365 results about "Vector diagram" patented technology

The invention belongs to the technical field of engineering information intelligent processing, and relates to a highway bridge drawing multi-modal information extraction and semantic understanding method and system.The method comprises the steps that firstly, self-adaptive judgment is conducted on a vector drawing and a scanning drawing, geometric distortion correction, drawing frame and title bar positioning and layout segmentation are completed, and then the vector drawing and the scanning drawing are obtained; constructing a hierarchical document structure comprising texts, tables, images and two-dimensional drawing objects; then, a front-end target detection network and a rear-end cross-modal document understanding model are fused, and detection and relation reasoning of elements such as view blocks, labels, symbols and tables are achieved; and image-text feature alignment is further performed by using a visual coding network and a text coding network, structural description conforming to engineering semantics is generated by means of a multi-modal language model, an engineering parameter database is established, and parameter query and multi-modal question and answer output are supported. According to the method, the accuracy and efficiency of automatic acquisition and semantic understanding of the key information of the highway bridge drawing are improved.

The invention discloses a query condition analysis method and device and a medium, and the method comprises the steps: receiving a natural language query statement input by a user for a human resource management system, and extracting a core semantic unit in the natural language query statement; based on a preset knowledge base, mapping the core semantic unit into a semantic structure corresponding to an Elasticsearch database to generate a corresponding key vector diagram; based on a preset pseudo code normal form, generating a pseudo code according to the key vector diagram; wherein the pseudo code comprises a query node set and a logical relationship between query nodes; and performing code verification on the pseudo-code, and converting the pseudo-code into a DSL query statement in an Elasticsearch database under the condition that the pseudo-code passes the code verification, so as to realize semantic analysis on the natural language query statement through the DSL query statement.

The invention discloses an identification and verification method and system for a secondary drawing of a transformer substation, and belongs to the technical field of image identification, and the method specifically comprises the steps: analyzing a CAD vector diagram, obtaining four-corner references and pixel coordinates of a scanning graph, building initial mapping of pixels and engineering millimeter coordinates by taking an engineering millimeter coordinate system as a reference, and generating a unified intermediate representation model; constructing a terminal strip parameterization template based on the vector anchor point set and the visual anchor point set; a composite deformation field is calculated through vector-bitmap-vector closed-loop rendering calibration, terminal row alignment and terminal sequence binding are completed in the composite deformation field, and a terminal pixel position-terminal sequence-engineering millimeter coordinate consistent mapping table is formed; comparing the topological netlist to obtain an electrical node corresponding table; and performing source decomposition on the terminal position residual error based on the composite deformation field and generating a self-adaptive tolerance band, and finally executing wiring verification by taking the self-adaptive tolerance band, the electrical connectivity and the serial number consistency as criteria and outputting a verification report.

The invention provides a seawall terrain extraction method and system fusing a vehicle-mounted laser point cloud and an inclination model. The method comprises the following steps: forming a seawall range according to a seawall vector diagram and a satellite image; dividing a seawall range into a vehicle-mounted laser radar acquisition range and an unmanned aerial vehicle oblique photogrammetry range; acquiring a vehicle-mounted laser point cloud collected by a vehicle-mounted laser radar, and performing preprocessing and precision optimization on the vehicle-mounted laser point cloud; obtaining oblique photography image data collected by a five-splicing camera carried by the unmanned aerial vehicle, and generating an oblique photography model and an oblique three-dimensional model point cloud; extracting edge line elements and angular point feature points of a common overlapping area in the inclined three-dimensional model point cloud and the vehicle-mounted laser point cloud, and performing point cloud fusion based on the edge line elements and the angular point feature points; filtering the fused point cloud to screen seawall terrain point cloud data; according to seawall terrain point cloud data, resolution-adaptive digital elevation models are constructed for different areas of a seawall, and seawall structure features can be accurately represented.

The invention relates to the technical field of bridge monitoring, in particular to a bridge displacement monitoring method based on unmanned aerial vehicle visual identification, which comprises the following steps: S1, generating a flight path covering all key parts of a bridge, and collecting a bridge image by adopting an unmanned aerial vehicle according to the flight path; the method comprises the steps of S1, preprocessing a bridge image, S2, carrying out feature extraction after the bridge image is preprocessed, S3, carrying out matching on image feature points at different time points, and calculating the displacement of a bridge, S4, carrying out model optimization by adopting a convolutional neural network to optimize image features, and S5, carrying out hierarchical monitoring on displacement magnitude differences of different components of the bridge, and superposing a displacement calculation result on the bridge image in the form of a thermodynamic diagram or a vector diagram, and representing the displacement by using a color gradient. The method adopts the unmanned aerial vehicle visual identification technology, only needs the unmanned aerial vehicle and the camera, combines the image processing algorithm and the deep learning model to calculate the bridge displacement, is high in precision, is low in cost, and is suitable for various types of bridge structures.

The invention relates to the technical field of artificial intelligence and digital modeling, and particularly discloses an automatic equipment modeling method and equipment based on artificial intelligence, and the method comprises the steps: obtaining data to construct a multi-modal fusion data set; extracting target features and integrating the target features into a unified high-dimensional feature vector so as to generate a semantic feature map for modeling equipment; obtaining geometric modeling parameters and assembly constraint conditions of modeling equipment by using a parameter optimization model constructed based on a reinforcement learning framework; based on the fault data, optimization is carried out through a Markov decision principle to generate a preliminary 3D model; and performing key point detection and feature alignment on the planar projection of the model and the BIM drawing vector diagram through a hierarchical matching strategy, correcting model deviation based on vertex information to generate a 3D model, and generating a digital twin 3D model. Thus, by means of multi-source data collaborative acquisition and deep feature fusion, the precision, efficiency and adaptability of equipment modeling are remarkably improved in combination with dynamic optimization and a closed loop verification mechanism.

The described systems and methods are configured generate a 3D virtual representation of a physical scene at a location, and output isometric and / or orthographic vector drawings based on the 3D virtual representation. The vector drawings are generated by rendering views of the 3D virtual representation in a scalable vector graphics (SVG) format, so that the views can be zoomed without blurring or other decreases in image viewability. Further, sub-rooms, tags, labels, and / or dimensions may be added to the output. Rather than taking hours to generate drawings, the described systems and methods enable generation in a few milliseconds, among other advantages.

The invention relates to the field of homogenizer intelligence, and discloses a homogenizer intelligent pressure increasing and reducing control system based on servo synchronous transmission, which comprises the following steps: extracting the operation inertia difference of each plunger mechanism under a multi-pump parallel structure, generating a synchronous offset vector map, and calculating the pressure increasing and reducing of the homogenizer based on the synchronous offset vector map. Calling a slip registration algorithm and an inertia field decoupling network, extracting reconstructed plunger stroke and pressure response mapping data, constructing a three-dimensional flow-path-stress tensor model, judging whether fluctuation-wear coupling sensitive points exist or not, activating a frequency conversion regulation and control strategy set of a servo driving layer based on a disturbance window and the coupling sensitive points, and carrying out the control of the servo driving layer. And judging whether structural thermal drift feedback unbalance exists or not, dynamically adjusting servo redundancy and a buffer response strategy in combination with a preset life curve and an abnormal response backtracking channel, and outputting a synchronous regulation and control instruction set. The method has the advantage of improving the long-term operation reliability of the homogenizer.

The invention relates to the technical field of three-dimensional map recognition, and discloses a semantic segmentation-based low-altitude three-dimensional map element autonomous recognition method and system. The method comprises the following steps: acquiring a low-altitude remote sensing image and preprocessing to generate a multi-channel image matrix containing geographic coordinates and spectral characteristics; extracting multi-scale features through a pyramid feature extraction network in combination with cavity convolution, and obtaining an adaptive weighted feature tensor through a cascade attention mechanism fusion channel and a spatial weight; adopting a bidirectional feature fusion strategy to generate fusion features, and outputting an initial category probability distribution diagram by a semantic segmentation header network; obtaining a refined mask through edge perception optimization and superpixel segmentation correction, and mapping the refined mask to a three-dimensional coordinate system to generate a vector layer with a semantic tag; a constraint rule is deduced through a topological relation inference engine, logic conflicts are eliminated through rule-driven post-processing, finally, a standardized three-dimensional map element database meeting the geographic information standard is generated, and efficient, accurate and autonomous recognition of low-altitude three-dimensional map elements is achieved.

The invention discloses a multi-modal depth perception and adaptive segmentation full-spectrum primitive intelligent identification method, system and device for a primary main wiring diagram of a plant station, and a medium, and belongs to the technical field of intelligent identification of engineering drawings of power system plant stations, and the method comprises the steps: fusing the dual-source data of a vector diagram and a grating diagram, and constructing a standard primitive library; secondly, primitive detection is realized by adopting a recognition and segmentation collaborative multi-stage network, and the contour precision is improved through model distillation; secondly, iteratively optimizing the recognition capability of the model on the difficult sample by using an active learning mechanism; and finally, finishing primitive classification and result optimization in combination with deep metric learning and electrical topology constraints. According to the invention, through multi-modal data fusion and multi-scale feature adaptive fusion, the recognition capability of a small target and a fine primitive is improved; by means of a double-branch heterogeneous architecture and a structural distillation mechanism, pixel-level high-precision edge segmentation is realized, and the identification problem of dense adhesion primitives is effectively solved.

The invention provides a document image-text integrated intelligent understanding and processing method and system, and relates to the technical field of artificial intelligence. Comprising the following steps: separating image-text elements and establishing context association; calling a graph vectorization engine, and executing intelligent vector conversion processing on the rasterized illustration; performing hierarchical classification, attribute endowing and structured reconstruction on the vector primitives in combination with text semantic analysis to generate vector entity objects with complete attributes; the text elements and the vector entity objects are jointly input into a pre-trained multi-mode large language model, unified knowledge expression containing vectors, topology, attributes and document contexts is generated, and applications such as question answering, editing, abstracting and reporting of image-text integration are supported. According to the method, the problems of graph semantic loss, difficulty in fine analysis and the like caused by vector-to-grid illustration in papers, reports and other types of documents are solved, the overall understanding depth and interpretability of AI for complex image-text documents are remarkably improved, and high-performance semantic understanding capacity is provided for document-based training and intelligent processing.

The invention discloses a process manufacturing method of a cut image, which belongs to the technical field of laser cutting, and comprises the following steps of: acquiring a grid area covered by a cut graph of a material to be processed, dividing the cut graph into a plurality of vector diagrams according to the grid area, and performing slotting compensation processing on each vector diagram to obtain a corresponding cutting track; obtaining attribute information of the multiple primitives, determining a reference point of the vector diagram according to the attribute information of the primitives and the cutting trajectory, determining a light-off position on the primitives according to the reference point, the included angle and the vertex, and performing path optimization on the vector diagram according to the light-off position and the cutting trajectory to obtain a target cutting trajectory, the laser machining parameters of the cutting pattern are set based on the target cutting track and the to-be-machined material, hole blasting or hole punching caused by unstable laser of the cutting starting point can be prevented, it is guaranteed that the cutting effect of the to-be-cut material is optimal, the size precision meets the requirement, and the laser cutting efficiency is also improved.

The invention relates to the technical field of image data processing, and discloses an intelligent drawing auditing method and device based on a vector atlas and an active perception closed loop, and the method comprises the steps: obtaining a to-be-audited engineering drawing file and a compliance specification text; analyzing vector data of the engineering drawing file, and converting the vector data into an attribute graph used for representing a topological structure and semantics of the drawing; generating an audit instruction through a multi-modal large language model planner based on the attribute graph and the compliance specification text; executing the auditing instruction on the attribute graph through a graph signal processing verifier so as to carry out iterative compliance verification and diagnostic analysis on the attribute graph, and generating a corresponding compliance verification result and a diagnostic result; and generating a compliance audit report containing the traceable evidence based on the compliance verification result and the diagnosis result. According to the method, the accuracy and the reliability of the auditing result can be improved while automatic auditing of the engineering drawing is realized.

The invention provides a graph structure guided remote sensing image interpretation method and system, a terminal and a medium, and the method comprises the steps: carrying out the interpretation through employing a visual language model based on an obtained remote sensing image and expert priori knowledge; the model training process comprises the steps of obtaining a graph structure based on a vector graph corresponding to a remote sensing image, and rapidly synthesizing a large number of samples for training by randomly modifying the graph structure; model training is carried out based on the synthesized training remote sensing images and the corresponding training graph structures and training vector diagrams, graph structure features obtained by the training graph structures are adopted as training priori knowledge, a large number of image features obtained by the training remote sensing images are interpreted, and feedback optimization is carried out with the training vector diagrams as labels. The visual language model adopted by the invention can obtain the spatial information and semantic information of the remote sensing image, avoids inaccurate interpretation caused by spatial relationship deficiency, and has a better interpretation effect.

The invention discloses an SVG vector diagram-based primitive matching and intelligent recognition system and method, and relates to the technical field of computer graphic processing and mode recognition. The system stores a PDF file through SHA-256 Hash duplicate removal, format conversion is achieved through a tool, an 800DPI PNG image is generated, and the resolution is verified; the affine transformation matrix is analyzed, coordinate normalization and graphic element classification conversion are executed, and complex paths are split, deduplicated and merged; detecting a character area, and deleting corresponding character elements in the SVG; geometric features are extracted to construct a multi-dimensional index, and a template topological structure is analyzed; and selecting anchor points according to priorities, adapting to multiple rotation directions, matching non-anchor point elements through dynamic tolerance, verifying connection points in combination with adaptive topology tolerance, and finally outputting a matching result containing confidence. The system realizes efficient identification and accurate matching of technical drawings through standardization processing and an intelligent matching algorithm, and is suitable for scenes such as industrial drawing analysis and document digitization.

The invention relates to the field of phasing instruments, in particular to an airborne wireless phase checking and phasing instrument which comprises an unmanned aerial vehicle, a host and a detector (composed of an X detector and a Y detector), a 4.3-inch 65K-color LCD color screen is selected for the host, the phase, frequency, phase sequence, phase checking results and dynamic vector diagram indication can be displayed on the same screen, and a voice prompt module is arranged in the host. The device can be used inside or outside a transformer substation and is not affected by topographic conditions.

The invention relates to the technical field of mineralization analysis, in particular to a coverage area iron-rich ore information analysis method, device and equipment and a storage medium, and the method integrates multi-dimensional information such as gravity data, magnetic aviation delta T data, remote sensing images and geological data of a to-be-predicted area, and constructs a feature system capable of comprehensively reflecting mineralization conditions. The limitation of single data source analysis is broken through, a rich and accurate data basis is provided for intelligent division of the metallogenic target area, and the accuracy of metallogenic prediction is remarkably improved; furthermore, according to the method, a fracture speculation diagram, a regional magnetic anomaly plane diagram, a magnetic body three-dimensional probability model and a hydroxyl anomaly distribution vector diagram are adopted for collaborative analysis, so that a rich and accurate data basis is provided for intelligent division of a metallogenic target region, and the accuracy of metallogenic prediction is further improved; the recognition systematicness of the hidden ore body is obviously enhanced; compared with a traditional method depending on artificial experience, the method has the advantage that the objectivity of metallogenic prediction is effectively improved.

The invention provides a multi-dimensional data processing method and system, and belongs to the technical field of data processing, and the method comprises the steps: obtaining vector image data containing to-be-recognized data; analyzing a document structure of the vector image data, and extracting text elements and graphic elements according to grouping tags in a document; according to a preset recognition target object, the text elements are classified into title text elements and data text elements, and the recognition target object comprises at least one of a table title or a text title; according to the title text element, the data text element and the graphic element, identifying a row-column structure of the table data to construct structured data; and carrying out format conversion on the structured data and then storing the structured data. According to the method, the document structure of the vector image is analyzed, and the row-column logic structure of the table is reconstructed by utilizing the coordinate information and the spatial position relationship of the text elements and the graphic elements, so that the vector image data is efficiently and accurately processed.

The present disclosure performs image in-painting with controlled text generations to overcome the challenges persisting in traditional diffusion-based methods, especially when it comes to generating textual content within the image with complex font attributes. In the present disclosure, initially, an input image and a textual prompt and a plurality of control parameters are given as input to the present disclosure. Further, character mask and conditional mask are extracted based on the inputs. Finally accurate customized textual images are generated based on the character mask and the conditional mask using a textual image generating diffusion model. The textual image generating diffusion model generates an intermediate image based on the input image and the random gaussian noise. This intermediate image is iteratively refined to generate a latent vector image, and the accurate customized textual image is generated from the latent vector image using a trained customized character map-guided consistency model.

The invention relates to a method and device for automatically generating an equipment data report based on a drawing and a storage medium, and is applied to the technical field of equipment drawing recognition. Comparing the vector graphic data with preset graphic data to extract signal equipment information of the vector graphic data; obtaining geometric features and associated attribute texts in the signal equipment information, and generating structured equipment data; associating the structured equipment data with the station yard BIM model to realize binding of lightweight data with machine account information; obtaining a query condition input by a user, developing a natural language understanding engine based on the BERT model to perform joint indexing of time dimension and space dimension on the query condition input by the user, and obtaining target equipment; and matching the target equipment with a preset report template, and generating a multi-dimensional statistical report through the preset report template.

The invention relates to the technical field of precision manufacturing, in particular to a precision machining system based on a multi-blade hollow hole spinneret plate, which comprises a geometric constraint modeling module, an energy self-adaptive laser module, a shape real-time feedback module and a spinneret plate finished product output module, wherein the geometric constraint modeling module is used for generating a multi-stage constraint processing model; the energy self-adaptive laser module is used for etching a spinneret plate base material to form a multi-leaf hollow pore channel and outputting an initially-etched pore channel base body; the morphology real-time feedback module is used for generating a morphology error vector diagram and inputting the morphology error vector diagram into the spinneret plate finished product output module; and the spinneret plate finished product output module is used for performing matching judgment on the morphology error vector diagram and the multi-stage constraint processing model. According to the method, through combination of multistage geometric constraint modeling and laser energy self-adaptive control, precise etching and closed-loop correction of the complex structure of the multi-blade hollow-hole spinneret plate are achieved, and the structural consistency and machining stability of a finished product are improved.

This invention provides an intelligent document generation system and its control method, characterized in that: the system includes: a dynamic template engine module; an intelligent content generation module; an adaptive format optimization module; and an automatic detection module; the dynamic template engine module determines logical branches through XML tags in a dynamic template language, which can overcome the limitations of traditional placeholder replacement, decouple document structure and data, and adapt different logical branches according to different data, effectively improving the adaptability of data dimensions; the intelligent content generation module can combine a pre-trained model to generate coherent natural language text descriptions, and dynamically render charts on this basis, embedding icons into the text in the form of vector graphics, realizing the collaborative generation of text and charts, and reducing the cost of manual writing, drawing and typesetting by collaboratively generating text and charts that conform to the context.

The invention provides a quantitative analysis method and system for an in-situ leaching uranium mining flow field. According to the method, the historical flow and pressure time sequence data of the liquid injection pipeline are collected, the flow pressure matrix reflecting the working state of the liquid injection pump is constructed, and the resonance frequency band energy characteristics are extracted to generate the pump health assessment map. Fluid scattering signals are synchronously collected and converted into a three-dimensional flow velocity vector diagram, fluid acoustic impedance parameters are calculated in combination with the flow velocity modulus and the direction change rate, and a flow field turbulence thermodynamic diagram is generated. And further dynamically matching the pump health assessment map with the turbulence thermodynamic diagram, calculating a flow field stability index, and generating a liquid injection pump adjusting instruction and a fault early warning report according to a preset risk threshold value and a deviation degree. And through multi-source data fusion and dynamic correlation analysis, real-time monitoring and active regulation and control on the stability of the in-situ leaching uranium mining flow field and the health state of the liquid injection pump are realized. According to the technical scheme, the efficiency and precision of quantitative analysis of the flow field can be improved.

The invention relates to an irrigation area canal system logic generalization graph generation method based on multi-source data fusion. The method comprises the steps of obtaining multi-source related data of an irrigation area, and performing preprocessing to obtain holographic data of the irrigation area; performing feature extraction according to the holographic data of the irrigation area, and determining a channel system contour line layer, a running water path layer and a continuous attribute layer; matching the channel system contour line graph layer with the running water path graph layer, comparing with the existing channel system vector graph layer, and screening to obtain a channel; generating an irrigation area topological graph based on the channel extraction nodes and the connection relationship in combination with control facility information; and according to a preset drawing rule, generating an irrigation area canal system logic generalization graph according to the irrigation area topological graph. By adopting the method, the remote sensing image, the three-dimensional point cloud, the vector layer and the sensor data can be utilized to construct a feature layer fusion mechanism and a topology identification mechanism under a unified geographic reference system so as to improve the accuracy of channel line extraction and the automation degree of channel system logic modeling.

The invention provides a method, a device and equipment for identifying total description specifications of multi-modal CAD drawings. The method comprises the steps that a to-be-recognized CAD drawing is received, and the CAD drawing comprises a to-be-recognized description specification belonging to a target specification; identifying a text describing the target specification in the CAD drawing to obtain first text information; obtaining a table name and a vector diagram name cited in the text for describing the target specification; extracting a table and a vector diagram from the CAD drawing according to the table name and the vector diagram name; recognizing texts in the table and the vector diagram to obtain second text information; and obtaining structured specification data corresponding to the description specification to be identified according to the first text information and the second text information. By means of the method and device, the multi-mode CAD drawing general description specification can be better recognized so as to adapt to diversified specification expression modes.

The invention relates to the technical field of three-dimensional scene reconstruction, and discloses a real-time three-dimensional rendering method and device based on reflection perception and a medium, and the method comprises the steps: recovering a point cloud from an input image, and defining each point as a three-dimensional Gaussian primitive; generating a rendering normal vector diagram and a reflection intensity diagram; extracting a depth map from the input image, and calculating a standard normal vector diagram based on the depth map; generating a mask based on the reflected intensity map to identify a highlight area; calculating the specular reflection color of each pixel based on the rendering normal vector diagram and the ambient light map; performing weighted fusion on the diffuse reflection color and the specular reflection color of each pixel, and outputting a final pixel color; and constructing a joint loss function, performing optimization training on the model by using a gradient descent algorithm, and finally realizing high-quality and real-time three-dimensional scene reconstruction. According to the invention, by introducing a reflection modeling and normal supervision mechanism, the rendering robustness and generalization ability of the system in a complex illumination and reflection environment are effectively improved.

A method, apparatus, non-transitory computer readable medium, and system for modulating the level of fidelity to an input image include obtaining an input image and a fidelity parameter. The input image depicts an entity, and the fidelity parameter indicates a level of fidelity, i.e., faithfulness, to the input image. Embodiments then add noise to the input image based on the fidelity parameter to obtain an intermediate noise image. Subsequently, embodiments generate a synthetic image based on the intermediate noise image using an image generation model. The synthetic image includes a vectorizable depiction of the entity and has the level of fidelity to the input image indicated by the fidelity parameter. The vectorizable depiction is more suitable for conversion to vector format, as the resulting vector image will have a reduced number of paths and shapes.

The invention provides a CAD drawing power grid equipment modeling element extraction and matching method and device. According to the CAD drawing power grid equipment modeling element extraction and matching method and device provided by the embodiment of the invention, cross-modal accurate matching of power grid equipment primitives and text parameters in a non-vector CAD drawing can be effectively realized, the integrity and accuracy of modeling element extraction are remarkably improved, and intelligent design, operation and maintenance of a power system are supported.

The present disclosure provides methods and apparatuses for writing and searching vector data in a vector database. An example method includes receiving a write request for writing target vector data into a vector database, adding index update information corresponding to the target vector data to a first index of the vector database in a memory table, where the first index is a memory-based real-time read-write vector graph index, in response to flushing the memory table to a disk, writing the index update information of the first index in the memory table into a distributed file system, and converting the first index in the distributed file system into a second index, where the second index is a disk-based vector graph index.

The embodiment of the invention provides a method and system for surveying and mapping the area of a peripheral area along a railway based on an unmanned aerial vehicle, and belongs to the technical field of area surveying and mapping. The method comprises the following steps: performing coordinate registration processing on laser point cloud data collected by an unmanned aerial vehicle and a railway red line vector diagram to obtain standard point cloud data and a red line reference boundary under a unified coordinate system; based on the standard point cloud data and the red line reference boundary, an edge point set of an actual occupied area outside the red line is extracted, and a closed boundary contour is obtained through fitting; based on the boundary contour obtained through fitting, unified plane projection and subdivision processing is executed, and a two-dimensional measurement grid used for area determination is generated; and based on the two-dimensional measurement grid, accumulating the area of each unit, and summarizing and outputting the total area and corresponding boundary coordinates of the red line external expansion region. According to the scheme, high-precision and full-process area surveying and mapping of the non-standard occupied area along the railway are realized, and the objectivity of boundary judgment and the stability of an area extraction result are improved.