187results about "CAD customisation/personalisation" patented technology

The invention discloses a presale fund supervision method and device based on multi-objective optimization, and relates to the field of financial risk management. Constructing a dynamic knowledge graph by fusing multi-source data, and forming an entity relationship network of a project, an enterprise and an associated party to quantify a risk path; predicting the comprehensive risk probability by adopting multiple models integrating static, time sequence and graph neural networks; the probability is input into an optimization decision engine, an improved multi-objective evolutionary algorithm is used to solve a Pareto optimal solution set of fund security, flow efficiency and project delivery rate, and objective weights are adjusted according to dynamic constraints; and finally, matching an optimal solution based on decision preference through a man-machine cooperation interface, automatically generating a personalized early warning and response strategy, and deploying and executing the personalized early warning and response strategy. According to the invention, dynamic and accurate supervision of presale funds is realized, and the fund security and the project delivery guarantee level are effectively improved.

The present invention relates to an artificial intelligence-based user-customized modular building design and BIM linkage apparatus comprising: a memory including at least one instruction; and at least one processor electrically connected to the memory and configured to perform the at least one instruction, wherein the at least one processor may: receive a user input related to generation of housing space data, wherein the user input includes natural language; apply space requirement analysis criteria to the user input to calculate a housing requirement index; determine, by means of a specification mapping model, hard specifications and soft specifications on the basis of the housing requirement index; if the housing requirement index cannot be calculated or if there exists an element, among the hard specifications, which cannot be calculated by the housing requirement index alone, analyze insufficient information to determine necessary additional requirement information; request, from a user, information necessary to obtain the additional requirement information; reflect an additional input from the user to sequentially update the housing requirement index, the hard specifications, and the soft specifications; and calculate, by means of a space generation model, housing space data on the basis of the updated hard specifications and soft specifications.

The invention relates to the technical field of intelligent design of optical lenses, and discloses a multi-series superposed complex periodic structure arrangement method and system.The method comprises the steps of normalized coordinate transformation, multiple sine wave superposition, an iterative function system, a Julia set algorithm, an LSystem grammar system, parameter adjustment, moire fringe fusion and the like; and a complex periodic structure with high complexity, adaptability resistance and natural morphological characteristics is generated. Advanced technologies such as logarithm uniform distribution wave number generation, a chaos game algorithm, linear mapping complex number conversion, a turn graph interpreter, multi-scale entropy complexity quantification and an Otsu automatic threshold method are adopted, and accurate parameterization control and manufacturing adaptation are achieved. The system comprises a coordinate transformation module, a wave interference calculation module, a fractal generation module, a complex power system module, an LSystem processing module, a parameter control module and a contour surface extraction module. According to the invention, a systematic solution can be provided for complex structure design of optical devices such as myopia prevention and control lenses.

The application provides a high-precision dot array density development method, system, medium and product of a beauty lens, relates to the technical field of beauty lens production, and comprises the following steps: obtaining multi-modal fashion data through a crawler technology and extracting a trend semantic vector from the multi-modal fashion data; mapping the trend semantic vector to micro-physical parameters for defining a beauty lens pattern based on a pre-trained neural network model to obtain an initial dot array parameter set; performing graphical rendering on the initial dot array parameter set to obtain a plurality of initial beauty lens dot array patterns; simulating the wearing effect of each initial beauty lens dot array pattern on a three-dimensional human eye model through simulation software to obtain a plurality of virtual wearing effect diagrams; and determining an initial beauty lens dot array pattern with an aesthetic evaluation score greater than a preset score threshold as a final beauty lens dot array pattern. By implementing the method, the limitations of a traditional design element library are broken, the generation of beauty lens patterns is more innovative and diverse, and the innovation and pop fit of the beauty lens patterns are improved.

The application provides a kind of urban design scheme image generation method and device, with such characteristics, including step S1, according to existing city planning image construction training data set;Step S2, construct planning parameter prediction model and design generation model, and according to training data set respectively training, obtain trained planning parameter prediction model and trained design generation model;Step S3, input specified region image into trained planning parameter prediction model, obtain corresponding predicted planning parameter;Step S4, input predicted planning parameter and specified region image into trained design generation model, obtain design scheme image.In short, the method can generate effective and have specified features and style design scheme image according to specified image.

The invention provides a footwear design method based on gait biomechanics and a footwear, which integrate an integrated process of foot biomechanics modeling, dynamic gait data acquisition, multi-region lattice structure configuration, multi-target collaborative optimization and additive manufacturing, and realize direct mapping from individual biomechanics characteristics to personalized footwear products. The fundamental problem that a traditional shoe design cannot meet the differential biomechanical requirements of multiple areas of the foot in the dynamic gait cycle at the same time is solved, and systematic and accurate adaptation is achieved.

Computer system (100) and computer-implemented method are provided for automated generation of manufacturing-machine control data (291) for the manufacturing of an orthodontic appliance (280) for a patient (2). Based on three-dimensional representations (210) of the patient's oral anatomy and an appliance type (211) of the orthodontic appliance, the system generates a control structure (111) comprising a mesh providing an initial representation (111pi) of an aimed appliance geometry, and subdivision manifold-related shape attribute information (Ills) with a subdivision scheme, implicit manifold-related shape attribute information (111i) with a scalar field, and information for evaluating a respective position of the respective vertex. Executing a subdivision according to the subdivision scheme generates a modified control structure (111m). For added vertices, respective shape attribute information is evaluated to obtain the position of the respective vertices. Once a final mesh is obtained, it is transformed into manufacturing-machine control data for the manufacturing of the orthodontic appliance, and provided to corresponding manufacturing means (290).

A system for selecting an intraocular lens (IOL) for implantation in an eye includes a controller adapted to selectively execute a finite element model (FEM) and a machine learning module. The controller is adapted to receive input data including one or more biometric parameters of the eye. Based on the input data, a plurality of capsule parameters are extracted via the machine learning module. The controller is adapted to determine an axial displacement factor, in part, based on the plurality of capsule parameters via the FEM. The axial displacement factor takes into account the predicted axial offset of the IOL after implantation in the eye. When calculating lens constant parameters using the FEM and machine learning module, the axial displacement factor can be incorporated into the final IOL power.

A computer-implemented method for designing a patient-specific orthopedic implant can include creating a user account associated with a patient. A patient-specific orthopedic implant can be designed based on patient data and imaging data. A healthcare provider can provide feedback for a design of the patient-specific orthopedic implant, treatment protocol, or other aspects of treatment. The patient can provide data and feedback.

The application provides a public area overall style transformation system and method based on a virtual scene, comprising: an information storage module: storing user portrait information, user interactive operation information and built-in style information in a computer host or a cloud server; a scene rendering module: obtaining data in the information storage module and presenting public area overall information to a user by using an instant rendering system; a style interactive module: changing overall style information attached to a structure to realize different users' imagination of the public area; and a control module: changing and recording each style information in the virtual scene and conducting a roaming experience in the public area. The application reduces the communication cost between an owner, a designer and a user, makes feedback instant and efficient, optimizes design, obtains a space more in line with user preferences and accurately and quickly adapts to changing market demands.

According to an embodiment, a method for designing of one or more virtual models of custom ear devices according to configuration requirements from a user input and according to component and / or material information that are associated with components and / or materials of a target product is provided. The method may comprise steps for displaying the designed one or more virtual models of custom ear devices together with meta data that comprise information on the designed one or more custom ear device's compatibility with the configuration requirements and the contained components. According to an embodiment, a computer-readable storage medium or computer program is provided, comprising commands, which when executed by a computer, causes the computer to execute and perform the method for designing and displaying the one or more virtual models of custom ear devices. According to an embodiment, a system for determining one or more virtual models of custom ear devices is further disclosed. The system may further be configured to display the determined one or more virtual models of custom ear devices together with associated meta data on a graphical user interface.

The invention belongs to the technical field of ophthalmic optics, and relates to a design method of a personalized spectacle lens and the spectacle lens. The design method comprises the following steps: constructing a spectacle-eye joint mathematical model based on spectacle frame posture and eyeball rotation, and analyzing and calculating the mathematical model to obtain a theoretical diopter calculation formula of the lens surface under prescription diopter; based on the basic eye model, according to the prescription diopter, the posture of the spectacle frame, and the central diopters, refractive indexes and central thicknesses of the inner and outer surfaces of the lenses, constructing a lens-eye system comprising the lenses to be optimized and eye models with different rotation angles; calculating the actual diopter of the surface of the to-be-optimized lens based on the intersection point of the human eye visual axis of the eye model with different rotation angles and the surface of the to-be-optimized lens; taking the minimum absolute value of the difference between the actual diopter and the theoretical diopter of the surface of the to-be-optimized lens as a target, ensuring the imaging quality and machinability of the lens, and optimizing the parameters of the inner surface of the to-be-optimized lens to obtain the personalized spectacle lens considering the posture of the spectacle frame and the rotation of the eyeball.

The invention relates to the technical field of decoration, and discloses a decoration interface combination processing method based on an MAHE method, and the method comprises the steps: S1, obtaining the decoration demands of a customer for three decoration interfaces of a wall surface, a ceiling and the ground; s2, the decoration requirements are analyzed, and respective configuration levels of the wall surface, the ceiling and the ground are determined; s3, calling corresponding wall surface, ceiling and ground components from a preset component library according to the numerical value of each bit of the three-bit binary code, and combining to generate a fabricated decoration scheme; and S4, on the basis of the three-bit binary code, performing weighted summation on each bit numerical value and a corresponding preset difference sequence weight value, and calculating to obtain an overall evaluation value of the fabricated decoration scheme. According to the invention, through artificial intelligence semantic recognition and a three-bit binary coding technology, automatic conversion of customer decoration requirements, systematic generation of the fabricated decoration scheme and objective quantitative evaluation of the comprehensive value of the scheme are realized.

The invention relates to the technical field of direct-current fans, and discloses a direct-current fan and a serialization design method.According to the direct-current fan and the serialization design method, general electromagnetic structure design of a series of direct-current fans is conducted through electromagnetic simulation optimization, magnetic steel surface magnetism is analyzed through a static magnetic field to determine the magnetic steel machining magnetizing inspection standard, and a boss in a shaft sleeve is adopted for replacing a clamping ring for limiting; a low-cost and standardized direct-current fan series structure is formed, and only the required performance output corresponding to the number of turns of the winding needs to be adjusted, so that low-cost and quick-response series product development is realized.

The present application discloses a method and an apparatus for determining a reference curve, a dental orthodontic appliance, and a design method. The method for determining a reference curve includes: obtaining a dental characteristic parameter of a dental arch model data; determining, based on the dental characteristic parameter, a first feature curve in a first coordinate plane and a second feature curve in a second coordinate plane, the first feature curve being a first orthodontic reference curve in a dental arch coordinate system, and the second feature curve being a dental arch curve; and adjusting the dental characteristic parameter, an adjusted dental characteristic parameter being used for determining a second orthodontic reference curve, and the adjusted dental characteristic parameter being adapted to a corresponding first feature curve and second feature curve. The method for determining an orthodontic reference curve provided by the present application may determine an orthodontic reference curve that conforms to an actual situation, may improve an accuracy and a rationality of an orthodontic treatment, and may enhance an efficiency of determining the curve and an orthodontic design.

An open architecture product coupling analysis method, which establishes a component comprehensive correlation matrix according to the correlation between the functions and structures of the components of an open architecture product, identifies the common platform, customized module and individualized module structure types of the open architecture product, determines the bus interface of the common platform, the input / output interface of the customized module and the input interface of the individualized module, identifies the coupling mode between the customized modules and the correlation between their functions and structures, calculates the coupling degree between the modules according to the comprehensive correlation between the functions and structures of the components between the correlated modules and the correlation density of the interfaces, establishes a change propagation probability matrix between the modules according to the interface relationship between the modules and the component dependency relationship within the modules, and calculates the change influence degree between the correlated modules. The present application is simple to calculate, improves work efficiency and shortens the development cycle.

The invention discloses a personalized doll clothing customization system based on traditional clothing elements, and relates to the technical field of clothing customization. Comprising a traditional costume element library module which is used for constructing a database in a layered manner according to a shape type, a pattern type and a color type and storing traditional costume elements, and each traditional costume element is attached with core feature parameters marked by AI, and is used for quickly retrieving and calling the traditional costume elements. According to the method, traditional clothing element feature parameters are accurately collected and labeled through the traditional clothing element library module, traditional clothing element features and customized keywords in user requirements are extracted in combination with the multi-modal input analysis module, and then the AI adaptation optimization module uses a proportion adjustment algorithm and a density adjustment algorithm; therefore, the traditional clothing elements are precisely matched with the size of the doll clothing, core details such as pattern texture and shape and structure are kept, and the problem that the traditional clothing elements are distorted to be matched with the small-size model of the doll clothing is effectively solved.

This invention discloses a smart clothing design method based on multi-signal collaborative monitoring using flexible strain sensing yarn. The method includes a self-locking sewing technique integrating flexible sensing yarn into clothing, smart clothing design, and a sensor signal acquisition, transmission, and display system. This invention develops a self-locking sewing technique that efficiently transmits human movement through clothing fabric to flexible sensing yarn. A lining is sewn into the inner side of the garment to form a wiring channel, and an elastic band is embedded on the outer side, with an internal pocket. The flexible sensing yarn is sewn into the lining fabric at locations such as the elbows, abdomen, wrists, and chest using the aforementioned sewing technique. Flexible conductive yarn is threaded through the wiring channel to connect the flexible sensing yarn to the interface of a multi-channel signal collector in the pocket. The multi-channel signal collector simultaneously acquires and processes signals from multiple flexible sensing yarns and wirelessly transmits them to a smart terminal. This method realizes a smart clothing design that collaboratively monitors human movement and physiological data.

A parameterized driving modeling method, a modeling system, an electronic device and a storage medium. The parameterized driving modeling method comprises: obtaining basic parameters and specific parameters of a three-dimensional space model to be modeled, and creating a sub-component model of a plate element of the three-dimensional space model; wherein the basic parameters comprise the type / number, material, color and / or finishing information of the three-dimensional space model; the specific parameters comprise parameters in the three-dimensional space model for user adjustment; based on the obtained basic parameters and specific parameters, determining physical parameters and production parameters corresponding to all plate elements of the three-dimensional space model; and based on the obtained basic parameters, specific parameters and corresponding production parameters, generating modeling data of the three-dimensional space model. Through the embodiments provided in the present application, machining data is involved in plate modeling at the same time, so that complex machining data can be compatible during modeling, and the integration from cabinet body design to production is realized.

According to the personalized recommendation system and method for the digital media art CAD design, user operation behaviors are captured, periodic laws are mined in combination with time sequence analysis, user portraits are updated, color distribution and geometric morphology characteristics are extracted through OpenCV, a knowledge graph is generated in combination with a BERT + ResNet multi-mode learning model, and the personalized recommendation system and method for the digital media art CAD design are obtained. A relation network between nodes is expanded, a design trend is analyzed through a crawler technology and social network data, a reinforcement learning optimization strategy is adopted, a knowledge graph is updated, a logic dependency relationship between CAD design parameters is analyzed, finite element analysis results and industry standards are integrated, an updated feasibility graph is generated, and a design scheme is encoded into a gene sequence; generating a candidate scheme through crossover variation, calculating the style deviation degree between the recommendation scheme and the existing works, tracking the adoption rate and the modification frequency, and evaluating the recommendation strategy effect through an A / B test.

The invention discloses a method and a system for generating an orthopedic insole model, relates to the technical field of foot orthopedic, and aims to solve the problems of low orthopedic insole generation efficiency and low insole matching accuracy in the prior art. The method comprises the following steps: acquiring a sole spatial-temporal feature vector, a foot static parameter and an initial orthopedic insole model of a user; the multi-dimensional feature vectors are input into a double-task machine learning model, and shape righting insole deformation parameters are output; the multi-dimensional feature vector pair is obtained based on splicing of foot static parameters and foot sole space-time feature vectors; and processing the initial orthopedic insole model based on the orthopedic insole deformation parameters to generate a target orthopedic insole model. According to the method, the personalized requirements of the user on the orthopedic insole can be efficiently and accurately met.

This invention proposes an efficient, customized concept replacement method, InstantSwap, which handles shape differences between source and target concepts while maintaining foreground-background consistency without training. The method includes automatically generating bounding boxes to locate the source concept, applying a background gradient mask to protect the background region, enhancing foreground consistency through semantically augmented concept representations, and performing concept replacement. Furthermore, a skip gradient update (SSGU) strategy is introduced, calculating gradients only at key time steps to reduce forward propagation and improve efficiency. Through extensive qualitative and quantitative evaluations, as well as comprehensive ablation studies, this invention demonstrates the effectiveness and superiority of its method, showcasing its versatility and broad applicability in relevant tasks. The method is particularly suitable for applications requiring precise concept replacement, such as selfie enhancement, photo blogging, and comic creation.

The invention discloses a shoe manufacturing method and system, and the method comprises the steps: obtaining the foot three-dimensional size data of a target user, the foot three-dimensional size data of the target user comprises the foot length of the target user, the foot width of the target user, and the foot height of the target user; determining a target shoe tree corresponding to the foot three-dimensional size data based on the foot three-dimensional size data and a target shoe type selected by the target user; based on the foot three-dimensional size data and the three-dimensional size data of the target shoe tree, determining a target foot mold shoe tree corresponding to the foot three-dimensional size data; determining shoe parts related to the target foot mold last; in response to the target shoe component selected by the target user, generating an order for making the target shoe; and splitting the order to obtain a plurality of sub-orders, and distributing the plurality of sub-orders to manufacturers corresponding to the target shoe parts. According to the scheme, foot-fitting and personalized services can be provided for the target user, and more foot-fitting shoes can be provided for the target user.

The invention provides an intelligent rail smoothness adjusting method and system based on dynamic detection and big data analysis, and belongs to the technical field of railway engineering maintenance. The method comprises the steps that track geometric data, vehicle dynamics response data and environment data are collected in real time through a multi-dimensional sensor array installed on an operating train; uploading the data to a cloud big data platform for fusion and deep mining, constructing a track state degradation prediction model by using a machine learning algorithm, and accurately predicting the development trend of track irregularity; and based on the prediction result, automatically generating a targeted track fine adjustment scheme, and issuing the scheme to an intelligent maintenance robot deployed on the line or guiding a manual maintenance team. The system comprises a data acquisition layer, a cloud analysis layer and an intelligent execution layer. According to the method, the change of the track state from'regular maintenance 'to'predictive maintenance' is realized, the maintenance efficiency, the precision and the line smoothness are remarkably improved, and the maintenance cost of the whole life cycle is reduced.

A user interface (48) for a lightweight viewer (46) may include a viewing window (52-1) operable to display geometry (33) established by geometric objects (54) of a tessellated model (36). Groups (54G) of the geometric objects (54) may be associated with the geometry (33) of respective components (C) of an assembly (A). Annotation objects (64) of the tessellated model (36) may be operable to depict annotation information associated with the tessellated model (36) as graphical annotations in the viewing window (52-1). The groups (54G) of the geometric objects (54) may be assigned to two or more responsible entities according to an interface requirements definition (43). The annotation information may be associated with one or more interfaces between adjacent components of the assembly according to the interface requirements definition (43).

The invention belongs to the technical field of intelligent manufacturing and product configuration, and particularly relates to a binary hybrid configuration model construction and implementation method based on a cloud model and an R-T cross-domain mapping mechanism. The method comprises the following steps: firstly, performing quantitative modeling on three-dimensional features of emotion, preference and cognition of a customer by utilizing a cloud model, and generating a cloud three-parameter vector of a personalized demand of the customer; then, through an R-T cross-domain mapping mechanism, the fuzzy feature vector of the demand space is converted into technical parameter representation of a product function, a structure and an information capacity; on this basis, a binary hybrid reasoning model composed of a personalized demand rule layer and a product configuration rule layer is constructed, and unified reasoning of subjective and objective elements is realized by adopting a t-norm fusion strategy; and a cognitive level dynamic adjustment mechanism is further introduced, and the weight of the rule is adaptively adjusted according to the cognitive difference of the user, so that personalized optimization of the configuration scheme is realized. According to the invention, accurate matching between subjective requirements of customers and product configuration parameters can be realized, and the method is particularly suitable for design and recommendation systems of multi-parameter customized products such as customized household appliances, intelligent furniture and configurable industrial equipment.

The invention relates to the technical field of intelligent manufacturing, in particular to a modular massager cloth cover preparation method and system based on human engineering, and the method comprises the following steps: obtaining body part size data of a target user; based on the size data of the body parts, calling a preset human engineering database and an algorithm, generating a cloth cover virtual model attached to the three-dimensional curved surface of the body parts, dividing the cloth cover virtual model into a plurality of independent production modules, unfolding the three-dimensional model of each production module into a two-dimensional plane model, and storing the two-dimensional plane model in the cloth cover virtual model; carrying out digital typesetting on all the two-dimensional plane models, and generating a numerical control instruction required for driving the automatic manufacturing equipment; based on the numerical control instruction, the automatic manufacturing equipment is controlled to complete cutting and sewing of all the production modules, and all the sewn production modules are assembled into the complete massager cloth cover. According to the invention, personalized customization, human engineering design, modularization concept and intelligent manufacturing are deeply integrated.

The invention provides a drawing verification method and system, a medium, electronic equipment and a program product. The method comprises the steps that data information of a target drawing is input into a trained AI large model; the data information comprises attribute information of equipment and parts in the ship, corresponding general specification data and personalized technical requirements of a target customer; the AI large model outputs a verification result; the AI large model is obtained based on general specification data, a customer personalized technical requirement sample and sample drawing training, and the verification result represents whether the target drawing passes verification or not; the verification result comprises equipment and parts which do not conform to the general specification data and / or equipment and parts which do not conform to the personalized technical requirements of the customer. According to the method and the device, whether the target drawing meets the general standard data and customer personalized technical requirements or not can be quickly and accurately checked, so that the accuracy and the efficiency are greatly improved, the error and the consumed time of checking are reduced, and the stable improvement of the design quality can be ensured.

The invention relates to the technical field of clothing customization recommendation, in particular to a clothing model and user body type matching system which comprises a structure segmentation module, a body type evaluation module, a component combination module, an adaptation judgment module and a matching output module. According to the invention, through comparative analysis of key node differences in clothing structure cut pieces and introduction of node tolerance section and alignment point offset evaluation, accurate identification and matching of clothing model detail levels are realized, and through identification of angle differences between a body shape curve direction and a structure extension path, the clothing model detail levels are accurately identified and matched. The method comprises the following steps: constructing a multi-dimensional body structure adaptation relationship, performing quantitative definition on a deviation condition of a structure path and a human body curvature in combination with integrity identification and combination coherence checking of suture point continuity, establishing an error judgment mechanism, and completing matching quality screening of key parts through matching rate accounting. And the matching precision and the customization adaptation effect between the clothing model and the user body type are obviously improved.