Patents by Inventor Andreas Wieweg
Andreas Wieweg 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: 11531905Abstract: A network of knowledge that combines different AI bots using a common communication NOK protocol, using a designated bot as a gateway through which all queries are passed while using the NOK protocol is used to draw information and capabilities from member bots transparently to the user. Eagerness scores are derived for each member and each query, indicating a given bot's ability to respond well to the query, and eagerness may be used to provide recommendations to the gateway for a specific member to handle a given query.Type: GrantFiled: July 16, 2020Date of Patent: December 20, 2022Assignee: ARTIFICIAL SOLUTIONS IBERIA S.L.Inventors: Eric Aili, Ramazan Gurbuz, Anna Hjalmarsson, Andreas Wieweg
-
Patent number: 11393475Abstract: A conversational system that recognizes, understands, and acts on multiple intents that may be explicit or implicit during conversations with humans. During a conversation, one or more utterances are received and processed through a plurality of machine learning algorithms to establish precise meanings, additional intentions, and alternative hypothesis. Using a combination of machine learning algorithms and datastores, conversations are interpreted as intended and may diverge where needed or desired, delivering a more useful, natural, and human-like dialogue between machines and people.Type: GrantFiled: January 13, 2021Date of Patent: July 19, 2022Assignee: ARTIFICIAL SOLUTIONS IBERIA S.LInventors: Eric Aili, Ramazan Gurbuz, Andreas Wieweg
-
Publication number: 20220223146Abstract: A conversational system that recognizes, understands, and acts on multiple intents that may be explicit or implicit during conversations with humans. During a conversation, one or more utterances are received and processed through a plurality of machine learning algorithms to establish precise meanings, additional intentions, and alternative hypothesis. Using a combination of machine learning algorithms and datastores, conversations are interpreted as intended and may diverge where needed or desired, delivering a more useful, natural, and human-like dialogue between machines and people.Type: ApplicationFiled: January 13, 2021Publication date: July 14, 2022Inventors: Eric Aili, Ramazan Gurbuz, Andreas Wieweg
-
Publication number: 20220019904Abstract: A network of knowledge that combines different AI bots using a common communication NOK protocol, using a designated bot as a gateway through which all queries are passed while using the NOK protocol is used to draw information and capabilities from member bots transparently to the user. Eagerness scores are derived for each member and each query, indicating a given bot's ability to respond well to the query, and eagerness may be used to provide recommendations to the gateway for a specific member to handle a given query.Type: ApplicationFiled: July 16, 2020Publication date: January 20, 2022Inventors: Eric Aili, Ramazan Gurbuz, Anna Hjalmarsson, Andreas Wieweg
-
Patent number: 11106711Abstract: A system for natural language analytics, stored and operating on a network-connected computing device, comprising a natural language application data importer, further comprising a natural language application data importer, a natural language application data augmenter that enriches the data and an analytics component which provides a means of querying structured as well as unstructured data and which also contains a method for providing adaptive natural language analytics.Type: GrantFiled: November 26, 2019Date of Patent: August 31, 2021Assignee: Artificial Solutions Iberia S.L.Inventors: Andreas Wieweg, David Hjelm, Sonja Petrovic Lundberg, Eric Aili
-
Publication number: 20200242145Abstract: A system for natural language analytics, stored and operating on a network-connected computing device, comprising a natural language application data importer, further comprising a natural language application data importer, a natural language application data augmenter that enriches the data and an analytics component which provides a means of querying structured as well as unstructured data and which also contains a method for providing adaptive natural language analytics.Type: ApplicationFiled: November 26, 2019Publication date: July 30, 2020Inventors: Andreas Wieweg, David Hjelm, Sonja Petrovic Lundberg, Eric Aili
-
Patent number: 10489433Abstract: A system for natural language analytics, stored and operating on a network-connected computing device, comprising a natural language application data importer, further comprising a natural language application data importer, a natural language application data augmenter that enriches the data and an analytics component which provides a means of querying structured as well as unstructured data and which also contains a method for providing adaptive natural language analytics.Type: GrantFiled: May 13, 2015Date of Patent: November 26, 2019Assignee: Artificial Solutions Iberia SLInventors: Andreas Wieweg, David Hjelm, Sonja Petrovic Lundberg, Eric Aili
-
Patent number: 10068174Abstract: A system for hybrid approach to natural language understanding is provided, comprising a machine learning configured to create a new natural language understanding model from user-provided examples, and provide a natural language understanding model dataset to other components of the system; an integrated development environment configured to retrieve the natural language understanding model dataset, and publish a hybrid runtime solution; and an interaction engine configured to: retrieve the hybrid runtime solution, receive a natural language input, and process the natural language input and generate a log dataset; wherein, the log dataset may be used to retrain and improve existing models.Type: GrantFiled: December 18, 2017Date of Patent: September 4, 2018Assignee: Artifical Solutions Iberia S.L.Inventors: Eric Aili, Rebecca Jonsson, Siem Uittenhout, Gareth Walters, Andreas Wieweg, Lucas Willering
-
Publication number: 20180089572Abstract: A system for hybrid approach to natural language understanding is provided, comprising a machine learning configured to create a new natural language understanding model from user-provided examples, and provide a natural language understanding model dataset to other components of the system; an integrated development environment configured to retrieve the natural language understanding model dataset, and publish a hybrid runtime solution; and an interaction engine configured to: retrieve the hybrid runtime solution, receive a natural language input, and process the natural language input and generate a log dataset; wherein, the log dataset may be used to retrain and improve existing models.Type: ApplicationFiled: December 18, 2017Publication date: March 29, 2018Inventors: Eric Aili, Rebecca Jonsson, Siem Uittenhout, Gareth Walters, Andreas Wieweg, Lucas Willering
-
Publication number: 20150339376Abstract: A system for natural language analytics, stored and operating on a network-connected computing device, comprising a natural language application data importer, further comprising a natural language application data importer, a natural language application data augmenter that enriches the data and an analytics component which provides a means of querying structured as well as unstructured data and which also contains a method for providing adaptive natural language analytics.Type: ApplicationFiled: May 13, 2015Publication date: November 26, 2015Inventors: Andreas Wieweg, David Hjelm, Sonja Petrovic Lundberg, Eric Aili
-
Patent number: 9172747Abstract: A system for the operation of a virtual assistant network, comprising a plurality of virtual assistants stored and operating on network-connected devices, and a plurality of virtual assistant brokers stored and operating on network-connected devices, wherein the virtual assistants receive user requests and send the requests to the virtual assistant brokers, and wherein the virtual assistant brokers delegate the requests to other virtual assistants for fulfillment.Type: GrantFiled: April 2, 2014Date of Patent: October 27, 2015Assignee: Artificial Solutions Iberia SLInventors: Gareth Walters, Ebba Gustavii, Rebecca Jonsson, Andreas Wieweg, Sonja Petrovic-Lundberg, David Hjelm
-
Patent number: 8903711Abstract: A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application.Type: GrantFiled: October 8, 2013Date of Patent: December 2, 2014Assignee: Artificial Solutions Iberia, S.L.Inventors: Sonja Petrovic Lundberg, Eric Aili, Andreas Wieweg, Rebecca Jonsson, David Hjelm
-
Patent number: 8892419Abstract: A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application.Type: GrantFiled: December 30, 2012Date of Patent: November 18, 2014Assignee: Artificial Solutions Iberia SLInventors: Sonja Petrovic Lundberg, Eric Aili, Andreas Wieweg, Rebecca Jonsson, David Hjelm
-
Publication number: 20140244712Abstract: A system for the operation of a virtual assistant network, comprising a plurality of virtual assistants stored and operating on network-connected devices, and a plurality of virtual assistant brokers stored and operating on network-connected devices, wherein the virtual assistants receive user requests and send the requests to the virtual assistant brokers, and wherein the virtual assistant brokers delegate the requests to other virtual assistants for fulfillment.Type: ApplicationFiled: April 2, 2014Publication date: August 28, 2014Applicant: Artificial Solutions Iberia SLInventors: Gareth Walters, Ebba Gustavii, Rebecca Jonsson, Andreas Wieweg, Sonja Petrovic-Lundberg, David Hjelm
-
Publication number: 20140019116Abstract: A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application.Type: ApplicationFiled: October 8, 2013Publication date: January 16, 2014Applicant: ARTIFICIAL SOLUTIONS IBERIA SLInventors: Sonja Petrovic Lundberg, Eric Aili, Andreas Wieweg, Rebecca Jonsson, David Hjelm
-
Publication number: 20130268260Abstract: A system for supervised automatic code generation and tuning for natural language interaction applications, comprising a build environment comprising a developer user interface, automated coding tools, automated testing tools, and automated optimization tools, and an analytics framework software module. Text samples are imported into the build environment and automated clustering is performed to assign them to a plurality of input groups, each input group comprising a plurality of semantically related inputs. Language recognition rules are generated by automated coding tools. Automated testing tools carry out automated testing of language recognition rules and generate recommendations for tuning language recognition rules. The analytics framework performs analysis of interaction log files to identify problems in a candidate natural language interaction application.Type: ApplicationFiled: December 30, 2012Publication date: October 10, 2013Applicant: Artificial Solutions Iberia SLInventors: Sonja Petrovic Lundberg, Eric Aili, Andreas Wieweg, Rebecca Jonsson, David Hjelm