757 results about "Urban planning" patented technology

The invention provides a business vitality prediction and business district evaluation method based on multi-modal feature fusion, and relates to the technical field of spatial data analysis, and the method comprises the steps: obtaining business POI data and time sequence trajectory data of a target area, extracting the score and emotion features of user comments, and calculating the pedestrian flow distribution based on the time sequence trajectory data; then inputting the features into a recurrent neural network to predict a commercial vitality time sequence, constructing POI data into a knowledge graph, and constructing and optimizing a network reachability matrix in combination with position information and human traffic; and finally, dividing a target region by using a Louvain algorithm, fusing multi-dimensional features by edge computing nodes of each sub-region, dynamically adjusting the weight of an evaluation index through reinforcement learning, and outputting a commercial service evaluation result. By fusing multi-source data and a deep learning method, the life circle business service quality can be evaluated more accurately and comprehensively, and decision support is provided for urban planning and business development.

The invention relates to the technical field of geographic information systems, in particular to a GIS-based urban land planning analysis method and system, and aims to construct a multi-scale space-time cube model by integrating remote sensing, historical planning, mobile terminals and social media data, generate standardized urban temporary land data and improve the urban land planning analysis efficiency. Adaptive feature extraction is adopted to identify temporary land, a hierarchical classification system is established, abnormal changes are monitored through a time sequence model, an association diagram of the temporary land and an urban function network is constructed, an interaction relation is analyzed, finally, differentiated urban planning optimization suggestions are proposed, efficient configuration and management of urban land resources are assisted, and through fusion of multi-source data, the urban planning optimization suggestions are optimized. Multi-dimensional cognition of space, time, functions and relations is achieved, and the understanding depth of temporary land is fundamentally improved.

The invention provides a multi-modal remote sensing and knowledge graph-based urban planning decision-making method and system, and the method comprises the steps: integrating multi-source heterogeneous data, achieving the feature alignment and fusion of an optical image and SAR data in a satellite remote sensing image through a deep learning technology, and generating an urban ground feature feature vector; associating the urban ground feature feature vector with an urban planning policy database, outputting a structured early warning report of an illegal construction early warning event set and a policy compliance label, and forming a dynamic policy constraint condition for subsequent multi-objective optimization; processing historical traffic flow data based on the dynamic graph model, and outputting a time-space distribution prediction result of future traffic conditions; and generating a Pareto optimal city planning scheme by combining multi-objective optimization with a spatial-temporal distribution prediction result of a future traffic condition. According to the method, high-precision urban surface feature classification, real-time violation extension early warning and traffic flow accurate prediction are realized through multi-modal remote sensing data fusion and a space-time knowledge graph technology, and multi-target optimization and digital twinborn verification are combined, so that the planning efficiency is improved, and extension applications such as carbon neutralization are supported.

The invention discloses a mobile robot positioning and navigation method based on laser SLAM (Simultaneous Localization and Mapping). The method relates to the fields of machine learning, automatic driving, computer vision and the like. Aiming at the balance of real-time performance and calculation efficiency, the method comprises the following steps: firstly, tracking and estimating a motion track of a sensor by using laser radar data in real time, and fusing LiDAR and IMU; secondly, selecting a key frame and expressing the key frame by using a neural network implicit scene; adjusting parameters represented by a key frame pose and a neural scene through joint optimization to minimize a loss function; and finally, dynamically adjusting the loss function margin of laser radar rays by adopting a JS dynamic margin loss function, and converting an implicit neural representation three-dimensional scene into an explicit three-dimensional network model, thereby facilitating visualization, evaluation and use. Compared with other methods, the method has the advantages that the method has continuous and fine scene modeling capability, has real-time performance of positioning and mapping, and can be expanded to the fields of automatic driving, urban planning and the like.

The invention discloses a smart city planning design method, and relates to the field of city planning, and the method comprises the steps: collecting monitoring data; determining two targets of land utilization rate maximization and traffic jam minimization according to the preprocessed monitoring data; an epsilon-constraint method is adopted to convert two targets of land utilization rate maximization and traffic jam minimization into a single-target optimization problem; solving a single-target optimization problem by adopting a swarm intelligence algorithm MOEAD to obtain a Pareto non-inferior solution set; performing clustering analysis on the Pareto non-inferior solution set by adopting a K-means clustering algorithm, and dividing the Pareto non-inferior solution set into K clusters according to a clustering result; and according to the preprocessed monitoring data, constructing a three-dimensional city information model by using a smart city CIM technology, mapping each solution in the representative solution set to a corresponding planning parameter in the three-dimensional city information model, and generating a corresponding city planning design scheme. The contradiction between the land utilization rate and the traffic efficiency in urban planning is balanced.

The invention provides a potential diffusion model-based building planning image generation method and system. The method comprises the steps of data preprocessing, potential diffusion model structure improvement, input condition optimization, model training, image generation and the like. The relevance between text description and architectural styles is enhanced by preprocessing data sets of architectural design images and urban planning images and introducing channel crossing and space crossing attention mechanisms. Meanwhile, an architectural style embedding vector, an architectural description text embedding vector and a geometric information embedding vector are combined as additional input conditions to ensure that the generated image contains complete information. In a model training process, a multi-scale strategy and depth separable convolution are adopted, so that the recognition capability and training efficiency of the model to a large scene are improved. The system comprises a data preprocessing module, a model optimization module, a model training module, an image generation module and the like, and can generate a high-resolution building image conforming to design specifications. The method and system can be widely applied to the fields of building design and urban planning, and design efficiency and accuracy are improved.

The invention discloses a remote sensing image open vocabulary segmentation method and system based on vision-language interaction. According to the method, the advantages of a multi-modal large language model and a semantic segmentation network based on a visual basic model are cooperatively utilized, language-pixel two-way mapping is taken as a core, five types of marks of images, texts, categories, objects and segmentation are introduced as carriers of cross-modal information, and three types of cross-modal fine-grained information interaction modules are taken as bridges, so that the cross-modal information interaction is realized. Bidirectional mapping and alignment of fine-grained information of the multi-modal large language model and the semantic segmentation network are realized, the open vocabulary segmentation capability of the semantic segmentation model is improved, and the method can adapt to different remote sensing scenes and category definitions. The method has the following advantages: the method has high performance, strong generalization ability and good expansibility, can provide any category of semantic segmentation maps for unlabeled target domain images based on instructions, and has high application value in the aspects of urban planning, map making, disaster response and the like.

The present invention discloses a city planning simulation system based on real-scene three-dimensional (3D) and relates to the technical field of city planning. The system comprises the following components: a data acquisition module, a real-scene three-dimensional (3D) and disaster simulation module, a comprehensive planning module and a comprehensive evaluation module. The present invention plans the optimal emergency evacuation route by utilizing a path planning algorithm and taking into account the area affected by the damaged infrastructure and the recovery time of the infrastructure, thereby not only ensuring the safety and feasibility of the evacuation route but also greatly improving the evacuation efficiency. At the same time, according to the emergency evacuation route planning results and the infrastructure resilience evaluation results, the type and layout of the rescue facilities are determined, the service scope and coverage of the rescue facilities are analyzed by a geographic information system, the layout of the rescue facilities is optimized, and it is ensured that the rescue resources can efficiently and accurately reach the disaster-stricken area.

The invention discloses a city planning information display method and system based on digital twinning, and relates to the technical field of city planning. Static data and dynamic data of a city are collected, a three-dimensional model of the city is constructed through the static data, and the dynamic data and the three-dimensional model are combined to construct a digital twinning model of the city; the method comprises the following steps: setting a random data generation pool to generate random data, importing the random data into a digital twinborn model, and monitoring and optimizing a chaos current situation in the digital twinborn model to obtain an optimization scheme; by constructing a public voting platform, public opinions are imported into city planning to obtain a final optimization scheme; according to the method, the digital twinborn model of the city is constructed, more random scenes are provided for city planning by using the random data generation pool, potential changes and uncertainty of the city are fully simulated, and in combination with public opinions, the perspectiveness and flexibility of the digital twinborn technology in the city planning are improved, and a new direction is brought to the city planning.

The invention provides an intelligent analysis method and system for territorial space planning data, and relates to the technical field of data processing, and the method comprises the steps: recognizing an overlapping region through comparative analysis; performing buffer area analysis on the geographic information data, the land utilization data and the urban planning data, and creating buffer areas for rivers, roads and protection areas to identify conflict areas; according to the overlapping region and the conflict region, a corresponding territorial space planning scheme is found through iterative search; performing pattern recognition on the territorial space planning scheme to obtain a planning risk assessment result; according to the planning risk assessment result, the risks are divided into different categories, and each risk is quantified to obtain a specific score of each risk category; and obtaining an overall risk assessment result of the whole territorial space planning scheme according to the scores of the various risks. According to the invention, the accuracy and efficiency of risk assessment can be improved.

The invention discloses an interactive sand table demonstration system based on artificial intelligence, and relates to the technical field of intelligent interactive sand table demonstration. Comprising a multi-mode perception module, a semantic intention recognition module, a three-dimensional simulation module, a decision feedback module and a visualization module. Accurate recognition and semantic analysis of a user instruction are realized by fusing various input modes such as voice, gestures and images; based on a knowledge graph and a deep learning model, user demands can be intelligently understood, and a three-dimensional sand table is driven to carry out dynamic interactive demonstration. The situation adaptation module automatically adjusts the sand table scene according to the environment and the demonstration progress, and the reality sense and immersion sense of demonstration are improved; the decision feedback module generates demonstration results and strategy suggestions in real time, and supports multi-dimensional and intelligent interactive experience; the system is widely applied to the fields of emergency drilling, military deduction, urban planning, educational training and the like, and the intelligent level and the operation convenience of sand table demonstration are remarkably improved.

The invention relates to the technical field of urban planning, in particular to an industrial space suitability optimization method and system, and the method comprises the steps: collecting geographic information data, industrial data, industrial service related data, enterprise information and infrastructure data as a multi-source data set, associating the multi-source data set with geographic space coordinates, and inputting the geographic space coordinates into a database; the adjusted weight coefficient is applied to the LSTM-ARIMA hybrid model, and updated future industry prediction data is obtained; generating optimized industrial land layout scheme data based on a preset parametric modeling rule; determining planning scale data selected by a user, and obtaining a unified database associated with cross-level data; and comparing the land utilization change condition and the enterprise activity state data with data in the unified database, and when it is detected that data updating lag exists, updating the latest data after verification and prediction filling to the unified database. According to the invention, the adaptability and the intelligent level of urban industrial space planning can be improved.

The invention discloses a new quality productivity space analysis method based on machine learning, relates to the technical field of urban planning, and constructs a new quality productivity space index system, constructs a plurality of machine learning models for optimization, and provides a new quality productivity space analysis method based on machine learning. A machine learning model with the best prediction and generalization effect is selected to analyze the influence of each element on the new quality productivity space, an SHAP model is used for explaining and analyzing, and an SHAP value explaining mechanism for calculating the marginal contribution degree of each feature based on the Shapley value theory is introduced; the contribution degree of key indexes such as enterprise facility density and night light intensity to new quality productivity space distribution is quantitatively analyzed, and collaborative optimization of a machine learning model in prediction precision and interpretability is achieved; and in combination with spatial visualization analysis, a priority intervention basis is provided for urban planning, and finally, accurate quantitative analysis of a nonlinear effect and an element interaction effect is realized.

The invention discloses an urban blue-green space microclimate prediction system and method based on AI fusion. The method comprises the following steps of: 1, acquiring field microclimate measured data through linkage of a portable weather station and a GPS (Global Positioning System); 2, utilizing a machine learning downscaling algorithm and a deep learning semantic segmentation technology to extract high-resolution land surface temperature and urban land surface coverage classification data from the remote sensing image; 3, constructing a time-space aligned multi-modal GIS data set, and constructing a high-precision microclimate prediction model by using an ensemble learning algorithm; and 4, introducing an SHAP interpretability framework, carrying out deep analysis on the model, and quantifying the contribution degree of various environmental elements to a microclimate prediction result and the complex nonlinear influence of the contribution degree. According to the method, unprecedented high-precision and explainable scientific decision support can be provided for formulating urban planning, landscape design and thermal environment mitigation strategies, and development of healthy, sustainable and climate-flexible cities is powerfully promoted.

The invention relates to an improved NSGA-III-based multi-target geographic site selection optimization method and system, belongs to the technical field of optimization in business management and resource planning, and particularly relates to resource allocation and site selection decision making by using a calculation model. The technology aims to solve the problems of slow scheme convergence, non-uniform solution set distribution and low calculation efficiency when multi-target site selection is carried out under limited resources. According to the scheme, geographic space data is preprocessed, and an initial population representing different site selection schemes is generated; carrying out optimization iteration by adopting an improved NSGA-III algorithm, and calculating a plurality of objective functions such as coverage rate, normalized population density and medical service accessibility; and performing individual selection and population updating by utilizing improved reference point generation and vertical distance measurement. The method is mainly used for improving the efficiency and effect of commercial and municipal decisions such as urban planning, medical resource configuration, energy station layout and logistics network optimization.

The invention discloses a building roof elevation extraction method and system based on city modeling, and the method comprises the steps: S1, point cloud data and image data fusion registration: extracting data features, and carrying out alignment registration; s2, roof denoising and boundary optimization: identifying interference information, extracting a roof boundary, and generating a roof digital surface model through interpolation; s3, roof elevation extraction: for a flat roof, extracting the top elevation of the flat roof through a plane fitting method; for the slope top roof, extracting the top elevation of the slope top roof through an extreme point detection method; and extracting the top elevation of the roofs except the flat roofs and the slope roofs through a point cloud clustering method. According to the scheme, the roof elevation can be rapidly and accurately extracted, and high-precision three-dimensional data support is provided for urban planning, energy assessment and disaster emergency; the problems that in the prior art, roof elevation extraction efficiency is low, complex roof structure recognition precision is insufficient, and multi-source data fusion is difficult are solved.

The invention discloses a remote sensing image segmentation method and system based on a high-similarity transmission attention mechanism. The method comprises the steps that a high-similarity transmission attention feature extraction network is constructed, multi-scale local features are extracted through preprocessing and a local exploration block, details are reserved in combination with jump connection, and high-similarity features are screened through an attention module; the features are fused with original features to obtain enhanced features; performing multi-scale up-sampling on the enhanced features to recover spatial information, optimizing details by combining coding features, and realizing model training by combining cross entropy and Dice loss; and inputting a target remote sensing image needing to be processed into the optimized model, outputting a segmentation mask image with the same size as the target input remote sensing image, and marking regions of different surface feature categories. According to the invention, the segmentation precision in a complex scene can be obviously improved; the generalization ability of the model is enhanced; the method provides powerful technical support for automatic processing of remote sensing images, and is suitable for practical applications such as urban planning and environment monitoring.

The invention discloses a precise urban near-surface fine wind field and pollutant concentration simulation system. The system comprises a data acquisition module, a wind field simulation module, a pollutant diffusion model module and a visualization module. The data acquisition module acquires comprehensive and accurate meteorological and geographical information through various sensors, GIS integration and data transmission processing. The wind field simulation module is based on a fluid mechanics theory, adopts a numerical model and an algorithm, considers influences such as an urban heat island effect, and realizes high-precision simulation of a near-surface wind field. The pollutant diffusion model simulates pollutant diffusion by applying a mathematical model and a proper calculation method in combination with wind field and meteorological data and the like. The visualization module converts simulation results and generates various visual graphs such as map views and time series diagrams, and is further provided with a user interaction interface and an analysis and prediction tool. The system can accurately simulate urban near-surface wind field and pollutant concentration, and provides scientific basis and powerful support for urban planning, environment management and decision making.

The invention belongs to the technical field of urban planning, and discloses an urban inland inundation toughness evaluation method and related equipment, rainfall event characteristic parameters are obtained through obtaining and analyzing rainfall early warning information, dynamic inland inundation toughness evaluation index weights are generated according to the parameters and a preset weight adjustment rule, and evaluation is executed according to the dynamic inland inundation toughness evaluation index weights. And finally, outputting an evaluation result containing weak link identification information, thereby effectively solving the problems of weight staticization and homogenization in the existing evaluation method. The evaluation index weight can be dynamically adjusted according to rainfall event characteristics and urban spatial heterogeneity, so that accurate evaluation of urban waterlogging toughness is realized, weak links are effectively identified, and a scientific basis is provided for accurate scheduling of emergency resources and effective implementation of disaster prevention measures.

The invention relates to the technical field of urban planning, and particularly discloses an urban planning construction land management and control system based on big data, and the system comprises the steps: obtaining geological environment, landform, engineering construction and human activity data through multi-source data collection; multi-source data fusion analysis is adopted to construct a construction land comprehensive evaluation field including geological stability, engineering suitability and environmental bearing capacity; a development suitability partition is generated based on a density peak value spatial clustering method; updating the development suitability level by dynamically monitoring the verification process; according to the method, accurate analysis and early warning of the three-dimensional deformation field are realized, and scientificity and safety of urban planning in a complex geological environment are improved.

The invention discloses a data processing system and method for three-dimensional real estate surveying and mapping, and relates to the technical field of intelligent surveying and mapping, and the system comprises a multi-source data fusion module, a model generation module, a spatial relationship analysis module, an efficient rendering module and a data security module. The multi-source data fusion module converts the original surveying and mapping data in different formats into a unified three-dimensional point cloud data set; the model generation module generates a parameterized three-dimensional building model based on the point cloud data; the spatial relation analysis module constructs a relation graph of the building model and generates a surveying and mapping index report; the efficient rendering module processes large-scale three-dimensional data and generates an interactive three-dimensional scene; and the data security module controls the data access authority and generates an operation log. According to the method, the processing efficiency and precision of the three-dimensional real estate surveying and mapping data are improved, efficient analysis and visualization of large-scale three-dimensional data are realized, the security of sensitive data is ensured, and advanced technical support is provided for modern city planning, real estate management and real estate development.

The invention discloses an urban rail transit station site selection multi-objective optimization method and a related device, and belongs to the crossing field of urban planning and traffic engineering, and the method comprises the following steps: according to preprocessed urban road network data, screening crossing points of urban three-level roads and roads above the three-level roads as candidate stations; the coordinates of the candidate sites are coded; based on the preprocessed crowd travel origin and destination data, POI data, building data and land utilization data, quantifying the service people flow, facility accessibility and land development intensity of each candidate site, and forming a feature matrix of each candidate site; and constructing a multi-target traffic station site selection model, screening candidate stations meeting distance constraints through a greedy search algorithm according to the feature matrix, inputting the candidate stations to NSGA-II, and solving a multi-target optimization function of the multi-target traffic station site selection model to obtain an optimal planning result. The method can solve the problems that in the prior art, the target is single during site selection, and the inter-site distance constraint is not considered.

The invention discloses an intelligent city planning method and system based on multi-source remote sensing data fusion, and particularly relates to the technical field of city planning, and the method comprises the steps: S1, region division: dividing a planning region into M dynamic management grids based on GIS geographic coordinates and city function zoning data, carrying out the auxiliary recognition of topographic relief and building height through LiDAR point cloud data, and adjusting the boundary of the grids, establishing a bidirectional mapping relation between the grid and the multi-source sensing equipment; s2, multi-source data acquisition: constructing a city holographic data set through global coverage and a multi-modal sensing technology, acquiring target city data in real time, then executing multi-stage cleaning and space-time alignment, and performing normalization operation on each layer of data by adopting a standardized processing mode to obtain city data; according to the invention, an air-sky-ground-network global sensing network and a multi-level space-time grid framework are constructed, satellite remote sensing, unmanned aerial vehicle point cloud, ground sensors and urban operation data are deeply fused, and the limitation of single-source data of a traditional system is broken through.

The invention relates to the field of intelligent city planning, and discloses a street space quality intelligent evaluation and image generation method and system based on deep learning, and the method specifically comprises the following steps: movably collecting a street space image, and recording the geographic position information; performing perspective correction and multi-view image segmentation on the acquired street image data, and performing spatial matching with geographical location information to obtain a fused image database; and performing semantic segmentation on the image in the fused image database based on a deep learning model, calculating objective and subjective visual perception indexes and facility function indexes of the image, and generating a street space quality evaluation result. The method solves the problems that in the prior art, evaluation dimensions are limited, and an automatic response generation mechanism is lacked, and has the advantages of being intelligent, efficient and comprehensive in subjective and objective evaluation.

The invention discloses an urban street land fine division method and system based on deep learning, and belongs to the field of geographic information processing. The method comprises the following steps: firstly, collecting remote sensing image data, building space form data, business form POI data and urban land data of a case city district, extracting various kinds of information, converting the information into two-dimensional plane image format data, and carrying out rasterization and data enhancement processing; then training the land use division convolutional neural network deep learning model through a grid translation window method and a grid land use function judgment rule, performing rasterization function judgment on urban land use in a target area, dividing grid boundaries through a watershed method, and finally checking and correcting a result to obtain a target urban land use function judgment result. And obtaining a final result of land division of the target district. According to the method, the internal land of the urban land street can be finely divided, automatic division and function judgment of the urban land are realized, and digital and intelligent application conversion of urban planning work is promoted.

The invention relates to a positioning device for urban planning topographic survey, and relates to the technical field of topographic survey equipment, the positioning device comprises a mounting body, a mounting plate, a mounting assembly, a leveling assembly and a locking assembly; a supporting telescopic rod and a metering telescopic rod are arranged at the bottom of the mounting body; the number of the supporting telescopic rods is at least three, and the fixed ends of the supporting telescopic rods are hinged to the installation body. The fixed end of the metering telescopic rod is fixedly connected with the mounting body; the surveying instrument is rotationally arranged on the mounting plate; the mounting assembly is arranged on the mounting body and is used for mounting the mounting plate on the mounting body; the leveling assembly is arranged on the mounting body and is used for enabling the surveying instrument to keep a horizontal state in a self-adaptive manner; the locking assembly is arranged on the surveying instrument and used for locking the surveying instrument after the surveying instrument is in the horizontal state. According to the invention, landform survey can be conveniently carried out on a city.

The invention relates to the technical field of building digitization, in particular to a public service facility planning method and system based on population prediction. The planning method comprises the following steps: dividing residences in an object area into a plurality of residential areas, and predicting population scale data and population structure data of each residential area; determining the predicted number of people of each age group in each residential area within the preset age limit, and calculating the average value of the activity ability of each residential area in each year within the preset age limit; and determining the walking limit distance of the target group in each residential area in each year within a preset age limit according to the activity capability mean value, and taking the minimum value of the walking limit distance of each residential area within the preset age limit as a reference limit value. And determining the location of the public service facility in the object area, so that the distance value from each residential area in the object area to the location is smaller than or equal to the corresponding reference limit value. The method can improve the overall quality of urban planning, and has positive significance for saving social resources.

According to the cold region city emotion perception evaluation and measurement method, a cold region city is selected as a research object, and physiological signals and subjective scores are comprehensively considered; street view images are scored by training the street view perception model, perception of the street view images is realized, physiological signals and subjective scores are combined to realize comprehensive evaluation of corresponding areas of the cold region city, and a comprehensive evaluation result is less subject to subjective influence and is stable; the method can analyze the influence of the winter street space of the cold region city on the residential emotion perception, accurately measure the quality of the cold region city street space influencing the residential emotion, has the advantages of high efficiency and easy popularization and application, can be widely applied to the field of urban planning living street space quality investigation and measurement, and has a wide application prospect. And a method and a basis are provided for cold region city planning street space optimization practice.

The invention relates to the technical field of urban planning, and particularly provides an intelligent site selection method and system based on a spatio-temporal data platform, and the method comprises the steps: collecting multi-source spatio-temporal data of key industry categories of a target region, constructing an enterprise demand feature set based on the multi-source spatio-temporal data, and building a quantitative demand standard based on the feature set; constructing an industrial ecology adaptation model based on the current industrial basic data of the target area, calculating the matching degree between the feature set and the industrial ecology of the target area through the industrial ecology adaptation model, and outputting candidate parks according to the matching degree by taking industrial ecology clustering as a target; establishing a multi-element adaptation relationship between the target enterprise and the candidate parks based on the quantitative demand standard, performing matching verification through a multi-dimensional compliance verification unit, and removing parks which do not meet the constraint condition of the quantitative demand standard; and based on the verification result, outputting a site selection scheme, finally realizing high matching of enterprise demands and public resources, improving site selection efficiency and quality, and assisting sustainable development of regional industries.

The invention provides a multi-conditional constraint fusion generation method and system for generating a planning intention graph. The method belongs to the technical field of urban planning and artificial intelligence crossing. The method comprises the following steps: acquiring sample data containing different territorial and different types of territorial space intention graphs, and cutting a planning graph sample into image segments by using an image cutting technology according to the sample data; generating a detailed description for each image segment by means of a visual model; refining the detailed description of the generated image segment by using a large language model, generating a standardized label group suitable for model training, and forming a multi-modal sample library containing image-text pairs as data to be analyzed; based on the primary screening and secondary screening evaluation results, the model parameters and the control conditions are adaptively adjusted, so that the model can continuously optimize the generation effect according to different design requirements and feedback information, and the adaptability and the flexibility of the model are improved.