Abstract: A computer-implemented method estimates a mass distribution of a physical product comprising a plurality of product parts. The method: a) creates a data structure comprising, for each part, data representing position and orientation of the part, its mass of the part, preferably its tolerance associated to each mass of the part, and its geometry in voxel format; b) decomposes a digital model of the physical product into a plurality of parallel slices (SL1); c) for each slice, uses the data structure for identifying a set of product parts of the data structure overlapping with the slice and determining a respective overlap rate; and d) attributes to each slice a mass value corresponding to a sum of the masses of all product parts overlapping with the slice, weighted by the respective overlap rates. A computer program product, non-transitory computer-readable data-storage medium, a computer system and a Computer Aided Design (CAD) Systems carry out such a method.

Abstract: A computer-implemented method of designing a 3D modeled object representing a mechanical product. The 3D modeled object has a feature tree and an original value of a set of semantic parameters. The method includes by a user graphically interacting with the 3D representation graphically selecting a semantic point of an outer surface of the 3D modeled object and graphically selecting one or more target 3D positions of the semantic point. The method further includes, automatically, iteratively modifying the value of the set of semantic parameters. Thereby the method obtains an updated value of the set of semantic parameters. The method further includes, automatically by the CAD system, updating the 3D representation of the 3D modeled object based on the updated value of the set of semantic parameters. This provides an improved solution for updating 3D modeled objects based on graphical interactions.

Abstract: A machine-learning method for learning a function for predicting a next feature in a feature tree. The method includes obtaining a dataset of examples each including a graph representing at least a part of a feature tree. The graph includes nodes each representing a feature and each labeled with a label of a set of labels each indicating a feature type of a predetermined set. The graph includes edges each connecting nodes and represents a parent-child relationship between the features represented by the nodes. The graph comprises ground truth data indicating a next feature according to one or more selected features each corresponding to a graph node. The method further includes training the function to take as input a graph representing at least a part of a feature tree and to output a prediction of one or more next features in the feature tree.

Abstract: A computer-implemented method for forming a gap on a surface. The surface represents a surface portion of a product to be manufactured. The method includes providing specifications of the gap. The specifications include a radius of a connection between the surface and flanges of the gap. The specifications further include a profile of the gap. The specifications further include a shape defining the gap on the surface. The method further includes sweeping the profile along the shape. The method further includes connecting the result of the sweep to the surface by applying a fillet operation. The fillet operation has as radius the provided radius.

Abstract: A computer-implemented method for determining a machine-learning function configured for taking an input 3D scene and for outputting one or more camera viewpoints each for generating a respective 2D rendering of the 3D scene. The method includes obtaining a library having 3D scenes. The method includes, based on the library, forming a first dataset for training a first neural network configured for outputting a camera position and forming a second dataset for training a second neural network configured for outputting a camera orientation. The method includes training the first neural network based on the first dataset and training the second neural network based on the second dataset. Each camera viewpoint outputted by the machine-learning function includes a camera position and a camera orientation. Such a method forms an improved solution for outputting one or more camera viewpoints of a 3D scene.

Abstract: A computer-implemented data structure representing an adjacency matrix associated with a predicate of a set of quads of an RDF graph database, the adjacency matrix being partitioned into a grid of rectangular partitions, the partitions having a same dimension, the adjacency matrix comprising a set of adjacency sub-matrices, each adjacency sub-matrix corresponding to a respective partition of the adjacency matrix; each adjacency sub-matrix being identified by its respective position in the grid.

Abstract: A method for executing linear recursive queries. The method comprises obtaining a first part of the query that defines as input one or more initial conditions of query elements in a second part of the query on the RDF graph database. The method also comprises obtaining at least two clauses specifying that a second part of the query will be executed recursively. The first clause defines how an output of an execution of the second part of the query is used as an input of a next execution of the second part of the query. The second clause defines the second part of the query and comprises the query elements describing how the output of an execution is queried using (i) the input of the one or more initial conditions for an initial execution or (ii) the output of a previous execution for the next execution.

Abstract: A computer-implemented data structure for storing RDF dataset including a set of RDF quads. The data structure includes a first data structure. The first data structure includes a first non-graph database with ACID properties for temporarily storing one or more modifications to be applied to the RDF dataset. The data structure also includes a second data structure. The second data structure includes a second non-graph database with ACID properties for storing a state of the RDF dataset as a binary representation. The binary representation is stored as binary data in a native structure of the second non-graph database.

Abstract: A computer-implemented method for designing a 3D modeled object representing a transmission mechanism with a target 3D motion behavior. The method including obtaining a 3D finite element mesh and data associated to the mesh, performing a topology optimization based on the mesh and on the associated data, therefore obtaining a density field representing distribution of material quantity of the 3D modeled object. The method further includes computing a signed field based on the density field and the associated data, identifying one or more patterns of convergence and divergence in the signed field, each pattern forming a region of the signed field, and for each identified pattern, identifying a joint representative of the identified pattern and replacing a part of the density field corresponding to the respective region formed by the identified pattern by a material distribution representing the identified joint.

Abstract: A computer-implemented method of machine-learning. The method includes obtaining a training dataset of 3D models of real-world objects. The method further includes learning, based on the training dataset and on a patch-decomposition of the 3D models of the training dataset, a finite codebook of quantized vectors and a neural network. The neural network comprises a rotation-invariant encoder. The rotation-invariant encoder is configured for rotation-invariant encoding of a patch of a 3D model into a quantized latent vector of the codebook. The neural network further includes a decoder. The decoder is configured for decoding a sequence of quantized latent vectors of the codebook into a 3D model. The sequence corresponds to a patch-decomposition. This constitutes an improved solution for 3D model generation.

Abstract: A computed-implemented method for processing a computer-aided design 3D model of a mechanical part including a portion having a distribution of material. The method including obtaining the 3D model, the 3D model including a skin portion of the 3D model representing an outer surface of the portion of the mechanical part. The method further including processing the skin portion based on an extrusion-processing algorithm, where a transform of the skin portion is inputted to the algorithm. The transform represents an unfolding of the distribution of material of the portion.

Abstract: A computer-implemented method for profile detection in a discrete 3D model. The discrete 3D model represents a mechanical part. The method includes, for each 3D surface of at least one 3D surface of the 3D model, providing a candidate parameterization of the 3D surface and a candidate projection of the 3D surface into . The method further includes computing a function. The function penalizes, for each couple of points of the 3D surface having neighboring parameter values, a distortion. The distortion is between a disparity between the projection of the points, and a disparity between the parameterization of the points. The method further includes determining that the candidate parameterization and the candidate projection form a valid profile of the 3D surface if the computed function is smaller than a predefined threshold.

Abstract: A computer-implemented method of machine-learning. The method includes obtaining a dataset of 3D modeled objects representing real-world objects. The method further includes learning, based on the dataset, a generative neural network. The generative neural network is configured for generating a deformation basis of an input 3D modeled object. The learning includes an adversarial training.

Abstract: A computer-implemented method for predicting a cardiovascular behavior of a newborn to birth from his/her fetus physiological parameters. The method comprises obtaining physiological parameters of the fetus, obtaining a non-calibrated surrogate cardiovascular model modeling a cardiovascular system of the fetus and modelling at least one physiological change triggered by the birth, calibrating the non-calibrated surrogate cardiovascular model with a data assimilation algorithm using the obtained physiological parameters of the fetus on the non-calibrated surrogate cardiovascular model, thereby obtaining a calibrated surrogate cardiovascular model of the fetus, and predicting the cardiovascular behavior of the newborn by triggering the at least one physiological change of the calibrated surrogate cardiovascular model of the fetus, thereby obtaining a calibrated surrogate cardiovascular model of the newborn.

Abstract: A computer-implemented method for generating a summary of a graph database comprising a set of RDF tuples including obtaining the graph database and generating a summary having a set of probabilistic filters. Each probabilistic filter of the set determines if at least one RDF tuple existing in the graph database corresponds to a respective basic graph pattern of the probabilistic filter with a possibility of false positive.

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.

Abstract: A computer-implemented method of applying a machine-learning function preconfigured for taking an input 3D layout and a given noise level, and for predicting an output 3D layout. The function is preconfigured with a conditioning drop-out with respect to at least one layout parameter. The method further comprises obtaining a set of conditioning inputs and, for each conditioning input, determining one or more conditioning candidate 3D layouts and determining a plurality of perturbed conditioning candidate 3D layouts. The method further includes, applying the preconfigured function to each perturbed conditioning candidate, in which the one layout parameter is dropped out, computing reconstruction errors, and averaging the reconstruction errors, thereby obtaining a score. This forms an improved solution for predicting 3D layouts.

Abstract: A computer-implemented method of machine-learning for assembling mechanical parts, based on a mating score and a mating axis. The method includes providing a dataset of pairs of B-Reps, each pair comprising at least one B-Rep representing an assembly of mechanical parts, being labelled with mating compatibility data and, when the B-Reps of the pair are compatible according to the mating compatibility data, mating axis compatibility data. The method also comprises training a neural network based on the dataset, configured for taking as input a pair of B-Reps. The neural network also outputs a mating score of a pair of single embeddings, each single embedding representing a B-Rep, the mating score representing a score of mating compatibility between the mechanical parts represented by the pair, and if the B-Reps are compatible according to the mating score, data defining a mating axis.

Abstract: A computer-implemented method of machine-learning. The method includes obtaining a dataset of ground truth 3D layouts. The machine-learning method further comprises obtaining a probability distribution of noise levels. The machine-learning method also comprises, for each ground truth 3D layout, obtaining a respective perturbed 3D layout. The machine-learning method moreover comprises training a function. The function is configured for taking an input 3D layout and a given noise level, and for predicting an output 3D layout. The training is performed over the dataset based on a loss which penalizes a dissimilarity metric between each ground truth 3D layout and a respective predicted 3D layout.

Abstract: A computer-implemented method for storing a database state. The method comprises providing a database, receiving by the database one or more write events, logging each write event, each logged write event thus forming a new state on the database, buffering pages modified or created by the write events, and creating a patch by flushing to a database storage the buffered pages if a threshold has been met.