公开(公告)号：US11804211B2

公开(公告)日：2023-10-31

申请号：US17112418

申请日：2020-12-04

Applicant: Google LLC

Inventor： Asaf Aharoni ,  Yaniv Leviathan ,  Eyal Segalis ,  Gal Elidan ,  Sasha Goldshtein ,  Tomer Amiaz ,  Deborah Cohen

IPC: G06N20/00 ,  G10L15/22 ,  H04M3/493 ,  G10L15/06 ,  H04L67/133 ,  G10L15/02 ,  G10L15/04

CPC classification number: G10L15/063 ,  G06N20/00 ,  G10L15/02 ,  G10L15/04 ,  G10L15/22 ,  H04L67/133 ,  H04M3/493 ,  G10L2015/0635

Abstract: Implementations are directed to providing a voice bot development platform that enables a third-party developer to train a voice bot based on training instance(s). The training instance(s) can each include training input and training output. The training input can include a portion of a corresponding conversation and a prior context of the corresponding conversation. The training output can include a corresponding ground truth response to the portion of the corresponding conversation. Subsequent to training, the voice bot can be deployed for conducting conversations on behalf of a third-party. In some implementations, the voice bot is further trained based on a corresponding feature emphasis input that attentions the voice bot to a particular feature of the portion of the corresponding conversation. In some additional or alternative implementations, the voice bot is further trained to interact with third-party system(s) via remote procedure calls (RPCs).

公开(公告)号：US20250061890A1

公开(公告)日：2025-02-20

申请号：US18936314

申请日：2024-11-04

Applicant: GOOGLE LLC

Inventor： Asaf Aharoni ,  Yaniv Leviathan ,  Eyal Segalis ,  Gal Elidan ,  Sasha Goldshtein ,  Tomer Amiaz ,  Deborah Cohen

IPC: G10L15/06 ,  G10L15/22 ,  G10L15/30 ,  H04L67/133 ,  H04L67/53 ,  H04M3/51

Abstract: Implementations are directed to providing a voice bot development platform that enables a third-party developer to train a voice bot based on training instance(s). The training instance(s) can each include training input and training output. The training input can include a portion of a corresponding conversation and a prior context of the corresponding conversation. The training output can include a corresponding ground truth response to the portion of the corresponding conversation. Subsequent to training, the voice bot can be deployed for conducting conversations on behalf of a third-party. In some implementations, the voice bot is further trained based on a corresponding feature emphasis input that attentions the voice bot to a particular feature of the portion of the corresponding conversation. In some additional or alternative implementations, the voice bot is further trained to interact with third-party system(s) via remote procedure calls (RPCs).

公开(公告)号：US11929900B2

公开(公告)日：2024-03-12

申请号：US18158623

申请日：2023-01-24

Applicant: Google LLC

Inventor： Mikhal Shemer ,  Roee Engelberg ,  Yonit Tova Halperin Worzel ,  Alex Gontmakher ,  Alexander Goldshtein ,  Gal Elidan ,  Benjamin Dov Kessler

IPC: G06F15/173 ,  G06F9/455 ,  G06F18/214 ,  H04L41/0604 ,  H04L41/0631 ,  H04L43/065 ,  H04L43/0817

CPC classification number: H04L43/0817 ,  G06F9/45558 ,  G06F18/214 ,  H04L41/0627 ,  H04L41/0631 ,  H04L43/065 ,  G06F2009/45575 ,  G06F2009/45595

Abstract: A cloud network is a complex environment in which hundreds and thousands of users or entities can each host, create, modify, and develop multiple virtual machines. Each virtual machine can have complex behavior unknown to the provider or maintainer of the cloud. Technologies disclosed include methods, systems, and apparatuses to monitor the complex environment to detect network anomalies using machine learning techniques. In addition, techniques to modify and adapt to user feedback are provided allowing the developed models to be tuned for specific use cases, virtual machine types, and users.

公开(公告)号：US20240163193A1

公开(公告)日：2024-05-16

申请号：US18419024

申请日：2024-01-22

Applicant: Google LLC

Inventor： Mikhal Shemer ,  Roee Engelberg ,  Yonit Tova Halperin Worzel ,  Alex Gontmakher ,  Alexander Goldshtein ,  Gal Elidan ,  Benjamin Dov Kessler

IPC: H04L43/0817 ,  G06F9/455 ,  G06F18/214 ,  H04L41/0604 ,  H04L41/0631 ,  H04L43/065

CPC classification number: H04L43/0817 ,  G06F9/45558 ,  G06F18/214 ,  H04L41/0627 ,  H04L41/0631 ,  H04L43/065 ,  G06F2009/45575 ,  G06F2009/45595

Abstract: A cloud network is a complex environment in which hundreds and thousands of users or entities can each host, create, modify, and develop multiple virtual machines. Each virtual machine can have complex behavior unknown to the provider or maintainer of the cloud. Technologies disclosed include methods, systems, and apparatuses to monitor the complex environment to detect network anomalies using machine learning techniques. In addition, techniques to modify and adapt to user feedback are provided allowing the developed models to be tuned for specific use cases, virtual machine types, and users.

公开(公告)号：US11595282B2

公开(公告)日：2023-02-28

申请号：US17381909

申请日：2021-07-21

Applicant: Google LLC

Inventor： Mikhal Shemer ,  Roee Engelberg ,  Yonit Tova Halperin Worzel ,  Alex Gontmakher ,  Alexander Goldshtein ,  Gal Elidan ,  Benjamin Dov Kessler

IPC: G06F15/173 ,  H04L43/0817 ,  G06F9/455 ,  G06K9/62 ,  H04L41/0604 ,  H04L41/0631 ,  H04L43/065

Abstract: A cloud network is a complex environment in which hundreds and thousands of users or entities can each host, create, modify, and develop multiple virtual machines. Each virtual machine can have complex behavior unknown to the provider or maintainer of the cloud. Technologies disclosed include methods, systems, and apparatuses to monitor the complex environment to detect network anomalies using machine learning techniques. In addition, techniques to modify and adapt to user feedback are provided allowing the developed models to be tuned for specific use cases, virtual machine types, and users.

公开(公告)号：US12283270B2

公开(公告)日：2025-04-22

申请号：US17541098

申请日：2021-12-02

Applicant: GOOGLE LLC

Inventor： Asaf Aharoni ,  Yaniv Leviathan ,  Eyal Segalis ,  Gal Elidan ,  Sasha Goldshtein ,  Tomer Amiaz ,  Deborah Cohen

IPC: G10L15/06 ,  G10L15/22 ,  G10L15/30 ,  H04L67/133 ,  H04L67/53 ,  H04M3/51

Abstract: Implementations are directed to providing a voice bot development platform that enables a third-party developer to train a voice bot based on training instance(s). The training instance(s) can each include training input and training output. The training input can include a portion of a corresponding conversation and a prior context of the corresponding conversation. The training output can include a corresponding ground truth response to the portion of the corresponding conversation. Subsequent to training, the voice bot can be deployed for conducting conversations on behalf of a third-party. In some implementations, the voice bot is further trained based on a corresponding feature emphasis input that attentions the voice bot to a particular feature of the portion of the corresponding conversation. In some additional or alternative implementations, the voice bot is further trained to interact with third-party system(s) via remote procedure calls (RPCs).

公开(公告)号：US20230164046A1

公开(公告)日：2023-05-25

申请号：US18158623

申请日：2023-01-24

Applicant: Google LLC

Inventor： Mikhal Shemer ,  Roee Engelberg ,  Yonit Tova Halperin Worzel ,  Alex Gontmakher ,  Alexander Goldshtein ,  Gal Elidan ,  Benjamin Dov Kessler

IPC: H04L43/0817 ,  G06F9/455 ,  H04L41/0604 ,  H04L41/0631 ,  H04L43/065 ,  G06F18/214

CPC classification number: H04L43/0817 ,  G06F9/45558 ,  H04L41/0627 ,  H04L41/0631 ,  H04L43/065 ,  G06F18/214 ,  G06F2009/45575 ,  G06F2009/45595

Abstract: A cloud network is a complex environment in which hundreds and thousands of users or entities can each host, create, modify, and develop multiple virtual machines. Each virtual machine can have complex behavior unknown to the provider or maintainer of the cloud. Technologies disclosed include methods, systems, and apparatuses to monitor the complex environment to detect network anomalies using machine learning techniques. In addition, techniques to modify and adapt to user feedback are provided allowing the developed models to be tuned for specific use cases, virtual machine types, and users.

公开(公告)号：US20220029902A1

公开(公告)日：2022-01-27

申请号：US17381909

申请日：2021-07-21

Applicant: Google LLC

Inventor： Mikhal Shemer ,  Roee Engelberg ,  Yonit Tova Halperin Worzel ,  Alex Gontmakher ,  Alexander Goldshtein ,  Gal Elidan ,  Benjamin Dov Kessler

IPC: H04L12/26 ,  H04L12/24 ,  G06F9/455 ,  G06K9/62

Abstract: A cloud network is a complex environment in which hundreds and thousands of users or entities can each host, create, modify, and develop multiple virtual machines. Each virtual machine can have complex behavior unknown to the provider or maintainer of the cloud. Technologies disclosed include methods, systems, and apparatuses to monitor the complex environment to detect network anomalies using machine learning techniques. In addition, techniques to modify and adapt to user feedback are provided allowing the developed models to be tuned for specific use cases, virtual machine types, and users.