58 results about "Boundary representation" patented technology

The invention relates to a medical image segmentation method and system based on residual Mama and multi-scale boundary enhancement. The method comprises the following steps: acquiring and preprocessing a medical image; inputting the image into a segmentation model based on an encoder-decoder architecture; the encoder synchronously extracts local texture features and models long-range spatial dependence through residual error convolution blocks and residual error Mama blocks which are alternately connected; fusing and enhancing the jump connection features between the encoder and the decoder through a boundary enhancement module to optimize boundary characterization; integrating a multi-scale gating attention module in a decoding path, and adaptively selecting and fusing multi-scale context features; and finally outputting the high-precision segmentation mask. The method effectively solves the problems that in the prior art, long-range dependence and local details are difficult to consider, the multi-scale feature fusion capability is insufficient, boundary segmentation is fuzzy and the like, and the segmentation accuracy, the boundary continuity and the clinical practicability are remarkably improved.

The invention discloses a three-dimensional physical field real-time prediction method and system based on geometric deep learning and physical constraint, and relates to the technical field of computer-aided engineering and artificial intelligence. The method comprises the following steps: directly extracting native boundary representation data (B-Rep) of a three-dimensional model from a computer aided design system; constructing a heterogeneous dual graph taking a parameterized curved surface as a graph node, skipping finite element grid division, and aggregating local and global topological features by using a graph neural network; in combination with a physical information driving mechanism, a partial differential equation (PDE) residual error is introduced as a loss function for constraint training, and generalization prediction of a novel geometric structure is realized; and finally, the physical field state quantity is predicted through direct regression and is rendered in real time. An incremental reasoning mechanism based on a local topology subgraph is adopted, millisecond-level physical field real-time feedback under design modification is achieved, and the method is suitable for scheme rapid screening and trend prediction in the initial stage of design.

The invention relates to the technical field of computer graphics, and provides a model data adaptation processing method for a graphics rendering engine, which comprises the following steps of: importing and analyzing model files from different geometric modeling engines, and extracting original geometric data, original topological data and auxiliary information in the model files; converting the original geometric data into a unified standard geometric data structure for representation and storage; converting the original topological data into a standard topological data structure based on a boundary representation method for representation and storage; creating, analyzing or setting spatial position and direction information of the model entity and the virtual camera in a world coordinate system; analyzing material attributes, surface textures and animation information in the affiliated information of the model file, and packaging the materials, the surface textures and the animation information into corresponding standard data structures; and combining the standardized geometric data, topological data, coordinate system information and affiliated information into a complete standardized model data packet which can be directly used by a graphic rendering engine.

The invention discloses a geometric topology fusion-based part assembly method, which comprises the following steps of: acquiring boundary representation models of at least two to-be-assembled CAD parts, and converting the boundary representation model of each CAD part into a structured heterogeneous geometric topology graph; performing feature coding on each node in the heterogeneous geometric topological graph to form node feature representation; inputting the node feature representation into a graph attention reasoning module, and obtaining a node embedding representation representing a geometrical relationship and a topological relationship in the CAD part through multi-layer residual graph structure information propagation and feature aggregation; based on the node embedding representations of the different parts, calculating association scores of node pairs among the different parts; and performing supervised training on the feature coding module and the graph attention reasoning module by using the labeled assembly constraint sample data. According to the method, fine geometric features can be extracted from a boundary representation B-Rep model, and a complex topological dependency relationship is inferred, so that robust assembly constraint inference is realized.

The invention provides a MaskRcnn-based tumor detection method and system, and the method comprises the steps: inputting medical image data into a MaskRcnn network integrated with an edge perception module, generating an edge response graph through a Sobel operator, and enabling the edge response graph to serve as an additional channel injection feature graph, and enhancing the boundary representation; fusing multi-scale features through a feature pyramid network FPN, extracting candidate tumor area features through RoI Align, introducing non-local attention modeling global dependence in the area, extracting directional entropy, texture energy, uniformity and contrast in combination with a gray level co-occurrence matrix GLCM, and splicing to generate structure sensing features; performing classification, bounding box regression and mask segmentation based on the structure perception features, and constructing a joint loss function including classification, regression, mask cross entropy, edge alignment and structure consistency; the positioning capability of the model on the fuzzy tumor contour is effectively improved, the boundary positioning error is remarkably optimized, and the defect that over-segmentation or missing detection is likely to occur in a traditional model is overcome.

The application discloses a point cloud analysis and reconstruction method and system based on a cloud CAD platform, belongs to the technical field of point cloud reconstruction, and is used for solving the technical problems that the existing point cloud data reconstruction mode depends on manual operation, is low in efficiency, poor in precision and consistency, and difficult to adapt to complex scenes and automation requirements. The method comprises the following steps: receiving a point cloud data file and determining a processing mode; determining a corresponding irregular sampling region according to the processing mode, and performing signed distance field prediction on the point cloud data file in the irregular sampling region to obtain unsigned distance field and gradient information; generating a sliding window, identifying local boundary information in the sliding window through a boundary prediction neural network, and performing splicing to obtain global boundary information; dividing a face region of the point cloud data file according to the global boundary information to obtain different types of faces; performing targeted fitting processing on each type of face, and solving a boundary representation relationship between the faces to reconstruct a CAD model.

The application discloses a method for intelligent component identification and segmentation of an aircraft CAD model based on three-mode fusion, comprising: obtaining an aircraft CAD model with a boundary representation structure; constructing a multi-modal training data set that fuses surface images, geometric parameters and component semantic labels; training a multi-modal identification model; using the model for preliminary identification; for low confidence or small area surfaces, starting a geometric rule auxiliary module based on geometric topology and parameterization rules for semantic completion and correction to form a final segmentation result; automatically extracting key geometric feature lines; and converting and outputting into a structured engineering semantic format that can be used by grid generation software. The application realizes full automation of component identification, solves the problems of low efficiency and consistency caused by manual dependence, improves the identification integrity and engineering practicability of complex geometry, and the output result can directly drive subsequent grid generation, thereby significantly improving the automation level of the digital simulation pre-processing process.

The application relates to the technical field of computer-aided engineering and computer-aided design data integration, and discloses a Catia data conversion method and system for CAE preprocessing modeling software, which comprises the following steps: loading a Catia model and traversing a product structure tree to extract parameterized semantic information; converting geometric data into a boundary representation format and detecting defects; automatically repairing serious topological defects by using a deep learning model; constructing a hierarchical intermediate format based on a general digital thread protocol, and associating geometry, semantics and analysis attributes; dynamically adjusting model precision according to simulation types; and exporting a format suitable for CAE software and generating a parameter mapping table. The application can realize lossless conversion of a Catia model to a CAE environment, retain design semantics and parameter association, support precision self-adaptive adjustment of multi-physical field analysis, and significantly improve CAE preprocessing efficiency.

The application provides a symmetric workpiece disorderly grabbing method and system based on hierarchical reasoning, relates to the technical field of industrial robots, and comprises the following steps: acquiring a multi-modal image of a stacking scene, and reconstructing a complete physical mask representation of each workpiece from the multi-modal image. Through multi-modal perception fusion and full-view geometric reconstruction processing, the application obtains complete physical boundary representation and unbalanced load feature data of each workpiece in a shielding state, and on this basis, a directed hierarchical topological model describing the physical pressing and stacking relationship between workpieces is constructed through spatial gradient analysis, a candidate workpiece in an absolute top layer in the current scene is screened out, and then, a grabbability quantitative evaluation is performed to determine a target to be grabbed, so that the robot can identify and eliminate the bottom shielding workpiece which is easy to cause the collapse of the material pile in advance based on the real physical support relationship before action execution, and interference and instability caused by blind grabbing are avoided from the root.

The invention relates to the technical field of computer-aided engineering and computer-aided design data integration, and discloses a Catia data conversion method and system for CAE pretreatment modeling software, and the method comprises the steps: loading a Catia model, and traversing a product structure tree to extract parameterized semantic information; converting the geometric data into a boundary representation format and detecting defects; a deep learning model is used for automatically repairing serious topology defects; constructing a hierarchical intermediate format based on a general digital thread protocol, and associating geometric, semantic and analysis attributes; dynamically adjusting the model precision according to the simulation type; and exporting a format adaptive to the CAE software and generating a parameter mapping table. According to the method, lossless conversion from the Catia model to the CAE environment can be realized, design semantics and parameter association are reserved, precision self-adaptive adjustment of multi-physics field analysis is supported, and the CAE pretreatment efficiency is remarkably improved.

The application discloses a high-dimensional data computing architecture, method, system and device based on recursive projection compression and closed audit. After the method obtains high-dimensional input data, at least one recursive projection compression is performed to form an intermediate audit state representation and / or a decision state representation; a state space deviation function and a state evolution trend prediction operator are calculated on the state representation; dimension hedging processing is performed between different recursive levels, different projection dimensions, different loop representations or different boundary representations, and combined with boundary legality audit, resource closed audit, capacity constraint audit, loop consistency audit, platform flatness audit and stability window audit, a control amount, a compensation amount, a reconstruction amount or a branch adjustment amount is generated; a deterministic early termination is triggered through consistency comparison of parallel audit loops, and in the preferred embodiment, the integrity of the compression result is verified through reverse checking. The application is suitable for industrial monitoring, omics data analysis and other high-dimensional complex system state audit scenarios.

The application belongs to the technical field of artificial intelligence and digital image processing, and discloses an extensible farmland boundary regularization simplification method, system, device and terminal, determines a farmland category list to be segmented; uses an existing labeled training segmentation model to obtain segmentation masks of all farmlands; performs binaryzation processing on the segmentation masks to obtain binaryzation images; performs digital image processing on the binaryzation images to extract the contours of each connected domain; uses the contour information obtained through image processing to perform polygon approximation and remove redundant points to obtain farmland boundary representation. The processing method for extracting local farmland regular boundary uses the farmland segmentation result obtained through deep learning segmentation, uses a traditional image processing method and is supplemented with a polygon approximation algorithm to perform regularization processing on the result, and simultaneously simplifies the contour points of the farmland, so that the number of farmland boundary points and boundary description accuracy can be better balanced while reducing labor cost.

The invention belongs to the field of boundary representation model transition feature simplification, and relates to a B-Rep model simplification method based on a fillet feature network. According to the method, based on the fillet radius of the fillet feature, accurate construction and reasonable classification of the fillet feature network are realized by combining the concavity and convexity of the fillet feature and whether the fillet feature is degraded or not, and the fillet feature network comprises equal-radius and non-equal-radius fillet feature networks. The equal-radius fillet feature network represents fillet surfaces possibly created in the same rounding operation, the variable-radius fillet feature network is an adjacent complex fillet surface set and can be inhibited through extension intersection of supporting surfaces, and the remaining fillet surfaces are inhibited through additional Boolean union and Boolean subtraction operations. And finally, high-precision identification and robust suppression of the fillet features are realized. According to the method, the problem that the design is limited due to insufficient generalization ability and robustness of fillet feature identification on a multi-scale heterogeneous model during the optimization design of the physical field characteristics of the existing product is solved.

This invention discloses a method and system for constructing a data model for a business intelligence agent based on deep learning, relating to the field of deep learning technology. Through continuous processing from steps S1 to S4, the business intelligence agent no longer trains its model solely based on the final adopted decision results. Instead, it incorporates candidate information explicitly rejected during historical decision-making processes into the modeling scope. It retains excluded candidate decisions by constructing a set of rejected information (Una), and transforms the original rejected information into computable multi-dimensional structured data by generating a set of rejected features (Ufc). Then, based on the density of rejected information (Ind), it characterizes the concentration of rejection behavior at different decision stages, forming a rejected boundary representation (Nbd) which is applied to the business intelligence agent. When generating new candidate decisions, it can proactively identify and avoid historically high rejection density regions. Compared to existing methods that rely solely on input and output results for training, this approach overcomes the problem of insufficient learning of decision boundaries.

The invention discloses a lightweight conversion method and system for a CAD (computer-aided design) model. According to the method, a standard STEP format model is converted into a lightweight PBZ format through a multi-stage conversion architecture, and the method comprises the following steps: analyzing a STEP file to extract boundary representation geometry, a topological structure and product assembly data, discretizing an NURBS curved surface into a triangular mesh according to configurable precision, and meanwhile, nondestructively retaining parameterized sideline geometric definition; organizing the extracted data into a structured JSON (JavaScript Object Notation) intermediate representation; carrying out serialization by utilizing an optimized protobuf message structure, applying differential coding to vertex data, and applying triangular stripe coding to a patch index; and finally, based on the file size and the application scene precision requirement, adaptively selecting a GZIP compression level to carry out compression packaging. According to the method, the submicron geometric accuracy is kept, meanwhile, the high compression rate is achieved, the network transmission and mobile terminal rendering efficiency is remarkably improved, and the method is suitable for industrial scenes such as online collaborative design, digital twinning and mobile terminal detection.

The present disclosure provides a system (100) and a method (200) for generating routes for flexible components that connect principal components in a predefined environment. The method (200) comprises converting (202) a boundary representation of the principal components into a geometric representation and defining (204) an enclosed space around the principal components based on user-defined parameters. The method (200) comprises discretizing (206) the enclosed space into a plurality of nodes, assigning (208) one or more parameters to a node to construct a spatial structure within the enclosed space, and identifying (210) neighboring nodes among the plurality of nodes connected to the enclosed space within the spatial structure in order to generate one or more connectors to the one or more neighboring nodes.Furthermore, the procedure (200) includes determining (212) a shortest path by identifying start and end points for each connector and generating (214) routes for the flexible component that connects the main components.

The invention relates to an annotation method for annotating a training data set (LD) for training an environment recognition system (3).The training dataset (LD) comprises environment perception data (4), which is a sensory representation of a vehicle environment containing at least one physical linear road surface boundary (Lim), and an ordered data structure for the computer-readable representation of a physical linear road surface boundary (Lim) in the environment of a vehicle as a virtual linear road surface boundary (10), wherein the ordered data structure (1) defines at least one line object with a list of support points (P1, P2, P3), wherein the line object is assigned a semantic line property (5) that identifies the line object as a whole as a virtual linear road surface boundary, and wherein at least one of the support points (P1, P2, P3) can be assigned a separate semantic point property (A, B, C) by the annotation procedure. The annotation procedure comprises the steps: a.a. Displaying a file of the environment capture data (4) in a visually recognizable representation on a display means (11), in particular on a monitor (11); b. Displaying the at least one line object with the list of vertices (P1, P2, P3), wherein the vertices P1, P2, P3 of the list of vertices (P1, P2, P3) are displayed in a visually recognizable representation overlaid on the environment capture file (4) on the display means (11); c. Capturing a selection of a first vertex P1 from the list of vertices (P1, P2, P3), wherein the first selected vertex P1 is selected with an area segment selection means (12), in particular with a cursor (12), on the display means (11); d. Capturing an assignment of a separate semantic point property (A, B, C) to the first selected vertex P1.

This invention provides a computer implementation method, system, and program for machine learning to assemble mechanical parts based on mating scores and mating axes. [Solution] The method includes the step of providing a dataset of pairs of B-Reps, each containing at least one boundary representation (B-Rep) representing an assembly of mechanical parts. The pairs are labeled with mating compatibility data and, if the B-Reps of the pair are compatible according to the mating compatibility data, with mating axis compatibility data. The method also includes the step of training a neural network on the dataset. The neural network outputs mating scores for pairs of single embeddings, where each single embedding represents a B-Rep, and mating scores representing a score of mating compatibility between the mechanical parts represented by the pair, and data defining the mating axis if the B-Reps are compatible according to the mating score.

The invention relates to a kidney tumor image segmentation method and system based on multi-scale feature extraction, and the method comprises the steps: extracting the multi-scale features of a kidney tumor image to be processed, dividing feature similarity groups, carrying out the optimization through combining the texture and shape, and obtaining similar feature groups; generating a complementary information flow, adaptively enhancing an interaction weight between groups by using an attention mechanism, and obtaining an enhanced complementary feature representation; evaluating and denoising noise, establishing association mapping among groups based on features after denoising, and performing multi-scale feature fusion and boundary refining by adopting a U-Net network to obtain tumor boundary representation; and the boundary fuzzy degree is evaluated, iterative optimization is carried out by adopting a graph convolutional network, optimized collaborative hierarchical representation is obtained, and finally a high-precision kidney tumor segmentation result and a pixel-level contour are output. According to the method, through multi-scale feature cooperation, attention interaction and boundary optimization, the problems of boundary blur and noise sensitivity in kidney tumor segmentation are effectively solved, and the accuracy and robustness of segmentation are remarkably improved.

The present application particularly relates to a computer-implemented method of machine learning for assembling mechanical parts based on fit scores and fit axes. The method comprises providing a dataset of B-Rep pairs, each pair comprising at least one B-Rep representing an assembly of the mechanical part, which is labeled with mating compatibility data, and if the B-Rep in the pair of boundary representations is compatible according to the mating compatibility data, labeled with mating axis compatibility data. The method further includes training a neural network based on the data set, the neural network configured to take a pair of B-Rps pairs as inputs. The neural network also outputs a fit score for a pair of single embedded vectors, each single embedded vector representing one B-Rep, the fit score representing a score of fit compatibility between the mechanical parts represented by the pair of B-Rps, and outputs data defining a fit axis if the B-Rps are compatible according to the fit score.

The invention is suitable for the technical field of part labeling, and provides an automatic part labeling method which comprises the following steps: analyzing an stp file through Open CASCADE, and extracting B-rep boundary representation; constructing a graph structure: regarding the surface of the part as a node of the graph, extracting the type, direction, area and other business information of the surface as node features, regarding the edge of the part as the edge of the graph, extracting the type of the edge of the part and an included angle between two connecting surfaces of the edge as edge features, and performing normalization processing; according to the automatic part labeling method, the corresponding labels are established between the faces with the reserved relation, the attention mechanism is introduced, the compactness between the faces is automatically judged, the labeling efficiency is improved, the labeling cost is reduced, for different labeling styles of different scenes, good robustness and expansibility are achieved, the algorithm design is simple, the calculation overhead is small, and the method is suitable for popularization and application. And integration into a lightweight CAD plug-in or script system is facilitated.

The application discloses a kind of three-dimensional boundary representation model blanking line generation method and system and electronic equipment, its characteristics are that the method obtains three-dimensional boundary representation model and viewpoint parameter, and the entity in model is discretized into surface grid unit;Surface grid is classified based on the direction of viewpoint, and forward surface is screened out towards the viewpoint;The projection transformation of edge in model is carried out, and the visibility interval of edge is determined by the projection coverage detection of forward surface to edge, and blanking line segment is generated after interval merging and post-processing;System includes: parameter configuration module, entity gridding module, face orientation classification module, occlusion detection module, interval merging module, line segment generation module and output management module.Compared with prior art, the application has the advantages that blanking line segment conforming to engineering drawing specification can be generated from three-dimensional CAD model, the problems of high coupling degree of blanking calculation and low efficiency of occlusion detection are solved, and the application is suitable for three-dimensional computer-aided design, engineering drawing and three-dimensional visualization interaction scenes.

This application provides a complex structure modeling system and method based on 3D surface skeleton extraction. The system acquires initial 3D point cloud data of pipelines and converts it into a 3D voxel mesh. A symbolic distance field is generated based on the pipeline voxel mesh. Local extremum traversal is performed on the symbolic distance field to obtain a discrete skeleton candidate point set. Topological homology extraction is performed based on the discrete skeleton candidate point set to generate an initial pipeline topological skeleton. Semantic topological classification is performed using the pipeline voxel mesh and the initial pipeline topological skeleton to obtain structural attribute labels for each skeleton segment. Local topological optimization is performed on the initial pipeline topological skeleton based on the structural attribute labels of all skeleton segments to obtain an optimized pipeline topological skeleton. A parameterized boundary representation model of the complex pipeline network structure is generated using the optimized pipeline topological skeleton. The technical solution provided in this application can effectively construct the topological skeleton of complex pipeline network structures, thereby improving the modeling accuracy of parametric modeling.

The invention relates to a Revit-based project and family information extraction and export method, which relates to the technical field of constructional engineering information, receives input through a user interface, actively filters invalid information, respectively processes basic geometries, built-in family elements and family instances according to element types, and records an element list. The method comprises the following steps: collecting element attributes, converting the element attributes into a target platform readable format, storing the element attributes into an attribute set, binding element IDs, processing Boolean operation, separating solid and hollow bodies, performing union set and difference set operation, recording results, and processing various geometric elements by adopting a feature reconstruction method or a B-rep boundary representation method according to the support condition of a target platform. And exporting the processed data to a target exchange format in batches, and supporting integrity, accuracy and efficiency verification on an exported result. According to the method, the problems of data loss, file redundancy and low efficiency in the existing conversion technology are effectively solved, and the cross-platform multiplexing capability of BIM data is remarkably improved.

Provided is technology for enabling a three-dimensional model search that can be processed at high speed even when the amount of data increases.　This three-dimensional model search device comprises: a search query accepting unit that accepts a search query indicated by a three-dimensional shape including a boundary representation; an overall shape embedding unit that calculates an overall vector targeting the entire three-dimensional shape of the search query; a partial shape embedding unit that calculates partial vectors targeting partial shapes that are units of solids, surfaces, and edges of the boundary representation; and a search unit that employs a vector search using the overall vector and the partial vectors to search for components having a similar shape, as similar components, from predetermined component information.

This application relates to a map construction method. Addressing the technical problem that existing environmental occupancy map construction methods, while aiming to improve query and update efficiency and significantly reduce memory usage, struggle to support real-time, large-scale autonomous navigation tasks in dynamic environments, this application provides a boundary representation-based map construction method and related apparatus. The map employs a global-local map framework. The local map includes the occupancy status of surrounding voxels centered on the robot, while the global map includes the voxel occupancy status in the boundary graph. The voxel occupancy status in the boundary graph is determined by using adjacent voxel pairs to represent the boundary surface layer separating free voxels from adjacent voxels, thus obtaining boundary voxels and constructing the boundary graph. A data structure combining two-dimensional hashing and one-dimensional arrays is used to manage the boundary voxels. Under this data structure, the occupancy status of any voxel is determined through the boundary graph. This application effectively improves query and update efficiency and significantly reduces memory usage.

The invention discloses a building model family parameter generation method and system based on AI driving. The method comprises the steps that a building design gene pool driving platform is called to extract and screen building model family calibration parameters; inputting the calibration parameters into a building boundary to represent a structured potential geometric tree diffusion model to generate a geometric feature parameter subset; generating a verification hybrid algorithm verification parameter through a building specification embedded parameter, and marking a parameter which does not accord with the rule; the mark parameters are adjusted and corrected in combination with historical data; integrating the parameters, and performing secondary diffusion through a diffusion model to generate an intermediate parameter set; and mapping the intermediate parameter as a building model family target parameter. The system comprises six units which are sequentially connected and cooperatively work. According to the method and the system, historical design data can be fully utilized, deep fusion of specification and parameter generation is realized, the geometric relevance of parameters is enhanced, the problems of low efficiency and lagging of specification verification in the prior art are solved, and the efficiency and the accuracy of parameter generation are improved.

The invention provides a cross-platform conversion method, device and equipment for a general information model of a power grid. The method comprises the following steps: acquiring power equipment model data; performing boundary data extraction on the power equipment model data to obtain initial boundary representation data; carrying out lossless conversion on bottom-layer geometric data in the initial boundary representation data to obtain middle boundary representation data; analyzing design features in the intermediate boundary representation data to obtain first intermediate data; performing integrity check and lightweight processing on the first intermediate data to obtain second intermediate data; performing type identification on the second intermediate data to obtain third intermediate data; according to a preset mapping rule, performing attribute matching on the third intermediate data to obtain fourth intermediate data; and performing quality verification and fault-tolerant repair on the fourth intermediate data to obtain power grid general information model data. According to the method, the efficiency, precision and semantic fidelity of cross-platform conversion of the general information model of the power grid can be improved.

Embodiments of the present application provide a method for finding similar parts. The method comprises: obtaining a boundary representation (B-rep) model of a reference part; calculating a part digital signature (PDS) of the reference part based on the B-rep model; and selecting a list of similar parts from a multi-part database according to a PDS of each part in the multi-part database and the PDS of the reference part, wherein the list of similar parts is similar to the reference part. The developed method provides a general method to search for similar parts of any complexity.

The application relates to the technical field of substation operation management, and particularly discloses a substation operation monitoring and early warning system based on 3D Gaussian splashing and Beidou RTK, which comprises a coordinate and model construction module, a dangerous boundary representation generation module and a two-stage alarm triggering module, wherein the coordinate and model construction module is used for constructing a human tool envelope and generating a 3D Gaussian splashing scene model; the dangerous boundary representation generation module generates a dangerous boundary representation in the 3D Gaussian splashing scene model from a set of operation steps, so that the dangerous boundary can be synchronously updated with the changes of the operation steps and the effectiveness of safety measures, and the consistency of risk constraints and field states is improved; the two-stage alarm triggering module calculates the minimum clear distance of the dangerous boundary representation and the human tool envelope to form an alarm constraint set, and triggers a reminding stage alarm or a dangerous stage alarm according to the alarm constraint set, so that the hierarchical prompt for approaching risks is realized, and the explainability and executability of alarm triggering are enhanced.