-
Patent Agency Ranking
公开(公告)号：US20170220926A1
公开(公告)日：2017-08-03
申请号：US15014140
申请日：2016-02-03
Applicant: XEROX CORPORATION
Inventor： Shruti Chhabra , SHOURYA ROY , Ragunathan Mariappan
CPC classification number: G06Q30/0269 , G06N7/005 , G06N20/00 , G06Q50/01
Abstract: The disclosed embodiments illustrate a method and a system for predicting future activities of a user on a social media platform. The method includes extracting a first time series of one or more historical activities performed by the user from a social media platform server. The method further includes receiving a second time series of one or more future events from a requestor-computing device. The method further includes determining a first set of forecast values and a second set of forecast values based on the first time series and/or the second time series, wherein the first set of forecast values is determined using an ARIMA technique, and the second set of forecast values is determined using a regression modelling technique. The method further includes predicting the future activities of the user based on the first set of forecast values and the second set of forecast values.
-
公开(公告)号：US20170364504A1
公开(公告)日：2017-12-21
申请号：US15183831
申请日：2016-06-16
Applicant: XEROX CORPORATION
Inventor： Sandipan Dandapat , Ragunathan Mariappan , Shourya Roy , Shreshtha Mundra
CPC classification number: G06F17/279 , G06F17/241 , G06F17/2765 , H04M3/51 , H04M2203/401
Abstract: The disclosed embodiments illustrate methods data processing for real-time text analysis. The method includes receiving text content from a plurality of user-computing devices, wherein the text content comprises at least a current text segment and a previous text segment. The method further includes extracting one or more first features from the current text segment, wherein at least a first feature of the one or more first features corresponds to a difference between timestamps associated with each of the current text segment and the previous text segment. The method further includes categorizing the current text segment into a predetermined category of one or more predetermined categories, based on at least the one or more first features, automatically by utilizing a classifier. Further, the method includes predicting a likelihood of evolution of an attribute in the text content, based on the predetermined category associated with the current text segment.
-
3.发明授权公开(公告)号：US09538007B1
公开(公告)日：2017-01-03
申请号：US14930965
申请日：2015-11-03
Applicant: XEROX CORPORATION
Inventor： Ragunathan Mariappan , Shourya Roy
CPC classification number: H04M3/5175 , H04M3/51 , H04M3/5232 , H04M2203/404 , H04M2203/551
Abstract: The disclosed embodiments illustrate methods and systems for managing a conversation between a first user and a customer care agent. The method includes extracting one or more features from a first conversation between said first user and said customer care agent. The first conversation corresponds to an ongoing conversation over an electronic communication medium. The method includes determining a score for a feature. The score indicates a deviation of a value of said feature from an average of values of said feature determined from historical conversations involving said first user. The method includes aggregating said score for each of said one or more features of said first conversation. Thereafter, the method includes redirecting said first conversation of said first user to a third user during said first conversation based on said aggregation. The third user manages said first conversation between said first user and said customer care agent.
Abstract translation: 所公开的实施例示出了用于管理第一用户和客户关怀代理之间的会话的方法和系统。 该方法包括从所述第一用户和所述客户关怀代理之间的第一对话中提取一个或多个特征。 第一个对话对应于通过电子通信介质进行的对话。 该方法包括确定特征的得分。 分数表示所述特征的值与从涉及所述第一用户的历史对话确定的所述特征的值的平均值的偏差。 该方法包括对所述第一对话的所述一个或多个特征中的每一个聚合所述得分。 此后，该方法包括基于所述聚合在所述第一对话期间将所述第一用户的所述第一对话重定向到第三用户。 第三用户管理所述第一用户和所述客户关怀代理之间的所述第一对话。
-
公开(公告)号：US09881614B1
公开(公告)日：2018-01-30
申请号：US15205047
申请日：2016-07-08
Applicant: XEROX CORPORATION
Inventor： Raghuveer Thirukovalluru , Ragunathan Mariappan , Shourya Roy
CPC classification number: G10L15/26 , G06F17/30616
Abstract: The disclosed embodiments illustrate methods and systems for summary generation of a real-time conversation. The method includes receiving a real-time conversation from a plurality of computing devices over a communication network. The method further includes determining one or more first features of the real-time conversation between at least a first user and a second user. The method further includes extracting one or more second features from the one or more first features, based on one or more pre-defined criteria. The method further includes generating a summary content of the real-time conversation, based on at least the extracted one or more second features and one or more annotations associated with the determined one or more first features by use of one or more trained classifier. Further, the method includes rendering the generated summary content on a user interface displayed on at least one of the plurality of computing devices.
-
公开(公告)号：US20180012598A1
公开(公告)日：2018-01-11
申请号：US15205047
申请日：2016-07-08
Applicant: XEROX CORPORATION
Inventor： Raghuveer Thirukovalluru , Ragunathan Mariappan , Shourya Roy
CPC classification number: G10L15/26 , G06F17/30616
Abstract: The disclosed embodiments illustrate methods and systems for summary generation of a real-time conversation. The method includes receiving a real-time conversation from a plurality of computing devices over a communication network. The method further includes determining one or more first features of the real-time conversation between at least a first user and a second user. The method further includes extracting one or more second features from the one or more first features, based on one or more pre-defined criteria. The method further includes generating a summary content of the real-time conversation, based on at least the extracted one or more second features and one or more annotations associated with the determined one or more first features by use of one or more trained classifier. Further, the method includes rendering the generated summary content on a user interface displayed on at least one of the plurality of computing devices.
-
-
-
-
Search Results
5
records
(took 0.01 seconds)
