Patents by Inventor Yunqi ZHANG
Yunqi ZHANG 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: 20230279584Abstract: The present invention provides an elastic fiber dry spinning component and spinning part. The spinning component includes: a temperature control box (3) including a box body (31), wherein the box body (31) is longitudinally provided with multiple polymer solution channels (32) separated from each other; areas in the box body (31) other than the polymer solution channels (32) are cavities, and the cavities are used for circulation of a fluid medium that exchanges heat with an elastic fiber dry spinning polymer solution in the polymer solution channels (32); and a spinneret part (4) detachably connected to the temperature control box (3), wherein the spinneret part (4) includes multiple spinneret orifice sets (41) separated from each other, and the multiple spinneret orifice sets (41) are correspondingly in communication with outlets of the multiple polymer solution channels (32).Type: ApplicationFiled: May 11, 2023Publication date: September 7, 2023Inventors: Zutao YUAN, Yunqi ZHANG
-
Patent number: 11714686Abstract: Techniques of managing oversubscription of network resources are disclosed herein. In one embodiment, a method includes receiving resource utilization data of a virtual machine hosted on a server in a computing system. The virtual machine is configured to perform a task. The method also includes determining whether a temporal pattern of the resource utilization data associated with the virtual machine indicates one or more cycles of resource utilization as a function of time and in response to determining that the temporal pattern associated with the virtual machine indicates one or more cycles of resource utilization as a function of time, causing the virtual machine to migrate to another server that is not oversubscribed by virtual machines in the computing system.Type: GrantFiled: May 4, 2020Date of Patent: August 1, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Ricardo Bianchini, William Clausen, Marcus Fontoura, Inigo Goiri, Yunqi Zhang
-
Patent number: 11481597Abstract: A system and method of configuring a graphical control structure for controlling a machine learning-based automated dialogue system includes configuring a root dialogue classification node that performs a dialogue intent classification task for utterance data input; configuring a plurality of distinct dialogue state classification nodes that are arranged downstream of the root dialogue classification node; configuring a graphical edge connection between the root dialogue classification node and the plurality of distinct state dialogue classification nodes that graphically connects each of the plurality of distinct state dialogue classification nodes to the root dialogue classification node, wherein (i) the root dialogue classification node, (ii) the plurality of distinct classification nodes, (iii) and the transition edge connections define a graphical dialogue system control structure that governs an active dialogue between a user and the machine learning-based automated dialogue system.Type: GrantFiled: January 15, 2021Date of Patent: October 25, 2022Assignee: Clinc, Inc.Inventors: Parker Hill, Jason Mars, Lingjia Tang, Michael A. Laurenzano, Johann Hauswald, Yiping Kang, Yunqi Zhang
-
Publication number: 20210241066Abstract: A system and method of configuring a graphical control structure for controlling a machine learning-based automated dialogue system includes configuring a root dialogue classification node that performs a dialogue intent classification task for utterance data input; configuring a plurality of distinct dialogue state classification nodes that are arranged downstream of the root dialogue classification node; configuring a graphical edge connection between the root dialogue classification node and the plurality of distinct state dialogue classification nodes that graphically connects each of the plurality of distinct state dialogue classification nodes to the root dialogue classification node, wherein (i) the root dialogue classification node, (ii) the plurality of distinct classification nodes, (iii) and the transition edge connections define a graphical dialogue system control structure that governs an active dialogue between a user and the machine learning-based automated dialogue system.Type: ApplicationFiled: January 15, 2021Publication date: August 5, 2021Inventors: Parker Hill, Jason Mars, Lingjia Tang, Michael A. Laurenzano, Johann Hauswald, Yiping Kang, Yunqi Zhang
-
Patent number: 11043208Abstract: Systems and methods for intelligently training a subject machine learning model includes identifying new observations comprising a plurality of distinct samples unseen by a target model during a prior training; creating an incremental training corpus based on randomly sampling a collection of training data samples that includes a plurality of new observations and a plurality of historical training data samples used in the prior training of the target model; implementing a first training mode that includes an incremental training of the target model using samples from the incremental training corpus as model training input; computing performance metrics of the target model based on the incremental training; evaluating the performance metrics of the target model against training mode thresholds; and selectively choosing based on the evaluation one of maintaining the first training mode and automatically switching to a second training mode that includes a full retraining of the target model.Type: GrantFiled: February 19, 2021Date of Patent: June 22, 2021Assignee: Clinc, Inc.Inventors: Daniel C. Michelin, Jonathan K. Kummerfeld, Kevin Leach, Stefan Larson, Joseph J. Peper, Yunqi Zhang
-
Patent number: 10936936Abstract: A system and method of configuring a graphical control structure for controlling a machine learning-based automated dialogue system includes configuring a root dialogue classification node that performs a dialogue intent classification task for utterance data input; configuring a plurality of distinct dialogue state classification nodes that are arranged downstream of the root dialogue classification node; configuring a graphical edge connection between the root dialogue classification node and the plurality of distinct state dialogue classification nodes that graphically connects each of the plurality of distinct state dialogue classification nodes to the root dialogue classification node, wherein (i) the root dialogue classification node, (ii) the plurality of distinct classification nodes, (iii) and the transition edge connections define a graphical dialogue system control structure that governs an active dialogue between a user and the machine learning-based automated dialogue system.Type: GrantFiled: November 13, 2019Date of Patent: March 2, 2021Assignee: Clinc, Inc.Inventors: Parker Hill, Jason Mars, Lingjia Tang, Michael A. Laurenzano, Johann Hauswald, Yiping Kang, Yunqi Zhang
-
Publication number: 20200364410Abstract: A system and method for intelligently configuring a machine learning-based dialogue system includes a conversational deficiency assessment of a target dialog system, wherein implementing the conversational deficiency assessment includes: (i) identifying distinct corpora of mishandled utterances based on an assessment of the distinct corpora of dialogue data; (ii) identifying candidate corpus of mishandled utterances from the distinct corpora of mishandled utterances as suitable candidates for building new dialogue competencies for the target dialogue system if candidate metrics of the candidate corpus of mishandled utterances satisfy a candidate threshold; building the new dialogue competencies for the target dialogue system for each of the candidate corpus of mishandled utterances having candidate metrics that satisfy the candidate threshold; and configuring a dialogue system control structure for the target dialogue system based on the new dialogue competencies, wherein the dialogue system control structureType: ApplicationFiled: July 30, 2020Publication date: November 19, 2020Inventors: Jason Mars, Lingjia Tang, Michael A. Laurenzano, Johann Hauswald, Parker Hill, Yiping Kang, Yunqi Zhang
-
Patent number: 10769384Abstract: A system and method for intelligently configuring a machine learning-based dialogue system includes a conversational deficiency assessment of a target dialog system, wherein implementing the conversational deficiency assessment includes: (i) identifying distinct corpora of mishandled utterances based on an assessment of the distinct corpora of dialogue data; (ii) identifying candidate corpus of mishandled utterances from the distinct corpora of mishandled utterances as suitable candidates for building new dialogue competencies for the target dialogue system if candidate metrics of the candidate corpus of mishandled utterances satisfy a candidate threshold; building the new dialogue competencies for the target dialogue system for each of the candidate corpus of mishandled utterances having candidate metrics that satisfy the candidate threshold; and configuring a dialogue system control structure for the target dialogue system based on the new dialogue competencies, wherein the dialogue system control structureType: GrantFiled: March 10, 2020Date of Patent: September 8, 2020Assignee: Clinc, Inc.Inventors: Jason Mars, Lingjia Tang, Michael A. Laurenzano, Johann Hauswald, Parker Hill, Yiping Kang, Yunqi Zhang
-
Publication number: 20200272855Abstract: Systems and methods of intelligent formation and acquisition of machine learning training data for implementing an artificially intelligent dialogue system includes constructing a corpora of machine learning test corpus that comprise a plurality of historical queries and commands sampled from production logs of a deployed dialogue system; configuring training data sourcing parameters to source a corpora of raw machine learning training data from remote sources of machine learning training data; calculating efficacy metrics of the corpora of raw machine learning training data, wherein calculating the efficacy metrics includes calculating one or more of a coverage metric value and a diversity metric value of the corpora of raw machine learning training data; using the corpora of raw machine learning training data to train the at least one machine learning classifier if the calculated coverage metric value of the corpora of machine learning training data satisfies a minimum coverage metric threshold.Type: ApplicationFiled: April 30, 2020Publication date: August 27, 2020Inventors: Yiping Kang, Yunqi Zhang, Jonathan K. Kummerfeld, Parker Hill, Johann Hauswald, Michael A. Laurenzano, Lingjia Tang, Jason Mars
-
Publication number: 20200264938Abstract: Techniques of managing oversubscription of network resources are disclosed herein. In one embodiment, a method includes receiving resource utilization data of a virtual machine hosted on a server in a computing system. The virtual machine is configured to perform a task. The method also includes determining whether a temporal pattern of the resource utilization data associated with the virtual machine indicates one or more cycles of resource utilization as a function of time and in response to determining that the temporal pattern associated with the virtual machine indicates one or more cycles of resource utilization as a function of time, causing the virtual machine to migrate to another server that is not oversubscribed by virtual machines in the computing system.Type: ApplicationFiled: May 4, 2020Publication date: August 20, 2020Inventors: Ricardo Bianchini, William Clausen, Marcus Fontoura, Inigo Goiri, Yunqi Zhang
-
Patent number: 10740371Abstract: A system and method for intelligently configuring a machine learning-based dialogue system includes a conversational deficiency assessment of a target dialog system, wherein implementing the conversational deficiency assessment includes: (i) identifying distinct corpora of mishandled utterances based on an assessment of the distinct corpora of dialogue data; (ii) identifying candidate corpus of mishandled utterances from the distinct corpora of mishandled utterances as suitable candidates for building new dialogue competencies for the target dialogue system if candidate metrics of the candidate corpus of mishandled utterances satisfy a candidate threshold; building the new dialogue competencies for the target dialogue system for each of the candidate corpus of mishandled utterances having candidate metrics that satisfy the candidate threshold; and configuring a dialogue system control structure for the target dialogue system based on the new dialogue competencies, wherein the dialogue system control structureType: GrantFiled: October 30, 2019Date of Patent: August 11, 2020Assignee: Clinc, Inc.Inventors: Jason Mars, Lingjia Tang, Michael A. Laurenzano, Johann Hauswald, Parker Hill, Yiping Kang, Yunqi Zhang
-
Publication number: 20200250382Abstract: A system and method for intelligently configuring a machine learning-based dialogue system includes a conversational deficiency assessment of a target dialog system, wherein implementing the conversational deficiency assessment includes: (i) identifying distinct corpora of mishandled utterances based on an assessment of the distinct corpora of dialogue data; (ii) identifying candidate corpus of mishandled utterances from the distinct corpora of mishandled utterances as suitable candidates for building new dialogue competencies for the target dialogue system if candidate metrics of the candidate corpus of mishandled utterances satisfy a candidate threshold; building the new dialogue competencies for the target dialogue system for each of the candidate corpus of mishandled utterances having candidate metrics that satisfy the candidate threshold; and configuring a dialogue system control structure for the target dialogue system based on the new dialogue competencies, wherein the dialogue system control structureType: ApplicationFiled: March 10, 2020Publication date: August 6, 2020Inventors: Jason Mars, Lingjia Tang, Michael A. Laurenzano, Johann Hauswald, Parker Hill, Yiping Kang, Yunqi Zhang
-
Publication number: 20200193265Abstract: A system and method of configuring a graphical control structure for controlling a machine learning-based automated dialogue system includes configuring a root dialogue classification node that performs a dialogue intent classification task for utterance data input; configuring a plurality of distinct dialogue state classification nodes that are arranged downstream of the root dialogue classification node; configuring a graphical edge connection between the root dialogue classification node and the plurality of distinct state dialogue classification nodes that graphically connects each of the plurality of distinct state dialogue classification nodes to the root dialogue classification node, wherein (i) the root dialogue classification node, (ii) the plurality of distinct classification nodes, (iii) and the transition edge connections define a graphical dialogue system control structure that governs an active dialogue between a user and the machine learning-based automated dialogue system.Type: ApplicationFiled: November 13, 2019Publication date: June 18, 2020Inventors: Parker Hill, Jason Mars, Lingjia Tang, Michael A. Laurenzano, Johann Hauswald, Yiping Kang, Yunqi Zhang
-
Patent number: 10678603Abstract: Techniques of managing oversubscription of network resources are disclosed herein. In one embodiment, a method includes receiving resource utilization data of a virtual machine hosted on a server in a computing system. The virtual machine is configured to perform a task. The method also includes determining whether a temporal pattern of the resource utilization data associated with the virtual machine indicates one or more cycles of resource utilization as a function of time and in response to determining that the temporal pattern associated with the virtual machine indicates one or more cycles of resource utilization as a function of time, causing the virtual machine to migrate to another server that is not oversubscribed by virtual machines in the computing system.Type: GrantFiled: September 1, 2016Date of Patent: June 9, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Ricardo Bianchini, William Clausen, Marcus Fontoura, Inigo Goiri, Yunqi Zhang
-
Patent number: 10679100Abstract: Systems and methods of intelligent formation and acquisition of machine learning training data for implementing an artificially intelligent dialogue system includes constructing a corpora of machine learning test corpus that comprise a plurality of historical queries and commands sampled from production logs of a deployed dialogue system; configuring training data sourcing parameters to source a corpora of raw machine learning training data from remote sources of machine learning training data; calculating efficacy metrics of the corpora of raw machine learning training data, wherein calculating the efficacy metrics includes calculating one or more of a coverage metric value and a diversity metric value of the corpora of raw machine learning training data; using the corpora of raw machine learning training data to train the at least one machine learning classifier if the calculated coverage metric value of the corpora of machine learning training data satisfies a minimum coverage metric threshold.Type: GrantFiled: April 10, 2019Date of Patent: June 9, 2020Assignee: Clinc, Inc.Inventors: Yiping Kang, Yunqi Zhang, Jonathan K. Kummerfeld, Parker Hill, Johann Hauswald, Michael A. Laurenzano, Lingjia Tang, Jason Mars
-
Publication number: 20190294925Abstract: Systems and methods of intelligent formation and acquisition of machine learning training data for implementing an artificially intelligent dialogue system includes constructing a corpora of machine learning test corpus that comprise a plurality of historical queries and commands sampled from production logs of a deployed dialogue system; configuring training data sourcing parameters to source a corpora of raw machine learning training data from remote sources of machine learning training data; calculating efficacy metrics of the corpora of raw machine learning training data, wherein calculating the efficacy metrics includes calculating one or more of a coverage metric value and a diversity metric value of the corpora of raw machine learning training data; using the corpora of raw machine learning training data to train the at least one machine learning classifier if the calculated coverage metric value of the corpora of machine learning training data satisfies a minimum coverage metric threshold.Type: ApplicationFiled: April 10, 2019Publication date: September 26, 2019Inventors: Yiping Kang, Yunqi Zhang, Jonathan K. Kummerfeld, Parker Hill, Johann Hauswald, Michael A. Laurenzano, Lingjia Tang, Jason Mars
-
Patent number: 10303978Abstract: Systems and methods of intelligent formation and acquisition of machine learning training data for implementing an artificially intelligent dialogue system includes constructing a corpora of machine learning test corpus that comprise a plurality of historical queries and commands sampled from production logs of a deployed dialogue system; configuring training data sourcing parameters to source a corpora of raw machine learning training data from remote sources of machine learning training data; calculating efficacy metrics of the corpora of raw machine learning training data, wherein calculating the efficacy metrics includes calculating one or more of a coverage metric value and a diversity metric value of the corpora of raw machine learning training data; using the corpora of raw machine learning training data to train the at least one machine learning classifier if the calculated coverage metric value of the corpora of machine learning training data satisfies a minimum coverage metric threshold.Type: GrantFiled: September 27, 2018Date of Patent: May 28, 2019Assignee: Clinc, Inc.Inventors: Yiping Kang, Yunqi Zhang, Jonathan K. Kummerfeld, Parker Hill, Johann Hauswald, Michael A. Laurenzano, Lingjia Tang, Jason Mars
-
Publication number: 20180291526Abstract: The present invention provides an elastic fiber dry spinning component and spinning part. The spinning component includes: a temperature control box (3) including a box body (31), wherein the box body (31) is longitudinally provided with multiple polymer solution channels (32) separated from each other; areas in the box body (31) other than the polymer solution channels (32) are cavities, and the cavities are used for circulation of a fluid medium that exchanges heat with an elastic fiber dry spinning polymer solution in the polymer solution channels (32); and a spinneret part (4) detachably connected to the temperature control box (3), wherein the spinneret part (4) includes multiple spinneret orifice sets (41) separated from each other, and the multiple spinneret orifice sets (41) are correspondingly in communication with outlets of the multiple polymer solution channels (32).Type: ApplicationFiled: December 4, 2014Publication date: October 11, 2018Inventors: Zutao YUAN, Yunqi ZHANG
-
Publication number: 20180060134Abstract: Techniques of managing oversubscription of network resources are disclosed herein. In one embodiment, a method includes receiving resource utilization data of a virtual machine hosted on a server in a computing system. The virtual machine is configured to perform a task. The method also includes determining whether a temporal pattern of the resource utilization data associated with the virtual machine indicates one or more cycles of resource utilization as a function of time and in response to determining that the temporal pattern associated with the virtual machine indicates one or more cycles of resource utilization as a function of time, causing the virtual machine to migrate to another server that is not oversubscribed by virtual machines in the computing system.Type: ApplicationFiled: September 1, 2016Publication date: March 1, 2018Inventors: Ricardo Bianchini, William Clausen, Marcus Fontoura, Inigo Goiri, Yunqi Zhang
-
Publication number: 20180016708Abstract: The present invention provides an elastic fiber dry spinning mechanism and a maintenance control method for a spinning assembly. The elastic fiber dry spinning mechanism includes: a spinning assembly (1) including a temperature control portion (13) and a spinneret portion (14), which are detachably overlapped with each other; and a rotary movement control portion used for driving the spinning assembly to ascend and descend, translate and rotate around a translation direction so as to change the orientation of the spinning assembly into an orientation facilitating the maintenance of the spinneret portion. By adoption of the spinning mechanism and the maintenance control method therefore, online replacement and other maintenance of the spinneret portion are convenient and quick, and the efficiency is high.Type: ApplicationFiled: January 23, 2015Publication date: January 18, 2018Applicant: ZHENGZHOU ZHONGYUAN SPANDEX ENGINEERING TECHNOLOGY CO., LTDInventors: Zutao YUAN, Yunqi ZHANG