-
公开(公告)号:US11605387B1
公开(公告)日:2023-03-14
申请号:US17217148
申请日:2021-03-30
Applicant: Amazon Technologies, Inc.
Inventor: Yamini Muralitharan , Mugunthan Govindaraju , Aparna Nandyal , Jintomon Joseph , Suresh Boddu , Leopold Bushkin
IPC: G10L15/32 , G10L15/22 , G10L13/033 , G10L15/18
Abstract: A speech-processing system may provide access to multiple virtual assistants. Speech-processing systems may perform actions for or on behalf of users with the aid of skills; e.g., a shopping skill, navigation skill, communications skill, etc. Some skills may be associated with more than one assistant. The speech-processing system may determine which assistant to invoke upon receiving a command from a user device. The identity of the virtual assistant is propagated to the skill and the device, as well as other components of the speech-processing system. In some cases, however, a multi-assistant skill may determine that an assistant other than the one initially selected by the speech-processing system is to handle the command. The skill may send the identity of the new assistant back to the speech-processing system. The speech-processing system may restart the command dissemination process to provide each component of the system with the updated assistant identity.
-
公开(公告)号:US20210398525A1
公开(公告)日:2021-12-23
申请号:US17387157
申请日:2021-07-28
Applicant: Amazon Technologies, Inc.
Inventor: Munir Mahmood , Leopold Bushkin , Alexander Thomas Loeb , Michael Schwartz , Mohammed Arif , Rongzhou Shen , Vikram Kumar Gundeti , Shemyla Anwar , Yaser Khan , Edward Page Foyle , Bo Li
Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.
-
公开(公告)号:US20210090572A1
公开(公告)日:2021-03-25
申请号:US16580721
申请日:2019-09-24
Applicant: Amazon Technologies, Inc.
Inventor: Munir Mahmood , Leopold Bushkin , Alexander Thomas Loeb , Michael Schwartz , Mohammed Arif , Rongzhou Shen , Vikram Kumar Gundeti , Shemyla Anwar , Yaser Khan , Edward Page Foyle , Bo Li
IPC: G10L15/30 , G10L15/22 , G10L15/08 , G10L13/033
Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input from a device. The NLP system may also receive one or more signals representing one or more assistants to be implemented with respect to the natural language input. The NLP system may intelligently select an assistant to be invoked with respect to the natural language input. Once the assistant is selected, the NLP system may cause content, output to a user, to have characteristics specific to the assistant.
-
公开(公告)号:US10783151B1
公开(公告)日:2020-09-22
申请号:US15197429
申请日:2016-06-29
Applicant: Amazon Technologies, Inc.
Inventor: Leopold Bushkin , Rajendra Kumar Vippagunta
IPC: G06F16/24 , G06F16/28 , G06F16/2457 , H04L29/08
Abstract: Features are provided for proactively grouping content for personalized content feeds based on the expected relevance of the content to groups or classes of users. Such proactive grouping can allow personalized (or semi-personalized) content feeds to be delivered with low user-perceived latency. The proactive grouping may be used in conjunction with a more computationally-intensive and higher-latency process for generating personalized feeds. A user's content feed may be provided using a two-phase delivery process in which an initial set of content for the feed is provided from the proactively grouped content collection with which the user is associated. While the user is viewing the initial set of content, the second phase of the delivery process may be performed in which additional content is selected specifically for the user.
-
公开(公告)号:US20230282206A1
公开(公告)日:2023-09-07
申请号:US18182762
申请日:2023-03-13
Applicant: Amazon Technologies, Inc.
Inventor: Munir Mahmood , Leopold Bushkin , Alexander Thomas Loeb , Michael Schwartz , Mohammed Arif , Rongzhou Shen , Vikram Kumar Gundeti , Shemyla Anwar , Yaser Khan , Edward Page Foyle , Bo Li
CPC classification number: G10L15/1815 , G10L15/22 , G10L15/30 , G10L13/00 , G10L2015/223
Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.
-
公开(公告)号:US11120790B2
公开(公告)日:2021-09-14
申请号:US16580643
申请日:2019-09-24
Applicant: Amazon Technologies, Inc.
Inventor: Munir Mahmood , Leopold Bushkin , Alexander Thomas Loeb , Michael Schwartz , Mohammed Arif , Rongzhou Shen , Vikram Kumar Gundeti , Shemyla Anwar , Yaser Khan , Edward Page Foyle , Bo Li
Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.
-
公开(公告)号:US20210090555A1
公开(公告)日:2021-03-25
申请号:US16580643
申请日:2019-09-24
Applicant: Amazon Technologies, Inc.
Inventor: Munir Mahmood , Leopold Bushkin , Alexander Thomas Loeb , Michael Schwartz , Mohammed Arif , Rongzhou Shen , Vikram Kumar Gundeti , Shemyla Anwar , Yaser Khan , Edward Page Foyle , Bo Li
Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.
-
公开(公告)号:US10728291B1
公开(公告)日:2020-07-28
申请号:US15197603
申请日:2016-06-29
Applicant: Amazon Technologies, Inc.
Inventor: Leopold Bushkin , Saket Saurabh , Rajendra Kumar Vippagunta
IPC: G06F15/173 , H04L29/06 , G06F3/0482 , G06F3/0484
Abstract: Features are provided for the use of persistent connections and efficient content synchronization in content delivery environments. A content management system may provide content feeds to user devices using a persistent duplex connection over which the content management system and user devices may communicate asynchronously. By using a persistent duplex connection to asynchronously communicate with user devices, the content management system can provide content for the content feeds while, in parallel, receiving requests and commands from the user devices, responding to the requests and commands, and transmitting other requests and commands to the user devices. In addition, the content management system and a particular user device can exchange information regarding the content items that the user device has or should have already received.
-
公开(公告)号:US11636851B2
公开(公告)日:2023-04-25
申请号:US17387157
申请日:2021-07-28
Applicant: Amazon Technologies, Inc.
Inventor: Munir Mahmood , Leopold Bushkin , Alexander Thomas Loeb , Michael Schwartz , Mohammed Arif , Rongzhou Shen , Vikram Kumar Gundeti , Shemyla Anwar , Yaser Khan , Edward Page Foyle , Bo Li
Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.
-
公开(公告)号:US20210090575A1
公开(公告)日:2021-03-25
申请号:US16580307
申请日:2019-09-24
Applicant: Amazon Technologies, Inc.
Inventor: Munir Mahmood , Leopold Bushkin , Alexander Thomas Loeb , Michael Schwartz , Mohammed Arif , Rongzhou Shen , Vikram Kumar Gundeti , Shemyla Anwar , Yaser Khan , Edward Page Foyle , Bo Li
IPC: G10L15/32 , G10L13/047 , G10L15/26 , G06F16/9032 , G10L17/10 , G10L15/18
Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant during a dialog between one or more users and the NLP system are described. The NLP system may receive a first natural language input and associate same with a dialog identifier. The NLP system may output audio, responsive to the first natural language input, in a first NLP system assistant's voice. Thereafter, the NLP system may receive a second natural language input and associate same with the dialog identifier. The NLP system may output audio, responsive to the second natural language input, in a second NLP system assistant's voice.
-
-
-
-
-
-
-
-
-