62 results about "Geometric computing" patented technology

The invention relates to a positioning method of large-space intelligent glasses, head display equipment and a storage medium, belongs to the technical field of meta-cosmic space calculation, and is suitable for a meta-cosmic positioning function that the head display equipment of players in a multi-user interaction large space can directly interact without learning or reasoning of a central server. A plurality of different texture pictures are arranged on the bottom surface or the ceiling of a large space, any camera on the intelligent glasses is used for collecting images, the texture pictures are recognized from the images collected by the camera T, picture information corresponding to the texture pictures is obtained, the world position of the camera T can be obtained through geometric calculation, and the texture pictures are displayed on the intelligent glasses. The method can be quickly realized on local head-mounted display equipment, so that the learning process of a server or the delay of image reasoning and position information returning and errors caused by a positioning sensor are avoided, and the problem of errors caused by long distance of a large-space site or shielded texture pictures is also avoided.

Provided is a calibration method for calibrating a scanning and imaging device. The calibration method comprises: by means of a detector, collecting rays which have passed through a geometric calibration phantom so as to obtain detector data, the detector data comprising an actual projection position of the rays on the detector after the rays have passed through the geometric calibration phantom; obtaining initial ray source parameters and initial detector parameters; according to the initial ray source parameters, the initial detector parameters, and the positional relationship of the geometric calibration phantom with respect to a ray source and the detector, obtaining a theoretical projection position of the geometric calibration phantom on the detector by means of geometric calculation; constructing an optimization function of the deviation between the actual projection position and the theoretical projection position in terms of the ray source parameters and the detector parameters; and according to the optimization function, determining the ray source parameters and the detector parameters which correspond to the minimum deviation value as optimized ray source parameters and optimized detector parameters, and determining the optimized ray source parameters and the optimized detector parameters as geometric calibration parameters.

The invention relates to a two-dimensional image and geometric constraint-based cargo stack three-dimensional pose detection method and device, which are applied to the technical field of computer vision and logistics automation, and comprises the following steps of: through an edge straight line screening strategy, combining robust fitting of a random sampling consistency algorithm, calculating a three-dimensional pose of a cargo stack; a real physical boundary can be effectively and accurately recognized from complex visual interference such as adhesive tape, labels and printed patterns on the surface of a container, the accuracy and robustness of edge detection are remarkably improved, and therefore the high precision of final three-dimensional pose calculation is guaranteed; and secondly, only a common industrial camera is needed, and an expensive three-dimensional sensor such as a laser radar or a depth camera is not needed, so that the hardware cost and the maintenance complexity of the system are greatly reduced, and the cost benefit is extremely high. And thirdly, an efficient image processing and geometric calculation algorithm is mainly adopted, the calculation complexity is low, and the requirement for real-time detection of the goods stack on an industrial automatic assembly line can be met.

The invention discloses a tool path and blank cutting volume calculation method based on point set representation, and the method converts a blank and a tool path into point sets, calculates the cutting volume through the intersection of the point sets, and simplifies the traditional geometric calculation. Meanwhile, the density of the point set can be flexibly adjusted, the calculation efficiency and precision of tool path optimization are improved, and dependence on an STL file and a third-party plug-in is avoided. The method is suitable for large-scale tool path optimization tasks, and the flexibility and controllability of the tool path optimization process can be improved.

The invention discloses a Mask-RCNN instance segmentation model-based building facade aperture ratio intelligent batch measurement and calculation method, and belongs to the technical field of urban and rural planning heritage protection. The method comprises the following steps: firstly, acquiring streetscape photos and video data of a block and preprocessing the streetscape photos and video data to construct a basic data set trained by a Mask-RCNN (Regional Convolutional Neural Network) model; next, the processed data set is input into a Mask-RCNN model for training, and an optimal model weight is obtained; and the trained model is used to carry out instance segmentation and labeling on the streetscape building style and feature elements including doors and windows. And performing same automatic perspective correction on the building facade image and the Mask mask image obtained by model reasoning through an OpenCV library of the Python platform. And finally, performing intelligent batch calculation by utilizing a computer vision technology in a Python programming language in combination with a geometric calculation method to obtain the hole opening rate of the building facade. Compared with the prior art, the method has the advantages that the efficiency and accuracy of building facade holing rate measurement and calculation are improved, and scientific basis and technical support are provided for block protection and building style and feature management and control in urban and rural planning.

The invention discloses a physical collision monitoring and feedback method and device based on a digital twin engine and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: carrying out the preliminary collision detection of a model physical entity in a digital twin model based on a to-be-detected physical entity, and determining a preliminary collision object; traversing the hierarchical tree of the hybrid hierarchical bounding box of the preliminary collision object in the digital twin model, checking whether each node is intersected with the bounding box of the physical entity to be detected layer by layer, and determining leaf nodes of the intersected hierarchical tree of the hybrid hierarchical bounding box; for leaf nodes intersecting with the bounding box of the physical entity to be detected, determining a collision detection result through geometric calculation, and synchronizing the collision detection result to the digital twinborn model in real time; and feeding back the collision detection result to a control system of the to-be-detected physical entity so as to adjust the running state of the to-be-detected physical entity. The technical effect of improving the instantaneity of collision monitoring and feedback is achieved.

The invention provides a credible permission mutual recognition method, device and system for cross-domain agents, and relates to the technical field of artificial intelligence security, and the method comprises the steps: receiving a call request from a source domain agent for executing a corresponding operation on a target domain agent; obtaining an affine transformation parameter set through a permission conversion model according to the space relation characteristics of a source domain permission space and a target domain permission space involved in the calling request, and finally screening out affine transformation parameters suitable for permission voucher mapping by utilizing cone volume measurement evaluation and security verification, and mapping an original permission voucher of the source domain agent from a source domain permission space to a target domain permission space by using the affine transformation parameter, and generating a mapped permission voucher which can be identified and verified by the target domain. According to the method, the permission space is geometrized, and affine transformation, space division and geometric calculation are utilized, so that the permission credible mutual recognition problem in cross-domain agent collaboration is effectively solved.

The invention relates to a geometric calculation teaching method for driving training, which comprises an abstract algorithm framework. According to the framework, teaching points in a driving training project are abstracted into an object algorithm framework with unified characteristics, all point positions in current teaching are calculated in real time according to the current state of a vehicle according to calculation methods of different subjects, a first uncompleted point position is found through traversal, and whether the vehicle reaches the point position or not is judged; the same project has a corresponding method for calculating the position of the point location, the method has a unified data format and calling mode, and a configuration file for configuring the feature of the point location exists for loading of an algorithm framework. According to the method, the teaching point is calculated in real time, corresponding guidance can be provided according to the actual running state of the vehicle, the method is suitable for changes of various vehicle initial postures, effective correction suggestions can be provided when trainees deviate from a standard path, and the effectiveness and flexibility of driving training are greatly improved.

The invention discloses a stage body virtual rotating shaft technology implementation method and a stage body structure. According to the method, a virtual rotating shaft system is constructed by applying a geometric model, so that an overturning table board can stably overturn along a specific geometric track and seamless butt joint is realized; the method specifically comprises the steps that a stage body structure comprising a fixed stage face, a rotating shaft support, a rotating shaft, an overturning stage face and an overturning driving device is constructed, the rotating shaft support is positioned according to set geometric parameters, the rotating shaft and the overturning stage face are connected, and the overturning driving device is used for driving the overturning stage face to overturn around a virtual rotating shaft. And the movement of the turnover table top is accurately controlled and optimized through a geometric calculation method. The stage body structure corresponds to the method, and stable overturning and seamless butt joint of the overturning table top are achieved through guidance of a geometric model; the technology can be widely applied to the field of stage performance and stage machinery, the problems of gaps and safety risks existing in an existing turnover stage are effectively solved, and remarkable innovativeness and practicability are achieved.

A computing system is provided, which receives a molecular graph at a message passing graph neural network (MPGNN), and produces scalar embeddings representing features of nodes and edges of the graph and vector embeddings representing geometric relationships of the graph. The system processes the scalar embeddings via a vector scalar interactive message passing mechanism of a message passing sub-block of theMPGNN to generate and pass scalar information from the scalar embeddings to an embedding space containing the vector embeddings. The system updates the vector embeddings based on the embedding space containing the scalar information and the vector embeddings. The system updates the scalar embeddings based on run-time geometry calculations of the geometric relationships encoded in the vector embeddings. The system computes an updated molecular graph based on the updated scalar and vector embeddings and outputs a target molecular property value based on the updated molecular graph.

The invention discloses an interference source positioning method based on a neural network and a ray tracing model, and belongs to the field of wireless communication technology and source positioning. According to the method, the neural network is combined with traditional geometric calculation, and the trained neural network can fit an originally complicated mathematical calculation or iterative optimization process to quickly position the interference source. Complex electromagnetic equation calculation is replaced by using a geometric calculation and neural network mixed mode, so that the calculation complexity of interference source positioning processing is reduced, and the prediction efficiency is improved; when an interference source position is predicted, space coordinates can be positioned, path prediction can be performed on main interference signal directions, an advancing path of an interference signal can be drawn, and path information can be acquired. The method is a technology for fusion development of a wireless communication technology and a deep learning / neural network technology, and provides a thought for improvement of a source positioning processing method.

The invention provides a communication method and a communication device, which are applied to the technical field of communication. For example, the communication method is adapted to an NTN scene, and the method comprises: a network device issues information related to a first AI model to a UE, so that the UE predicts channel information (such as time delay and / or Doppler frequency shift) at a future moment based on the first AI model. Compared with a mode in the prior art that the UE calculates the channel information (including time delay and / or Doppler frequency shift) through a geometric calculation mode, the first AI model in the embodiment of the invention considers historical measurement data (or historical rules), and the UE predicts the channel information (including time delay and / or Doppler frequency shift) at the future moment through the first AI model; the accuracy of the prediction result can be improved, so that it is ensured that the time and / or frequency of the transmitted signal arriving at the satellite are / is synchronous.

The invention discloses a deep and far sea platform multi-target form generation and optimization method based on a geometric agent model, and belongs to the cross technical field of ocean engineering and computer aided design. According to the method, a parameterized voxel growth model based on an offshore storm environment interference field is constructed, the digital generation logic of a platform entity structure is established, and the modular assembly process is simulated; constructing a geometric agent construction process and a final general agent function based on a rapid mapping relation from the three-dimensional voxel form set G to the physical performance index set P; constructing a multi-objective optimization problem based on an NSGA-II algorithm, and aiming at searching a Pareto optimal solution set in a variable space; and finally, automatically outputting final three-dimensional form model data and a module assembling sequence according to the specific environment weight of the target sea area. According to the method, the mapping relation between the physical performance and the geometric characteristics is constructed, expensive physical field simulation is replaced with geometric calculation, and rapid and intelligent generation of the floating type platform form is achieved.

A geometric modeling method for a fault of an intelligent mine belongs to the field of data modeling, and is characterized by comprising the following steps: surveying and acquiring position data and physical and mechanical attribute data of the fault; extracting mid-plane thickness data in the GIS data; then reconstructing a stratum interface; establishing a stratum by extracting a stratum interface; and finally, adding a fault unit. On the basis of an existing stratum geometry generation method, fault data are integrated into a geometric model, so that the problem that storage and display of the fault data are lacked in the prior art is solved, compared with the prior art, spatial position information of the fault is included, meanwhile, attribute information of the fault at different spatial positions is further included, and the fault data can be stored and displayed more accurately. Due to the fact that the fault data are not correlated geometrically, the complex geometric calculation process is omitted, the modeling efficiency is remarkably improved, the stored fault data serve as the basis for grid division and grid attribute endowing, more detailed geological data storage can be provided for a mine digital model, and accurate data support is provided for intelligent mine simulation.

A geometric modeling method for faults for smart mines belongs to the field of data modeling and is characterized by: surveying to obtain the position data and physical and mechanical property data of the fault; extracting the mid-surface thickness data in the GIS data; then reconstructing the stratum interface; establishing the stratum by extracting the stratum interface: and finally adding the fault unit. Based on the existing stratum geometry generation method, the fault data is integrated into the geometric model to solve the problem of lack of storage and display of fault data in the prior art. Compared with the prior art, it not only contains the spatial position information of the fault, but also contains the attribute information of the fault at different spatial positions. Since it is geometrically unrelated, it saves the complex geometric calculation process and significantly improves the modeling efficiency. The stored fault data is used as the basis for grid division and grid attribute assignment, which can provide more detailed geological data storage for the digital model of the mine and provide accurate data support for the simulation of smart mines.

The present application relates to the field of photovoltaic power generation, and more particularly to a double-sided photovoltaic tracking method and system based on a genetic algorithm. The method comprises: constructing a basic data structure based on multi-source data such as field station geographic time parameters and actuator constraint parameters; performing solar position and attitude geometric calculation to obtain solar geometric structure and candidate attitude geometric structure; inputting the solar geometric structure and the candidate attitude geometric structure into double-sided irradiation calculation to obtain front effective irradiation, back effective irradiation and shading factor; performing temperature calculation and electrical output calculation to obtain a candidate attitude power sequence and an energy index; performing fitness construction and feasible region processing to obtain a fitness evaluator and a feasible region processor; performing genetic algorithm calculation to output optimal strategy parameters and an angle curve, and generating a target angle instruction. The present application can realize collaborative evaluation and constraint optimization output of geometric, irradiation and electrical links, effectively improving the availability and stability of control instruction generation.

The invention discloses a dynamic modeling method and system for a three-dimensional model, and the method comprises the steps: recognizing an interactive operation, and obtaining coordinate point data in a three-dimensional scene in real time according to the interactive operation, so as to complete vertex assignment and form a vertex list; calculating a geometric center point of the vertex list based on the vertex list; connecting the vertexes in the vertex list with the geometric center point in a clockwise sequence to generate a planar triangular surface index array, and forming an initial plane; copying a vertex list of the initial plane and offsetting a target numerical value along a specified direction to generate a target plane; and connecting the vertex of the initial plane and the vertex of the target plane in sequence to generate a side triangular surface so as to complete modeling of the three-dimensional model. According to the method, the user interaction track is directly converted into the vertex data and the geometric calculation logic, so that the user can independently complete the whole-process modeling from plane to three-dimensional without relying on a modeler, the Unity scene development efficiency is remarkably improved, and a low-cost and high-flexibility solution is provided for interactive three-dimensional application.

The application discloses a kind of deep sea platform multi-objective form generation and optimization method based on geometric proxy model, belong to the cross technical field of ocean engineering and computer aided design.This application constructs the parametric voxel growth model based on the interference field of offshore wind and wave environment, aims to establish the digital generation logic of platform entity structure, simulates the modular assembly process;Based on the fast mapping relationship of three-dimensional voxel form set G to physical performance index set P, construct geometric proxy construction process and final total proxy function;Based on NSGA-II algorithm, construct multi-objective optimization problem, aims to find the Pareto optimal solution set in variable space;Finally, according to the specific environmental weight of target sea area, automatically output the final three-dimensional form model data and module assembly sequence.This application realizes the fast intelligent generation of floating platform form by constructing the mapping relationship of physical performance and geometric characteristics, using geometric calculation instead of expensive physical field simulation.

The invention discloses a household photovoltaic plotting method and system, and belongs to the technical field of household photovoltaics, and the method comprises the following steps: converting private graphic data into general format data based on a format conversion rule, and packaging an internal graphic element object and a geometric calculation rule thereof based on the general format data to obtain a graphic library; defining a business object and business logic according to the graphic library to obtain a domain entity library, and matching the external graphic data with the domain entity library to obtain a domain object document; and obtaining the household photovoltaic graph based on the domain object document. The graphic library is obtained by packaging the internal graphic element object and the geometric calculation rule of the internal graphic element object, the business object and the business logic are defined according to the graphic library to obtain the domain entity library, decoupling of the business object and the business logic from the platform is achieved, when external graphic data are obtained, the external graphic data only need to be matched with the domain entity library to obtain the domain object document, and the user experience is improved. And a household photovoltaic graph is obtained. The dependence on a specific platform is broken through, and the adaptability is remarkably improved.

A computing system is provided that receives a molecular graph at a messaging graph neural network (MPGNN) and produces scalar embedding representing features of nodes and edges of the graph and vector embedding representing geometric relationships of the graph. The system processes scalar embedding via a vector scalar interactive messaging mechanism of a messaging sub-block of the MPGNN to generate and pass scalar information from the scalar embedding to an embedding space containing the vector embedding. The system updates the vector embedding based on an embedding space containing scalar information and the vector embedding. The system updates scalar embedding based on runtime geometric calculations of geometric relationships encoded in vector embedding. The system calculates an updated molecular map based on the updated scalar embedding and vector embedding, and outputs a target molecular attribute value based on the updated molecular map.

The application provides a kind of marine structure flow field simulation method, the method comprises: generating calculation grid and object surface grid for flow field simulation;Initialize object surface grid level set function field;According to flow field information, calculate the force condition of object surface, calculate object translation vector and rotation vector;Complete data mapping of object surface grid to calculation grid, obtain the level set function field of calculation grid;According to the obtained calculation grid level set function field, divide cell type;Carry out geometric calculation to cut cell, based on cut cell flow field reconstruction strategy, complete fluid cell, cut cell estimated speed update;Solve pressure Poisson equation, obtain pressure field, pressure gradient, update velocity field according to the obtained pressure gradient, obtain the final velocity field satisfying continuity condition.The marine structure flow field simulation method of the application greatly improves the numerical simulation efficiency of complex structure flow field, and reduces the implementation difficulty.

The invention discloses a multi-agent natural language formation control method and system based on a large language model. The method comprises the steps of receiving a natural language instruction; calling a large language model to generate a target state sequence containing a space-time stamp; collision detection is carried out based on time sequence deduction and geometric calculation, and the minimum safety distance between the intelligent agents is verified; and after the verification is passed, synchronously issuing a control instruction in a direct connection or relay mode through radio frequency communication. The system comprises a ground station, a radio frequency communication module and a heterogeneous agent cluster. Microsecond-level synchronization precision, cross-platform compatibility and full-closed-loop AI planning are achieved, and the method is suitable for collaborative operation scenes of unmanned aerial vehicles, robots and the like.

This invention discloses an automated testing method, system, equipment, storage medium, and program product for microscopic imaging measurements. It addresses the problem of objective verification of measurement results through a log-driven automatic extraction and judgment mechanism; establishes a geometrically dependent linkage verification link to solve the correctness verification problem in dynamic linkage scenarios; uses the start timestamp of the test step as a filtering anchor point for pattern grouping and matching to solve the problem of accurate location of effective logs; and constructs a unified "log parsing—geometric calculation—threshold judgment" process to solve the integrated verification problem of multiple types of measurement scenarios, forming a traceable link of "operation action—log fragment—geometric reference value—judgment result," thus solving the problem of difficulty in tracing back the cause of failure.

The present application relates to the technical field of digital design of architectural decoration, and particularly relates to an intelligent generation method and system of a customized decoration scheme, comprising the following steps: obtaining decoration data and building a local coordinate system, generating a quantitative candidate starting point and an effective joint line, determining the starting point and outputting the customized decoration scheme according to the evaluation sorting of the stable blocking level and the exposed area. The present application controls the calculation scale by fixing the number of candidate starting points, and regards the joint line as an independent evaluation object. The process combines the stable blocking area accurately generated according to the floor type of furniture, and the exposed area generated based on the high-frequency line of sight such as the entrance and the window, and sorts the joint line jointly, so that it is hidden in the blocking area as much as possible and avoids the exposed area. In addition, the system uses the coordinate range overlap to trigger accurate intersection to reduce invalid geometric calculation, and realizes local update when the scene changes by binding multi-dimensional numbers to the joint line, thereby greatly improving the overall processing efficiency.

This invention provides a method, apparatus, and system for trusted mutual recognition of permissions between cross-domain intelligent agents, relating to the field of artificial intelligence security technology. The method includes: receiving a call request from a source domain intelligent agent to perform a corresponding operation on a target domain intelligent agent; based on the spatial relationship characteristics between the source domain permission space and the target domain permission space involved in the call request, obtaining a set of affine transformation parameters through a permission transformation model, and using cone volume measurement for evaluation and security verification to finally select affine transformation parameters suitable for permission credential mapping; and using the affine transformation parameters to map the original permission credential of the source domain intelligent agent from the source domain permission space to the target domain permission space, generating a mapped permission credential that can be recognized and verified by the target domain. This invention effectively solves the problem of trusted mutual recognition of permissions in cross-domain intelligent agent collaboration by geometricizing the permission space and utilizing affine transformation, spatial partitioning, and geometric calculation.

The invention relates to the technical field of BIM change identification, in particular to a design change identification tracking method and system based on BIM data association. The invention relates to the technical field of BIM design recognition, in particular to a design change recognition tracking method and system based on BIM data association. The method comprises the following steps: preprocessing an obtained BIM model and drawing data; carrying out change identification based on the preprocessed BIM model and drawing data; carrying out change classification and labeling based on an identification result; performing mode analysis on the change data by using a deep learning model; and predicting a high-frequency change risk based on a pattern analysis result. By unifying BIM attribute fields and a coordinate system, component geometry is compared by using an SHA-256 Hash algorithm, an attribute difference rate is calculated, and primitive-level automatic identification is realized.

The invention relates to a monomer building contour batch extraction method based on a live-action three-dimensional model, and the method can achieve the quick and batch extraction of building contours, and controls the contour extraction precision and the batch endowing height. Comprising the following steps: S1, based on a live-action three-dimensional model, cutting osgb data by adopting a facade cutting technology, and cutting off redundant models on the ground so as to obtain a building three-dimensional model; s2, performing orthographic grid image production on the cut osgb model data by using an orthographic output basic tool to obtain grid tif data; s3, vectorizing the background of the grid tif data by using a grid vectorization algorithm to obtain vector shapefile data; s4, performing reverse vector cutting on the shapefile to obtain high-precision vector building contour data; s5, using a geometric calculation tool to calculate and generate a contour center point; and S6, extracting three-dimensional building altitudes corresponding to the x-y longitude and latitude by using coordinate mapping of the central point in the three-dimensional model, and obtaining vector point data with the altitudes.

A computing system is provided that receives a molecular graph in a message-passing graph neural network (MPGNN) and generates a scalar embedding that represents the characteristics of the nodes and edges of the graph and a vector embedding that represents the geometric relationships of the graph. The system processes the scalar embedding through a vector-scalar interactive message-passing mechanism of a message-passing subblock of the MPGNN, generates scalar information from the scalar embedding, and passes it to an embedding space that includes the vector embedding. The system updates the vector embedding based on the scalar information and the embedding space that includes the vector embedding. The system updates the scalar embedding based on runtime geometry calculations of the geometric relationships encoded in the vector embedding. The system computes an updated molecular graph based on the updated scalar embedding and vector embedding, and outputs target molecular property values ​​based on the updated molecular graph.

Examples are disclosed that relate to computer-predicting behavior of foreign object debris (FOD) in a machine. In one example, a geometric computer model of the machine is recognized. FOD initial conditions within the geometric computer model of the machine are recognized. A movement schedule for the geometric computer model of the machine is recognized. A movement trajectory of a FOD from a starting position consistent with the FOD initial conditions throughout the geometric computer model of the machine is simulated based at least on the movement schedule for the geometric computer model of the machine. Simulation data detailing a likelihood that the FOD will come to rest at a location within the geometric computer model of the machine based on the simulated movement trajectory is output.

The invention discloses a structure deformation automatic monitoring system and method based on a GNSS three-dimensional displacement curve. The method comprises the following steps: acquiring three-dimensional coordinate initial data of key points from a GNSS receiver, performing quality screening and simple smoothing, unifying timestamps, and outputting an initial position sequence; on the basis of the initial position sequence, extracting relative motion and frequency spectrum features after linear interpolation, and splicing the relative motion and frequency spectrum features to obtain a monitoring point feature vector; establishing a joint model of a structure deformation state and a vibration state by combining the feature vectors of the monitoring points, and outputting an accurate deformation track and an accurate vibration state by the joint model after filtering; based on the accurate deformation track and the accurate vibration state, calculating a vibration health index to evaluate the health degree of the vibration level; based on the accurate deformation track and the accurate vibration state, geometric calculation is carried out on the key point coordinates, and an alarm state identifier is output; and inputting a graph neural network based on the accurate deformation track and the accurate vibration state to realize classification of the hinge region failure mode.