Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

184 results about "Geometric representation" patented technology

A geometric representation allows us to visualize mathematical properties. This visualization makes it easier to understand and remember the property. One geometric representation you may be familiar with is the representation of multiplication using rows and columns of dots.

Building steel structure deepening design and virtual pre-assembly system based on BIM

The invention discloses a building steel structure deepening design and virtual pre-assembly system based on BIM, and a multi-professional model integration platform is formed by constructing a BIM system server to integrate multi-professional models. A three-dimensional model of the steel structure is created and refined on the platform, design parameters and engineering data are input, and accurate geometric representation is formed. And automatically checking relative positions and overlapping conditions among the models by using a geometric algorithm, establishing association and dependency relationships among the models, automatically updating the models, and carrying out collision detection. In the deepening design process, steel structure nodes are optimized, and a drawing and a material list are generated. According to the generated drawings and lists, trial assembly and simulated assembly of the steel structure segmented components are carried out to form a virtual assembly contour model, fitting comparison with a theoretical model is carried out, the machining and assembly precision is analyzed, the precision of engineering installation is ensured, and zero-error installation is achieved. According to the method, the design efficiency is improved, the construction error is reduced, and the method is suitable for deep design and pre-assembly of complex steel structure projects.
Owner:GUIZHOU CONSTR ENG GRP FOURTH CONSTR ENG CO LTD +1

Ship shoreline illegal invasion and occupation identification method and system based on AIS big data

The invention relates to a ship shoreline illegal invasion and occupation identification method and system based on AIS big data, and the method comprises the steps: obtaining the AIS data of a ship, and carrying out the preprocessing; obtaining geographic information data, and constructing geometric representation of geographic information; performing superposition matching on the preprocessed AIS data and the geometric representation of the geographic information to obtain a ship behavior occurrence area, and combining a set threshold to obtain a ship abnormal behavior identification result; and based on the ship abnormal behavior identification result, adopting a multistage clustering algorithm to perform coarse clustering on ship berthing points, then performing fine clustering on each coarse clustering group, and performing statistical analysis in combination with the preprocessed AIS data to obtain a ship shoreline illegal invasion and occupation identification result. Compared with the prior art, the method has the advantages of improving the capability of identifying shoreline resources and illegal wharfs and the like.
Owner:SHANGHAI MARITIME UNIVERSITY

System and Method for Geometric Compression and Persistent Memory Management of Genomic Data Using Dynamic Latent Manifolds

A system and method for processing genomic data using dynamic latent manifolds that transforms multi-modal genomic datasets into geometric representations within a curved manifold space. The system receives genomic datasets including DNA sequences, genetic variants, and expression data, then extracts biological features and assesses importance using trained neural networks. Manifold curvature values are computed based on biological significance, and genomic data is embedded as geometric structures where semantic relationships are represented through distance and curvature properties. The system generates compression pressure fields that influence processing decisions and computes optimal geodesic paths through the manifold to minimize cognitive action functionals. Adaptive compression rates are determined for different genomic regions based on geometric properties and biological importance. The manifold structure evolves through use, strengthening frequently accessed pathways while applying thermodynamic decay to unused concepts. The system supports hierarchical organization across biological scales, reversible navigation, and federated learning capabilities that enable privacy-preserving collaboration.
Owner:ATOMBEAM TECH INC

Method and apparatus for conversion into sketches for geometrical representation learning

Proposed herein are an apparatus and method for conversion into sketches. The apparatus for conversion into sketches includes: an input / output interface configured to receive an image and output the results of processing of the image; storage configured to store a program for performing a method for conversion into sketches; and a controller including at least one processor, and configured to convert the image into a sketch by executing the program. The controller receives (i) initial stroke information having attribute parameters and (ii) image information about a target image, converts the target image into a plurality of final strokes having geometric information about the target image by using a stroke generation model, and outputs the results of data processing of the plurality of final strokes.
Owner:SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION

Cross-format lightweight and geometric consistency maintenance method based on three-dimensional model

The invention discloses a virtual space multi-person interaction synchronous control method oriented to an end-cloud collaborative architecture. The invention relates to a computer graphics and three-dimensional modeling technology, and discloses a cross-format lightweight and geometric consistency maintenance method based on a three-dimensional model. Through format-independent geometric representation and a self-adaptive lightweight strategy, efficient compression and precision maintenance of three-dimensional model cross-format conversion are realized. The method specifically comprises the following steps: performing format analysis and geometric feature extraction on an input model, and establishing a unified internal representation; adaptively selecting a multi-level LOD lightweight strategy based on the complexity of the model; the accuracy of key information is ensured through geometric feature keeping and topology consistency detection; the geometric consistency is dynamically maintained by combining error monitoring and an iterative correction mechanism; and generating a target format lightweight model and carrying out quality verification. According to the method, adaptive precision control, multi-level consistency maintenance and format irrelevant processing are combined, the model size and conversion errors are effectively reduced, and cross-platform compatibility and geometric fidelity are improved. The method can be widely applied to the fields of industrial design, game development, virtual reality and the like.
Owner:BITMAP3D TECH (SHANGHAI) CO LTD

Data processing method in electric power construction supervision project

The invention provides a data processing method in an electric power construction supervision project, and the method comprises the steps: carrying out the scanning of an engineering construction site through a data collection device, obtaining a three-dimensional point cloud data set containing geometric information, and enabling the three-dimensional point cloud data set to comprise the complete geometric representation of a site space; according to the three-dimensional point cloud data set, a data processing algorithm is adopted to remove noise information, processed point cloud data is obtained, and the processed point cloud data is used for subsequent modeling analysis; aiming at the aligned point cloud model, geometric parameters of key parts are extracted, actually measured geometric feature data are obtained, and the actually measured geometric feature data comprise actual size information of site construction; and generating a quality evaluation report according to the deviation distribution data, and sorting the abnormal regions according to deviation degrees to obtain a quality adjustment priority sequence.
Owner:ZHONGSHAN LUCHENG ENG MANAGEMENT CO LTD

Multi-modal sensor online calibration method based on dynamic environment self-adaption

The invention relates to a multi-modal sensor online calibration method based on dynamic environment self-adaption, which comprises the following steps: constructing a memory enhanced scene understanding network architecture, embedding a topology memory unit in a Segment Anything Model basic framework, and constructing a double-layer knowledge solidification mechanism; performing construction and feature extraction of a differential geometric field, and proposing a continuous geometric representation scheme based on a neural radiation field; a decoupling type cross-modal adversarial optimization mechanism is introduced, and a calibration task is decomposed into a geometric constraint and semantic association dual-channel optimization problem; a Bayesian-genetic hybrid optimization framework is provided for an environment-adaptive hybrid optimization engine, and global exploration and local fine tuning of a parameter space are realized. According to the invention, the automatic driving function with high efficiency, accuracy and high adaptability is realized.
Owner:NANJING UNIV OF POSTS & TELECOMM

Hardware-accelerated ray-tracing for intelligent robot task execution

Use of hardware-accelerated raytracing for intelligent robot task execution is disclosed. In various embodiments, data comprising a geometric representation of a robot and one or more obstacles in a workspace in which the robot is located are used to determine, with respect to a pose of the robot in the workspace, whether the pose is associated with a collision condition with respect to one or more of the one or more obstacles, at least in part by performing hardware accelerated ray tracing with respect to rays originating from each of a plurality of points associated with the robot.
Owner:DEXTERITY INC

Physical field determination system and method

Variants of the method can include determining a design, generating a geometric representation of the design, generating a topological representation of the design, determining a context value set, predicting a physical field using a trained physics model, optionally verifying the physical field, optionally generating a corrected physical field, and optionally training the physics model based on the corrected physical field.
Owner:VINCI4D AI INC

Reconstruction method and device of three-dimensional face model and electronic equipment

The invention discloses a reconstruction method and device of a three-dimensional face model and electronic equipment. The method comprises the steps that an initial parameter set used for reconstructing a three-dimensional face model is determined according to a target data set, an initial three-dimensional face model is constructed according to the initial parameter set, and the three-dimensional face model is geometric representation of a three-dimensional face corresponding to a target object; determining a projection relationship between the initial three-dimensional face model and the face images at a plurality of preset angles; adjusting the initial parameter set according to the projection relation to obtain a target parameter set, and updating the initial three-dimensional face model according to the target parameter set to obtain a target three-dimensional face model; and optimizing the target three-dimensional face model according to a preset constraint condition to obtain a three-dimensional face model. According to the method and the device, the technical problems of low reconstruction efficiency and poor precision of the three-dimensional face model due to the fact that a three-dimensional face model reconstruction method in related technologies needs to depend on complex equipment and needs a large amount of face image data are solved.
Owner:CHINA TELECOM ARTIFICIAL INTELLIGENCE TECHNOLOGY (BEIJING) CO LTD

Multi-scale feature fusion complex scene object recognition system

The invention relates to the technical field of computer vision, in particular to a complex scene object recognition system based on multi-scale feature fusion, which comprises a feature extraction module, a Riemannian geometric feature pyramid module, a candidate region generation module and an instance recognition and positioning module, and is characterized in that the feature extraction module extracts multi-scale spatial features; the Riemannian geometric feature pyramid module maps spatial features to a Riemannian manifold space, calculates curvature distribution of feature manifolds, dynamically adjusts feature extraction levels and fusion strategies, and realizes geometric consistent fusion of different scale features through geodesic line feature fusion; the candidate region generation module generates an object candidate region based on the fusion features; and the instance identification and positioning module completes final object classification and positioning, introduces a differential geometry theory to construct a Riemannian geometric feature pyramid, realizes geometric representation and adaptive fusion of features, solves the problems of scale change, partial occlusion, background interference and the like in a complex scene, and effectively improves the accuracy and robustness of object identification.
Owner:NORTH CHINA UNIVERSITY OF SCIENCE AND TECHNOLOGY

Training method, apparatus and system for feature extraction network of three-dimensional mesh model

A training method, apparatus and system for a feature extraction network of a 3D mesh model are provided. The method includes dividing a training 3D mesh model into a plurality of patches which do not overlap with each other, dividing the plurality of patches into first-type patches and second-type patches, and using mask embedding as a feature encoding of each second-type patch; inputting geometric representation information and positional representation information of each first-type patch into a feature extraction network; determining predicted geometric representation information of each face based on a feature encoding of each first-type patch output from the feature extraction network, the mask embedding, and positional representation information of each second-type patch, and adjusting parameters of the feature extraction network based on differences between the predicted geometric representation information and geometric representation information of the each face.
Owner:JD DIGITS HAIYI INFORMATION TECHNOLOGY CO LTD

Semantic hierarchical geometric representations for digital twins

One example method includes performing geometrical modeling of a digital twin network that includes a dynamically informed digital twin of a near-edge node and dynamically informed digital twins of far-edge nodes. Each digital twin is defined by a set of geometrical modeling variables and contextual variables that are used to map each digital twin to a graph. The geometrical modeling includes obtaining measurements from sensors in an edge environment that includes the near-edge and the far-edge nodes; associating measurements to a digital twin node in the graph; updating the digital twin node in the graph associated with the measurements and updating the corresponding far-edge node with a local update; updating digital twin nodes associated with the digital twin node that was updated; and updating digital twin nodes not associated with the digital twin node that was updated.
Owner:DELL PROD LP

Point cloud registration method based on unsupervised multi-scale feature fusion and geometric representation

The invention discloses a point cloud registration method based on unsupervised multi-scale feature fusion and geometric representation. Two innovative modules, namely a multi-scale neighborhood feature fusion module and a triangle-based representation learning module, are provided. The multi-scale neighborhood feature fusion module is used for extracting local neighborhood information from point clouds of different scales, balancing fine details and a global structure on multiple scales by combining multi-scale neighborhood construction, an attention mechanism and a feature fusion strategy, and overcoming the challenge of single-scale feature extraction in processing local shape similarity. And the triangle-based representation learning module deeply fuses the multi-scale neighborhood features and geometric constraints based on triangular geometric descriptors to generate feature representation with higher discrimination, so that the accuracy and stability of registration are remarkably improved. Finally, the multi-scale neighborhood feature fusion module and the triangle-based representation learning module enable the model provided by the invention to show excellent registration performance and have excellent applicability.
Owner:ZHEJIANG SCI-TECH UNIV

Real time, resource efficient virtual representation generation for a location

Resource-efficient systems, methods, and software to estimate the geometry of indoor space(s) (e.g., a location) and render a model of the indoor space(s) to a user in real time natively on mobile smartphones is described. Lightweight neural networks are used to estimate depths for each frame in received video data of the location, and a surfel representation is used to fuse location depth information into a geometric representation. Detecting when a user has entered a new room based on the geometric representation in real time is also described, and the resulting ability to create full floor scans where each room is fused together and labeled during a scan.
Owner:YEMBO INC

Three-dimensional semantic scene completion method and system based on semantic-physical joint representation

The invention provides a three-dimensional semantic scene completion method and system based on semantic-physical joint representation. The method comprises the following steps: extracting image features according to multi-view image input, and mapping the image features to a three-dimensional voxel space; voxel features containing local semantic information and three-view features containing global semantic information are extracted through a double-branch encoder, key anchor points with identifiable semantic features are screened out according to semantic consistency of the voxel features and the three-view features, and efficient initialization of Gaussian representation in a key area is guided; and then introducing a semantic spherical harmonic function, projecting Gaussian semantic representation to an orthogonal spherical harmonic space, enhancing the modeling capability of local context geometric structure information, and promoting the semantic-geometric representation consistency of the context by using key voxel distribution alignment, thereby realizing three-dimensional semantic scene completion with both precision and efficiency.
Owner:PEKING UNIV

System and method for determining a three-dimensional model of an object using neural structured light

There is provided a system and method for determining a three-dimensional model of an object using a projector and a light sensor arranged in a stereo configuration. The method including: receiving pixel intensity values captured by the light sensor for a plurality of images of a scene containing the object, wherein the images of the scene each capture different projection patterns emitted by the projector onto the scene; determining, using the pixel intensity values from a set of the plurality of images, correspondence between a projector plane and a camera plane to form a three-dimensional model of the object, the correspondence determined using a trained artificial neural network model that uses a combination of volume rendering and geometric representation; and outputting the three-dimensional model of the object.
Owner:THE GOVERNING COUNCIL OF THE UNIV OF TORONTO

Spacecraft monopulse maneuvering reachable domain geometric representation and rapid calculation method

The invention belongs to the technical field of aerospace, and relates to a spacecraft monopulse maneuver reachable domain geometric characterization and rapid calculation method, which comprises the following steps: constructing a reachable domain envelope geometric feature characterization model; randomly generating a fixed time reachable domain geometrical shape feature sample and long axis rotation angle sample database; respectively constructing deep neural networks for fitting the shape features and the rotation angle features, and completing network training by using the obtained samples; respectively mapping shape features and rotation angle features of the reachable domain at a reference position in combination with a completely trained deep neural network, and realizing efficient and accurate calculation of the geometrical features of the spacecraft monopulse fixed time reachable domain; according to the method, the defects that an existing fixed-time reachable domain optimization solving method is low in calculation efficiency, and an uncertainty propagation solving method is difficult to accurately characterize a reachable domain envelope shape are overcome.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS +1

Visualization method and device of finite element result data in dam three-dimensional model

The invention provides a visualization method of finite element result data in a dam three-dimensional model, and relates to the technical field of finite element analysis, and the method comprises the steps: constructing a finite element spatial discrete model based on geometric information in the finite element result data; based on a sampling position in the dam three-dimensional model, determining a target space unit or a target space region corresponding to the sampling position in the finite element spatial discrete model, and obtaining first dam body displacement data corresponding to the target space unit or the target space region from the finite element result data; converting the first dam body displacement data into a first visual parameter according to a preset mapping relationship, and associating the first visual parameter to a geometric representation of the dam three-dimensional model to form a visual attribute for rendering; and carrying out rendering display on the dam three-dimensional model based on the visualization attribute so as to output a displacement visualization result of the surface of the dam three-dimensional model. According to the method, the intuition, interactivity and updating efficiency of visual display can be improved.
Owner:BEIJING 51WORLD DIGITAL TWIN TECH CO LTD +1

System and Method for Experiential Manifold Cognition in Persistent Cognitive Machines

A system and method for implementing experiential manifold cognition that extends persistent cognitive machines beyond discrete thought caching to continuous geometric representation of experience. The system maintains an experiential manifold comprising a differentiable manifold with Riemannian metric tensor encoding semantic relationships, compression pressure field governing memory consolidation, and potential field encoding goals and attention. Input data is projected onto the manifold through adaptive geometric diffusion preserving semantic structure. The system executes geometric transformations including metric evolution, geodesic computation, and curvature estimation. During non-interactive periods, autonomous evolution occurs through trajectory recombination and selective pruning. A user interface enables visualization and direct manipulation of manifold geometry, translating navigation into geodesic traversal and edits into metric modifications. The system maintains persistence across sessions and enables controlled federation between multiple manifolds through consent-bounded synchronization. Applications include persistent narrative worlds, collaborative cognitive spaces, and experiential intelligence systems that learn through geometric evolution.
Owner:ATOMBEAM TECH INC

Collision detection method, system and device in clothes simulation, medium and product

The invention discloses a collision detection method, system and device in clothes simulation, a medium and a product, and relates to the field of computer vision and graphic processing, for the first time, a deep learning network is used for collision detection in clothes simulation, and a skin weight field prediction network based on MLP and an implicit geometric representation deep learning network are trained, so that the collision detection efficiency is improved. Therefore, accurate collision detection in clothes simulation is carried out by using an MLP-based skin weight field prediction network and an implicit geometric representation deep learning network, and a discrete sdf or occupancy field formed by space voxels is generated for a bounding box where a human body is located. By means of the mode that fine collision detection is conducted through space hash, the calculation expenditure is large, and the calculation expenditure can be remarkably reduced while collision detection and removal between the cloth and the human body can be accurately achieved.
Owner:NANJING UNIV

Unstructured grid division method based on structured grid and electronic equipment

The invention provides a structured grid-based unstructured grid division method and electronic equipment, and the method comprises the steps: determining a computational domain range of a combustion detonation simulation task, carrying out the surface grid division of a geometric model, obtaining a geometric representation surface grid, generating a structured grid according to the geometric representation surface grid and the computational domain range, and carrying out the calculation of a combustion detonation simulation task. The method comprises the following steps: constructing a structured grid, performing simulation calculation on the structured grid, and determining a grid encryption parameter according to a simulation calculation result of the structured grid, so that an unstructured grid is generated according to the grid encryption parameter, a calculation domain range and a geometric representation surface grid, and unstructured grid division based on the structured grid is realized. The method can replace the trial-and-error iterative optimization or complex dynamic adaptive process of the unstructured grid, improves the generation efficiency of the unstructured grid, guarantees the generation quality of the unstructured grid, balances the calculation efficiency while meeting the high-precision requirement, and is suitable for a large-scale parallel environment.
Owner:国家超级计算天津中心 +1

Electromagnetic field simulation adaptive grid generation method taking electromagnetic field distribution characteristics as core guidance and system thereof

The invention discloses an electromagnetic field simulation adaptive grid generation method taking electromagnetic field distribution characteristics as core guidance and a system thereof. Combining the geometric model data of each radio frequency device with the connection relation information to form a geometric representation containing topological connection information; setting a current sampling point on a non-contact surface of the surface of the metal radio frequency device and other radio frequency devices based on the geometric representation containing the topological connection information, and obtaining a current value of the current sampling point; s parameters of two rounds and current values of current sampling points are obtained through the first two rounds of mesh generation; if the convergence condition is met, the grid generated in the first round is used for full-wave-band simulation; and if the convergence condition is not met, carrying out a local encryption process until the convergence condition is met, and carrying out full-wave band simulation by using the grid generated in the previous round. According to the method, the limitation that traditional grid generation is only adaptive to geometric shapes and neglects electromagnetic characteristics is broken through, and collaborative optimization of grid quality and calculation efficiency in a high-frequency electromagnetic field simulation scene is realized.
Owner:HANGZHOU DIANZI UNIV +1

Persistent cognitive machine with curated long term memory

A system and method for implementing persistent cognitive computation through geometric representation of thought in a dynamic latent manifold. The system encodes inputs into a curved space characterized by time-evolving metric tensors, compression pressure fields derived from Ricci curvature, and goal potential fields that shape attention flow. Cognition occurs through geodesic traversal of this manifold, with attention following paths that minimize cognitive action while balancing semantic density and goal relevance. A Cognitive Dynamics Engine maintains manifold geometry, computing optimal trajectories and managing thought bundle operations including consolidation, expansion, and higher-order abstraction. During idle periods, autonomous dreaming processes reorganize the manifold through perturbation, recombination, and topological surgery. This architecture enables persistent memory through geometric encoding, where frequently accessed concepts develop high-curvature regions and cognitive shortcuts emerge from usage patterns, transforming artificial intelligence from stateless computation to structured motion through shaped memory space.
Owner:ATOMBEAM TECH INC

Efficient sounding leveraging multilink operation

A system and method are disclosed for characterizing the propagation properties of a plurality of radio frequency links without sounding each link. An access point sounds a first link and receives, from a station connected to the access point, channel state information, which may be compressed, from which it constructs a geometric representation applicable to the plurality of radio frequency links. The access point performs a sounding of a second link and receives from the station delta information, which may be compressed, regarding propagation differences between the first link and the second link. The access point then derives the propagation characteristics of the second link based on the geometric representation and the delta information. In some cases, the delta information is null, indicating no difference between the two links.
Owner:CISCO TECHNOLOGY INC

Deformable Object Shape Control Method Based on Visual Language Model and Historical Data Learning

The present invention discloses a deformable object shape control method based on visual language model and historical data learning, which combines the guidance at the microscopic pixel level in the visual target and uses the information in the language target for task planning and logical reasoning at the macroscopic semantic level. Finally, the visual language model is used to fuse the target information of the two modalities, enabling the visual target and the language target to promote and cooperate with each other, ensuring the precise planning of the deformable object shape control task. An online parameter estimation is carried out using a black-box optimization algorithm to achieve real-time tracking and updating of the object deformation state. The parametric polygon model, as a geometric representation, compresses the high-dimensional visual observation data into a low-dimensional parameter space, significantly reducing the dimension of the deformable object state observation and only retaining the key state information related to the task.
Owner:ZHEJIANG UNIV

A method and system for parsing multi-source CAD native formats and constructing a unified data model

This invention relates to the field of CAD data processing technology, and in particular to a method and system for parsing multi-source CAD native formats and constructing a unified data model. The method includes: receiving CAD files; identifying the format of the CAD files; scheduling a parser for the corresponding format based on the identification results; the parser parses the files based on a self-developed geometric kernel, converting heterogeneous CAD data into a unified intermediate geometric representation; calculating the content hash value based on the part geometric data as a globally unique identifier, and building an associated data model containing geometric, structural, and semantic layers; calculating the geometric fingerprint of each part and constructing multiple types of indexes; when importing a new version of the CAD file, comparing the globally unique identifier only processes the changed parts, performing surface-level geometric comparison on the modified parts, and outputting the difference location results. This invention achieves native parsing and unified data modeling of multi-source CAD formats, supports automatic deduplication and geometric retrieval of cross-format parts, and allows incremental processing and precise location of geometric differences in version changes.
Owner:CHANGSHA JINGYUE GALAXY TECHNOLOGY CO LTD