32 results about "Design evaluation" patented technology

The invention relates to the technical field of computer aided design and visual computing, and provides a visual communication design evaluation system and method based on data analysis. The method comprises the following steps: acquiring original design data, and extracting a spatial layout feature matrix, a color distribution feature vector and a semantic content feature set; calling a design specification knowledge base based on the design purpose information; performing simulated attention distribution analysis and design compliance analysis to generate corresponding features; constructing a transmission efficiency prediction model to generate a comprehensive transmission efficiency score and an initial design evaluation report; performing interference effect joint analysis to obtain a comprehensive interference effect quantitative evaluation result; and performing efficiency optimization correction on the initial design evaluation report based on the result, and outputting a final design evaluation report integrating spatial layout and visual attribute optimization suggestions. According to the method, the interference effect is accurately quantified through conjoint analysis of spatial layout and semantic attributes, and the accuracy and reliability of design conveying efficiency evaluation are improved.

The invention discloses a sheet metal part manufacturability reasoning method based on space-semantic map alignment, and relates to the field of manufacturing-oriented design evaluation and industrial knowledge reasoning, and the method comprises the following steps: carrying out geometric analysis on a CAD geometric model of a sheet metal part to be evaluated; abstracting the geometric features and the topological / metric spatial relationship thereof into a computable spatial semantic graph; performing semantic analysis on the process specification described by a natural language, converting the process rule into formalized logic check expression by using a large language model through context learning, and generating an executable domain-specific language check script; executing the script on a spatial semantic graph, realizing deterministic reasoning through graph matching and attribute verification, and completing accurate mapping and violation detection of text rules and geometric features; and outputting an interpretable diagnosis result containing violation feature positioning, triggering rules and numerical evidence. In order to solve the problems that a process rule'natural language-geometric model 'has a semantic gap, a traditional rule system is poor in adaptability, and an end-to-end learning method is high in data dependence and cannot be explained, a new rule can be quickly adapted under the condition that a large amount of data does not need to be labeled and a model does not need to be retrained; the method can accurately identify the violation of the micro-size and spatial relationship, and has reasoning preciseness, interpretability and engineering availability.

The invention discloses a cooperative training data generation method for an adjustment and optimization problem and electronic equipment, and the method comprises the following steps: carrying out the filtering processing of an input code description text, and obtaining input data; injecting the problem data into the input data to generate first adversarial sample data containing the problem data; gradient information and disturbance amplitude are calculated, and second adversarial sample data are obtained through adjustment and optimization; designing a shared encoder based on the second adversarial sample data to obtain problem data and normal code data features; carrying out separation processing on the two in a feature space; according to the separated features, the shared encoder is promoted to learn through feature comparison, and finally a model generated by code training data is obtained; and designing an evaluation index for judging whether a generation result of the model in the problem data injection scene is correct and stable, thereby completing model training of code training data generation. According to the method, generalization and robustness of the large language model in the process of processing actual problems are improved.

The application discloses a product design intelligent evaluation system based on big data, and particularly relates to the technical field of product design evaluation, and the system comprises an anchor point account establishing module, a product evaluation module, a scheme rating module and a result output module; the anchor point account establishing module forms a design anchor point table according to a demand preliminary evaluation sheet and initial scheme information; the product evaluation module acquires a scheme change sheet and calls scheme verification data, and performs product undertaking verification; the scheme rating module combines the undertaking verification result and an auxiliary verification result to output a scheme evaluation state; and the result output module outputs product design intelligent evaluation results in a summarized manner. The application can continuously verify whether customer demand is undertaken by design parameters, versions, materials, processes, samples, costs and market feedback after scheme change, and can locate abnormalities to specific change fields, change components, anchoring relationships and data sources, thereby improving the traceability and review efficiency of evaluation results.

The invention provides an optimization design evaluation method for a labyrinth welding drum based on a parameterized model, and belongs to the technical field of aero-engines, and the method comprises the steps: building a drum parameterized mathematical model, and determining a drum stress expression; determining a dangerous part of the drum at the maximum working rotating speed, and determining the section average stress of the dangerous part based on the stress expression; aiming at the welding part, determining the residual strength reserve coefficient of the drum based on the initial defect, and determining the stress reserve coefficient of the welding part; for the maximum stress part, the ratio of the minimum self-sustaining radius of the two wheel discs connected with the drum to the pitch diameter of the drum is obtained; when the ratio does not meet the preset condition, the stress reserve coefficient of the maximum stress part is determined; and carrying out optimization design on the structural parameters of the drum by taking the lightest weight of the drum as an objective function and taking the condition that the residual strength reserve coefficient and the stress reserve coefficient do not exceed the material performance as a constraint condition. A complete evaluation system is established, the design period is shortened, and the evaluation accuracy is improved.

A big data-driven automatic evaluation method for automotive exterior styling design is proposed. First, a large-scale multi-view automotive image dataset is created for vehicle angle recognition and grade recognition, and deep neural network methods are used to train the corresponding vehicle angle recognition and grade recognition machines. Next, an automotive styling evaluation dataset is created for exterior styling scoring. This dataset includes multi-view automotive images and corresponding brand, model, and other labeled information, with styling score annotations and semantic evaluation annotations for end users and styling experts respectively. The automotive styling evaluation dataset is then split into corresponding subsets according to vehicle grade and evaluator attributes, and trained using deep learning regression and classification methods to obtain automatic scoring machines and automatic semantic evaluation machines at different levels for automotive exterior styling users and experts. The significant features affecting styling scores and semantic evaluations are visualized, providing stylists with real-time and objective styling design evaluations during the development process.

The invention provides a dynamic multi-level evaluation system, which comprises an evaluation specification management module used for storing an evaluation plug-in integration specification, an evaluation data description specification, an evaluation plug-in development specification and an evaluation model description specification; the evaluation data management module is used for creating an evaluation data model required by the task based on the evaluation data description specification; the evaluation model management module is used for completing the design of a comprehensive calculation model on the basis of an evaluation model which is developed by the evaluation model description specification; the evaluation plug-in management module is used for managing an evaluation plug-in, and the evaluation plug-in is packaged according to an evaluation plug-in integration specification and is called by the evaluation model management module; the evaluation system management module is used for designing and managing a multi-level index system required by an evaluation task; and the evaluation scheme management module selects a multi-level index system based on the evaluation task to create an evaluation scheme, and executes the evaluation scheme to generate an evaluation result. The method is clear in logic and simple to operate, and the evaluation work efficiency is greatly improved.

This invention discloses a method for constructing an AI-assisted assessment system for physical education teaching scenarios, belonging to the field of education. The method includes the following steps: First, a standard movement sample database is constructed based on physical education teaching standards, containing movement samples and feature annotations from multiple angles and difficulty levels; second, an AI assessment model is designed, using computer vision technology to extract key points of human posture, and combining temporal analysis algorithms to achieve automatic recognition and quantitative scoring of movements; then, a recording module, a feedback module, and a report generation module are integrated to provide video acquisition, real-time analysis, and personalized guidance functions; finally, the system is continuously improved through an iterative optimization path of data acquisition, model training, system integration, and experimental verification. This invention realizes the transformation of physical education teaching assessment from a subjective experience-driven model to a data-driven model, supports multi-dimensional movement scoring and deviation localization, provides objective and unified evaluation results, and offers immediate and accurate feedback, effectively improving teaching guidance efficiency and students' movement skill levels.

The invention discloses an automobile instrument software design evaluation policy information extraction method and system, a medium and equipment. The method comprises the following steps: constructing design evaluation policy annotation data containing noise; screening a clean set and a noise set from the design evaluation policy annotation data based on a k-fold cross validation method; combining the clean set and the noise set based on a weighted weak supervision loss function to perform weighted training on an information extraction model to obtain a trained information extraction model; and performing information extraction on the to-be-identified automobile instrument software design evaluation policy document by utilizing the trained information extraction model. According to the method, through a two-stage adaptive noise processing framework, high-confidence-coefficient cleaning samples are screened based on loss values, and then noise sample training is fused through a weighted weak supervision loss function. According to the method, the extraction precision in a noise environment is remarkably improved, the dependence on expert labeling is reduced, and efficient compliance development of automobile software is facilitated.

This design evaluation system comprises: a feature quantification unit that, on the basis of a first trained model obtained by learning a first correspondence relationship between a material image indicating the design of a material and a feature amount obtained by quantifying an appearance feature of the design, quantifies the appearance feature of the design of a material indicated by a material image inputted as an evaluation target and generates feature amount information indicating the feature amount of the evaluation target; and a sensibility quantification unit that, on the basis of a second trained model obtained by learning a second correspondence relationship between the feature amount and a sensibility amount obtained by quantifying a sensibility word representing the appearance of the design, quantifies the sensibility word corresponding to the feature amount of the evaluation target indicated by the inputted feature amount information and generates sensibility amount information indicating the sensibility amount of the evaluation target.

The invention discloses an EEG-based old-age institution visual environment cognitive performance evaluation method, relates to the technical field of environment monitoring, and aims to solve the problem that the cognitive performance of a scheme cannot be effectively pre-judged and optimized in the prior art. Objective quantitative evaluation of the cognitive performance of the visual environment of the pension institution is achieved, the problem that a traditional design evaluation method is low in evaluation accuracy is solved, and then effective pre-judgment and optimization of the cognitive performance of the scheme are achieved.

This invention discloses an intelligent control optimization method for cryogenic liquid evaporators. The method includes modeling a multi-valve control unit for the cryogenic liquid evaporator, designing an adaptive evaporator loss function, designing a centralized execution evaluation architecture for the multi-valve control unit, prioritizing experience replay training, and optimizing evaporator control. This invention belongs to the field of intelligent control, specifically referring to an intelligent control optimization method for cryogenic liquid evaporators. This scheme constructs precision control reward terms, energy consumption penalty terms, and safety penalty terms to balance control precision and system synergy. Based on the adaptive evaporator loss function design, conflict penalties are used to avoid contradictions in action logic, thereby improving the stability of control optimization. The degree of action conflict is incorporated into the experience priority calculation, prioritizing the learning of conflict scenarios. Importance weights and collaborative penalty designs are added to evaluate network loss, significantly reducing the probability of action conflict. Importance sampling is used to correct distribution offsets, thereby improving the reliability of control optimization.

The invention discloses a system interface design evaluation method and device, a storage medium and electronic equipment, and the method comprises the steps: collecting system interface data and a design rule, and setting a static evaluation index and a dynamic evaluation index according to the design rule; evaluating the system interface data based on the static evaluation index and the dynamic evaluation index to obtain a static evaluation value and a dynamic evaluation value; obtaining a human error evaluation value of the system interface based on the cognitive possibility model; and constructing a comprehensive score model according to the static evaluation value, the dynamic evaluation value and the human error evaluation value, and obtaining a design evaluation result according to the comprehensive score model.

The present application relates to a target detection network evaluation method based on quantitative evaluation and explainability method. The present application combines quantitative evaluation and explainability method, which can more comprehensively and accurately evaluate the performance and decision basis of the target detection network. The present application uses multiple quantitative evaluation indicators (accuracy, recall rate, average precision, FPS) to comprehensively evaluate the target detection network. An explainability method based on perturbation and class activation mapping is proposed, which can help users understand the decision-making process of the target detection network. A visualization method based on gradient descent method and regularization technique is proposed, which can help users understand the semantics contained in the target detection network. The explainability method proposed in the present application can intuitively show the internal operation process and knowledge of the target detection network, thereby enhancing the explainability of the model and improving the credibility of the model results. Experimental results show that the present application can effectively evaluate the performance of the target detection network, improve the explainability of the model, and can be used for the design, evaluation and improvement of the target detection network.

The application discloses a kind of based on big language model's chart alternative text quality automation evaluation method and system, it is related to big language model field and chart alternative text field, including: by demand investigation, obtain chart alternative text quality evaluation scheme;Artificially construct chart alternative text evaluation standard data set carries out data preprocessing, based on GLM4-9B model carries out Finetune training and performance tuning.The chart alternative text quality automation evaluation method proposed in the application is based on chart accessibility reading criteria to design evaluation scheme, and the prediction score of the transfer model obtained by training is highly correlated with the artificial evaluation score, which can provide high-reliability automated chart alternative text quality evaluation results and can be applied to text quality evaluation in the field of chart alternative text.

The present application belongs to the technical field of green building design evaluation technology and multi-objective optimization algorithm combination technology, and provides a green building design scheme evaluation system based on a multi-objective optimization algorithm, which comprises: screening quantifiable and optimizable green building design targets and identifying strong conflicts between the targets; if there is a strong conflict, a judgment module is used to test the anti-interference ability of the selected optimal solution set obtained by multi-objective optimization to weight fluctuation; if the solution set has poor anti-interference ability, a sensitivity analysis is used to locate the weight sensitive target; then, in combination with subjective weighting, objective weighting and sensitive target characteristics, reliable benchmark weights are generated; finally, the priority of the selected scheme is output by considering the comprehensive performance and stability of the scheme through priority calculation, thereby solving the problems of subjective weight setting and poor scheme anti-interference in the existing green building design evaluation, significantly improving the scientificity and reliability of the evaluation results, and providing precise support for the decision of the green building design scheme.

This invention relates to a method, apparatus, and equipment for evaluating the single-event immunity of aerospace chips. By dividing the evaluation process into three stages—preliminary design evaluation, preliminary assessment, and chip compliance evaluation—the single-event immunity capability of aerospace chips is quantitatively measured. Simultaneously, the early evaluation in the preliminary design stage, the secondary verification in the preliminary assessment stage, and the comprehensive comparison in the chip compliance evaluation stage clearly and in a closed-loop manner assess whether the chip's single-event immunity performance meets the orbital insertion standards, greatly enhancing the risk control of aerospace chips. This evaluation technology is characterized by high universality and strong operability, improving the reliability of aerospace chips while avoiding design risks, and can be widely applied in the aerospace field.

The application provides a situation comprehensive multi-satellite task planning design evaluation system and method, belongs to the satellite system overall technical field, and aims to solve the problems of difficult evaluation of multi-satellite task planning efficiency and difficult verification of algorithm. The system comprises a task planning control plug-in, a perception data generation plug-in, a comprehensive situation processing plug-in, a system efficiency evaluation plug-in, and a comprehensive simulation deduction platform integrated with the foregoing plug-ins. The system builds a closed-loop verification environment for task planning-situation processing. The corresponding method comprises scene building, service configuration, running simulation and evaluation analysis. The application can simulate multi-algorithm concurrent execution, and quantitatively evaluate based on a multi-dimensional index system at the levels of coverage planning, task and situation, thereby providing reliable data support for task planning design.

The application discloses a highway route design evaluation system based on data analysis, relates to the technical field of route design, converts natural language into a target vector, outputs current evaluation data based on historical design parameter data and operation effect data, inputs the target vector into a mapping relationship model to generate a design parameter candidate set, and verifies the design parameter candidate set through a sample guiding mechanism, iteratively corrects the design through error feedback and dynamic weight adjustment, samples in a parameter space to construct a path control point sequence and configures structure parameters, and the application realizes automatic generation of design parameters from the target vector through a bidirectional coupling mechanism of forward modeling and reverse modeling, realizes multi-round optimization iteration through error feedback, and improves the adaptability of the design result to the user target. Compared with a traditional passive evaluation process, the application has the advantages of target driving, closed-loop optimization and adaptive adjustment, significantly improves the intelligent degree and multi-target consistency of route design, and has strong practicality and technical progressiveness.

This application relates to the field of landscape design and digital modeling technology, and discloses a method and apparatus for establishing a landscape model based on data fusion technology. The method includes the following steps: collecting original point cloud data and images of the site; extracting key growth morphology parameters through data registration, semantic segmentation, and individual vegetation segmentation; constructing a multi-dimensional quantitative evaluation model of the landscape's ecology and aesthetics based on these parameters; transforming the design problem into a multi-objective optimization mathematical model and solving it to generate a Pareto optimal solution set; finally, converting the specific design scheme selected from the solution set into a parametric building information model and integrating it with a digital terrain model to generate an interactive three-dimensional integrated landscape model. This invention can objectively and efficiently generate optimized design schemes that take into account both ecological and aesthetic values, automating the design evaluation and optimization adjustment process, and improving the efficiency and optimization level of design scheme generation.

This application discloses a collaborative training data generation method and electronic device for tuning problems, comprising the following steps: filtering the input code description text to obtain input data; injecting problem data into the input data to generate first adversarial sample data containing the problem data; calculating its gradient information and perturbation magnitude, and obtaining second adversarial sample data through tuning; designing a shared encoder based on the second adversarial sample data to obtain the features of the problem data and normal code data; separating the two in the feature space; prompting the shared encoder to learn based on the separated features through feature comparison, and finally obtaining the model generated from the code training data; designing an evaluation index to judge whether the model's generation results are correct and stable in the problem data injection scenario, thereby completing the model training for the code training data generation. This method improves the generalization and robustness of large language models when dealing with practical problems.

The application relates to a method and device for evaluating the design of an aero-engine fuel system and an oil system. The method comprises the following steps: obtaining system design parameters, system operation data and system coupling logic information of each system associated with the fuel system and the oil system, and operation associated information of the aero-engine, and constructing system simulation models of each system; then performing model association processing on the system simulation models to obtain a fuel-oil simulation model, simulating the operation process of the fuel system and the oil system through the fuel-oil simulation model, obtaining simulation operation results, identifying abnormal information between the fuel system and the oil system through a performance evaluation strategy, comprehensively evaluating the fuel system and the oil system to obtain evaluation results. The method can improve the comprehensiveness and accuracy of the evaluation of the fuel system and the oil system.

The invention discloses a nuclear power plant structural mechanical analysis method and device.Modeling software and analysis software are used in the method, model data in the modeling software are model data with components as units, and model data in the analysis software are model data with components as units. The method comprises the following steps: converting a model in modeling software into a shell element model and inputting the shell element model into analysis software; performing finite element analysis on the shell element model in analysis software to obtain a mechanical analysis result; and returning the mechanical analysis result to the modeling software through a data returning interface. According to the method, independent re-modeling of analysis software is avoided, the model data utilization rate is greatly improved, in addition, the calculation and analysis result of the analysis software can also be reversely input into modeling software and directly used for preliminary design evaluation and iterative optimization of the factory building structure, the analysis efficiency is greatly improved, the construction period is shortened, and labor time is saved.

The invention discloses a road route design evaluation system based on data analysis, which relates to the technical field of route design, and comprises the following steps: converting a natural language into a target vector, outputting current evaluation data based on historical design parameter data and operation effect data, inputting the target vector into a mapping relation model to generate a design parameter candidate set, according to the method, a forward modeling and reverse modeling bi-directional coupling mechanism is constructed, design parameters are automatically generated from a target vector, the design parameters are automatically generated, the design parameters are automatically generated, and the design precision is greatly improved by constructing a forward modeling and reverse modeling bi-directional coupling mechanism, so that the design precision is greatly improved, and the design efficiency is improved. And multi-round optimization iteration is realized through error feedback, so that the suitability of a design result to a user target is improved. Compared with a traditional passive evaluation process, the method has the advantages of target driving, closed-loop optimization and adaptive adjustment, the intelligent degree and multi-target consistency of route design are remarkably improved, and high practicability and technical progress are achieved.

The application provides an optimization design evaluation method of a gilled welding drum based on a parameterized model, and belongs to the technical field of aero-engines. The method comprises the following steps: establishing a drum parameterized mathematical model, and determining a drum stress expression; determining a dangerous position of the drum under a maximum working speed, and determining a cross-section average stress of the dangerous position based on the stress expression; determining a residual strength reserve coefficient of the drum based on an initial defect for a welding position, and determining a stress reserve coefficient of the welding position; obtaining a minimum self-supporting radius to drum mean diameter ratio of two disc wheels connected with the drum for a maximum stress position; determining a stress reserve coefficient of the maximum stress position when the ratio does not satisfy a preset condition; and optimizing design of drum structure parameters with the lightest drum weight as an objective function, and the residual strength reserve coefficient and the stress reserve coefficient not exceeding material performance as constraint conditions. The application establishes a complete evaluation system, shortens a design cycle, and improves evaluation accuracy.

The application relates to the field of computer-aided design and visual computing technology, and provides a visual communication design evaluation system and method based on data analysis. The method comprises the following steps: obtaining original design data, extracting a spatial layout feature matrix, a color distribution feature vector and a semantic content feature set; calling a design specification knowledge base based on design purpose information; performing simulation attention distribution analysis and design compliance analysis to generate corresponding features; constructing a communication efficiency prediction model to generate a comprehensive communication efficiency score and an initial design evaluation report; performing joint analysis of interference effects to obtain a comprehensive interference effect quantitative evaluation result; based on the result, optimizing and correcting the efficiency of the initial design evaluation report, and outputting a final design evaluation report integrating spatial layout and visual attribute optimization suggestions. The application accurately quantifies the interference effect through joint analysis of spatial layout and semantic attributes, thereby improving the accuracy and reliability of design communication efficiency evaluation.

The application relates to an artificial intelligence-based heating ventilation design evaluation method, device and computer equipment. The method comprises the following steps: acquiring a heating ventilation design image according to a heating ventilation model, the heating ventilation design image comprising at least one heating ventilation object, inputting the heating ventilation design image into a preset neural network, and performing design relationship identification and evaluation on the heating ventilation object to obtain an identification evaluation result, so that the heating ventilation model can be adjusted according to the identification evaluation result, and the heating ventilation model does not need to be adjusted by relying on artificial experience, so that the adjustment efficiency is high and accurate.

The present application relates to the technical field of tunnel design evaluation, and specifically relates to a surrounding rock four-dimensional applicability evaluation method for tunnel design, which comprises the following steps: S1, a three-dimensional geological model of surrounding rock is established, and the three-dimensional geological model is divided into a plurality of four-dimensional space-time topological geological partitions; S2, a physical information neural operator coupling model is constructed; S3, chaotic instability characteristics of surrounding rock are quantitatively identified and disaster warning is performed; S4, a stratum applicability dynamic evaluation system is constructed, and in combination with Monte Carlo uncertainty propagation analysis, probability distribution characteristics of a comprehensive index of stratum design applicability of each partition are determined; S5, a hierarchical determination is performed with the comprehensive index of applicability expectation value and the chaotic instability index as double control thresholds, a surrounding rock stratum applicability four-dimensional partition result and a three-dimensional visualized cloud chart are generated; the problems of static homogeneity, missing physical constraints, insufficient nonlinear instability criteria, disconnection with survey and design processes and difficulty in realizing four-dimensional dynamic precise evaluation of the existing tunnel surrounding rock evaluation method are solved.

The present invention addresses the problems of: providing a design proposal system capable of proposing, in a short time and at a low cost, the selection of a design that matches information from a user and that takes into consideration the feasibility of the proposal itself and the actual use environment; and providing a computer program for causing a computer to function as a design proposal system capable of proposing, in a short time and at a low cost, the selection of a design that matches information from a user and that takes into consideration the feasibility of the proposal itself and the actual use environment. As a solution, a design proposal system for proposing a design to a user is provided, the design proposal system comprising: an information acquisition unit that acquires information related to a design desired by the user; an information analysis unit that analyzes the acquired information; a design extraction unit that, on the basis of the analysis result of the information analysis unit, establishes one or more concepts, and extracts a design matching each concept; a design evaluation unit that evaluates the design extracted for each concept; and a design proposal unit that proposes a design to the user on the basis of the evaluation.

The invention discloses a highway engineering route design evaluation method and system, and relates to the field of traffic, and the method comprises the steps: enabling data of each dimension in design vectors of all known routes to form a dimension set; constructing a spatial index of the dimension set by using a KD tree, carrying out k-nearest neighbor query on the spatial index through a nearest neighbor search algorithm, obtaining k nearest neighbor points of each data point, and obtaining a k-nearest neighbor dimension set X; according to the k-neighbor dimension set X, establishing a neighborhood relation graph between the data points by calculating the distance between the data points; according to the neighborhood relation graph, constructing a Laplacian matrix, and solving eigenvalues and eigenvectors of the Laplacian matrix; mapping the original k-neighbor dimension set X to a low-dimensional space according to the feature values and the feature vectors; performing clustering analysis on the dimension set Z after dimension reduction, and evaluating the to-be-evaluated route according to a clustering analysis result; aiming at large design evaluation calculation amount in the prior art, the calculation efficiency is improved.