Patents by Inventor Fangyi Zhao
Fangyi Zhao has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11863711Abstract: A transcript of a conference is processed to extract a conference summary. The transcript includes strings that are associated with respective timestamps and respective speaker identifiers. Speaker segments—sequences of consecutive strings attributed to the same speaker—are identified in the transcript. A speaker segment is selected based on its duration in time and one or more strings are selected from with the selected speaker segment for inclusion in the conference summary. A short video conference summary or a short audio conference summary is then generated using timestamps from the transcript associated with strings that have been selected for inclusion in the conference summary. The short video or audio summary may be presented to users to enable efficient storage and transmission of information from the conference within a unified communications system.Type: GrantFiled: October 10, 2022Date of Patent: January 2, 2024Assignee: Zoom Video Communications, Inc.Inventors: Tao Huang, Xiaoli Song, Hui Wen, Melinda Min Xiao-Devins, Ran Yan, Fangyi Zhao
-
Publication number: 20230245658Abstract: Methods and systems provide an asynchronous pipeline for artificial intelligence service requests. In one embodiment, the system receives, at a gateway service, access to content associated with a communication session; sends, to an artificial intelligence (AI) cluster including a number of AI services, a data payload, the data payload including a location to access the content and a number of requests for AI services to be performed by one or more AI models hosted on the AI cluster using the content as an input; receives one or more AI service results as the AI cluster completes the corresponding requests for the AI services; and stores each received AI service result in one or more databases.Type: ApplicationFiled: January 31, 2022Publication date: August 3, 2023Inventors: Haifeng Geng, Jian Jin, Stephen Muchovej, Mengxiao Qian, Min Xiao-Devins, Fangyi Zhao
-
Patent number: 11616658Abstract: A transcript of a conference (e.g., a video conference, an audio conference, or a telephone call with two or more participants) is processed to extract a conference summary. A graphical user interface is presented that enables a user to edit highlighting to select portions of a conference recording for inclusion in the conference summary. The user can edit highlighting on strings of a transcript and/or on a playback slide bar and the highlighting edits are propagated to both of these interfaces. Video clips selected for inclusion in a summary based on timestamps of strings in a transcript may be extended forward in time to incorporate a nearest I-frame of video. The short video or audio summary may be presented to users along with a text summary of the conference to enable efficient storage and transmission of information from the conference within a unified communications system.Type: GrantFiled: April 30, 2021Date of Patent: March 28, 2023Assignee: Zoom Video Communications, Inc.Inventors: Dan Hu, Hao Huang, Tao Huang, Dingping Jiang, Shuo Luo, Juhua Ma, Chuan Qin, Xiaoli Song, Facheng Wang, Hongjuan Wang, Hui Wen, Melinda Min Xiao-Devins, Qingquan Xie, Ran Yan, Fangyi Zhao
-
Publication number: 20230035155Abstract: A transcript of a conference (e.g., a video conference, an audio conference, or a telephone call with two or more participants) is processed to extract a conference summary. The transcript includes strings that are associated with respective timestamps and respective speaker identifiers. Speaker segments—sequences of consecutive strings attributed to the same speaker—are identified in the transcript. A speaker segment is selected based on its duration in time and one or more strings are selected from with the selected speaker segment for inclusion in the conference summary. A short video conference summary or a short audio conference summary is then generated using timestamps from the transcript associated with strings (e.g., sentences) that have been selected for inclusion in the conference summary. The short video or audio summary may be presented to users to enable efficient storage and transmission of information from the conference within a unified communications system.Type: ApplicationFiled: October 10, 2022Publication date: February 2, 2023Inventors: Tao Huang, Xiaoli Song, Hui Wen, Melinda Min Xiao-Devins, Ran Yan, Fangyi Zhao
-
Patent number: 11570403Abstract: A transcript of a conference (e.g., a video conference, an audio conference, or a telephone call with two or more participants) is processed to extract a conference summary. A short video conference summary or a short audio conference summary is then generated using timestamps from the transcript associated with strings (e.g., sentences) in the transcript that have been selected for highlighting as part of the conference summary. The short video or audio summary may be presented to users along with a text summary of the conference to enable efficient storage and transmission of information from the conference within a unified communications system.Type: GrantFiled: April 30, 2021Date of Patent: January 31, 2023Assignee: Zoom Video Communications, Inc.Inventors: Tao Huang, Xiaoli Song, Hui Wen, Melinda Min Xiao-Devins, Ran Yan, Fangyi Zhao
-
Publication number: 20220353469Abstract: A transcript of a conference (e.g., a video conference, an audio conference, or a telephone call with two or more participants) is processed to extract a conference summary. A short video conference summary or a short audio conference summary is then generated using timestamps from the transcript associated with strings (e.g., sentences) in the transcript that have been selected for highlighting as part of the conference summary. The short video or audio summary may be presented to users along with a text summary of the conference to enable efficient storage and transmission of information from the conference within a unified communications system.Type: ApplicationFiled: April 30, 2021Publication date: November 3, 2022Inventors: Tao Huang, Xiaoli Song, Hui Wen, Melinda Min Xiao-Devins, Ran Yan, Fangyi Zhao
-
Publication number: 20220353470Abstract: A transcript of a conference (e.g., a video conference, an audio conference, or a telephone call with two or more participants) is processed to extract a conference summary. The transcript includes strings that are associated with respective timestamps and respective speaker identifiers. Speaker segments—sequences of consecutive strings attributed to the same speaker—are identified in the transcript. A speaker segment is selected based on its duration in time and one or more strings are selected from with the selected speaker segment for inclusion in the conference summary. A short video conference summary or a short audio conference summary is then generated using timestamps from the transcript associated with strings (e.g., sentences) that have been selected for inclusion in the conference summary. The short video or audio summary may be presented to users to enable efficient storage and transmission of information from the conference within a unified communications system.Type: ApplicationFiled: April 30, 2021Publication date: November 3, 2022Inventors: Tao Huang, Xiaoli Song, Hui Wen, Melinda Min Xiao-Devins, Ran Yan, Fangyi Zhao
-
Publication number: 20220353101Abstract: A transcript of a conference (e.g., a video conference, an audio conference, or a telephone call with two or more participants) is processed to extract a conference summary. A graphical user interface is presented that enables a user to edit highlighting to select portions of a conference recording for inclusion in the conference summary. The user can edit highlighting on strings of a transcript and/or on a playback slide bar and the highlighting edits are propagated to both of these interfaces. Video clips selected for inclusion in a summary based on timestamps of strings in a transcript may be extended forward in time to incorporate a nearest I-frame of video. The short video or audio summary may be presented to users along with a text summary of the conference to enable efficient storage and transmission of information from the conference within a unified communications system.Type: ApplicationFiled: April 30, 2021Publication date: November 3, 2022Inventors: Dan Hu, Hao Huang, Tao Huang, Dingping Jiang, Shuo Luo, Juhua Ma, Chuan Qin, Xiaoli Song, Facheng Wang, Hongjuan Wang, Hui Wen, Melinda Min Xiao-Devins, Qingquan Xie, Ran Yan, Fangyi Zhao
-
Publication number: 20220353100Abstract: A transcript of a conference (e.g., a video conference, an audio conference, or a telephone call with two or more participants) is processed to extract a conference summary. Scores are determined for strings of the transcript that are used to select strings for inclusion in the conference summary. Determining the scores includes determining respective sentence vectors for strings. A sentence vector has elements corresponding to words in the transcript that are proportional to occurrences of the word in the string and inversely proportional to occurrences of the word in the transcript. A short video conference summary or a short audio conference summary is then generated using timestamps from the transcript associated with strings (e.g., sentences) that have been selected for inclusion in the conference summary. The short video or audio summary may be presented to users to enable efficient storage and transmission of conference information within a unified communications system.Type: ApplicationFiled: April 30, 2021Publication date: November 3, 2022Inventors: Tao Huang, Xiaoli Song, Hui Wen, Melinda Min Xiao-Devins, Ran Yan, Fangyi Zhao
-
Patent number: 11470279Abstract: A transcript of a conference (e.g., a video conference, an audio conference, or a telephone call with two or more participants) is processed to extract a conference summary. The transcript includes strings that are associated with respective timestamps and respective speaker identifiers. Speaker segments—sequences of consecutive strings attributed to the same speaker—are identified in the transcript. A speaker segment is selected based on its duration in time and one or more strings are selected from with the selected speaker segment for inclusion in the conference summary. A short video conference summary or a short audio conference summary is then generated using timestamps from the transcript associated with strings (e.g., sentences) that have been selected for inclusion in the conference summary. The short video or audio summary may be presented to users to enable efficient storage and transmission of information from the conference within a unified communications system.Type: GrantFiled: April 30, 2021Date of Patent: October 11, 2022Assignee: Zoom Video Communications, Inc.Inventors: Tao Huang, Xiaoli Song, Hui Wen, Melinda Min Xiao-Devins, Ran Yan, Fangyi Zhao
-
Patent number: 10434348Abstract: The invention discloses a plant type active antiflaming extinguishant and preparation method and application thereof, wherein the plant type active antiflaming extinguishant is mainly prepared by compounding 15-20% of plant anti-burning agent, 8-17% of plant composite flame retardant active agent and 63-82% of plant slag water, etc.; and mixed with water at a concentration of 1-5%, and the mixed liquid is filled into fire extinguishing equipments for supporting use. The plant type active flame retardant extinguishing agent provided by the present invention increases a variety of plant fruits, increases the different sources of plant protein, pectin, polyhydroxy compounds rich in tannin, lignin and anti-burning material, and obtains a stronger extinguishing function and an ideal extinguishing effect, which is beyond the reach of the existing fire extinguishing agent; raw material is easy to get and its price is low, and manufacturing process and required equipment are easy to access.Type: GrantFiled: October 26, 2017Date of Patent: October 8, 2019Assignee: NINGBO MERCURY ENVIRONMENTAL TECHNOLOGY CO., LTD.Inventors: Zhongwei Zhao, Fangyi Zhao, He Zhuo, Chenguang Zhuo
-
Publication number: 20190105522Abstract: The invention discloses a plant type active antiflaming extinguishant and preparation method and application thereof, wherein the plant type active antiflaming extinguishant is mainly prepared by compounding 15-20% of plant anti-burning agent, 8-17% of plant composite flame retardant active agent and 63-82% of plant slag water, etc.; and mixed with water at a concentration of 1-5%, and the mixed liquid is filled into fire extinguishing equipments for supporting use. The plant type active flame retardant extinguishing agent provided by the present invention increases a variety of plant fruits, increases the different sources of plant protein, pectin, polyhydroxy compounds rich in tannin, lignin and anti-burning material, and obtains a stronger extinguishing function and an ideal extinguishing effect, which is beyond the reach of the existing fire extinguishing agent; raw material is easy to get and its price is low, and manufacturing process and required equipment are easy to access.Type: ApplicationFiled: October 26, 2017Publication date: April 11, 2019Applicant: Ningbo Mercury Environmental Technology Co., Ltd.Inventors: Zhongwei ZHAO, Fangyi Zhao, He Zhuo, Chenguang ZHUO