-
公开(公告)号:US20210089721A1
公开(公告)日:2021-03-25
申请号:US17115944
申请日:2020-12-09
发明人: Benjamin Gene CHEUNG , Andres MONROY-HERNANDEZ , Todd Daniel NEWMAN , Mayerber Loureiro De CARVALHO NETO , Michael Brian PALMER , Pamela BHATTACHARYA , Justin Brooks CRANSHAW , Charles Yin-Che LEE
IPC分类号: G06F40/30 , G06F16/9032 , H04L12/58 , G06Q10/10
摘要: A software agent, that is used to assist in providing a service, receives communications from a set of users that are attempting to use the software agent. The communications include communications that are interacting with the software agent, and communications that are not interacting with the software agent. The software agent performs natural language processing on all communications to identify such things as user sentiment, user concerns or other items in the content of the messages, and also to identify actions taken by the users in order to obtain a measure of user satisfaction with the software agent. One or more action signals are then generated based upon the identified user satisfaction with the software agent.
-
公开(公告)号:US20220092265A1
公开(公告)日:2022-03-24
申请号:US17025557
申请日:2020-09-18
IPC分类号: G06F40/295 , G06F40/284 , G06F40/30 , G06F40/117
摘要: The disclosure relates to systems and methods for identifying entities related to a task in a natural language input. An entity detection model is provided which receives a natural language input. The entity detection model processes the natural language input using an entity encoder and an input encoder. The entity encoder identifies and encodes relevant entities while the input encoder generates a contextual encoding which represents contextual information associated with a relevant entity. The encoded entity and contextual encodings may then be combined and processed to generate a probability score for an identified entity. A negation constraint model is also disclosed. The negation constraint model receives the natural language input and the identified entities. The natural language input is analyzed to identify negation cues and determine if the negation cue is associated with an identified entity.
-
3.
公开(公告)号:US20190333022A1
公开(公告)日:2019-10-31
申请号:US15966648
申请日:2018-04-30
发明人: Charles Yin-Che LEE , Pamela BHATTACHARYA , Mayerber LOUREIRO DE CARVALHO NETO , Warren JOHNSON , Juliana Pena OCAMPO , Chala FUFA , Benjamin Gene CHEUNG , Shahil SONI
IPC分类号: G06Q10/10
摘要: A time aggregation and control system detects when an automated scheduling assistant is invoked to perform a scheduling operation. It detects scheduling characteristics corresponding to the scheduling operation and identifies a time saving value corresponding to the scheduling operation. The time saving value is aggregated over a plurality of different scheduling operations until a time block trigger is detected. A scheduling control signal is generated, to automatically reserve a block of time, based upon the aggregated time saving values.
-
公开(公告)号:US20220335043A1
公开(公告)日:2022-10-20
申请号:US17235517
申请日:2021-04-20
发明人: Yating ZHENG , Shuo LI , Yijia XU , Sandip NATH , Duc Mai Thanh LE , Priyanka Subhash KULKARNI , Manan SANGHI , Pamela BHATTACHARYA , Jignesh SHAH
IPC分类号: G06F16/2452 , G06F16/2457 , G06F16/28 , G06N3/08 , G06N3/04
摘要: A method and system for one or more application command recommendations may include receiving a search query, the search query being an in-application assistance query, accessing contextual data associated with the search query, providing at least one of the search query and the contextual data as input to a multilingual machine-learning (ML) model to identify one or more application command recommendations, obtaining the one or more application command recommendations as an output from the multilingual ML model, and providing data about the output to the application for display. The multilingual ML model uses a multilingual encoder to provide command recommendations for a plurality of languages.
-
5.
公开(公告)号:US20220261539A1
公开(公告)日:2022-08-18
申请号:US17738312
申请日:2022-05-06
IPC分类号: G06F40/211 , G06N20/00 , G06F40/30 , G06Q10/10
摘要: In non-limiting examples of the present disclosure, systems, methods and devices for resolving temporal ambiguities are presented. A natural language input may be received. A temporal component of the input may be identified. A determination may be made that the temporal component includes a conjunction that separates temporal meeting block alternatives. A temporal ambiguity may be identified in one of the meeting block alternatives. A plurality of syntax tree permutations may be generated for the meeting block alternative where the ambiguity was identified. A machine learning model that has been trained to identify a most relevant permutation for a given natural language input may be applied to each of the plurality of permutations. A temporal meeting block alternative corresponding to the most relevant permutation may be surfaced.
-
公开(公告)号:US20190340244A1
公开(公告)日:2019-11-07
申请号:US16511724
申请日:2019-07-15
发明人: Benjamin Gene CHEUNG , Andres MONROY-HERNANDEZ , Todd Daniel NEWMAN , Mayerber Loureiro De CARVALHO NETO , Michael Brian PALMER , Pamela BHATTACHARYA , Justin Brooks CRANSHAW , Charles Yin-Che LEE
IPC分类号: G06F17/27 , G06F16/9032 , H04L12/58 , G06Q10/10
摘要: A software agent, that is used to assist in providing a service, receives communications from a set of users that are attempting to use the software agent. The communications include communications that are interacting with the software agent, and communications that are not interacting with the software agent. The software agent performs natural language processing on all communications to identify such things as user sentiment, user concerns or other items in the content of the messages, and also to identify actions taken by the users in order to obtain a measure of user satisfaction with the software agent. One or more action signals are then generated based upon the identified user satisfaction with the software agent.
-
公开(公告)号:US20220343079A1
公开(公告)日:2022-10-27
申请号:US17230300
申请日:2021-04-14
IPC分类号: G06F40/30 , G06F40/284 , G06N20/00
摘要: A method and system for predicting an intended time interval for a content segment may include receiving a request for natural language processing (NLP) of the content segment, the content segment including one or more temporal expressions, accessing contextual data associated with each of the one or more temporal expressions, decoding the content segment into a program that describes a temporal logic of the content segment based on the one or more temporal expressions, evaluating the program using the contextual data to predict an intended time interval for the content segment, and providing the intended time interval as an output.
-
公开(公告)号:US20190095424A1
公开(公告)日:2019-03-28
申请号:US15714077
申请日:2017-09-25
发明人: Benjamin Gene CHEUNG , Andres MONROY-HERNANDEZ , Todd Daniel NEWMAN , Mayerber Loureiro De CARVALHO NETO , Michael Brian PALMER , Pamela BHATTACHARYA , Justin Brooks CRANSHAW , Charles Yin-Che LEE
CPC分类号: G06F17/2785 , G06F16/90332 , G06Q10/107 , G06Q10/109 , H04L51/02 , H04L51/046
摘要: A software agent, that is used to assist in providing a service, receives communications from a set of users that are attempting to use the software agent. The communications include communications that are interacting with the software agent, and communications that are not interacting with the software agent. The software agent performs natural language processing on all communications to identify such things as user sentiment, user concerns or other items in the content of the messages, and also to identify actions taken by the users in order to obtain a measure of user satisfaction with the software agent. One or more action signals are then generated based upon the identified user satisfaction with the software agent.
-
公开(公告)号:US20180239752A1
公开(公告)日:2018-08-23
申请号:US15960791
申请日:2018-04-24
发明人: Pamela BHATTACHARYA
摘要: Linguistic analysis based correlation of distinct events is provided. In examples, trouble shooting tickets may be received over a time period. A linguistic analysis may be performed on one or more portions of the one or more comments using a linguistic model and a similarity score may be computed for one or more keywords within the one or more portions of the one or more comments based on criteria associated with each of the keywords. The similarity score for each of the keywords may be compared to a validation threshold and if the similarity score for a subset of the keywords within a trouble shooting ticket exceeds the validation threshold, the trouble shooting ticket may be validated as associated with the incident. If a number of trouble shooting tickets are validated as being associated with the incident exceeds a service outage threshold, an alert may be issued for the service outage.
-
-
-
-
-
-
-
-