Patents by Inventor James B. Robinson
James B. Robinson 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: 20210232761Abstract: Systems and methods are presented for providing improved machine performance in natural language processing. In some example embodiments, an API module is presented that is configured to drive processing of a system architecture for natural language processing. Aspects of the present disclosure allow for a natural language model to classify documents while other documents are being retrieved in real time. The natural language model and the documents are configured to be stored in a stateless format, which also allows for additional functions to be performed on the documents while the natural language model is used to continue classifying other documents.Type: ApplicationFiled: December 22, 2020Publication date: July 29, 2021Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Jason Brenier, Paul A. Tepper, Jessica D. Long, James B. Robinson, Aneesh Nair, Michelle Casbon, Stefan Krawczyk
-
Publication number: 20210232762Abstract: Systems are presented for generating a natural language model. The system may comprise a database module, an application program interface (API) module, a background processing module, and an applications module, each stored on the at least one memory and executable by the at least one processor. The system may be configured to generate the natural language model by: ingesting training data, generating a hierarchical data structure, selecting a plurality of documents among the training data to be annotated, generating an annotation prompt for each document configured to elicit an annotation about said document, receiving the annotation based on the annotation prompt, and generating the natural language model using an adaptive machine learning process configured to determine patterns among the annotations for how the documents in the training data are to be subdivided according to the at least two topical nodes of the hierarchical data structure.Type: ApplicationFiled: February 3, 2021Publication date: July 29, 2021Applicant: Al IP INVESTMENTS LTDInventors: Robert J. Munro, Schuyler D. Erie, Christopher Walker, Sarah K. Luger, Jason Brenier, Gary C. King, Paul A. Tepper, Ross Mechanic, Andrew Gilchrist-Scott, Jessica D. Long, James B. Robinson, Brendan D. Callahan, Michelle Casbon, Ujjwal Sarin, Aneesh Nair, Veena Basavaraj, Tripti Saxena, Edgar Nunez, Martha G. Hinrichs, Haley Most, Tyler J. Schnoebelen
-
Publication number: 20210150130Abstract: Methods are presented for generating a natural language model. The method may comprise: ingesting training data representative of documents to be analyzed by the natural language model, generating a hierarchical data structure comprising at least two topical nodes within which the training data is to be subdivided into by the natural language model, selecting a plurality of documents among the training data to be annotated, generating an annotation prompt for each document configured to elicit an annotation about said document indicating which node among the at least two topical nodes said document is to be classified into, receiving the annotation based on the annotation prompt; and generating the natural language model using an adaptive machine learning process configured to determine patterns among the annotations for how the documents in the training data are to be subdivided according to the at least two topical nodes of the hierarchical data structure.Type: ApplicationFiled: February 20, 2020Publication date: May 20, 2021Inventors: Robert J. Munro, Schuyler D. Erle, Christopher Walker, Sarah K. Luger, Jason Brenier, Gary C. King, Paul A. Tepper, Ross Mechanic, Andrew Gilchrist-Scott, Jessica D. Long, James B. Robinson, Brendan D. Callahan, Michelle Casban, Ujjwal Sarin, Aneesh Nair, Veena Basavaraj, Tripti Saxena, Edgar Nunez, Martha G. Hinrichs, Haley Most, Tyler Schnoebelen
-
Publication number: 20210110111Abstract: Systems, methods, and apparatuses are presented for a trained language model to be stored in an efficient manner such that the trained language model may be utilized in virtually any computing device to conduct natural language processing. Unlike other natural language processing engines that may be computationally intensive to the point of being capable of running only on high performance machines, the organization of the natural language models according to the present disclosures allows for natural language processing to be performed even on smaller devices, such as mobile devices.Type: ApplicationFiled: May 26, 2020Publication date: April 15, 2021Applicant: Singapore Biotech PTE. LTD.Inventors: Schulyer D. Erle, Robert J. Munro, Brendan D. Callahan, Gary C. King, Jason Brenier, James B. Robinson
-
Publication number: 20200034737Abstract: Systems are presented for generating a natural language model. The system may comprise a database module, an application program interface (API) module, a background processing module, and an applications module, each stored on the at least one memory and executable by the at least one processor. The system may be configured to generate the natural language model by: ingesting training data, generating a hierarchical data structure, selecting a plurality of documents among the training data to be annotated, generating an annotation prompt for each document configured to elicit an annotation about said document, receiving the annotation based on the annotation prompt, and generating the natural language model using an adaptive machine learning process configured to determine patterns among the annotations for how the documents in the training data are to be subdivided according to the at least two topical nodes of the hierarchical data structure.Type: ApplicationFiled: February 28, 2019Publication date: January 30, 2020Applicant: AIPARC HOLDINGS PTE. LTD. `Inventors: Robert J. Munro, Schuyler D. Erle, Christopher Walker, Sarah K. Luger, Jason Brenier, Gary C. King, Paul A. Tepper, Ross Mechanic, Andrew Gilchrist-Scott, Jessica D. Long, James B. Robinson, Brendan D. Callahan, Michelle Casbon, Ujjwal Sarin, Aneesh Nair, Veena Basavaraj, Tripti Saxena, Edgar Nunez, Martha G. Hinrichs, Haley Most, Tyler J. Schnoebelen
-
Publication number: 20190384809Abstract: Systems, methods, and apparatuses are presented for a trained language model to be stored in an efficient manner such that the trained language model may be utilized in virtually any computing device to conduct natural language processing. Unlike other natural language processing engines that may be computationally intensive to the point of being capable of running only on high performance machines, the organization of the natural language models according to the present disclosures allows for natural language processing to be performed even on smaller devices, such as mobile devices.Type: ApplicationFiled: January 11, 2019Publication date: December 19, 2019Applicant: AIPARC HOLDINGS PTE. LTD.Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Gary C. King, Jason Brenier, James B. Robinson
-
Publication number: 20190303428Abstract: Methods are presented for generating a natural language model. The method may comprise: ingesting training data representative of documents to be analyzed by the natural language model, generating a hierarchical data structure comprising at least two topical nodes within which the training data is to be subdivided into by the natural language model, selecting a plurality of documents among the training data to be annotated, generating an annotation prompt for each document configured to elicit an annotation about said document indicating which node among the at least two topical nodes said document is to be classified into, receiving the annotation based on the annotation prompt; and generating the natural language model using an adaptive machine learning process configured to determine patterns among the annotations for how the documents in the training data are to be subdivided according to the at least two topical nodes of the hierarchical data structure.Type: ApplicationFiled: November 5, 2018Publication date: October 3, 2019Inventors: Robert J. Munro, Schuyler D. Erle, Christopher Walker, Sarah K. Luger, Jason Brenier, Gary C. King, Paul A. Tepper, Ross Mechanic, Andrew Gilchrist-Scott, Jessica D. Long, James B. Robinson, Brendan D. Callahan, Michelle Casbon, Ujjwal Sarin, Aneesh Nair, Veena Basavaraj, Tripti Saxena, Edgar Nunez, Martha G. Hinrichs, Haley Most, Tyler Schnoebelen
-
Publication number: 20190243886Abstract: Systems and methods are presented for providing improved machine performance in natural language processing. In some example embodiments, an API module is presented that is configured to drive processing of a system architecture for natural language processing. Aspects of the present disclosure allow for a natural language model to classify documents while other documents are being retrieved in real time. The natural language model and the documents are configured to be stored in a stateless format, which also allows for additional functions to be performed on the documents while the natural language model is used to continue classifying other documents.Type: ApplicationFiled: September 7, 2018Publication date: August 8, 2019Applicant: Idibon, Inc.Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Jason Brenier, Paul A. Tepper, Jessica D. Long, James B. Robinson, Aneesh Nair, Michelle Casbon, Stefan Krawczyk
-
Patent number: 10127214Abstract: Methods are presented for generating a natural language model. The method may comprise: ingesting training data representative of documents to be analyzed by the natural language model, generating a hierarchical data structure comprising at least two topical nodes within which the training data is to be subdivided into by the natural language model, selecting a plurality of documents among the training data to be annotated, generating an annotation prompt for each document configured to elicit an annotation about said document indicating which node among the at least two topical nodes said document is to be classified into, receiving the annotation based on the annotation prompt; and generating the natural language model using an adaptive machine learning process configured to determine patterns among the annotations for how the documents in the training data are to be subdivided according to the at least two topical nodes of the hierarchical data structure.Type: GrantFiled: December 9, 2015Date of Patent: November 13, 2018Assignee: Sansa Al Inc.Inventors: Robert J. Munro, Schuyler D. Erle, Christopher Walker, Sarah K. Luger, Jason Brenier, Gary C. King, Paul A. Tepper, Ross Mechanic, Andrew Gilchrist-Scott, Jessica D. Long, James B. Robinson, Brendan D. Callahan, Michelle Casbon, Ujjwal Sarin, Aneesh Nair, Veena Basavaraj, Tripti Saxena, Edgar Nunez, Martha G. Hinrichs, Haley Most, Tyler J. Schnoebelen
-
Publication number: 20180137098Abstract: Systems, methods, and apparatuses are presented for a trained language model to be stored in an efficient manner such that the trained language model may be utilized in virtually any computing device to conduct natural language processing. Unlike other natural language processing engines that may be computationally intensive to the point of being capable of running only on high performance machines, the organization of the natural language models according to the present disclosures allows for natural language processing to be performed even on smaller devices, such as mobile devices.Type: ApplicationFiled: November 20, 2017Publication date: May 17, 2018Applicant: Idibon, Inc.Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Gary C. King, Jason Brenier, James B. Robinson
-
Patent number: 9836450Abstract: Systems, methods, and apparatuses are presented for a trained language model to be stored in an efficient manner such that the trained language model may be utilized in virtually any computing device to conduct natural language processing. Unlike other natural language processing engines that may be computationally intensive to the point of being capable of running only on high performance machines, the organization of the natural language models according to the present disclosures allows for natural language processing to be performed even on smaller devices, such as mobile devices.Type: GrantFiled: December 9, 2015Date of Patent: December 5, 2017Assignee: Sansa AI Inc.Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Gary C. King, Jason Brenier, James B. Robinson
-
Patent number: 9737363Abstract: The present disclosure describes a draping system for a two-tiered hospital instrument back table can be used to quickly and conveniently create a sterile field. The system has a drape that is a single piece of material, desirably a film that may be clear. The single piece of material has other material attached to it on its upper side or surface in areas that generally coincide with the two upper surfaces of the table when the drape is installed on the table, and that has a lower coefficient of friction than the single piece of material. The drape may be held in place with a continuous or discontinuous band that encircles the upper tier or the upper tier support posts.Type: GrantFiled: December 11, 2012Date of Patent: August 22, 2017Assignee: Avent, Inc.Inventors: Ajay Y. Houde, Jeffrey S. Robinson, Jose Luis Coronado, Keith J. Edgett, James B. Robinson, Denise E. O'Connor
-
Publication number: 20160162468Abstract: Systems, methods, and apparatuses are presented for a trained language model to be stored in an efficient manner such that the trained language model may be utilized in virtually any computing device to conduct natural language processing. Unlike other natural language processing engines that may be computationally intensive to the point of being capable of running only on high performance machines, the organization of the natural language models according to the present disclosures allows for natural language processing to be performed even on smaller devices, such as mobile devices.Type: ApplicationFiled: December 9, 2015Publication date: June 9, 2016Applicant: Idibon, Inc.Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Gary C. King, Jason Brenier, James B. Robinson
-
Publication number: 20160162456Abstract: Methods are presented for generating a natural language model. The method may comprise: ingesting training data representative of documents to be analyzed by the natural language model, generating a hierarchical data structure comprising at least two topical nodes within which the training data is to be subdivided into by the natural language model, selecting a plurality of documents among the training data to be annotated, generating an annotation prompt for each document configured to elicit an annotation about said document indicating which node among the at least two topical nodes said document is to be classified into, receiving the annotation based on the annotation prompt; and generating the natural language model using an adaptive machine learning process configured to determine patterns among the annotations for how the documents in the training data are to be subdivided according to the at least two topical nodes of the hierarchical data structure.Type: ApplicationFiled: December 9, 2015Publication date: June 9, 2016Applicant: Idibon, Inc.Inventors: Robert J. Munro, Schuyler D. Erle, Christopher Walker, Sarah K. Luger, Jason Brenier, Gary C. King, Paul A. Tepper, Ross Mechanic, Andrew Gilchrist-Scott, Jessica D. Long, James B. Robinson, Brendan D. Callahan, Michelle Casbon, Ujjwal Sarin, Aneesh Nair, Veena Basavaraj, Tripti Saxena, Edgar Nunez, Martha G. Hinrichs, Haley Most, Tyler J. Schnoebelen
-
Publication number: 20160162569Abstract: Systems and methods are presented for providing improved machine performance in natural language processing. In some example embodiments, an API module is presented that is configured to drive processing of a system architecture for natural language processing. Aspects of the present disclosure allow for a natural language model to classify documents while other documents are being retrieved in real time. The natural language model and the documents are configured to be stored in a stateless format, which also allows for additional functions to be performed on the documents while the natural language model is used to continue classifying other documents.Type: ApplicationFiled: December 9, 2015Publication date: June 9, 2016Applicant: Idibon, Inc.Inventors: Schuyler D. Erle, Robert J. Munro, Brendan D. Callahan, Jason Brenier, Paul A. Tepper, Jessica D. Long, James B. Robinson, Aneesh Nair, Michelle Casbon, Stefan Krawczyk
-
Publication number: 20140041669Abstract: The present disclosure describes a draping system for a two-tiered hospital instrument back table can be used to quickly and conveniently create a sterile field. The system has a drape that is a single piece of material, desirably a film that may be clear. The single piece of material has other material attached to it on its upper side or surface in areas that generally coincide with the two upper surfaces of the table when the drape is installed on the table, and that has a lower coefficient of friction than the single piece of material. The drape may be held in place with a continuous or discontinuous band that encircles the upper tier or the upper tier support posts.Type: ApplicationFiled: December 11, 2012Publication date: February 13, 2014Applicant: KIMBERLY-CLARK WORLDWIDE, INC.Inventors: Ajay Y. Houde, Jeffrey S. Robinson, Jose Luis Coronado, Keith J. Edgett, James B. Robinson, Denise E. O'Connor
-
Publication number: 20130112589Abstract: The present disclosure describes a disposal bag, kit and method for performing pleural drainage that may be used by a patient at home or away from home. The kit for drainage of a body cavity has instruments and supplies needed to drain the body cavity, a disposal bag made from two superposed, water impervious sheets sealed about a substantial portion of their perimeter using a water impervious bond. The bag is usable for disposal of the instruments and supplies after drainage of the body cavity. The superposed sheets also provide a work sheet to prepare and use the instruments and supplies.Type: ApplicationFiled: November 4, 2011Publication date: May 9, 2013Inventors: Khoa T. Lien, Henry L. Griesbach, III, James B. Robinson
-
Patent number: 5100269Abstract: A cutting insert with improved chip control and metal cutting capabilities and a toolholder with an improved clamping arrangement for use in combination therewith. The insert includes a first notch disposed in the insert body extending from the cutting end to the mounting end thereof. A top wall of the insert body has a forward section with a cutting edge, a middle section with a second notch extending across substantially the entire insert body and a rearward section. In one embodiment, the forward section of the insert body includes a chipbreaker. In another embodiment, the forward portion includes an advanced cutting material which defines a cutting edge. In yet another embodiment of the insert, the insert body top wall forward section defines the cutting edge and the insert body does not include a chipbreaker.Type: GrantFiled: February 12, 1991Date of Patent: March 31, 1992Assignee: Kennametal Inc.Inventors: James R. Lyon, Gary L. Morsch, Gerald D. Murray, James B. Robinson
-
Patent number: 4946319Abstract: A cutting insert with improved chip control and metal cutting capabilities and a toolholder with an improved clamping arrangement for use in combination therewith. The insert includes a first notch disposed in the insert body extending from the cutting end to the mounting end thereof. A top wall of the insert body has a forward section with a cutting edge, a middle section with a second notch extending across substantially the entire insert body and a rearward section. In one embodiment, the forward section of the insert body includes a chipbreaker. In another embodiment, the forward portion includes an advanced cutting material which defines a cutting edge. In yet another embodiment of the insert, the insert body top wall forward section defines the cutting edge and the insert body does not include a chipbreaker.Type: GrantFiled: August 12, 1988Date of Patent: August 7, 1990Assignee: Kennametal Inc.Inventors: James R. Lyon, Gary L. Morsch, Gerald D. Murray, James B. Robinson