Fabricated building intelligent design system based on multi-source data analysis

Abstract

The invention discloses a fabricated building intelligent design system based on multi-source data analysis, and relates to the technical field of building engineering, and the method comprises the steps that an information collection module establishes equipment collection data to generate an initial data set; and the information labeling module performs position identification and position association on the initial data set. And the extraction processing module obtains a building demand, performs feature evaluation on the initial data set, and inputs a result to a decision result of the adaptive scale decision model. The fusion extraction module establishes and fuses features. The additional feature extraction module identifies an additional feature set. And the search module performs similar search to obtain building search results. And the evaluation selection module performs adaptive evaluation sorting on the search results based on the building requirements to complete the prefabricated building design. The technical problem that it is difficult to achieve efficient, high-quality and low-cost design meeting diversified requirements when the building scale and complexity are improved in existing building design is solved, and the technical effect of improving the quality, efficiency and comprehensive benefits of fabricated building design is achieved.

Description

Technical Field

[0001] The present application relates to the field of construction engineering technology, and in particular to an intelligent design system for prefabricated buildings based on multi-source data analysis. Background Art

[0002] In the field of architectural design, with the increase in building size and the increasing complexity of their appearance and structure, the workload for data analysis in areas such as building lighting, water supply and drainage, HVAC, energy conservation, and carbon emissions has increased significantly. The difficulty of building pipeline layout, mechanical and electrical installation, and fire protection has also increased significantly. Achieving reasonable and safe standards for the overall structural design of buildings, mechanical and electrical piping design, water supply and drainage, and HVAC design within the scope of national standards, while achieving efficient and low-cost building design, has become a key issue that needs to be addressed urgently. Traditional architectural design is often relatively one-sided and isolated, relying solely on specific design tools or limited empirical judgment. It lacks comprehensive overall planning for construction projects and lacks the integrated analysis and utilization of multi-source data. It is difficult to accurately grasp the needs and potential risks of various designs. There are also unscientific phenomena in resource allocation, resulting in a shortage of resources in some key links and an oversupply in others. The formulation of design plans is relatively rigid and single-minded, and cannot effectively adapt to the increasingly complex and changing actual conditions of construction projects.

[0003] At present, relevant technologies have problems such as insufficient data collection and association in architectural design, unscientific design decisions, poor feature fusion and search, and incomplete scheme evaluation and selection, which make it difficult to achieve efficient, high-quality, low-cost design that meets diverse needs as the scale and complexity of buildings increase. Summary of the Invention

[0004] The present application provides an intelligent design system for prefabricated buildings based on multi-source data analysis, adopts an information collection module to establish collection partitions including target areas and associated areas, and activates equipment including exploration vehicles, drones, and satellite image collection units to collect data to generate an initial data set. The information annotation module identifies and associates the location of the initial data set. The extraction and processing module obtains building requirements, evaluates the characteristics of the initial data set of the target area, and inputs the results into the decision results of the adaptive scale decision model. The fusion extraction module extracts and identifies the characteristics of the initial data set of the target area based on the decision results, establishes and fuses the features. The additional feature extraction module identifies the additional feature set of the characteristics of the initial data set of the associated area. The search module performs a similar search for building search results based on the feature fusion results and the additional feature set. The evaluation and selection module completes the prefabricated building design by adapting the evaluation and ranking of the search results based on the building requirements, realizing the optimization and intelligence of the entire process of building design from data collection to scheme evaluation and selection, and achieving the technical effect of improving the quality, efficiency and comprehensive benefits of prefabricated building design.

[0005] This application provides an intelligent design system for prefabricated buildings based on multi-source data analysis, including: An information collection module is used to establish collection partitions, which include target areas and associated areas, activate collection equipment to perform regional data collection in the collection partitions, and generate an initial data set. The collection equipment includes an exploration vehicle, an unmanned aerial vehicle, and a satellite image collection unit. An information annotation module is used to identify the location of the initial data set and establish location associations for the data. An extraction processing module is used to obtain the building requirements of the target building and perform feature evaluation on the initial data set corresponding to the target area. The feature evaluation results and building requirements are input into the adaptive scale decision model to establish an adaptive scale decision result. A fusion extraction module is used to use the adaptive scale decision result to The initial data set of the target area is subjected to feature extraction and identification, and a feature extraction and identification result is established. A multi-layer feature fusion framework is established based on location association and building requirements, and feature fusion is performed on the feature extraction and identification result based on the multi-layer feature fusion framework to establish a feature fusion result; an additional feature extraction module is provided, and the additional feature extraction module is used to perform feature identification on the initial data set corresponding to the associated area and establish an additional feature set; a search module is provided, and the search module is used to perform similarity search for building projects based on the feature fusion result and the additional feature set and establish a building search result; an evaluation and selection module is provided, and the evaluation and selection module is used to perform adaptive evaluation and ranking of the building search results based on the building requirements, and complete the prefabricated building design with the adaptive evaluation and ranking results.

[0006] The proposed intelligent design system for prefabricated buildings based on multi-source data analysis is designed to: First, the information collection module establishes collection partitions including target areas and associated areas, and activates equipment including exploration vehicles, drones, and satellite image acquisition units to collect data to generate an initial data set. The information annotation module identifies and associates the initial data set with locations. The extraction and processing module obtains building requirements, evaluates the features of the initial data set for the target area, and inputs the results into the decision results of the adaptive scale decision model. The fusion extraction module extracts and identifies the features of the initial data set for the target area based on the decision results, and establishes and fuses the features. The additional feature extraction module identifies additional feature sets for the features of the initial data set for the associated areas. The search module performs a similar search for building search results based on the feature fusion results and the additional feature set. The evaluation and selection module completes the prefabricated building design by adaptively evaluating and ranking the search results based on building requirements. This achieves the technical effect of improving the quality, efficiency, and overall benefits of prefabricated building design by optimizing and intelligentizing the entire process of building design, from data collection to scheme evaluation and selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0008] Figure 1 A schematic diagram of the structure of an intelligent design system for prefabricated buildings based on multi-source data analysis provided in an embodiment of the present application; Figure 2 Schematic diagram of the structure of the additional feature extraction module of the prefabricated building intelligent design system based on multi-source data analysis provided in an embodiment of the present application.

[0009] Explanation of the reference numerals: information collection module 10 , information labeling module 20 , extraction and processing module 30 , fusion extraction module 40 , additional feature extraction module 50 , search module 60 , evaluation and selection module 70 . DETAILED DESCRIPTION

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0011] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0012] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0013] The present application embodiment provides an intelligent design system for prefabricated buildings based on multi-source data analysis, such as Figure 1 As shown, the method includes: The information collection module 10 is used to establish collection zones, each comprising a target area and associated areas. The collection equipment, which includes exploration vehicles, drones, and satellite image acquisition units, is activated to collect regional data within the zones, generating an initial data set. Specifically, the information collection module 10 performs a factor analysis on the collection zones, identifying key information such as topography, geological conditions, and the surrounding environment of the target and associated areas. Using various collection techniques, the module acquires data from various aspects of the zones and analyzes the relationships and interactions between them. Based on the results of the factor analysis, the module determines collection zone information. This information includes information such as the target area, the delineation of associated areas, the collection sequence, and any required special collection methods (such as specific angle collection and intensified collection of key areas). This information guides the operation of the collection equipment and extracts and classifies key elements from the acquired collection zone information. Key elements refer to important factors that influence collection effectiveness, such as collection accuracy, collection range, and collection equipment type. Using a classification algorithm, the module groups zones with similar key elements into a single category. Based on the classification results and the characteristics of the zones, the module assigns the corresponding collection category.

[0014] The information annotation module 20 is used to identify the location of the initial dataset and establish location associations for the data. Specifically, the information annotation module 20 analyzes the initial dataset, identifying the location characteristics of the data, including key points such as specific geographic coordinates and regional affiliation. Using positioning and association technologies, it identifies the specific location identifiers of the data and analyzes the spatial and logical connections between them. Based on the analysis results, the location association information of the data is established. The location association information includes the relative positions between data points, the hierarchical relationship of the areas to which they belong, and possible special location association patterns (such as the association between the core area and the surrounding area, etc.), etc., which is intended to provide guidance for subsequent data processing and application. For example, if multiple data points are close to each other in space or have logical associations, such as belonging to different parts of the same building structure, or adjacent geographical terrain features, the information annotation module 20 will clarify this location association between them. By establishing location identification and location association, the information in the initial data set is no longer an isolated point, but forms a whole with spatial structure and logical relationship, which provides support for subsequent more in-depth data analysis and processing. For example, in an urban planning project, the initial data set contains information such as terrain, building distribution, etc. of different blocks. The information annotation module 20 will perform location identification for the relevant data points of each block, and then determine the location association between different blocks, such as which blocks are adjacent and which blocks functionally influence each other.

[0015] The extraction processing module 30 is used to obtain the building requirements of the target building, and perform feature evaluation on the initial data set corresponding to the target area, input the feature evaluation results and building requirements into the adaptive scale decision model, and establish an adaptive scale decision result. Specifically, the extraction processing module 30 conducts a comprehensive demand analysis on the target building, accurately identifies key factors such as building purpose, size, functional layout, etc., and uses professional analysis methods and techniques to extract the specific requirements of the target building, and analyzes the logical relationship and importance between the requirements. Based on this analysis result, the core points of the building requirements are clarified. The requirements cover the purpose of the building, such as residential, commercial or industrial use; the scale of the building, including the floor area, building area and number of floors; and the special requirements of the building, such as environmental protection standards, energy-saving requirements or unique design styles. After obtaining the building requirements, the extraction processing module 30 performs feature evaluation on the initial data set corresponding to the target area, It involves multiple aspects such as the assessment of geological stability, analysis of terrain complexity, and the impact of the surrounding environment on buildings, and conducts quantitative and qualitative evaluations of the characteristics. For geological stability, physical parameters such as the bearing capacity of the soil and the hardness of the rock are measured, and specific numerical quantifications are given. For example, the bearing capacity of the soil is measured in tons per square meter, and the complexity of the terrain is quantified by calculating the average value of the slope, the standard deviation of the undulation, and other indicators. The impact of the surrounding environment on the building, such as the noise level, can be expressed in decibels, and the duration of sunlight can be quantified in hours per day. The geological type is qualitatively classified as stable, relatively stable, unstable, etc. The terrain characteristics are described as flat, undulating, steep, etc. When evaluating, multiple relevant factors will be considered comprehensively. For example, when assessing geological stability, not only the physical parameters of soil and rock are considered, but also factors such as local geological history and whether it is located in an earthquake zone. For terrain complexity, in addition to direct slope and undulation measurements, its potential impact on the difficulty and cost of construction will also be considered. When evaluating the surrounding environment, noise, light, air quality, landscape and other aspects will be comprehensively considered to provide a comprehensive and accurate qualitative description and quantitative value. For example, for a construction project located in a mountainous area, the quantitative evaluation may include measuring the average slope of the hillside as 30 degrees, and the qualitative evaluation may be that the terrain is undulating and the construction difficulty is high.At the same time, the ambient noise level is quantified as 50 decibels and qualitatively assessed as relatively quiet. After completing the feature evaluation, the extraction and processing module 30 inputs the feature evaluation results and the acquired building requirements into the adaptive scale decision model. The model analyzes the input information and automatically adjusts and optimizes the decision scale and parameters. The adaptive scale decision model requires collecting a large amount of architectural design-related data, preprocessing and feature engineering the data, extracting key features and patterns, and constructing an initial model structure through a neural network. During the model training phase, the model is repeatedly trained and optimized using the preprocessed data. After multiple iterations and optimizations, the adaptive scale decision model is ultimately obtained. Finally, the extraction and processing module 30 establishes the adaptive scale decision results based on the model output. The results provide key guidance for subsequent design and processing, such as determining the basic scale and layout of the building, or selecting appropriate building materials and construction methods. For example, in a hospital construction project, the extraction and processing module 30 first determines the need for a hospital building with specific departments and bed numbers. It then performs a feature evaluation of the target area's geological conditions, surrounding transportation, and environment. After inputting these evaluation results and building requirements into the model, adaptive scaling decisions were made, including the building size, floor distribution, and location arrangement of special departments suitable for the hospital.

[0016] In one possible implementation, the extraction processing module 30 further includes: a result recognition unit, the result recognition unit being configured to call the preprocessing layer of the adaptive scale decision model, identify the feature evaluation results based on the preprocessing layer, and establish a mapping scale constraint for the initial data set corresponding to the target area. Specifically, the result recognition unit calls the preprocessing layer of the adaptive scale decision model to preliminarily organize and standardize the input feature evaluation results. Based on the preprocessing layer, the feature evaluation results are finely identified from multiple perspectives, such as feature size and attributes. For example, for building features, the size of the room area, the attributes of the building materials, and other aspects are considered to establish a mapping scale constraint for the initial data set corresponding to the target area. For example, the building height in a certain area cannot exceed a specific value to meet local planning requirements.

[0017] A network synchronization unit is used to synchronize feature evaluation results and building requirements with the scale importance analysis network of the adaptive scale decision model, perform scale importance analysis based on image content and analysis tasks, and establish scale importance analysis results. Specifically, the network synchronization unit transmits and analyzes information, synchronizing feature evaluation results and building requirements with the scale importance analysis network of the adaptive scale decision model. The analysis network comprehensively considers the image content of the building, such as whether the overall appearance is aesthetically pleasing and coordinated, as well as specific analysis tasks, such as whether it meets the pedestrian flow requirements of commercial buildings or the lighting requirements of residential buildings. Through analysis and calculation, it establishes scale importance analysis results, clearly indicating which features and requirements occupy a more critical position in the overall building design.

[0018] A decision result establishment unit is used to establish an adaptive scale decision result based on the mapping scale constraint and the scale importance analysis results. Specifically, the decision result establishment unit uses the results obtained by the previous two units, namely the mapping scale constraint and the scale importance analysis results, combined with various constraints and the order of importance, to perform calculations and trade-offs to obtain an adaptive scale decision result that adapts to the specific situation. For example, to determine the floor distribution of an office building, the area of each floor, and the layout of public facilities, etc., taking a school construction project as an example, the result recognition unit determines the mapping scale constraints of the classroom area and playground size with the initial data set, the network synchronization unit analyzes the scale importance of teaching functions and student activity needs, and the decision result establishment unit derives the specific planning of the teaching building and sports facilities based on this.

[0019] The fusion extraction module 40 is configured to perform feature extraction and recognition on the initial dataset of the target area using the adaptive scale decision result, generate a feature extraction and recognition result, and establish a multi-layer feature fusion framework based on location associations and building requirements. Based on the multi-layer feature fusion framework, the feature extraction and recognition results are then subjected to feature fusion to generate a feature fusion result. Specifically, the fusion extraction module 40 obtains the adaptive scale decision result and, based on the decision result, performs feature extraction and recognition operations on the initial dataset of the target area, filtering out key features relevant to the decision result from the dataset. For example, if the decision result emphasizes the building's lighting requirements, the module extracts features related to lighting, such as window size and orientation, and generates a feature extraction and recognition result. Based on the established location associations and the clear building requirements, a multi-layer feature fusion framework is constructed to organize and integrate features of different types and levels according to certain rules and logic. Based on the constructed multi-layer feature fusion framework, the previously extracted and recognized features are subjected to deep feature fusion, organically combining the previously scattered features to form a unified, comprehensive, and highly representative feature fusion result. For example, for a commercial building project, the building's exterior features (such as shape and color), interior space, and other features are combined to form a unified, comprehensive, and highly representative feature fusion result. Layout features (such as room size and channel width) and surrounding environment features (such as traffic flow and surrounding architectural style) are deeply integrated. By analyzing building needs and design goals, weights are determined for different features. Deep learning models are used to learn the potential relationships between these features, and the key features after fusion are automatically extracted. Clustering is performed based on the similarity of features. For example, features related to space utilization are clustered into one category, and this category of features is comprehensively considered to optimize the building design plan. Deep feature fusion requires selecting appropriate methods based on specific application scenarios and data characteristics, and combining professional knowledge and actual needs to achieve the best fusion effect and provide more comprehensive and accurate decision support for architectural design.

[0020] The additional feature extraction module 50 is used to perform feature recognition on the initial data set corresponding to the associated area and establish an additional feature set. Specifically, the additional feature extraction module 50 carries out a detailed feature analysis on the initial data set corresponding to the associated area, accurately identifies key points such as geographical features, socio-economic conditions, traffic conditions, etc., and uses professional analysis methods and techniques to extract each feature element in the data set, and analyzes the intrinsic correlation and interaction between them. Based on this analysis result, the scope of the additional features is clarified. The key elements of the acquired feature information are extracted and classified. The key elements refer to factors that have an important impact on the additional features, such as the significance of the features, the closeness of the association, etc. A scientific classification algorithm is used to classify features with similar key elements into one category. According to the classification results and the unique properties of the features, the corresponding additional feature categories are configured. Each additional feature category represents a set of features with the same or similar key elements.

[0021] In one possible implementation, Figure 2 As shown, the additional feature extraction module 50 further includes an attenuation coefficient establishment unit configured to establish an attenuation coefficient for the location distance effect of the associated region. Specifically, the attenuation coefficient establishment unit analyzes the degree of influence of the location distance factor on the associated region and establishes an attenuation coefficient for the location distance effect using a specific calculation method and model. The coefficient quantitatively reflects the trend that the influence gradually decreases with distance from the target region.

[0022] A first feature extraction result establishment unit is configured to extract economic activity and business layout features from the initial dataset corresponding to the associated region to establish a first feature extraction result. Specifically, the first feature extraction result establishment unit extracts features of economic activity and business layout from the initial dataset corresponding to the associated region, for example, analyzing the distribution of business types, business activity, and economic development trends within the region, and summarizes these extraction results to establish the first feature extraction result.

[0023] The second feature extraction result establishment unit is configured to extract traffic flow and accessibility features from the initial data set corresponding to the associated area to establish a second feature extraction result. Specifically, the second feature extraction result establishment unit extracts traffic flow and accessibility features, such as road traffic volume, public transportation station distribution and route density, and travel convenience between different locations, from the initial data set corresponding to the associated area, and then establishes the second feature extraction result.

[0024] A planning feature extraction unit is configured to extract planning features from the initial dataset corresponding to the associated area and generate a third feature extraction result. Specifically, the planning feature extraction unit mines planning features from the initial dataset corresponding to the associated area, including information on land use planning, urban functional zoning planning, and future development planning, to ultimately generate the third feature extraction result.

[0025] A population density feature extraction unit is configured to extract population density features from the initial dataset corresponding to the associated region to generate a fourth feature extraction result. Specifically, the population density feature extraction unit extracts features related to population density from the initial dataset corresponding to the associated region, such as statistics on the population size, population distribution, and population growth trends in different regions, thereby generating the fourth feature extraction result.

[0026] The additional feature set establishment unit is configured to compensate the first, second, third, and fourth feature extraction results based on the location distance impact attenuation coefficient to establish the additional feature set. Specifically, the additional feature set establishment unit compensates and adjusts the first, second, third, and fourth feature extraction results based on the previously established location distance impact attenuation coefficient. It comprehensively analyzes the importance of each feature extraction result and the impact of distance, and integrates the compensated results to establish a complete additional feature set. For example, in a building planning project in a city center, the attenuation coefficient establishment unit determines that the impact begins to significantly attenuate beyond 5 kilometers from the center. The first feature extraction result establishment unit determines that retail is the primary commercial sector within a 3-kilometer radius. The second feature extraction result establishment unit identifies high traffic volumes during peak hours on major roads. The planning feature extraction unit identifies plans for new commercial areas within the next five years. The population density feature extraction unit calculates differences in population density across different regions. Finally, the additional feature set establishment unit integrates these results to establish a comprehensive additional feature set, providing a richer reference for building planning.

[0027] The search module 60 is used to perform a similar search for building projects based on the feature fusion result and the additional feature set, and to establish a building search result. Specifically, the search module 60 obtains the feature fusion results and additional feature sets generated in the previous steps. The feature fusion results contain key feature information of the target area after in-depth processing and fusion, covering comprehensive characteristics of multiple aspects such as building needs, location associations, and scale decisions. The additional feature sets provide important supplementary information about the associated area, such as economic activities, traffic conditions, and population density. The search module 60 uses search algorithms and pattern matching techniques to convert the features into a series of search keywords, indicators, or feature vectors, and conducts a comprehensive search in the building project database, which stores information on building projects of various types, sizes, and characteristics. During the search process, the search module 60 carefully compares and matches the current feature information with the corresponding features of each building project in the database, considering multiple similarities, such as the similarity of the building's functional layout, the fit of the exterior style, and the matching of surrounding environmental characteristics. The module scores and ranks the similarity between each building project and the current feature. Finally, a building search result is established, screening out a group of building projects with high similarity and sorting them in descending order of similarity, providing a basis for subsequent evaluation and selection.

[0028] In one possible implementation, the search module 60 further includes: a perceptual search preference establishment unit, which is used to establish a context-aware search strategy based on the feature fusion results and the additional feature set. The context-aware search strategy is a perceptual search preference established based on the search user's project history data and common parameter feedback. Specifically, the perceptual search preference establishment unit obtains the feature fusion results and the additional feature set, conducts in-depth analysis to extract key elements and patterns, and then collects the search user's project history data, including the types of architectural projects that have been searched in the past, the features that are of interest, the choices made, etc. At the same time, the user's feedback on common parameters will also be obtained, such as preferences for specific architectural styles, sizes, cost budgets, etc. Based on the comprehensive analysis of the data, a context-aware search strategy is established. The strategy can fully take into account the user's personalized needs and search habits, thereby more accurately meeting the user's expectations.

[0029] The project similarity search establishment unit is configured to perform a similarity search for building projects using the context-aware retrieval strategy, feature fusion results, and additional feature sets. Specifically, the project similarity search establishment unit obtains the context-aware retrieval strategy generated by the perception search preference establishment unit, as well as the previously obtained feature fusion results and additional feature sets, and inputs this information into a specialized search algorithm to conduct an extensive and in-depth search within the database of building projects. During the search, the algorithm, based on the context-aware retrieval strategy, focuses on building projects that closely match the user's preferences. Combining the feature fusion results and additional feature sets, it comprehensively considers the similarities of building projects in terms of function, layout, and environment. Through complex calculations and comparisons, it finds the building project that most closely resembles the user's needs, completing the project similarity search. For example, for a user who frequently focuses on environmentally friendly residential buildings and prefers large bay designs, the perception search preference establishment unit will establish a retrieval strategy that focuses on environmentally friendly materials and spacious spaces based on their historical searches and feedback. Based on this strategy, the project similarity search establishment unit then searches the database for residential projects with similar environmental characteristics and spatial layouts, using the current feature fusion results and additional feature sets.

[0030] In one possible implementation, the search module 60 further includes: a database establishment module, which is used to obtain public data based on big data, establish data tags for the public data, and after performing data trust authentication, establish a first-layer database, establish digital communication with trusted three parties, and configure a data interaction channel with the trusted three parties, establish a second-layer database based on the data interaction channel, the second-layer database is an encrypted database, and a matching database is established with the first-layer database and the second-layer database. Based on the feature fusion results and the additional feature set, a similar search for building projects is performed in the matching database to establish building search results. Specifically, the database establishment module uses big data technology to obtain public data from data sources, including the Internet, public databases, industry reports, etc. After obtaining the public data, data labels are established for the data. The role of data labels is to mark key information such as the type, subject, and source of the data for subsequent classification and retrieval, and perform data trust authentication on the data. After ensuring the accuracy, completeness and reliability of the data, only the authenticated data has the authority to be entered into the database. After completing the trusted authentication, the first-level database is established. The database stores the screened and sorted public data, and establishes digital communication with trusted third parties. Trusted third parties are institutions or enterprises with authoritative data sources or professional data services. Data interaction channels with trusted third parties are configured, and data from trusted third parties are obtained through the channels. According to the data The data acquired through the interactive channel is used to establish a second-tier database, which is encrypted to ensure data security and privacy. The first and second-tier databases are combined to form a matching database. This database integrates data from multiple sources and types, forming a rich and comprehensive dataset. Based on the previously obtained feature fusion results and additional feature sets, similar searches for building projects are conducted within this matching database, and building search results are established through comparison. For example, when conducting a database search for a large commercial complex project in a city, the database establishment module first obtains a large amount of public urban planning data, establishes relevant tags, and performs trusted authentication. Then, through a data interaction channel established with a professional geographic information service provider, encrypted data for a specific area is obtained, which together form the matching database. Based on the project's feature fusion results and additional feature sets, commercial complex building projects of similar scale and function are searched in this database, providing reference and reference for the current project.

[0031] In one possible implementation, the search module 60 further includes: a feedback module, which is used to record the user's adaptation feedback on the adaptation evaluation ranking results, extract the adaptation reward coefficient for the same-direction search based on the recorded results, and configure a penalty factor for continuous rewards, punish and compensate the adaptation reward coefficient extraction result according to the penalty factor, generate search feedback based on the penalty compensation result, and optimize the search module based on the search feedback. Specifically, when users provide feedback on the results of the adaptive evaluation ranking, the feedback module records their reactions and comments in detail. Based on the recorded results, the feedback module extracts the adaptive reward coefficient for the same-direction search. It analyzes the user feedback, identifies positive feedback that aligns with the intended search direction, and extracts the corresponding reward coefficient from it. To avoid excessive bias or inaccuracy caused by continuous rewards, the feedback module configures a penalty factor for continuous rewards. Based on the penalty factor, it penalizes and compensates the previously extracted adaptive reward coefficient to achieve a balanced reward effect and ensure the fairness and accuracy of the search results. Based on the results of this penalty compensation, search feedback is generated. The search feedback includes an evaluation of the previous search process and suggestions for future search improvements. Based on the generated search feedback, the search module performs search optimization, such as adjusting search algorithm parameters, changing search weight settings, and updating search data sources, to improve the quality and accuracy of future search results and better meet user needs and expectations. For example, if a user repeatedly expresses satisfaction with a particular style of building, the feedback module extracts the corresponding reward coefficient, but due to the continuous feedback of the same style, a penalty factor is introduced for adjustment. The resulting search feedback will prompt the search module to focus more on this type of architectural style in subsequent searches, while also avoiding over-reliance on a single factor and achieving more optimized search results.

[0032] In one possible implementation, the search module 60 further includes: a system access module, which is used to read the access database content if the user provides an access database, and determine the basic search template, reconstruct the search module according to the reading results and the basic search template, and complete the similarity search of the construction project based on the reconstructed search module. Specifically, the system access module determines whether the user has provided an access database. If the user has provided one, it begins to read the contents of the access database. When reading the contents of the access database, it carefully analyzes and understands the data therein, extracts key information and features, and determines a basic search template. The basic search template may contain some default search conditions, parameter settings, and search logic. Based on the results of the access database read and the determined basic search template, the existing search module is reconstructed. The reconstruction process involves adjusting the search algorithm, modifying search parameters, reconfiguring the search priority, and other operations to make it better adapt to the newly accessed database and the user's specific needs. The task of similar search for architectural projects is performed based on the reconstructed search module. By applying the new search architecture and settings, a comprehensive and accurate search is performed in the database to find similar results for architectural projects that match the user's needs. For example, when a professional architectural designer provides an access database containing his past design cases and specific design requirements, the system access module reads the detailed information therein, such as specific building material usage preferences, unique spatial layout designs, etc., and reconstructs the search module based on the general basic search template. This allows the designer to accurately search for projects with similar styles and needs in a wider database of architectural projects, providing valuable references and inspiration for their new design work.

[0033] Evaluation and selection module 70 is used to evaluate and rank building search results based on building requirements, and complete the prefabricated building design based on the evaluation and ranking results. Specifically, evaluation and selection module 70 obtains detailed information about building requirements, including the building's purpose, scale, functional layout, cost budget, construction period, and other aspects. It then compares and analyzes each building search result against the building requirements, evaluating the degree of match between each search result and the requirements from multiple dimensions. For example, the module considers whether the architectural designs in the search results meet the actual use requirements in terms of function, whether the scale is consistent with expectations, and whether the cost is within the budget. Based on the evaluation results, the architectural search results are adaptively evaluated and ranked. The ranking is based on the degree of fit with the building requirements. The search results with higher fit are ranked higher. Based on the results of the adaptive evaluation ranking, the design of the prefabricated building is completed, including drawing inspiration and borrowing excellent design elements from the higher-ranked search results, or directly selecting the result that best meets the requirements as a design blueprint, and making necessary adjustments and optimizations based on actual conditions to ensure that the final prefabricated building design can meet the building requirements to the greatest extent. For example, for the prefabricated building design requirements of a factory building, the evaluation and selection module 70 will evaluate and rank the multiple factory building results found. If the building requirements emphasize space utilization and rapid construction, then in the ranking, those search results with spacious interior space and efficient construction plans will be ranked at the top. Based on the ranking results, the prefabricated building design of the factory building is completed to ensure that the design can both meet production requirements and be efficiently completed.

[0034] In one possible implementation, the evaluation and selection module 70 further includes an index establishment unit configured to establish a functional adaptability index, a benefit index, an environmental adaptability index, a compliance index, and a real-time feasibility index based on the building requirements. Specifically, after obtaining the building requirements, the index establishment unit analyzes these requirements and establishes a functional adaptability index based on the specific use of the building, such as residential, commercial, or industrial. This index measures the extent to which the building search results meet specific functions, such as residential living comfort and the rationality of the layout of commercial space. It also establishes a benefit index, including construction cost, operating cost, and potential economic benefits, taking into account factors such as the cost and benefit of the building project. It also establishes an environmental adaptability index based on the building's location and environmental conditions, such as climate and topography, to assess the environmental adaptability of the search results, such as energy efficiency and wind and earthquake resistance. It also establishes a compliance index based on relevant laws, regulations, and building codes to ensure that the search results comply with various regulations, such as fire protection requirements and building safety standards. It also establishes a real-time feasibility index based on current technical levels, construction conditions, and resource availability to determine the feasibility of the search results in actual operations, such as construction difficulty and material availability.

[0035] The adaptive evaluation ranking unit is used to configure adaptive weights for the functional adaptability index, benefit index, environmental adaptability index, compliance index, and real-time feasibility index, and evaluate the building search results using the adaptive weights, functional adaptability index, benefit index, environmental adaptability index, compliance index, and real-time feasibility index to complete the adaptive evaluation ranking. Specifically, the adaptive evaluation ranking unit configures adaptive weights for the functional adaptability index, benefit index, environmental adaptability index, compliance index, and real-time feasibility index based on the specific project context and key focus areas. For example, for a project emphasizing environmental protection and sustainable development, a higher weight may be assigned to the environmental adaptability index. Using the configured adaptive weights, combined with various specific indicators, a comprehensive evaluation of the building search results is performed, comprehensively considering the performance of each search result in terms of functional adaptability, benefit, environmental adaptability, compliance, and real-time feasibility. Through comparison, the building search results are ranked to complete the adaptive evaluation ranking, providing a clear basis for the final building design decision. For example, in a school building project located in an earthquake-prone area, the indicator establishment unit will focus on establishing compliance indicators and environmental adaptability indicators for earthquake resistance. The adaptive evaluation ranking unit will assign higher weights to earthquake resistance-related indicators, so that search results that perform well in this regard will be ranked higher.

[0036] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0037] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. The intelligent design system for prefabricated buildings based on multi-source data analysis is characterized by: The system comprises: An information acquisition module, which is used to establish acquisition partitions, each of which includes a target area and associated areas, activate acquisition equipment to perform regional data acquisition in the acquisition partitions, and generate an initial data set. The acquisition equipment includes an exploration vehicle, an unmanned aerial vehicle, and a satellite image acquisition unit; An information labeling module, which is used to identify the location of the initial data set and establish location association of the data; An extraction processing module is used to obtain the building requirements of the target building, perform feature evaluation on the initial data set corresponding to the target area, input the feature evaluation results and the building requirements into the adaptive scaling decision model, and establish an adaptive scaling decision result; A fusion extraction module is used to perform feature extraction and recognition on the initial data set of the target area based on the adaptive scale decision result, establish a feature extraction and recognition result, establish a multi-layer feature fusion framework based on location association and building requirements, perform feature fusion on the feature extraction and recognition result based on the multi-layer feature fusion framework, and establish a feature fusion result; An additional feature extraction module, the additional feature extraction module is used to perform feature recognition on the initial data set corresponding to the associated area and establish an additional feature set; A search module, the search module is used to perform a similar search for building projects based on the feature fusion result and the additional feature set, and establish a building search result; An evaluation and selection module is used to perform adaptive evaluation and sorting of building search results based on building requirements, and complete the prefabricated building design based on the adaptive evaluation and sorting results.

2. The intelligent design system for prefabricated buildings based on multi-source data analysis according to claim 1, characterized in that: The extraction processing module also includes: a result recognition unit, the result recognition unit being configured to call a preprocessing layer of the adaptive scale decision model, recognize the feature evaluation results based on the preprocessing layer, and establish a mapping scale constraint for an initial data set corresponding to a target area; A network synchronization unit is used to synchronize feature evaluation results and building requirements to a scale importance analysis network of the adaptive scale decision model, perform scale importance analysis based on image content and analysis tasks, and establish scale importance analysis results; The decision result establishing unit is used to establish an adaptive scale decision result according to the mapping scale constraint and the scale importance analysis result.

3. The intelligent design system for prefabricated buildings based on multi-source data analysis according to claim 1, characterized in that: The additional feature extraction module further includes: an attenuation coefficient establishing unit, the attenuation coefficient establishing unit being used to establish an attenuation coefficient of the position distance effect of the associated area; a first feature extraction result establishing unit, configured to extract economic activity and commercial layout features from an initial data set corresponding to the associated area and establish a first feature extraction result; a second feature extraction result establishing unit, the second feature extraction result establishing unit being used to extract traffic flow and accessibility features from an initial data set corresponding to the associated area, and establish a second feature extraction result; a planning feature extraction unit, configured to extract planning features from an initial data set corresponding to the associated area and establish a third feature extraction result; A population density feature extraction unit, configured to extract population density features from an initial data set corresponding to the associated area and establish a fourth feature extraction result; An additional feature set establishment unit is used to compensate the first feature extraction result, the second feature extraction result, the third feature extraction result, and the fourth feature extraction result according to the position distance influence attenuation coefficient to establish an additional feature set.

4. The intelligent design system for prefabricated buildings based on multi-source data analysis according to claim 1, characterized in that: The search module is also used to: A perceptual search preference establishing unit, configured to establish a context-aware search strategy based on the feature fusion result and the additional feature set, wherein the context-aware search strategy is a perceptual search preference established based on the search user's project history data and common parameter feedback; A project similarity search establishment unit is used to perform a similarity search for construction projects using the context-aware retrieval strategy, feature fusion results, and additional feature sets.

5. The intelligent design system for prefabricated buildings based on multi-source data analysis according to claim 4, characterized in that: The system further comprises: A database establishment module is used to obtain public data based on big data, establish data tags for the public data, and after performing data trust authentication, establish a first-tier database, establish digital communication with trusted three parties, and configure data interaction channels with trusted three parties. A second-tier database is established based on the data interaction channel. The second-tier database is an encrypted database. A matching database is established with the first-tier database and the second-tier database. Based on the feature fusion results and the additional feature set, a similar search for building projects is performed in the matching database to establish building search results.

6. The intelligent design system for prefabricated buildings based on multi-source data analysis according to claim 1, characterized in that: The system further comprises: A feedback module is used to record users' adaptation feedback on the adaptation evaluation ranking results, extract the adaptation reward coefficient for the same-direction search based on the recorded results, configure a penalty factor for continuous rewards, punish and compensate the adaptation reward coefficient extraction result based on the penalty factor, generate search feedback based on the penalty compensation result, and perform search optimization of the search module based on the search feedback.

7. The intelligent design system for prefabricated buildings based on multi-source data analysis according to claim 1, characterized in that: The evaluation selection module also includes: An indicator establishment unit, the indicator establishment unit being used to establish a functional adaptability index, a benefit index, an environmental adaptability index, a compliance index, and a real-time feasibility index according to the building requirements; The adaptation evaluation ranking unit is used to configure the adaptive weights of the functional adaptability index, the benefit index, the environmental adaptability index, the compliance index, and the real-time feasibility index, and evaluate the building search results based on the adaptive weights, the functional adaptability index, the benefit index, the environmental adaptability index, the compliance index, and the real-time feasibility index to complete the adaptation evaluation ranking.

8. The intelligent design system for prefabricated buildings based on multi-source data analysis according to claim 1, characterized in that: The system further comprises: The system access module is used to read the access database content if the user provides the access database, determine the basic search template, reconstruct the search module according to the read results and the basic search template, and complete the similarity search of the construction project based on the reconstructed search module.

Images