Patents by Inventor Junyan Chen

Junyan Chen 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).

  • Publication number: 20200302019
    Abstract: A system for training and deploying an artificial conversational entity using an artificial intelligence (AI) based communications system is disclosed. The system may comprise a memory storing machine readable instructions. The system may also comprise a processor to execute the machine readable instructions to receive a request via an artificial conversational entity. The processor may also transmit a response to the request based on a dialog tree generated from at least a model-based action generator and a memory-based action generator. The processor may further provide a training option to a user in the event the response is suboptimal. The processor may additionally receive a selection from the user via the training option. The selection may be associated with an optimal response.
    Type: Application
    Filed: March 22, 2019
    Publication date: September 24, 2020
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Matthew Brigham HALL, Weizhu CHEN, Junyan CHEN, Pengcheng HE, Yu ZHAO, Yi-Min WANG, Yuting SUN, Zheng CHEN, Katherine Winant OSBORNE
  • Publication number: 20200005118
    Abstract: Generally discussed herein are devices, systems, and methods for detecting a conversation with a virtual agent is offtrack and responding appropriately. A method can include receiving a prompt, expected responses to the prompt, and a response of an interaction session with the virtual agent, the interaction session to solve a problem of a user, determining whether the response indicates the interaction session is in an offtrack state based on the prompt, expected responses, and response, in response to a determination that the interaction session is in the offtrack state, determining a taxonomy of the offtrack state, and providing, based on the determined taxonomy, a next prompt to the interaction session.
    Type: Application
    Filed: June 28, 2018
    Publication date: January 2, 2020
    Inventors: Zhirong Chen, Junyan Chen, Xin Wan, Volodymyr Trubachov, Huicheng Song, Yanfen Song, Jiayuan Huang, Jiantao Sun, Shichao Hu, Zheng Chen
  • Publication number: 20200007380
    Abstract: Generally discussed herein are devices, systems, and methods for virtual agent selection of an option not expressly selected by a user. A method can include receiving, from a virtual agent interface device of the virtual agent device, a response regarding a problem, wherein the response is responsive to a prompt, and wherein the prompt is associated with one or more expected responses, determining whether the response is a match to one of the expected answers by performing one or more of (a) an ordinal match, (b) an inclusive match, (c) an entity match, and (d) a model match, and providing, responsive to a determination that the response is a match, a next prompt, or provide a solution to the problem, the next prompt associated with expected responses to the next prompt.
    Type: Application
    Filed: June 28, 2018
    Publication date: January 2, 2020
    Inventors: Junyan Chen, Zhirong Chen, Changhong Yuan, Eslam Kamal AbdelReheem, Bing Xu, Huicheng Song, Xin Wan
  • Patent number: 10354525
    Abstract: An alerting system includes an image capturing module continuously captures traffic images surrounding a vehicle and showing at least one traffic sign therein; a gaze detector continuously detects a gaze direction of a driver in the vehicle; a control unit analyzes the traffic images and generates a trigger signal when it determines that the traffic sign changes and the driver fails to notice the change; and an alarming device alerts the driver upon the receipt of the trigger signal.
    Type: Grant
    Filed: May 18, 2018
    Date of Patent: July 16, 2019
    Assignees: Mindtronic Al Co., Ltd., Shanghai XPT Technology Limited
    Inventors: Mu-Jen Huang, Ya-Li Tai, Yu-Sian Jiang, Tianle Chen, Junyan Zhang
  • Publication number: 20190139407
    Abstract: An alerting system includes an image capturing module continuously captures traffic images surrounding a vehicle and showing at least one traffic sign therein; a gaze detector continuously detects a gaze direction of a driver in the vehicle; a control unit analyzes the traffic images and generates a trigger signal when it determines that the traffic sign changes and the driver fails to notice the change; and an alarming device alerts the driver upon the receipt of the trigger signal.
    Type: Application
    Filed: May 18, 2018
    Publication date: May 9, 2019
    Inventors: Mu-Jen Huang, Ya-Li Tai, Yu-Sian Jiang, Tianle Chen, Junyan Zhang
  • Patent number: 8977624
    Abstract: Computer-readable media, computer systems, and computing devices facilitate enhancing a web index with uniform resource locator (URL)/non-encoding character (NEC) word pairs to facilitate relevance ranking of search results provided in response to a search query that includes NEC words. URLs are received from web pages and substrings extracted therefrom. Additional elements are received from the web page, word-broken into sequences of NEC words, and the NEC words are converted into encoding-language representations which are matched against the URL substrings to identify candidate URL/NEC pairs for utilization in relevance ranking.
    Type: Grant
    Filed: August 30, 2010
    Date of Patent: March 10, 2015
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ruihua Song, Qi Yao, Junyan Chen
  • Patent number: 8380722
    Abstract: This document describes tools for adjusting anchor text weight to provide more relevant search engine results. Specifically, these tools take advantage of a site-relationship model to consider relationships not only between an anchor text source site and a destination page but also relationships between multiple anchor text source sites to improve web searches. Consideration of these relationships aids in determining a new an anchor text weight, which in turn results in more relevant search results.
    Type: Grant
    Filed: March 29, 2010
    Date of Patent: February 19, 2013
    Assignee: Microsoft Corporation
    Inventors: Zhicheng Dou, Junyan Chen, Ruihua Song, Ji-Rong Wen
  • Patent number: 8301638
    Abstract: A method using a RankBoost-based algorithm to automatically select features for further ranking model training is provided. The method reiteratively applies a set of ranking candidates to a training data set comprising a plurality of ranking objects having a known pairwise ranking order. Each round of iteration applies a weight distribution of ranking object pairs, yields a ranking result by each ranking candidate, identifies a favored ranking candidate for the round based on the ranking results, and updates the weight distribution to be used in next iteration round by increasing weights of ranking object pairs that are poorly ranked by the favored ranking candidate. The method then infers a target feature set from the favored ranking candidates identified in the iterations.
    Type: Grant
    Filed: September 25, 2008
    Date of Patent: October 30, 2012
    Assignee: Microsoft Corporation
    Inventors: Ning-Yi Xu, Feng-Hsiung Hsu, Rui Gao, Xiong-Fei Cai, Junyan Chen
  • Publication number: 20120054192
    Abstract: Computer-readable media, computer systems, and computing devices facilitate enhancing a web index with uniform resource locator (URL)/non-encoding character (NEC) word pairs to facilitate relevance ranking of search results provided in response to a search query that includes NEC words. URLs are received from web pages and substrings extracted therefrom. Additional elements are received from the web page, word-broken into sequences of NEC words, and the NEC words are converted into encoding-language representations which are matched against the URL substrings to identify candidate URL/NEC pairs for utilization in relevance ranking.
    Type: Application
    Filed: August 30, 2010
    Publication date: March 1, 2012
    Applicant: MICROSOFT CORPORATION
    Inventors: Ruihua Song, Qi Yao, Junyan Chen
  • Publication number: 20110238644
    Abstract: This document describes tools for adjusting anchor text weight to provide more relevant search engine results. Specifically, these tools take advantage of a site-relationship model to consider relationships not only between an anchor text source site and a destination page but also relationships between multiple anchor text source sites to improve web searches. Consideration of these relationships aids in determining a new an anchor text weight, which in turn results in more relevant search results.
    Type: Application
    Filed: March 29, 2010
    Publication date: September 29, 2011
    Applicant: Microsoft Corporation
    Inventors: Zhicheng Dou, Junyan Chen, Ruihua Song, Ji-Rong Wen
  • Publication number: 20100076911
    Abstract: A method using a RankBoost-based algorithm to automatically select features for further ranking model training is provided. The method reiteratively applies a set of ranking candidates to a training data set comprising a plurality of ranking objects having a known pairwise ranking order. Each round of iteration applies a weight distribution of ranking object pairs, yields a ranking result by each ranking candidate, identifies a favored ranking candidate for the round based on the ranking results, and updates the weight distribution to be used in next iteration round by increasing weights of ranking object pairs that are poorly ranked by the favored ranking candidate. The method then infers a target feature set from the favored ranking candidates identified in the iterations.
    Type: Application
    Filed: September 25, 2008
    Publication date: March 25, 2010
    Applicant: Microsoft Corporation
    Inventors: Ning-Yi Xu, Junyan Chen, Rui Gao, Xiong-Fei Cai, Feng-Hsiung Hsu
  • Publication number: 20090276414
    Abstract: Search results provided by a search engine (e.g., for the Internet) are improved and/or made more accurate by addressing the limited availability of human labeled training data for certain domains (e.g., languages other than English, within certain date ranges, corresponding to queries over a certain length, etc.). More particularly, a ranking model trained on in-domain data, for which a small amount of human labeled training data (e.g., query/URL pairs) is available (e.g., languages other than English) is adjusted based upon out-domain data, for which a large amount of human labeled training data (e.g., query/URL pairs) is available (e.g., English). Thus, even though the resulting adapted in-domain ranking model is used in the context of in-domain data (e.g., non-English) to provide search results, the search results are improved because they are influenced by an abundance of, albeit out-domain, human labeled training data.
    Type: Application
    Filed: April 30, 2008
    Publication date: November 5, 2009
    Applicant: MICROSOFT CORPORATION
    Inventors: Jianfeng Gao, Qiang Wu, Jiangyun Song, Junyan Chen, Steven Yao
  • Patent number: D887501
    Type: Grant
    Filed: January 30, 2019
    Date of Patent: June 16, 2020
    Assignee: GUANGDONG QMAN CULTURE COMMUNICATION CO., LTD.
    Inventors: Junyan Zhan, Tiexin Chen