公开(公告)号：US12299015B2

公开(公告)日：2025-05-13

申请号：US18216553

申请日：2023-06-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Aparna Krishnan ,  Christopher Wright Lloyd, II ,  Jeremy K. Owen ,  Christopher J. Fong ,  Suman Sundaresh ,  Lavish Shah ,  Muhammad Basit Khurram ,  Michaela Jillings

IPC: G06F17/30 ,  G06F16/3329 ,  G06F16/334 ,  G06F16/338

Abstract: Embodiments of the disclosed technologies include generating a search prompt based on an input portion of an online dialog involving a user of a computing device. The search prompt includes a dialog summarization instruction configured to instruct a generative artificial intelligence model to generate and output a dialog summary. The search prompt is sent to a first generative model. In response to the search prompt, a search query is generated and output by the first generative model based on the dialog summary. The search query is sent to a search system. Search result data is determined based on an execution of the search query by the search system. At least some of the search result data is included in an output portion of the online dialog. The output portion is configured to be displayed at the computing device in response to the input portion of the online dialog.

公开(公告)号：US20250005050A1

公开(公告)日：2025-01-02

申请号：US18216553

申请日：2023-06-29

Applicant: Microsoft Technology Licensing, LLC

Inventor： Aparna Krishnan ,  Christopher Wright Lloyd, II ,  Jeremy K. Owen ,  Christopher J. Fong ,  Suman Sundaresh ,  Lavish Shah ,  Muhammad Basit Khurram ,  Michaela Jillings

IPC: G06F16/332 ,  G06F16/33 ,  G06F16/338

Abstract: Embodiments of the disclosed technologies include generating a search prompt based on an input portion of an online dialog involving a user of a computing device. The search prompt includes a dialog summarization instruction configured to instruct a generative artificial intelligence model to generate and output a dialog summary. The search prompt is sent to a first generative model. In response to the search prompt, a search query is generated and output by the first generative model based on the dialog summary. The search query is sent to a search system. Search result data is determined based on an execution of the search query by the search system. At least some of the search result data is included in an output portion of the online dialog. The output portion is configured to be displayed at the computing device in response to the input portion of the online dialog.

公开(公告)号：US20240378425A1

公开(公告)日：2024-11-14

申请号：US18214939

申请日：2023-06-27

Applicant: Microsoft Technology Licensing, LLC

Inventor： Praveen Kumar Bodigutla ,  Suman Sundaresh ,  Souvik Ghosh ,  Saurabh Gupta ,  Sai Krishna Bollam ,  Arya Ghatak Choudhury ,  Weiheng Qian ,  Jiarui Wang

IPC: G06N3/0455 ,  G06N3/09

Abstract: Embodiments of the disclosed technologies include receiving first message attribute data and inputting the first message attribute data to a first machine learning model. The first machine learning model is configured to generate and output suggested message content based on first correlations between message content and message acceptance data. The first machine learning model generates a first set of message content suggestions based on the first message attribute data, and selects at least one message content suggestion from the first set of message content suggestions based on message evaluation data. Feedback data related to the selected at least one message content suggestion is received. The first machine learning model is tuned based on the feedback data. The tuned first machine learning model generates a second set of message content suggestions based on the first message attribute data.

公开(公告)号：US20240378424A1

公开(公告)日：2024-11-14

申请号：US18214905

申请日：2023-06-27

Applicant: Microsoft Technology Licensing, LLC

Inventor： Praveen Kumar Bodigutla ,  Suman Sundaresh ,  Souvik Ghosh ,  Saurabh Gupta ,  Sai Krishna Bollam ,  Arya Ghatak Choudhury ,  Weiheng Qian ,  Jiarui Wang

IPC: G06N3/0455 ,  G06N3/08

Abstract: Embodiments of the disclosed technologies include configuring a first machine learning model to generate and output suggested message content based on first correlations between message content and message acceptance data, where the first machine learning model includes a first encoder-decoder model architecture, configuring a second machine learning model to generate and output message evaluation data based on second correlations between the message content and the message acceptance data, where the second machine learning model includes a second encoder-decoder model architecture, coupling an output of the first machine learning model to an input of the second machine learning model, and coupling an output of the second machine learning model to an input of the first machine learning model.