139 results about "Blueprint" patented technology

The invention relates to the technical field of laser cutting control, in particular to a laser cutting control system and method for a lens assembly. The method comprises the following steps that a lens assembly is scanned in an omnibearing mode to obtain point cloud data, then abnormal points are removed, three-dimensional reconstruction is carried out, a lens assembly model is generated, cutting task data are obtained, a cutting target is recognized, optimal cutting space-time arrangement is carried out on the lens assembly model on the basis, and an optimized cutting blueprint is generated. Cutting path planning is conducted according to the optimal blueprint, candidate cutting paths are obtained and dynamically compensated, a compensation cutting path is formed, mapping of control parameters is conducted according to the compensation cutting path, change control parameters are obtained, then parameter replacement is conducted, and accurate intelligent laser cutting control is achieved. The laser cutting control method for the lens assembly is more accurate and more efficient.

The invention discloses an image reconstruction method based on a multi-window cross feature fusion attention mechanism. According to the method, the resolution of an original image is reduced through bicubic interpolation to obtain model training data, and the original image is used as a sample label. For training data, shallow layer features are extracted through blueprint separable convolution; and improving an efficient separable distillation module to obtain a plurality of attention fusion distillation modules, and extracting deep features. A feature fusion module based on multi-window cross attention is used to carry out operations such as multiple times of segmentation, attention calculation, multi-window cross attention calculation, recombination and the like on deep features, and feature enhancement is realized. And fusing the features with shallow layer features, and outputting a reconstructed high-resolution image. Models with different reconstruction multiplying powers can be obtained according to different sampling multiplying powers under training data.

The invention relates to a 3D printing method and system for a composite prestressed reinforcing rib, and solves the main problems of weak interlayer adhesive force, large thermal stress and lack of an effective reinforcing rib adding method in the mechanical property of an existing 3D printing technology. Printing parameters and prestress release are cooperatively controlled on the basis of characteristic parameters of printing materials through a stress linkage algorithm, vertical ribs are tensioned for the second time through an interlayer compensation algorithm every time a preset number of layers are printed, and the printing parameters are dynamically adjusted through a path optimization algorithm in a high-stress area; when printing is completed and the material is not completely cured, stress distribution of all the reinforcing ribs is scanned through a stress balance algorithm and adjusted to a preset deviation range, and it is ensured that stress distribution of the whole structure is uniform; and after the printing material and the reinforcing ribs are compounded and cured, corresponding curing is performed according to the characteristics of the printing material. The 3D printing structure has the following effects that the mechanical property and reliability of the 3D printing structure are improved, and the interlayer strength and the overall stress distribution are optimized.

The invention provides an adversarial attack method for deep forgery detection based on a diffusion model, and the method comprises the steps: taking a deep forgery picture as an attack sample blueprint, and taking a deep forgery detection model as an attack object; initializing attack method parameters; performing T rounds of iteration, performing adversarial disturbance addition from 0 to T-1 rounds on the deeply-forged picture through a momentum iteration type fast gradient symbol method in each iteration, and adjusting the attenuation speed of momentum through an attenuation factor; calculating whether the disturbance intensity parameter of the processed deeply-forged picture exceeds a set value or not in each round of iteration, and if the disturbance intensity parameter exceeds the set value, trimming; and after T rounds of iteration are carried out, de-noising is carried out on the obtained sample through a diffusion model to obtain a more natural antagonistic sample, and the antagonistic sample is applied to the deep forgery detection model to detect an attack effect. According to the method, the attack concealment is improved, and the purpose of an invisible interference detection model is achieved.

To provide a system.SOLUTION: The system includes: generation means for inputting a specific prompt sentence into a generative AI model, thereby automatically generating a blueprint of a housing desired by a user on the basis of user house-related information including the design, the style and the condition of the house and real estate information; means for proposing the housing on the basis of the generated blueprint; means for adjusting the interior design and the layout in the blueprint of the housing on the basis of an emotion engine for recognizing the emotion of the user and the emotion; and means for displaying the adjusted blueprint by using a virtual reality display device.SELECTED DRAWING: Figure 1

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 present invention is directed to a system and method for displaying interior design proposals for a given room according to known design principles and user preferences. The system is operative to convert user-input sketches and / or blueprints of two-dimensional space geometry into digital floor plans and identify and propose blocks of appliances and / or articles of furniture as design elements defined by their dimensions and any limiting characteristics. Each block is functionally and dimensionally appropriate for the floor plan based on user preferences, as filters, and floor plan limitations and may be defined by minimum space requirements, anchor point restrictions, and configuration restrictions. The system and method may further comprise visual tools for conveying a user's creative taste, style, and aesthetic for each floor plan, and be operative to display hyperlinked shopping lists in accordance with filtered blocks of design elements.

The invention discloses a thermosensitive color-changing modifying pen and a color fixing device. The device comprises a modifying pen and a portable color fixing device. A main cavity and an auxiliary cavity which are separated by a partition plate are arranged in a penholder of the modifying pen and are respectively filled with thermosensitive covering ink and colorless fixation accelerant, and a fine fiber pen point and a metal needle tube pen point which are communicated with the penholder are arranged at two ends of the penholder. The portable color fixing device comprises a constant-temperature heating piece, a power supply unit and a control circuit, according to the principle that thermosensitive covering ink changes color under heating to be matched with the base color of the blueprint, fine smearing and controllable heat fixation technologies are combined, rapid, traceless and lossless modification of the engineering blueprint is achieved, and the problems that a traditional modification method is obvious in color difference, the blueprint is damaged, and operation is tedious are effectively solved. The device is easy and convenient to operate and firm in modification effect, and subsequent use of drawings is not affected.

Method of recognizing elements and symbols in construction engineering drawings detailing heating, ventilation, and air conditioning (HVAC) and / or plumbing elements, comprising: receiving a construction blueprint 301; recognising ducts, pipe fittings and duct fittings using a first neural network 310; performing text detection using a second neural network 320 and text recognition using a third neural network 340; filtering the recognized text for known fitting type and size 345; performing pixel tracing to detect pipes using the bounding boxes of text and symbols as a starting point; generating a list of construction elements 370; and providing an interactive visualization of an annotated construction engineering schematic 380. The first neural network may be a convolutional network (CNN), the second neural network a Character-Region Awareness for Text detection (CRAFT) CNN, and the third neural network a convolutional recurrent neural network (CRNN). The first neural network may recognise element symbols, the symbols being associated with the filtered text 370 by matching the bounding box coordinates of the text with the bounding box coordinates of the symbol. The user may alter construction elements in the interactive visualization. A costing list of individual construction elements, via quantity takeoff, may be provided to the user 390.

Provided are a trolley changeover control method and a trolley changeover system. The trolley changeover control method comprises: when a trolley (3) to be inspected arrives at a preset position, acquiring current blueprint information of the trolley (3) to be inspected; receiving target blueprint information sent by a manufacturing execution system, and performing consistency matching on the current blueprint information and the target blueprint information; when the current blueprint information is inconsistent with the target blueprint information, controlling a jacking mechanism (2) to execute positioning and jacking actions on the trolley (3) to be inspected, and then sending a control instruction to a robot (4), wherein the control instruction is used for controlling a gripper mechanism (1) disposed on the robot (4) to perform grasping and placing actions on at least one limiting block (32) on a pallet (31); and when the position of the at least one limiting block (32) matches a limiting block position in the target blueprint information, determining that the changeover of the trolley (3) to be inspected is successful, and controlling the jacking mechanism (2) to execute a releasing action, so as to release the trolley (3) to be inspected. In this way, labor costs and production costs can be reduced, and the production efficiency during product changeover can also be improved.

The invention relates to a blueprint generation method and device based on an unreal engine, equipment and a storage medium. The method comprises the following steps: acquiring an interactive text input by a user; the interactive text comprises a blueprint function needing to be realized; based on the interactive text and the large language model, obtaining a blueprint generation result; the blueprint generation result comprises at least one of a blueprint description text and a blueprint template identifier; the blueprint description text comprises a description text of a plurality of blueprint nodes and a description text of a connection relationship among the plurality of blueprint nodes; the blueprint template identifier is used for indicating a corresponding blueprint template; and obtaining a blueprint code based on the blueprint generation result, converting the blueprint code into a target blueprint through an unreal engine, and displaying the target blueprint in the unreal engine. The method can meet the complex and changeable requirements of developers, and the development efficiency is improved.

Disclosed in the present disclosure are an adaptation control method and system. The method comprises: when a trolley to be tested reaches a preset position, acquiring the current blueprint information of said trolley, wherein a tray is placed on the upper surface of said trolley, and the tray is used for bearing a component to be transferred; determining target blueprint information of said trolley, wherein the target blueprint information has an association relationship with specification parameters of said component; and when the current blueprint information is inconsistent with the target blueprint information, controlling at least one limiting block on the tray to perform position adjustment, such that the tray adapts to said component, and thus said component can be placed on the tray.

The embodiment of the invention provides an automatic poster generation method and related equipment, and belongs to the cross technical field of computer vision and natural language processing. The method comprises the steps that firstly, through a detail insensitive demand analysis (DIPR) mechanism, user demands of different detailed degrees are analyzed into a structured design blueprint in a unified mode through a large language model subjected to instruction fine adjustment; secondly, based on the style description in the blueprint, a diffusion model subjected to style-based fine adjustment is called to generate a high-quality background image; and finally, fusing the text content and the background image by using a multi-modal large language model, and directly outputting an editable HTML format poster. According to the method, the problems of poor text rendering accuracy, weak demand understanding ability and non-editable output results in the prior art are fundamentally solved, the text accuracy is remarkably improved, full-process automatic generation is realized, and the method has excellent commercial practicability.

1. Name of the Design Product: Wine Box (Jinjiang Spring - Great Blueprint). 2. Use of the Design Product: For product packaging. 3. Design Key Points of the Design Product: The combination of shape and pattern. 4. Picture or Photograph Most Indicating the Design Key Points: Perspective view.

We provide the system. [Solution] An information terminal that receives blueprints, An analysis device that analyzes the received design drawings and extracts the necessary instructions for each phase, A translation device that translates the analyzed instructions into a specified foreign language, A generation device that expresses translated instructions in audio, text, and video formats, A transmitting device that sends the generated information content to an information terminal, A system that includes this.

The utility model discloses an urban and rural planning design blueprint publicity device which comprises a display board, two cavities used for pasting design blueprints are symmetrically arranged at the two ends of the front side of the display board respectively, display windows are arranged on the front sides of the two cavities respectively, and two sets of fixing structures are arranged at the centers of the ends, close to each other, of the two display windows respectively. The two sides of the display board are fixedly connected with two rotating sleeves respectively, two lifting structures are arranged in the two rotating sleeves in a penetrating mode respectively, top plates are arranged at the top ends of the two lifting structures respectively, four supporting structures are arranged on the four sides of the bottom of each lifting structure respectively, and bases are arranged at the bottom ends of the two lifting structures respectively. The display device has the advantages that the lifting structure is arranged, the motor drives the threaded column to rotate, the threaded column drives the rotating sleeve in meshed connection to move up and down, then the display board moves up and down, use is convenient, the supporting structure is arranged, and the overall length of the supporting structure can be adjusted by screwing a threaded rod; the device can be stably placed in rugged terrains, and the publicity display effect is guaranteed.

The invention relates to a deep learning-based method and system for inspecting embedding boxes before batch dehydration. The method comprises the following steps of: acquiring dehydration basket embedding box images and marking to construct a data set; constructing an Eghost-YOLO model by adopting an EGhostC3 module and depth separable convolution, and training models for respectively identifying an embedding box and a corresponding number by using a data set; inputting the to-be-analyzed dehydrated blueprint image into the embedding box detection model, and detecting and cutting each embedding box; inputting the cut embedding box image into a number detection model, and detecting and cutting a number area; and identifying the numbering area based on a pre-trained PP-OCRv4 character identification model, comparing the identified numbering with a real numbering, and outputting a verification condition. Through a three-stage cascade strategy, rotating frame detection positioning is carried out on an embedding box in the whole image; cutting an embedding box area and accurately detecting a numbering area of the embedding box area; according to the method, omission, repetition and abnormal numbers are automatically marked, the number of the embedding box is automatically identified, omission and repetition problems are verified, full-process accurate tracking of pathological samples is realized, and the reliability of diagnostic data is ensured.

The application discloses a kind of based on alliance chain's drawing life cycle evidence method and system, the method includes: the drawing to be stored in evidence is divided into multiple drawing blocks, the numerical characteristics of each block and are normalized, the numerical value of the whole and each drawing block of the drawing to be stored in evidence is matrixed, and the drawing digital fingerprint of the drawing to be stored in evidence is generated by digital fingerprint generation model;When the drawing to be stored in evidence is modified or updated, obtain the modification matrix difference, and through drawing version evolution model, the evolution value of each drawing version is calculated in conjunction with drawing digital fingerprint;For each access user, according to the identity key of user, authority level, drawing digital fingerprint and the evolution value of each drawing version, the authorized value of user access each drawing version is calculated, and according to authorized value, it is judged whether user can access corresponding drawing version.

The invention discloses a science and technology policy analysis method. The method comprises the following steps: 1, collecting scientific policy documents; 2, classifying the collected scientific policy documents, and completing feature extraction by utilizing a technology of grouping and classifying fragments, paragraphs or documents; 3, establishing a 3 + 5 policy topic statement library, a text abstract library, an entity library and a relation library; and 4, constructing a model, and dividing the database obtained in the step 3 into a training set and a test set for training and testing to obtain a science and technology policy file analysis module capable of completing analysis on the science and technology policy file. According to the method, contents in the aspects of three blueprints and five construction drawings are selected as national science and technology policy analysis elements, so that effects of various policies can be comprehensively evaluated, policy making is optimized, and an analysis basis is provided for boosting and promoting science and technology innovation and social and economic development in China; and the scientific policy understanding and analysis efficiency is improved, and correct understanding of the scientific policy can be ensured.

The present invention is directed to a system and method for displaying interior design proposals for a given room according to known design principles and user preferences. The system is operative to convert user-input sketches and / or blueprints of two-dimensional space geometry into digital floor plans and identify and propose blocks of appliances and / or articles of furniture as design elements defined by their dimensions and any limiting characteristics. Each block is functionally and dimensionally appropriate for the floor plan based on user preferences, as filters, and floor plan limitations and may be defined by minimum space requirements, anchor point restrictions, and configuration restrictions. The system and method may further comprise visual tools for conveying a user's creative taste, style, and aesthetic for each floor plan, and be operative to display hyperlinked shopping lists in accordance with filtered blocks of design elements.

1. The name of the product of this design: A graphical user interface for composing test papers, practicing questions, correcting and explaining test questions for a tablet computer. 2. The purpose of this design product: to display the services provided by Huilantu high school learning machine, display service information, and introduce the platform. 3. The design key point of this appearance design product lies in the combination of pattern and color. 4. The picture or photo that best illustrates the key points of the design: main view. 5. The design for which protection is sought includes color. 6. Other views are of conventional design and are omitted. 7. Purpose of the graphical user interface: to display the services provided by the Huilantu high school learning machine, display service information, and introduce the platform. 8. Human-computer interaction method of the graphical user interface: The product's graphical user interface is used to display the introduction of the Huilantu high school learning machine and its service content. The main view screen displays the home page interface of the program. Click "Blueprint Secret Volume" on the home page interface to open the Blueprint Secret Volume service module.

The systems described in this disclosure can be used with a storage system to provide a platform for items and / or papers such as blueprints. A container includes a top panel that is pivotal relative to the container. The container may include additional panels that are pivotal with respect to the top panel and that rotate away from the top panel to extend the platform provided by the top panel.

A system is provided.SOLUTION: The system of claim 1, further comprising: means for transmitting the generated blueprint to an architect to check and correct the blueprint from a legal and technical point of view; means for allowing the user to confirm the checked and corrected blueprint; means for forming an architectural structure using a 3D printer based on the blueprint; and means for providing the user with a progress status of the architectural structure in real time. AI.SELECTED DRAWING: Figure 1

Methods and systems for improved generation and georeferencing of floor plans are presented. In one embodiment, a method is presented that includes receiving images that depict sheets of a blueprint of a structure. Subsets of the images depicting floor sheets and elevation sheets may be identified. Exterior contours may be extracted from the images depicting floor sheets and elevation contours may be extracted from the images depicting elevation sheets. A corresponding structure within a three-dimensional map may be identified based on the exterior contours and the elevation contours. A three-dimensional contour of the exterior of the structure may be extracted from the three-dimensional map.

The present invention relates to the field of laser cutting control technology, and particularly to a laser cutting control system and method for a lens assembly. The method includes the following steps: scanning the lens assembly in all directions to obtain point cloud data, then removing abnormal points, performing three-dimensional reconstruction to generate a lens assembly model, obtaining cutting task data and identifying cutting targets, based on which an optimal cutting time and space arrangement is carried out on the lens assembly model to generate an optimized cutting blueprint, planning a cutting path according to the optimized blueprint to obtain a candidate cutting path, and performing dynamic compensation on it to form a compensated cutting path, mapping control parameters according to the compensated cutting path to obtain variable control parameters, and then performing parameter replacement to achieve precise intelligent laser cutting control. The present invention realizes a more precise and efficient laser cutting control method for lens assemblies.

An object of a system according to an embodiment is to enable a user to quickly propose an interior design that matches the characteristics of a room.SOLUTION: A system according to an embodiment includes a photograph / design drawing upload unit, an image analysis unit, a customization unit, and a design display unit. The photograph / design drawing upload unit uploads a photograph or a design drawing of a room from a user. The image analysis unit analyzes the photograph or the design drawing uploaded by the photograph / design drawing upload unit. The customization unit generates a design in accordance with the characteristics of the room on the basis of the result analyzed by the image analysis unit. The design display unit displays the design generated by the customization unit to the user.SELECTED DRAWING: Figure 1

The invention relates to an accurate drawing fusion device and method based on an unmanned aerial vehicle real-time video, and the device comprises a data acquisition module which is used for synchronously collecting an unmanned aerial vehicle load video stream, camera information and unmanned aerial vehicle positioning information; the positioning auxiliary module is used for performing feature matching on the real-time image of the unmanned aerial vehicle load video stream and a pre-stored map image, and generating final positioning information in combination with the unmanned aerial vehicle positioning information; the coordinate transformation and calibration module is used for mapping physical space information of a drawing to a video pixel space according to the final positioning information and the camera shooting information and performing dynamic calibration of a mapping relation to obtain drawing information after coordinate transformation and calibration; and the graphic rendering module is used for carrying out real-time superposition rendering on the drawing information subjected to coordinate transformation and calibration and the load video stream to obtain a rendered fusion video. Compared with the prior art, the method has the advantages of high data synchronism, accurate positioning, high fusion precision and the like.

The application relates to the technical field of image enhancement, in particular to a mine environment super-resolution image reconstruction method based on vibration induction for mine monitoring, which comprises collecting vibration data and image data and performing pretreatment; the processed vibration data sequence is input into a double-layer LSTM network, vibration data is analyzed by using the LSTM, vibration characteristics at the next moment are predicted, and dynamic compensation parameters are generated; the processed image is input into a convolutional neural network constructed by using a blueprint separable convolution, a residual attention module and a coordinate attention mechanism, and multi-scale feature extraction is performed; time alignment of the vibration data and the image data is performed, corresponding compensation parameters are generated, and meanwhile, spatial alignment and fusion of the two are performed to obtain fusion features; based on the fusion features, super-resolution reconstruction is performed on the image to generate a high-resolution image. Through technical fusion innovation, the recognition quality of image quality in a complex vibration scene is significantly enhanced.

The invention is suitable for the technical field of architectural design process management, provides an architectural design dynamic process management method and system, and realizes remarkable optimization of a drawing review process through intelligent comparison and priority ranking of architectural construction drawings. The method comprises the following steps: firstly, acquiring a specified construction blueprint of a target building and a building construction primary drawing submitted by each corresponding construction participation unit, and combining with a selected revised drawing, so that the system can automatically evaluate the matching degree of the drawings of each unit; the cumulative calculation of the matching degree provides a clear basis for subsequent sorting, and the generated first priority set enables units with high drawing quality to be recognized preferentially.

The invention relates to the technical field of building construction, and discloses a large-span roof construction method and monitoring system based on an intelligent model, and the method comprises the steps: carrying out the multi-objective optimization and structure verification of roof slope finding parameters in a BIM platform, so as to generate a final construction blueprint model, formulating a laser-guided construction scheme according to the model, in the paving operation, self-adaptive paving of the slope making layer is completed through real-time sampling inspection and feedback, finally, a completion point cloud model is generated through three-dimensional laser scanning and compared with a blueprint model, and closed-loop verification of the construction quality is completed; the system comprises a model generation module, a construction strategy module, a self-adaptive construction control module and a quality verification module. According to the method, multi-objective optimization of the design front end, dynamic closed-loop feedback of the construction process and digital verification of the completion stage are deeply fused, and digital closed-loop management and control of the whole process from design, construction to acceptance are achieved.