Patents by Inventor Andre Lapointe
Andre Lapointe 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: 20240127046Abstract: In example embodiments, techniques are provided for classifying elements of infrastructure models using a convolutional graph neural network (GNN). Graph-structured data structures are generated from infrastructure models, in which nodes represent elements and edges represent contextual relationships among elements (e.g., based on proximity, functionality, parent-child relationships, etc.). During training, the GNN learns embeddings from the nodes and edges of the graph-structured data structures, the embeddings capturing contextual clues that distinguish between elements that may share similar geometry (e.g., cross section, volume, surface area, etc.), yet serve different purposes.Type: ApplicationFiled: October 11, 2022Publication date: April 18, 2024Inventors: Marc-André Lapointe, Louis-Philippe Asselin, Karl-Alexandre Jahjah, Evan Rausch-Larouche
-
Publication number: 20240112043Abstract: In example embodiments, techniques are provided for labeling elements of an infrastructure model with classes. The techniques may be implemented by a labeling tool that uses an ML model to create element selections and provides a cycle review mode to speed review within such selections. The labeling tool may further provide for two file loading and a number of visualization schemes to speed comparison of label files and prediction files.Type: ApplicationFiled: September 28, 2022Publication date: April 4, 2024Inventors: Karl-Alexandre Jahjah, Marc-André Lapointe, Hugo Bergeron, Justin Dehorty, Arnob Mallick
-
Patent number: 11645363Abstract: In example embodiments, techniques are provided to automatically identify misclassified elements of an infrastructure model using machine learning. In a first set of embodiments, supervised machine learning is used to train one or more classification models that use different types of data describing elements (e.g., a geometric classification model that uses geometry data, a natural language processing (NLP) classification model that uses textual data, and an omniscient (Omni) classification model that uses a combination of geometry and textual data; or a single classification model that uses geometry data, textual data, and a combination of geometry and textual data). Predictions from classification models (e.g., predictions from the geometric classification model, NLP classification model and the Omni classification model) are compared to identify misclassified elements, or a prediction of misclassified elements directly produced (e.g., from the single classification model).Type: GrantFiled: October 20, 2020Date of Patent: May 9, 2023Assignee: Bentley Systems, IncorporatedInventors: Karl-Alexandre Jahjah, Hugo Bergeron, Marc-André Lapointe, Kaustubh Page, Evan Rausch-Larouche
-
Patent number: 11521026Abstract: In example embodiments, techniques are provided to automatically classify individual elements of an infrastructure model by training one or more machine learning algorithms on classified infrastructure models, producing a classification model that maps features to classification labels, and utilizing the classification model to classify the individual elements of the infrastructure model. The resulting classified elements may then be readily subject to analytics, for example, enabling the display of dashboards for monitoring project performance and the impact of design changes. Such techniques enable classification of elements of new infrastructure models or in updates to existing infrastructure models.Type: GrantFiled: September 28, 2020Date of Patent: December 6, 2022Assignee: Bentley Systems, IncorporatedInventors: Marc-André Lapointe, Karl-Alexandre Jahjah, Hugo Bergeron, Kaustubh Page
-
Publication number: 20220358360Abstract: In example embodiments, a software service may employ a neural network to learn a non-linear mapping that transforms element features into embeddings. The neural network may be trained to distribute the embeddings in multi-dimensional embedding space, such that distance between the embeddings is meaningful to the class or category classification, or property prediction, task at hand. The neural network may be trained using weakly supervised machine learning, using weakly labeled infrastructure models. Embeddings for groups may be used to determine prototypes. Elements of an infrastructure model may be classified into classes or categories, or their properties predicted, as the case may be, by finding a nearest prototype.Type: ApplicationFiled: May 7, 2021Publication date: November 10, 2022Inventors: Louis-Philippe Asselin, Marc-André Lapointe, Karl-Alexandre Jahjah, Evan Rausch-Larouche
-
Publication number: 20220121886Abstract: In example embodiments, techniques are provided to automatically identify misclassified elements of an infrastructure model using machine learning. In a first set of embodiments, supervised machine learning is used to train one or more classification models that use different types of data describing elements (e.g., a geometric classification model that uses geometry data, a natural language processing (NLP) classification model that uses textual data, and an omniscient (Omni) classification model that uses a combination of geometry and textual data; or a single classification model that uses geometry data, textual data, and a combination of geometry and textual data). Predictions from classification models (e.g., predictions from the geometric classification model, NLP classification model and the Omni classification model) are compared to identify misclassified elements, or a prediction of misclassified elements directly produced (e.g., from the single classification model).Type: ApplicationFiled: October 20, 2020Publication date: April 21, 2022Inventors: Karl-Alexandre Jahjah, Hugo Bergeron, Marc-André Lapointe, Kaustubh Page, Evan Rausch-Larouche
-
Publication number: 20210117716Abstract: In example embodiments, techniques are provided to automatically classify individual elements of an infrastructure model by training one or more machine learning algorithms on classified infrastructure models, producing a classification model that maps features to classification labels, and utilizing the classification model to classify the individual elements of the infrastructure model. The resulting classified elements may then be readily subject to analytics, for example, enabling the display of dashboards for monitoring project performance and the impact of design changes. Such techniques enable classification of elements of new infrastructure models or in updates to existing infrastructure models.Type: ApplicationFiled: September 28, 2020Publication date: April 22, 2021Inventors: Marc-André Lapointe, Karl-Alexandre Jahjah, Hugo Bergeron, Kaustubh Page
-
Publication number: 20210101307Abstract: A cylindrical cutting head for a wood workpiece, comprising an even number of main grooves disposed on helices running on a length of a surface thereof, wherein each main groove comprises cutting inserts; each cutting insert comprising a knife removably locked in position in relation to the main groove by a clamp. A cutting insert for a cylindrical cutting head for a wood workpiece, comprising a knife and a clamp, wherein the knife is removably positioned and locked in position in relation to the cylindrical cutting head by a clamp.Type: ApplicationFiled: October 2, 2020Publication date: April 8, 2021Inventor: André LAPOINTE
-
Patent number: 9880355Abstract: The present relates to a spatially modulated cladding mode stripper and to an optical fiber comprising a spatially modulated cladding mode stripper. The spatially modulated cladding mode stripper comprises a series of alternating high cladding light extracting regions and low cladding light extracting regions located along a portion of a cladding to modulate extracting of cladding light therefrom.Type: GrantFiled: August 7, 2013Date of Patent: January 30, 2018Assignee: CORACTIVE HIGH-TECH INC.Inventors: Marc-André Lapointe, Serge Doucet, Jean-Noel Maran
-
Publication number: 20160202419Abstract: The present relates to a spatially modulated cladding mode stripper and to an optical fiber comprising a spatially modulated cladding mode stripper. The spatially modulated cladding mode stripper comprises a series of alternating high cladding light extracting regions and low cladding light extracting regions located along a portion of a cladding to modulate extracting of cladding light therefrom.Type: ApplicationFiled: August 7, 2013Publication date: July 14, 2016Applicant: CORACTIVE HIGH-TECH INC.Inventors: Marc-André LAPOINTE, Serge DOUCET, Jean-Noel MARAN
-
Publication number: 20150210409Abstract: A system and method for stacking two bulk bags one on top of the other on a pallet, the method comprising controlling a pallet feeder into providing a pallet; filling a first bag with a first amount of product on the pallet and sealing the first bag; filling a second bag with a second amount of product, and depositing the second bag filled with the second amount of product on top of the first bag on the pallet; and straightening the bags on the pallet; wherein these steps of controlling, filling the first and second bags, and straightening are controlled by a programmable controller, the programmable controller selecting the first amount to be fed to the first bag supported by the pallet and, selecting the second amount to be fed to the second bag.Type: ApplicationFiled: January 27, 2014Publication date: July 30, 2015Applicant: LES TOURBIERES BERGER LTEEInventors: Regis BERGER, Sylvain BERUBE, Stephane BOURGAULT, Renaud BOURGOIN, Andre LAPOINTE, Denis LEBEL, Michel OUELLET, Marco PARE, Robert PLANTE, Jean-Yves SAVOIE, Jean-François SENECHAL
-
Patent number: 8082960Abstract: A method and a system for classifying a plurality of random length boards of random grade, using a conveyer provided with reading units to read both the length and the grade of each board at a first end of said conveyer; a processor, receiving length and grade data from the reading units; calculating combinations of board lengths and grades and selecting a preferred combination of boards from the combinations; and a distribution section, located at a second end of the conveyer, and operated by the processor according to the preferred combination; the processor being fed with a large number of identified boards, from which to calculate the combinations of board lengths and grades, before they reach the distribution section.Type: GrantFiled: March 1, 2007Date of Patent: December 27, 2011Assignee: OSI MachinerieInventor: Andre Lapointe
-
Patent number: 7971612Abstract: A floor planks production method, for producing wood flooring from raw lumbers, by surfacing top and lower faces of the lumbers to a final thickness of the lumbers; optimizing the lumbers along a length thereof to determine lengths of best faces; and profiling edges of the optimized lumbers. The system comprises a surfacing unit processing both top and lower faces of each lumber to final dimensions; an optimizing unit receiving lumbers from the surfacing unit; and a profiling unit processing edges of each length of best faces positioned by the optimizing unit.Type: GrantFiled: July 2, 2008Date of Patent: July 5, 2011Assignee: OSI Machinerie Inc.Inventor: Andre Lapointe
-
Patent number: 7866662Abstract: A vacuum belt feeder comprising a means of conveyance having a pitch, for retrieving items from a supply zone, and then distributing them at target locations in a discharge zone.Type: GrantFiled: May 7, 2008Date of Patent: January 11, 2011Assignee: OSI Machinerie Inc.Inventor: Andre Lapointe
-
Publication number: 20090007988Abstract: A floor planks production method, for producing wood flooring from raw lumbers, by surfacing top and lower faces of the lumbers to a final thickness of the lumbers; optimizing the lumbers along a length thereof to determine lengths of best faces; and profiling edges of the optimized lumbers. The system comprises a surfacing unit processing both top and lower faces of each lumber to final dimensions; an optimizing unit receiving lumbers from the surfacing unit; and a profiling unit processing edges of each length of best faces positioned by the optimizing unit.Type: ApplicationFiled: July 2, 2008Publication date: January 8, 2009Applicant: OSI Machinerie Inc.Inventor: Andre Lapointe
-
Publication number: 20080251994Abstract: A vacuum belt feeder comprising a means of conveyance having a pitch, for retrieving items from a supply zone, and then distributing them at target locations in a discharge zone.Type: ApplicationFiled: May 7, 2008Publication date: October 16, 2008Inventor: Andre Lapointe
-
Publication number: 20080210339Abstract: A method and a system for classifying a plurality of random length boards of random grade, using a conveyer provided with reading units to read both the length and the grade of each board at a first end of said conveyer; a processor, receiving length and grade data from the reading units; calculating combinations of board lengths and grades and selecting a preferred combination of boards from the combinations; and a distribution section, located at a second end of the conveyer, and operated by the processor according to the preferred combination; the processor being fed with a large number of identified boards, from which to calculate the combinations of board lengths and grades, before they reach the distribution section.Type: ApplicationFiled: March 1, 2007Publication date: September 4, 2008Inventor: Andre Lapointe
-
Patent number: 7387298Abstract: A vacuum belt feeder comprising a means of conveyance having a pitch, for retrieving items from a supply zone, and then distributing them at target locations in a discharge zone.Type: GrantFiled: November 9, 2005Date of Patent: June 17, 2008Assignee: OSI Machinerie Inc.Inventor: Andre Lapointe
-
Publication number: 20060181005Abstract: A vacuum belt feeder comprising a means of conveyance having a pitch, for retrieving items from a supply zone, and then distributing them at target locations in a discharge zone.Type: ApplicationFiled: November 9, 2005Publication date: August 17, 2006Inventor: Andre Lapointe
-
Patent number: 6447386Abstract: A presser roll for surface planers is described herein. The presser roll comprises a longitudinal shaft, a radially deformable generally cylindrical sleeve mounted on said longitudinal shaft for rotation in unison therewith and a biasing assembly mounted between the shaft and the sleeve for outwardly biasing the sleeve.Type: GrantFiled: September 12, 2000Date of Patent: September 10, 2002Assignee: OSI Machinerie Inc.Inventor: André LaPointe