-
公开(公告)号:US11763550B2
公开(公告)日:2023-09-19
申请号:US17086078
申请日:2020-10-30
Applicant: DASSAULT SYSTEMES
Inventor: Louis Dupont De Dinechin , Asma Rejeb Sfar
IPC: G06V10/774 , G06N20/10 , G06T7/70 , G06F18/21 , G06F18/23 , G06F18/28 , G06F18/214 , G06V10/44 , G06V10/24 , G06N3/08
CPC classification number: G06V10/7753 , G06F18/2155 , G06F18/2185 , G06F18/23 , G06F18/28 , G06N3/08 , G06N20/10 , G06T7/70 , G06V10/245 , G06V10/454
Abstract: A computer-implemented method of signal processing comprises providing images. The method comprises for each respective one of at least a subset of the images: applying a weakly-supervised learnt function, the weakly-supervised learnt function outputting respective couples each including a respective localization and one or more respective confidence scores, each confidence score representing a probability of instantiation of a respective object category at the respective localization. The method further comprises determining, based on the output of the weakly-supervised learnt function, one or more respective annotations, each annotation including a respective localization and a respective label representing instantiation a respective object category at the respective localization. The method further comprises forming a dataset including pieces of data, each piece of data including a respective image of the subset and at least a part of the one or more annotations determined for the respective image. This improves the field of object detection.
-
公开(公告)号:US20230290064A1
公开(公告)日:2023-09-14
申请号:US18169529
申请日:2023-02-15
Applicant: DASSAULT SYSTEMES
Inventor: Aurelien Jean Marie ALLEAUME , Nicolas DUNY , Mark LORIOT
IPC: G06T17/20
CPC classification number: G06T17/20
Abstract: The disclosure relates to a computer-implemented method for tessellation processing. The tessellation forms a surface representation of a real-world 3D object. The method comprises providing a constrained tetrahedral Delaunay mesh comprising the tessellation. The mesh is conformal and comprises one or more sets of tetrahedrons, each set representing a gap between portions of the tessellation, each gap having a size lower than a predefined threshold. The method further comprises determining a set of one or more tetrahedra faces of the mesh to be added to the tessellation, includes minimizing an objective function that includes a term penalizing surface creation by face addition to the tessellation. The minimization is under the constraint that a given set of tetrahedra faces of the Delaunay mesh is to be added to the tessellation. The given set of tetrahedra faces includes, for each gap of one or more gaps, the tetrahedra faces meshing the gap.
-
公开(公告)号:US11714040B2
公开(公告)日:2023-08-01
申请号:US16243285
申请日:2019-01-09
Applicant: Dassault Systemes Simulia Corp.
Inventor: Bernd Crouse , David M. Freed , Ashraful Islam
IPC: G01N13/00 , G01N15/08 , G01N33/24 , G06F30/20 , G01N23/00 , G01N23/046 , G01N23/04 , G01N23/02 , G06F30/28 , G06F111/10
CPC classification number: G01N13/00 , G01N15/0826 , G01N23/00 , G01N23/02 , G01N23/04 , G01N23/046 , G01N33/24 , G06F30/20 , G06F30/28 , G06F2111/10
Abstract: Techniques including methods, apparatus and computer program products are disclosed. These techniques include computer instructions that are encoded on computer storage media for determining wettability. The techniques use a numerical aging computation process to provide a representation of a wettability alteration of a physical rock sample in the presence of at least two fluids is disclosed. The techniques include retrieving a representation of a physical rock sample, the representation including pore space and grain space data corresponding to the physical rock sample, calculating local curvature for each surface in the pore space, determining from the calculated local curvature whether water-film breakage will occur, and classifying the wettability of the physical rock based on the determination of water-film breakage.
-
公开(公告)号:US20230237207A1
公开(公告)日:2023-07-27
申请号:US17580695
申请日:2022-01-21
Applicant: Dassault Systemes Simulia Corp
Inventor: Wesley McLendon , Joshua Stewart
CPC classification number: G06F30/10 , G01N3/08 , G01N3/066 , G01N2203/0016 , G01N2203/0617
Abstract: A computer-implemented method includes receiving, in computer memory, a first test data set that comprises results of a real-world test of a material, where the first test data set comprises a plurality of test data points. The method further includes identifying one or more critical points among the test data points in the first test data set and processing the first test data set with a computer processor to produce a second test data set with differing (e.g., fewer) test data points than the first test data set, wherein the second test data set includes all the test data points that were identified as critical points in the first test data set and at least some other data points.
-
公开(公告)号:US20230195725A1
公开(公告)日:2023-06-22
申请号:US18067848
申请日:2022-12-19
Applicant: DASSAULT SYSTEMES
IPC: G06F16/2453 , G06F16/901 , G06F16/2455
CPC classification number: G06F16/24537 , G06F16/9024 , G06F16/24565
Abstract: A computer-implemented method for generating by a query engine a graph of operators for a SPARQL query over an RDF graph. The method includes obtaining a graph of operators executable by the query engine, the graph comprising a plurality of basic operators, at least two of said operators being of a first type each configured to find RDF triples of the RDF graph that match a respective basic graph pattern. The method further comprises identifying a group of operators among the at least two basic operators of the graph which are of the first type. The respective basic graph patterns of the group of operators have same subject and/or predicate and/or object and the identified group of operators is replaced in the graph by an equivalent operator configured to find RDF triples of the RDF graph that match the respective basic graph patterns of the group of operators.
-
公开(公告)号:US20230185425A1
公开(公告)日:2023-06-15
申请号:US18080401
申请日:2022-12-13
Applicant: DASSAULT SYSTEMES
Inventor: Christophe DELFINO
IPC: G06F3/04815 , G06F3/04842 , G06F3/04845
CPC classification number: G06F3/04815 , G06F3/04842 , G06F3/04845 , G06F2203/04803 , G06F2203/04806
Abstract: A computer-implemented method for rendering at least two visualization modes of a 3D model. The method comprises rendering the 3D model in a main view according to a first visualization mode. The method further comprises splitting the main view in at least two split views. Each split view corresponding to one visualization mode of a plurality of visualization modes. The method further comprises, for each split view, determining a rendering area of the 3D model associated to the current split view. The method further comprises rendering the 3D model in each split view according to its corresponding visualization mode and determined rendering area. This constitutes an improved method for rendering various visualization modes of a 3D model simultaneously.
-
公开(公告)号:US20230177228A1
公开(公告)日:2023-06-08
申请号:US18063338
申请日:2022-12-08
Applicant: Dassault Systemes Americas Corp.
Inventor: Quentin Bourret , Julie Charland , Daniel Imbeau , David Brouillette , Jean-Baptist Djire
Abstract: Embodiments assess ergonomic risk in environments, such as factories and workstations. One such embodiment begins by receiving process planning data for an operator performing a task. In turn, the received process planning data is used to generate a posture for the operator to perform the task in a certain real-world environment. The generated posture is processed using a hierarchical decision tree to determine ergonomic risk of the posture in the certain real-world environment. Output includes an indication of the determined ergonomic risk.
-
公开(公告)号:US11669660B2
公开(公告)日:2023-06-06
申请号:US16673649
申请日:2019-11-04
Applicant: DASSAULT SYSTEMES
IPC: G06F30/23 , B29C64/393 , G06F17/18 , B33Y50/02 , G06F119/18
CPC classification number: G06F30/23 , B29C64/393 , G06F17/18 , B33Y50/02 , G06F2119/18
Abstract: The disclosure notably relates to a computer-implemented method for designing a modeled object. The method includes obtaining a finite element mesh, data associated to the finite element mesh and a non-uniform distribution of one or more local quantity constraints. The data associated to the finite element mesh include forces, boundary conditions, parameters, and a global quantity constraint. The method also comprises performing a topology optimization based on the finite element mesh, the data associated to the finite element mesh, and the non-uniform distribution. The method improves the design of a modeled object representing a mechanical part by topology optimization.
-
公开(公告)号:US20230169225A1
公开(公告)日:2023-06-01
申请号:US17456933
申请日:2021-11-30
Applicant: Dassault Systemes Americas Corp.
Inventor: David Brouillette , Julie Charland , Hugues Caron
CPC classification number: G06F30/20 , G06F11/3457 , G06F9/4881
Abstract: Embodiments determine manikin posture for simulations of real-world environments. An embodiment automatically generates a phrase by performing a hierarchical analysis using data regarding the real-world environment. According to an embodiment, the generated phrase describes a task, to be simulated, performed by a manikin in an environment. In turn, one or more posture engine inputs are determined based on the generated phrase. The posture for the manikin in a simulation of the manikin performing the task in the environment is then automatically determined based on the determined one or more posture engine inputs.
-
公开(公告)号:US20230162093A1
公开(公告)日:2023-05-25
申请号:US18147671
申请日:2022-12-28
Applicant: DASSAULT SYSTEMES
Inventor: Louis DUPONT DE DINECHIN
Abstract: The disclosure notably relates to a computer-implemented method for teaching a generative autoencoder. The generative autoencoder is configured to generate functional structures. A functional structure is a data structure representing a mechanical assembly of rigid parts and which includes a tree. Each leaf node represents a shape and positioning of a respective rigid part and a force exerted on the respective rigid part. Each non-leaf node with several children represents a mechanical link between sub-assemblies. Each sub-assembly is represented by a respective one of the several children. Each non-leaf node with a single child represents a duplication of the sub-assembly represented by the single child. The method includes obtaining a dataset including functional structures. The method further comprises teaching the generative autoencoder on the dataset. This constitutes an improved method for teaching a generative autoencoder configured for generating functional structures.
-
-
-
-
-
-
-
-
-