Patents by Inventor Benjamin Peter Levin

Benjamin Peter Levin 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: 20250190458
    Abstract: A dialogue system, comprising: a first input configured to obtain first input data relating to speech or text provided by a user through a first interface; a first output configured to provide first output data relating to speech or text information specified by a determined dialogue act through the first interface; one or more processors, configured to: receive second input data through a second interface; store information specifying one or more configuration settings based on the second input data; and perform a dialogue method using a dialogue platform, the dialogue method comprising: determining dialogue information from the first input data; determining a dialogue act based on the determined dialogue information using a dialogue management module, wherein determining the dialogue act comprises selecting a next state from a plurality of states stored in the dialogue management module, wherein at least some of the plurality of states comprise information specifying a dialogue act and at least some of the
    Type: Application
    Filed: August 9, 2024
    Publication date: June 12, 2025
    Inventors: Tsung-Hsien Wen, Ivan Vulic, Nikola Mrkšic, Pei-Hao Su, Pawel Franciszek Budzianowski, Razvan-Emanuel Kusztos, Paul Julian Annetts, Ho Man Yau, Catherine Rachel Oxley, Emmanuel Sevrin, Vincent Yohann Dollet, Iñigo Casanueva Perez, Benjamin Peter Levin, Duong Hà Anh Nguyên, Swaroop Jagadeesh, Qian Zheng, Joshua Luke Jeffries Hook, Samuel John Coope
  • Patent number: 12061636
    Abstract: A dialogue system, comprising: a first input configured to obtain first input data relating to speech or text provided by a user through a first interface; a first output configured to provide first output data relating to speech or text information specified by a determined dialogue act through the first interface; one or more processors, configured to: receive second input data through a second interface; store information specifying one or more configuration settings based on the second input data; and perform a dialogue method using a dialogue platform, the dialogue method comprising: determining dialogue information from the first input data; determining a dialogue act based on the determined dialogue information using a dialogue management module, wherein determining the dialogue act comprises selecting a next state from a plurality of states stored in the dialogue management module, wherein at least some of the plurality of states comprise information specifying a dialogue act and at least some of the
    Type: Grant
    Filed: May 15, 2023
    Date of Patent: August 13, 2024
    Assignee: POLYAI LIMITED
    Inventors: Tsung-Hsien Wen, Ivan Vulić, Nikola Mrk{hacek over (s)}ić, Pei-Hao Su, Pawel Franciszek Budzianowski, R{hacek over (a)}zvan-Emanuel Kusztos, Paul Julian Annetts, Ho Man Yau, Catherine Rachel Oxley, Emmanuel Sevrin, Vincent Yohann Dollet, I{circumflex over (n)}igo Casanueva Perez, Benjamin Peter Levin, Duong Hà Anh Nguyên, Swaroop Jagadeesh, Qian Zheng, Joshua Luke Jeffries Hook, Samuel John Coope
  • Patent number: 11861521
    Abstract: A computer-implemented method comprising: obtaining, by way of an input, input data relating to speech provided by a user; deriving one or more hypotheses for each of a plurality of user data fields from the input data; obtaining one or more reference values for each of the plurality of user data fields for each of one or more candidate users; calculating a score for at least one candidate user of the one or more candidate users, calculating the score comprising: calculating a plurality of user data field scores comprising, for each of the plurality of user data fields, a respective user data field score using the one or more hypotheses and the one or more reference values for the candidate user for the respective user data field; performing one or more fuzzy logic operations on the plurality of user data field scores; using the score for a candidate user of the one or more candidate users to perform a verification or identification process for the user.
    Type: Grant
    Filed: January 19, 2022
    Date of Patent: January 2, 2024
    Assignee: PolyAI Limited
    Inventors: Georgios Spithourakis, Pawel Franciszek Budzianowski, Michal Lis, Avishek Mondal, Ivan Vulic, Nikola Mrksic, Eshan Singhal, Benjamin Peter Levin, Pei-Hao Su, Tsung-Hsien Wen
  • Publication number: 20230196151
    Abstract: A computer-implemented method comprising: obtaining, by way of an input, input data relating to speech provided by a user; deriving one or more hypotheses for each of a plurality of user data fields from the input data; obtaining one or more reference values for each of the plurality of user data fields for each of one or more candidate users; calculating a score for at least one candidate user of the one or more candidate users, calculating the score comprising: calculating a plurality of user data field scores comprising, for each of the plurality of user data fields, a respective user data field score using the one or more hypotheses and the one or more reference values for the candidate user for the respective user data field; performing one or more fuzzy logic operations on the plurality of user data field scores; using the score for a candidate user of the one or more candidate users to perform a verification or identification process for the user.
    Type: Application
    Filed: January 19, 2022
    Publication date: June 22, 2023
    Inventors: Georgios SPITHOURAKIS, Pawel Franciszek BUDZIANOWSKI, Michal LIS, Avishek MONDAL, Ivan VULIC, Nikola MRKSIC, Eshan SINGHAL, Benjamin Peter LEVIN, Pei-Hao SU, Tsung-Hsien WEN
  • Patent number: 11537661
    Abstract: A system comprising: an input configured to receive input speech data originating from a user; an output configured to output speech or text information; and a processor configured to: provide first input data to a character sequence determination module to determine a character sequence from the first input data, wherein determining a character sequence comprises: obtaining a first list of one or more candidate character sequences from the first input data; selecting a first candidate character sequence from the first list; generating a first confirm request to confirm the selected first candidate character sequence, wherein the first confirm request is outputted by way of the output; if second input data indicating that the first candidate character sequence is not confirmed is received, selecting a second candidate character sequence and generating a second confirm request to confirm the selected second candidate if the second candidate character sequence is different from the first candidate character s
    Type: Grant
    Filed: October 2, 2020
    Date of Patent: December 27, 2022
    Assignee: PolyAI Limited
    Inventors: Samuel John Coope, Emmanuel Sevrin, Kacper Jakub Żyłka, Benjamin Peter Levin
  • Publication number: 20220107979
    Abstract: A system comprising: an input configured to receive input speech data originating from a user; an output configured to output speech or text information; and a processor configured to: provide first input data to a character sequence determination module to determine a character sequence from the first input data, wherein determining a character sequence comprises: obtaining a first list of one or more candidate character sequences from the first input data; selecting a first candidate character sequence from the first list; generating a first confirm request to confirm the selected first candidate character sequence, wherein the first confirm request is outputted by way of the output; if second input data indicating that the first candidate character sequence is not confirmed is received, selecting a second candidate character sequence and generating a second confirm request to confirm the selected second candidate if the second candidate character sequence is different from the first candidate character s
    Type: Application
    Filed: October 2, 2020
    Publication date: April 7, 2022
    Inventors: Samuel John Coope, Emmanuel Sevrin, Kacper Jakub Zylka, Benjamin Peter Levin
  • Patent number: 11204964
    Abstract: A system comprising: an input configured to receive input speech data originating from a user; an output configured to output speech or text information; and a processor configured to: provide first input data to a character sequence determination module to determine a character sequence from the first input data, wherein determining a character sequence comprises: obtaining a first list of one or more candidate character sequences from the first input data; selecting a first candidate character sequence from the first list; generating a first confirm request to confirm the selected first candidate character sequence, wherein the first confirm request is outputted by way of the output; if second input data indicating that the first candidate character sequence is not confirmed is received, selecting a second candidate character sequence and generating a second confirm request to confirm the selected second candidate if the second candidate character sequence is different from the first candidate character s
    Type: Grant
    Filed: December 30, 2020
    Date of Patent: December 21, 2021
    Assignee: PolyAl Limited
    Inventors: Samuel John Coope, Emmanuel Sevrin, Kacper Jakub Zylka, Benjamin Peter Levin