents may be associated with one or more respective second values of the second values. The device may determine scores for the plurality of second textual documents. A score may be determined based on comparing one or more of the first values to one or more of the second values associated with a second textual document. The device may provide information identifying the plurality of second textual documents and the scores.
-
公开(公告)号：US12101279B2
公开(公告)日：2024-09-24
申请号：US17459888
申请日：2021-08-27
发明人： Shubhashis Sengupta , Anutosh Maitra , Roshni Ramesh Ramnani , Sriparna Saha , Abhisek Tiwari , Pushpak Bhattacharyya
IPC分类号： H04L51/02 , G06F40/279 , G06F40/35 , G06N20/00
CPC分类号： H04L51/02 , G06F40/279 , G06F40/35 , G06N20/00
摘要： Systems and methods that offer significant improvements to current virtual agent (VA) conversational experiences are disclosed. The proposed systems and methods are configured to manage conversations in real-time with human customers while accommodating a dynamic goal. The VA includes a goal-driven module with a reinforcement learning-based dialogue manager. The VA is an interactive tool that utilizes both task-specific rewards and sentiment-based rewards to respond to a dynamic goal. The VA is capable of handling dynamic goals with a significantly high success rate. As the system is trained primarily with a user simulator, it can be readily extended for applications across other domains.
-
公开(公告)号：US20220156582A1
公开(公告)日：2022-05-19
申请号：US17313555
申请日：2021-05-06
发明人： Shubhashis Sengupta , Anutosh Maitra , Roshni Ramesh Ramnani , Zishan Ahmad , Pushpak Bhattacharyya , Asif Ekbal
摘要： Techniques for building knowledge graphs from conversational data are disclosed. The systems include a high-performance relation classifier developed with active learning and requiring minimal supervision. The classifier is used to classify relation triples extracted from conversational text, which are then used to populate the knowledge graph. A heuristic for constructing the knowledge graph is also disclosed. The proposed embodiments provide a way to efficiently build and/or augment knowledge graphs and improve the quality of the generated responses by a dialogue agent despite a sparsity of data.
-
公开(公告)号：US11010829B2
公开(公告)日：2021-05-18
申请号：US16450783
申请日：2019-06-24
发明人： Anutosh Maitra , Shubhashis Sengupta , Abhisek Mukhopadhyay , Shilpi Jain , Sarabjit Singh Gugneja , Leonardo Orlando
IPC分类号： G06Q40/02
摘要： A device may determine a behavioral pattern of an account over a past time period based on data relating to one or more transactions associated with the account. The device may identify one or more quantitative features of the behavioral pattern and one or more spatial features of the behavioral pattern. The device may determine an account type cluster to which the account belongs, based on the one or more quantitative features and the one or more spatial features identified. The device may determine, based on the account type cluster that is determined, a model for processing the behavioral pattern. The device may predict, using the model that is determined, an amount of funds that is likely to remain in the account during a future time period. The device may perform one or more actions based on the amount of funds that is predicted.
-
公开(公告)号：US20190034760A1
公开(公告)日：2019-01-31
申请号：US15698277
申请日：2017-09-07
发明人： Shrikanth NARAYANASWAMY CHANDRASEKARAN , Venkatesh Subramanian , Anutosh Maitra , Anurag Dwarakanath , Pradeepkumar Duraisamy , Aditya Bhola
摘要： In some examples, incident prediction and prevention may include ascertaining a plurality of past incidents, clustering the plurality of past incidents to generate a plurality of incidents clusters, and identifying, for each past incident of the plurality of past incidents that is in a respective incidents cluster of the plurality of incidents clusters, a time of occurrence. Incident prediction and prevention may include ascertaining a new incident, assigning the new incident to an incidents cluster of the plurality of incidents clusters, and determining, for the assigned incidents cluster, at least one further predicted incident associated with at least one further corresponding incidents cluster. Further, incident prediction and prevention may include determining a resolution to the at least one further predicted incident, and preventing occurrence of the at least one further predicted incident by executing the determined resolution to the at least one further predicted incident.
-
公开(公告)号：US11854540B2
公开(公告)日：2023-12-26
申请号：US17301489
申请日：2021-04-05
发明人： Anutosh Maitra , Shubhashis Sengupta , Sowmya Rasipuram , Roshni Ramesh Ramnani , Junaid Hamid Bhat , Sakshi Jain , Manish Agnihotri , Dinesh Babu Jayagopi
IPC分类号： G10L15/183 , G10L15/18 , G06T7/70 , G10L25/63 , G06F40/35 , G10L25/57 , G10L15/16 , G10L15/22 , G10L25/90 , G06N3/08 , G06N3/04 , A61B5/16 , A61B5/00 , A61B5/11 , G06V20/40 , G06V40/16 , G06N3/0455
CPC分类号： G10L15/1815 , A61B5/0077 , A61B5/1107 , A61B5/1114 , A61B5/1128 , A61B5/163 , A61B5/165 , A61B5/4803 , A61B5/7267 , G06F40/35 , G06N3/04 , G06N3/0455 , G06N3/08 , G06T7/70 , G06V20/41 , G06V40/168 , G10L15/16 , G10L15/183 , G10L15/22 , G10L25/57 , G10L25/63 , G10L25/90 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/30201 , G10L2015/223
摘要： A device may receive text data, audio data, and video data associated with a user, and may process the received data, with a first model, to determine a stress level of the user. The device may process the received data, with second models, to determine depression levels of the user, and may combine the depression levels to identify an overall depression level. The device may process the received data, with a third model, to determine a continuous affect prediction, and may process the received data, with a fourth model, to determine an emotion of the user. The device may process the received data, with a fifth model, to determine a response to the user, and may utilize a sixth model to determine a context for the response. The device may utilize seventh models to generate contextual conversation data, and may perform actions based on the contextual conversational data.
-
公开(公告)号：US20230063131A1
公开(公告)日：2023-03-02
申请号：US17459888
申请日：2021-08-27
发明人： Shubhashis Sengupta , Anutosh Maitra , Roshni Ramesh Ramnani , Sriparna Saha , Abhisek Tiwari , Pushpak Bhattacharyya
IPC分类号： H04L12/58 , G06N20/00 , G06F40/279
摘要： Systems and methods that offer significant improvements to current virtual agent (VA) conversational experiences are disclosed. The proposed systems and methods are configured to manage conversations in real-time with human customers while accommodating a dynamic goal. The VA includes a goal-driven module with a reinforcement learning-based dialogue manager. The VA is an interactive tool that utilizes both task-specific rewards and sentiment-based rewards to respond to a dynamic goal. The VA is capable of handling dynamic goals with a significantly high success rate. As the system is trained primarily with a user simulator, it can be readily extended for applications across other domains.
-
-
-
-
-
-
-
-
-
搜索结果
10 条记录 (耗时 0.022 秒)
