-
公开(公告)号：US20230049813A1
公开(公告)日：2023-02-16
申请号：US17829093
申请日：2022-05-31
发明人： Tianlin Shi
摘要： Techniques for initiating system actions based on conversational content are disclosed. A system identifies a first conversational moment type. The first conversational moment type is defined by a first set of one or more conversational conditions. The system receives a user-selected action to be performed by the system in response to detecting conversational moments of the first conversational moment type. The system stores the user-selected action in association with the first conversational moment type. The system performs the user-selected action in response to detecting the conversational moments of the first conversational moment type.
-
公开(公告)号：US20210306458A1
公开(公告)日：2021-09-30
申请号：US17135342
申请日：2020-12-28
发明人： Tianlin Shi , Peter Elliot Schmidt-Nielsen , Navjot Matharu , Alexander Donald Roe , JungHa Lee , Syed Zayd Enam
摘要： A conversation may be monitored in real time using a trained machine learning model. This real-time monitoring may detect attributes of a conversation, such as a conversation type, a state of a conversation, as well as other attributes that help specify a context of a conversation. Contextually appropriate behavioral targets may be provided by machine learning model to an agent participating in a conversation. In some embodiments, these “behavioral targets” are identified by applying a set of rules to the contemporaneously identified conversation attributes. The behavioral targets may be defined in advance prior to the start of a conversation. In this way, the machine learning model may be trained to associate particular behavioral target(s) with one or more conversation attributes (or collections of attributes). This facilitates the real-time monitoring of a conversation and contemporaneous guidance of an agent with machine-identified behavioral targets.
-
公开(公告)号：US11049497B1
公开(公告)日：2021-06-29
申请号：US17083486
申请日：2020-10-29
发明人： Tianlin Shi , Kenneth George Oetzel
IPC分类号： G10L15/16 , G10L15/22 , G06F21/62 , G10L15/06 , G10L25/51 , G06N20/00 , G10L15/08 , H04M3/51
摘要： Described techniques select portions of an audio stream for transmission to a trained machine learning application, which generates response recommendations in real-time. This real-time response is facilitated by the system identifying, selecting and transmitting those portions of the audio stream likely to be most relevant to the conversation. Portions of an audio stream less likely to be relevant to the conversation are identified accordingly and not transmitted. The system may identify the relevant portions of an audio stream by detecting events in a contemporaneous event stream, use a trained machine learning model to identify events in an audio stream, or both.
-
公开(公告)号：US10965811B1
公开(公告)日：2021-03-30
申请号：US16944718
申请日：2020-07-31
发明人： Tianlin Shi , Peter Elliot Schmidt-Nielsen , Navjot Matharu , Alexander Donald Roe , JungHa Lee , Syed Zayd Enam
摘要： A conversation may be monitored in real time using a trained machine learning model. This real-time monitoring may detect attributes of a conversation, such as a conversation type, a state of a conversation, as well as other attributes that help specify a context of a conversation. Contextually appropriate behavioral targets may be provided by machine learning model to an agent participating in a conversation. In some embodiments, these “behavioral targets” are identified by applying a set of rules to the contemporaneously identified conversation attributes. The behavioral targets may be defined in advance prior to the start of a conversation. In this way, the machine learning model may be trained to associate particular behavioral target(s) with one or more conversation attributes (or collections of attributes). This facilitates the real-time monitoring of a conversation and contemporaneous guidance of an agent with machine-identified behavioral targets.
-
公开(公告)号：US11115531B1
公开(公告)日：2021-09-07
申请号：US17135342
申请日：2020-12-28
发明人： Tianlin Shi , Peter Elliot Schmidt-Nielsen , Navjot Matharu , Alexander Donald Roe , JungHa Lee , Syed Zayd Enam
摘要： A conversation may be monitored in real time using a trained machine learning model. This real-time monitoring may detect attributes of a conversation, such as a conversation type, a state of a conversation, as well as other attributes that help specify a context of a conversation. Contextually appropriate behavioral targets may be provided by machine learning model to an agent participating in a conversation. In some embodiments, these “behavioral targets” are identified by applying a set of rules to the contemporaneously identified conversation attributes. The behavioral targets may be defined in advance prior to the start of a conversation. In this way, the machine learning model may be trained to associate particular behavioral target(s) with one or more conversation attributes (or collections of attributes). This facilitates the real-time monitoring of a conversation and contemporaneous guidance of an agent with machine-identified behavioral targets.
-
公开(公告)号：US11417337B1
公开(公告)日：2022-08-16
申请号：US17400915
申请日：2021-08-12
发明人： Tianlin Shi
摘要： Techniques for initiating system actions based on conversational content are disclosed. A system identifies a first conversational moment type. The first conversational moment type is defined by a first set of one or more conversational conditions. The system receives a user-selected action to be performed by the system in response to detecting conversational moments of the first conversational moment type. The system stores the user-selected action in association with the first conversational moment type. The system performs the user-selected action in response to detecting the conversational moments of the first conversational moment type.
-
公开(公告)号：US11282507B1
公开(公告)日：2022-03-22
申请号：US17352543
申请日：2021-06-21
发明人： Tianlin Shi , Kenneth George Oetzel
IPC分类号： G10L15/16 , G10L15/22 , G06F21/62 , G10L15/06 , G10L25/51 , G06N20/00 , G10L15/08 , H04M3/51
摘要： Described techniques select portions of an audio stream for transmission to a trained machine learning application, which generates response recommendations in real-time. This real-time response is facilitated by the system identifying, selecting and transmitting those portions of the audio stream likely to be most relevant to the conversation. Portions of an audio stream less likely to be relevant to the conversation are identified accordingly and not transmitted. The system may identify the relevant portions of an audio stream by detecting events in a contemporaneous event stream, use a trained machine learning model to identify events in an audio stream, or both.
-
8.发明授权公开(公告)号：US11157695B1
公开(公告)日：2021-10-26
申请号：US17206591
申请日：2021-03-19
发明人： Tianlin Shi , Saurabh Misra , Motoki Dean Wu
IPC分类号： G06F40/289 , G10L15/08 , G06N20/00
摘要： A conversation may be monitored in real time using a trained machine learning model to identify a desired outcome of a conversation and generate one or more phrases for accomplishing the desired outcome. A confidence score may also be determined for one or more phrases that indicates a likelihood that the one or more phrases may help accomplish the desired outcome of the conversation. In some examples, a confidence score may be based on whether an agent, a caller, or both responded unfavorably to a similar phrase used previously in another conversation. In other examples, a confidence score corresponding to one or more phrases may be based on whether a prior conversation in which one or more similar phrases was used resulted in the desired outcome being accomplished.
-
公开(公告)号：US20220139382A1
公开(公告)日：2022-05-05
申请号：US17579059
申请日：2022-01-19
发明人： Tianlin Shi , Kenneth George Oetzel
摘要： Described techniques select portions of an audio stream for transmission to a trained machine learning application, which generates response recommendations in real-time. This real-time response is facilitated by the system identifying, selecting and transmitting those portions of the audio stream likely to be most relevant to the conversation. Portions of an audio stream less likely to be relevant to the conversation are identified accordingly and not transmitted. The system may identify the relevant portions of an audio stream by detecting events in a contemporaneous event stream, use a trained machine learning model to identify events in an audio stream, or both.
-
公开(公告)号：US20210306459A1
公开(公告)日：2021-09-30
申请号：US17135364
申请日：2020-12-28
发明人： Tianlin Shi , Peter Elliot Schmidt-Nielsen , Navjot Matharu , Alexander Donald Roe , JungHa Lee , Syed Zayd Enam
摘要： A conversation may be monitored in real time using a trained machine learning model. This real-time monitoring may detect attributes of a conversation, such as a conversation type, a state of a conversation, as well as other attributes that help specify a context of a conversation. Contextually appropriate behavioral targets may be provided by machine learning model to an agent participating in a conversation. In some embodiments, these “behavioral targets” are identified by applying a set of rules to the contemporaneously identified conversation attributes. The behavioral targets may be defined in advance prior to the start of a conversation. In this way, the machine learning model may be trained to associate particular behavioral target(s) with one or more conversation attributes (or collections of attributes). This facilitates the real-time monitoring of a conversation and contemporaneous guidance of an agent with machine-identified behavioral targets.
-
-
-
-
-
-
-
-
-
搜索结果
13 条记录 (耗时 0.015 秒)
