System and method for matching floor plan to multiple turnkey interior designs

Abstract

The present invention relates to the Intelligent Configuration for All Project, and discloses a system and a method for matching a floor plan to multiple turnkey interior designs. The present invention addresses the world-level technical shortcoming that traditional decoration does not allow data re-utilization and direct information delivery, and cannot meet the decoration result and information requirements of users. Deep learning enables intelligent analysis of a large amount of turnkey interior design spatial features and extraction of precise matching, which serves as an entry to recycle real sample data of the whole web, activate highly-effective transfer of data values, to match a great number of sets of strong visual files, such as decoration samples, rendered images, construction drawings, and materials, to lower the operation cost of practitioners, to enable communication between isolated fields such as design, decoration, and material, to include the user in the decoration experience, to better satisfy the needs of users for decoration effects and information, and to promote all residents of earth toward real digital synergy.

Description

Invention Title: A System and Method for Matching Multiple Integrated Decoration Designs with Floor Plans 1. Technical Field

[0001] This invention belongs to the "Smart Home Matching Project" and relates to the technical field of strong visual residential space data elements. Specifically, it is a system and method for matching floor plans with multiple integrated decoration designs. Based on universal matching, it achieves efficient reuse of existing data such as design, construction, and materials through intelligent floor plan analysis and precise matching with integrated decoration samples, enabling second-level traceability. This meets users' needs for decoration effects and information, driving the true digitalization of human habitation. 2. Background Technology

[0002] With the rapid development of the real estate industry, various types of apartment layouts have emerged, and people's demands for interior design are also increasing. Currently, when people need to renovate, if they want to obtain interior design renderings of their homes, most of the time it is done by renovation companies using professional design software to draw the floor plan, and then designing according to the user's needs. To obtain a satisfactory interior design, it often requires thorough communication between the designer and the user, and multiple revisions of the design plan to arrive at the desired home renovation plan. This process is time-consuming and labor-intensive.

[0003] When designing interior designs for homes, designers often need to spend a significant amount of time communicating and confirming details with clients. The process also involves tedious drawing creation, severely impacting work efficiency. Clients may experience frustration during repeated revisions of the plans, potentially leading to lost clients. This invention addresses this by referencing similar design schemes from previous floor plans. This significantly reduces design costs and time, and allows for a more intuitive presentation of existing floor plan renderings, making it easier for users to choose and accept the design. This also substantially reduces the time designers spend communicating with clients.

[0004] This method improves the optimization and integration of social resource allocation, enhances innovation and productivity, thereby solving all the problems brought about by the design process of traditional decoration companies, and saving production costs and increasing customer acquisition rates for decoration companies.

[0005] When referencing similar apartment layouts, it's necessary to traverse and filter through a pre-established database of apartment types. These databases are often very large, and the layouts of the apartments vary widely, making the manual screening process time-consuming and laborious. This hinders designers from quickly selecting suitable apartment types for reference, resulting in low overall design efficiency for the decoration company.

[0006] Chinese invention patent publication number "CN109992693A" entitled "Apartment Type Matching Method and Apparatus" discloses an apartment type matching method and apparatus. The method includes: acquiring an apartment type image to be matched; extracting geometric features from the apartment type image; the geometric features include contour features, area features, and positional features; performing similarity matching between the geometric features and sample apartment type images in a pre-established database to obtain the similarity between the geometric features and the sample apartment type images in the database; and selecting sample apartment type images from the database that match the apartment type image to be matched based on the similarity. By performing similarity matching between the geometric features of the apartment type and the sample apartment type images in the database, the most similar apartment type can be quickly obtained from the database, improving the efficiency of apartment type matching in the design process for decoration companies.

[0007] The patents disclosed above achieve the filtering of similar apartment layouts through apartment type matching, thus improving the efficiency of apartment design. However, they do not propose corresponding decoration schemes for each apartment type, while the design of decoration schemes for different apartment types is extremely important. 3. Invention Overview 3.1 This invention belongs to the technical field of strong visual residential space data elements, specifically a system and method for matching floor plans with multiple integrated decoration designs. Addressing long-standing pain points in the traditional decoration industry, this invention achieves accurate matching with existing decoration samples, design projects, and material information through intelligent analysis of floor plan images and feature extraction of integrated decoration schemes. It connects to a database to complete a true digital upgrade, significantly reducing industry operating costs, efficiently meeting users' decoration effect and information needs, and promoting high-quality, true digital development in the decoration industry. 3.2 This invention, based on deep learning and image recognition technology, overcomes the limitations of BIM system applications and the defects of traditional apartment type matching algorithms. It supports mobile phone photography and PC-based uploading of apartment type information, and can instantly match hundreds of real existing decoration cases. It completely solves the technical defects of industry template application and AI generation that cannot achieve WYSIWYG, and quickly outputs a complete set of design documents, bidding farewell to the blind box-like decoration experience for users, and promoting the industry to achieve design sharing and resource sharing. 3.3 This invention has realized the implementation of multi-entity traceability technology, broken down data silos in the industry, ended the blind box-like decoration experience for consumers, made up for the shortcomings of existing technologies in data reuse and direct information delivery, escaped the dilemma of involution in industry traffic, realized a virtuous cycle where good money drives out bad money, and provided an efficient, reliable and scalable digital solution for the field of residential space decoration. 4. Technical issues 4.1 BIM systems in the construction field are only applied to large-scale commercial projects and cannot be adapted to residential and small-scale public decoration scenarios; the existing apartment type matching mode is difficult to solve the inherent pain points of the industry. Faced with personalized decoration needs, relying solely on basic algorithms cannot achieve intelligent and accurate matching between apartment types and decoration plans. 4.2 Currently, the global market generally adopts template-based application and AI generation models, lacking mature technology for matching various existing decoration samples with different apartment types. This results in a lack of capabilities for reusing real data, tracing multiple sources, revitalizing existing data, efficient data flow, and direct information delivery. 4.3 The industry cannot automatically and accurately output a complete set of decoration documents matching the apartment types, leading to a "blind box" decoration experience for consumers. Decoration companies face high customer acquisition and operating costs, are trapped in a long-term cycle of internal competition for traffic, and struggle to build an industry ecosystem where good practices drive out bad ones. Furthermore, there is a lack of feasible technical solutions for design sharing and resource sharing. 4.4 In summary, for decades, the traditional decoration industry has not developed a mature technology that can meet users' needs for desired decoration effects and accurate information. 5. Solution to the problem

[0008] To address the aforementioned problems, the present invention aims to provide a system and method for matching floor plans with various integrated decoration designs that is highly efficient in designing apartment renovation schemes, adaptable to multiple apartment types, and provides excellent apartment design schemes.

[0009] Another objective of this invention is to provide a system and method for matching floor plans with various integrated decoration designs, which is reasonable, complete, and fully functional.

[0010] To achieve the above objectives, the technical solution of the present invention is as follows.

[0011] A system for matching floor plans with multiple integrated decoration designs, characterized in that the system includes a floor plan image processing module, a data storage module, a central control module, and a data processing module that uses the TensorFlow framework for deep learning for modeling, wherein the floor plan image processing module, the data processing module, and the data storage module are all communicatively connected to the central control module;

[0012] Apartment Layout Image Processing Module: This module acquires apartment layout images and processes them to obtain an outline of the apartment layout, meeting the application requirements of the data processing module. Apartment layout images can be acquired in various ways, including but not limited to: A) taking photos of the apartment layout. B) uploading the images. C) using voice recognition. Specifically, voice recognition can be used to input "XX City, XX District, XX Building, XX Number," and the system automatically recognizes the voice information and retrieves the pre-stored apartment layout image information from the data storage module.

[0013] Data processing module: Utilizes deep learning to process the floor plan outline image processed by the floor plan image processing module. The data obtained from the data processing module is compared with the floor plan sample data stored in the data storage module to obtain a more matching floor plan decoration sample data.

[0014] Data storage module: Used to store decoration sample data for different apartment types;

[0015] The central control module handles data processing and transformation between the floor plan image processing module, data processing module, and data storage module. Through these modules, the system sequentially acquires images, processes image parameters, extracts data using deep learning, and compares the extracted data with sample data stored in the data storage to match suitable floor plan decoration sample data. The entire system accurately and efficiently generates suitable floor plan decoration schemes quickly based on the floor plans provided by clients, significantly reducing design costs. Furthermore, referencing previous design schemes facilitates client approval and improves work efficiency. The use of deep learning for data analysis and matching ensures the accuracy and efficiency of data processing, reducing the time required for manual comparison and retrieval.

[0016] Furthermore, the apartment layout image processing module includes an acquisition module and an image processing module. Both the acquisition module and the image processing module are communicatively connected to the central control module. The acquisition module is used to acquire the apartment layout to be matched, and the image processing module is used to perform image processing on the apartment layout acquired by the acquisition module to obtain an apartment layout outline.

[0017] Furthermore, the data processing module includes a data analysis module, a data matching module, a data sorting module, and a file association module. These modules are all communicatively connected to the central control module. The data analysis module analyzes and processes the apartment layout outline, extracting its geometric features. The data matching module compares the geometric features obtained from the data analysis module with the apartment decoration sample data stored in the data storage module to match suitable apartment decoration sample data. The data sorting module sorts the matched apartment decoration sample data according to the matching degree of the data matching module, and simultaneously presents the associated effect diagrams of the sample data to the client. The file association module extracts all design drawings and related files associated with the apartment sample; selecting the sample data allows downloading the associated design drawings and related files. The data analysis module analyzes the floor plan outline, and the data matching module matches suitable floor plan decoration samples. The matched floor plan decoration samples are sorted according to the degree of matching to facilitate customers' priority selection. The file association module provides corresponding design drawings for each floor plan decoration sample, which facilitates the selection and preview of decoration styles.

[0018] Furthermore, the data storage module stores previous decoration sample data for each apartment type. When a customer modifies the decoration data, it can be updated in the data storage module. This data storage module enables the storage of multiple apartment decoration samples, facilitating the retrieval, updating, and saving of these samples.

[0019] Furthermore, the data acquisition module includes camera capture and mobile phone photography. The floor plan can be acquired conveniently and efficiently using both a camera and a mobile phone.

[0020] Furthermore, the geometric features include outline, area, floor plan, and decoration style. The design drawings associated with the apartment decoration sample data include decoration renderings, construction drawings, material white papers, bills of quantities, VR panoramas, and virtual tours. Providing decoration renderings, construction drawings, material white papers, bills of quantities, VR panoramas, and virtual tours facilitates the selection and preview of apartment decoration samples, ensuring that the apartment decoration achieves the best results.

[0021] Furthermore, the data analysis module employs the TensorFlow deep learning framework for modeling. Known apartment layout sample data is input into the model for training to obtain a pre-model. The apartment layout outline is then input into the pre-model to extract the geometric features of the layout outline. This deep learning framework ensures the accuracy and efficiency of the data processed by the data analysis module.

[0022] Furthermore, the data matching module utilizes a pre-model to match the geometric feature data of the layout outline with the apartment decoration sample data stored in the data storage module, ensuring the accuracy and comprehensiveness of the matching.

[0023] A method for matching multiple complete home renovation designs with a floor plan, characterized by the following specific steps:

[0024] Sl: The floor plan image is acquired through the acquisition module;

[0025] S2: The image processing module processes the collected floor plan to obtain the floor plan outline, in order to meet the application requirements of the data processing module.

[0026] S3: The data analysis module is used to analyze and process the apartment layout outline map and extract the geometric feature data of the layout outline map;

[0027] S4: The data matching module compares the geometric feature data obtained by the data analysis module with the data of the house decoration samples stored in the data storage module to match a more suitable house decoration sample.

[0028] S5: The data sorting module sorts the matched apartment decoration samples according to their matching degree, and then presents the sorted samples to the client.

[0029] S6: The file association module is used to extract all design drawings and related files associated with the sorted apartment type samples;

[0030] S7: Data storage module: Used to store decoration sample data for different apartment types. The apartment decoration sample data includes decoration renderings, construction drawings, material white papers, bill of quantities, VR panoramas, and virtual tours.

[0031] Furthermore, the image processing module includes the following steps:

[0032] S21: Use OpenCV technology to process the acquired images to obtain a grayscale image of the apartment layout;

[0033] S22: Perform OTSU binarization on the grayscale image of the apartment layout to remove the image background;

[0034] S23: Use the Sobel operator to obtain the edge image of the image after removing the background, and then crop the outline of the apartment layout from the edge image;

[0035] S24: The wall threshold segmentation method is used to process the apartment layout outline and perform door and window recognition.

[0036] By processing images to meet the format requirements of the data processing module, the system can also identify and acquire information about apartment layouts, doors, and windows, facilitating the matching and selection of apartment decoration styles.

[0037] The use of this invention can save industry operating costs, but in a sense, in addition to saving a lot of operating costs, the more important core is our system. It can completely bridge the gap between peers in the decoration industry and achieve design sharing and resource sharing. It is a new pioneering system for the decoration and design industry, which will take the industry a big step forward.

[0038] In summary, this system sequentially completes image acquisition, image parameter processing, and data storage through a floor plan image processing module, a data processing module, a data storage module, and a central control module. It utilizes deep learning to extract data from the images and compares the extracted data with sample data stored in the data storage to match suitable floor plan decoration sample data. The entire system accurately and efficiently obtains suitable floor plan decoration schemes quickly based on the floor plans provided by customers, significantly saving design costs. Furthermore, referencing previous design schemes facilitates customer acceptance and improves work efficiency. The use of deep learning for data analysis and matching ensures the accuracy and efficiency of data processing, reducing the time spent on manual comparison and retrieval. This technology can be applied to various terminal devices such as mobile phones, tablets, and computers. It can be used to develop apps, e-commerce websites, and operating systems for decoration companies, revolutionizing the current traditional decoration company model. This model of artificial intelligence + internet + design + physical business is also a new development model with significant innovation. 6. Brief description of the attached drawings

[0039] Figure 1 is a flowchart of a method for matching a floor plan with multiple integrated decoration designs according to the present invention.

[0040] Figure 2 is a flowchart illustrating the specific implementation of a method for matching floor plans with multiple integrated decoration designs according to the present invention.

[0041] Figure 3 is a structural diagram of a system for matching floor plans with multiple integrated decoration designs according to the present invention. 7. Implementation Instructions

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0043] To achieve the above objectives, the technical solution of the present invention is as follows.

[0044] Referring to Figures 1-3, a system for matching floor plans with multiple integrated decoration designs is characterized in that the system includes a floor plan image processing module, a data storage module, a central control module, and a data processing module that uses the TensorFlow framework for deep learning for modeling. The floor plan image processing module, the data processing module, and the data storage module are all communicatively connected to the central control module.

[0045] Apartment layout image processing module: Completes the acquisition of apartment layout images and the processing of the acquired apartment layout images to obtain the apartment layout outline map to meet the application requirements of the data processing module;

[0046] Data processing module: Utilizes deep learning to process the floor plan outline image processed by the floor plan image processing module. The data obtained from the data processing module is compared with the floor plan sample data stored in the data storage module to obtain a more matching floor plan decoration sample data.

[0047] Data storage module: Used to store decoration sample data for different apartment types;

[0048] The central control module handles data processing and transformation between the floor plan image processing module, data processing module, and data storage module. The system sequentially completes image acquisition, image parameter processing, and data storage through these modules. Deep learning is used to extract data from the images, and the extracted data is compared with sample data stored in the data storage to match suitable floor plan decoration sample data. The entire system accurately and efficiently generates suitable floor plan decoration schemes quickly based on the floor plans provided by clients, significantly saving design costs. Furthermore, referencing previous design schemes facilitates client approval and improves work efficiency. The use of deep learning for data analysis and matching ensures the accuracy and efficiency of data processing, reducing the time required for manual comparison and retrieval.

[0049] In this embodiment, the floor plan image processing module includes an acquisition module and an image processing module. Both the acquisition module and the image processing module are communicatively connected to the central control module. The acquisition module is used to acquire the floor plan to be matched, and the image processing module is used to perform image processing on the floor plan acquired by the acquisition module to obtain the floor plan layout outline.

[0050] In this embodiment, the data processing module includes a data analysis module, a data matching module, a data sorting module, and a file association module. These modules are all communicatively connected to the central control module. The data analysis module analyzes and processes the floor plan outline to extract its geometric features. The data matching module compares the geometric feature data obtained from the data analysis module with the floor plan decoration sample data stored in the data storage module to match suitable floor plan decoration sample data. The data sorting module sorts the matched floor plan decoration sample data according to the matching degree of the data matching module and simultaneously presents the associated effect diagrams of the sample data to the client. The file association module extracts all design drawings and related files associated with the sorted floor plan samples. After selecting the sample data, the associated design drawings and related files can be downloaded. The data analysis module analyzes the floor plan outline, and the data matching module matches suitable floor plan decoration samples. The matched floor plan decoration samples are sorted according to the degree of matching to facilitate customers' priority selection. The file association module provides corresponding design drawings for each floor plan decoration sample, which facilitates the selection and preview of decoration styles.

[0051] Referring to Figure 2, in this embodiment, the data storage module stores previous decoration sample data. When a customer modifies the decoration data, it can be updated in the data storage module. The data storage module enables the storage of multiple decoration samples, facilitating the retrieval, updating, and saving of these samples.

[0052] In this embodiment, the data acquisition module includes camera capture and mobile phone photography. The floor plan can be acquired conveniently and efficiently by using both a camera and a mobile phone to capture images.

[0053] In this embodiment, the geometric features include outline, area, floor plan, and decoration style. The design drawings associated with the apartment decoration sample data include decoration renderings, construction drawings, material white papers, bill of quantities, VR panoramas, and virtual tours. Providing decoration renderings, construction drawings, material white papers, bill of quantities, VR panoramas, and virtual tours facilitates the selection and preview of apartment decoration samples, ensuring that the apartment decoration achieves the best results.

[0054] In this embodiment, the data analysis module uses the TensorFlow deep learning framework for modeling. Known apartment layout sample data is input into the model for training to obtain a pre-model. The apartment layout outline is then input into the pre-model to extract the geometric features of the layout outline. The modeling and use of the deep learning framework ensures the accuracy and efficiency of the data processed by the data analysis module.

[0055] In this embodiment, the data matching module uses a pre-model to match the geometric feature data of the layout outline with the apartment decoration sample data stored in the data storage module, ensuring the accuracy and comprehensiveness of the matching.

[0056] Referring to Figures 1-2, a method for matching multiple integrated decoration designs with a floor plan is characterized by the following specific steps:

[0057] Sl: The floor plan image is acquired through the acquisition module;

[0058] S2: The image processing module processes the collected floor plan to obtain the floor plan outline, in order to meet the application requirements of the data processing module.

[0059] S3: The data analysis module is used to analyze and process the apartment layout outline map and extract the geometric feature data of the layout outline map;

[0060] S4: The data matching module compares the geometric feature data obtained by the data analysis module with the data of the house decoration samples stored in the data storage module to match a more suitable house decoration sample.

[0061] S5: The data sorting module sorts the matched apartment decoration samples according to their matching degree, and then presents the sorted samples to the client.

[0062] S6: The file association module is used to extract all design drawings and related files associated with the sorted apartment type samples;

[0063] S7: Data storage module: Used to store decoration sample data for different apartment types. The apartment decoration sample data includes decoration renderings, construction drawings, material white papers, bill of quantities, VR panoramas, and virtual tours.

[0064] In this embodiment, the image processing module includes the following steps:

[0065] S21: Use OpenCV technology to process the acquired images to obtain a grayscale image of the apartment layout;

[0066] S22: Perform OTSU binarization on the grayscale image of the apartment layout to remove the image background;

[0067] S23: Use the Sobel operator to obtain the edge image of the image after removing the background, and then crop the outline of the apartment layout from the edge image;

[0068] S24: The wall threshold segmentation method is used to process the apartment layout outline and perform door and window recognition.

[0069] By processing images to meet the format requirements of the data processing module, the system can also identify and acquire information about apartment layouts, doors, and windows, facilitating the matching and selection of apartment decoration styles.

[0070] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention. 8. Industrial Applicability: This invention belongs to the underlying technology of strong visual data elements. It uses the instant matching of residential floor plans with N sets of complete decoration samples as its entry point, enabling the reuse of existing decoration and design case samples, direct information access, and precise matching. This invention can be quickly implemented and used through mobile phone photography, PC uploads, mini-programs, apps, and large model interface services. It is widely applicable to data services in fields such as home decoration, small-scale public decoration, space design, and building materials supply chain. It can revitalize existing visual data, activate the data element market, and efficiently meet the decoration effect and information needs of global users. It possesses rapid implementation, scalable replication, and cross-industry expansion capabilities, meeting the requirements of industrial applicability. It is an entry-level foundational technology for the digital economy and the marketization of data elements. 9. List of reference numerals in attached figures: 10. Notes on the preservation of biological materials: 11. Sequence List Free Content: None 12. List of cited documents: None 13. Patent Documents: None 14. Non-patent literature: None 15. Inventor's Declaration Except for the abstract, summary of the invention, technical problem, technical field, and industrial applicability supplemented to match international patent applications, this invention includes the claims and the content of the invention.

[0002] to

[0070] The accompanying drawings and embodiments in the specification remain unchanged, fully preserving the original, mature, and original technical solution. In June 2018, while managing the decoration project of the Grady Hotel in Huizhou, China, the inventor, after revising nearly 2,000 construction drawings within a month, profoundly discovered that the root cause of the problem lay in the broken matching relationship between visual data and the creative subject, rather than insufficient drawing efficiency. Based on this, the inventor deeply realized that "only matching is the way of civilized operation; without matching, there is an imbalance of order, disorder of operation, and internal economic friction." This invention originated in 2019, upholding the spirit of Wanhu and the original intention of matching everything. It is an entry-level core technology for the global data element marketization and also an important source and core driving force for subsequent related patents.

Claims

Claims 1. A system for matching floor plans with multiple complete home furnishing designs, characterized in that, The system includes a floor plan image processing module, a data storage module, a central control module, and a data processing module that uses the TensorFlow framework for deep learning to model data. The floor plan image processing module, the data processing module, and the data storage module are all connected to the central control module. Floor plan image processing module: Completes the acquisition of floor plan images and the processing of the acquired floor plan images to obtain floor plan layout outlines to meet the application requirements of the data processing module; Data processing module: Utilizes deep learning to process the floor plan outline image processed by the floor plan image processing module. It then compares the data obtained from the data processing module with the floor plan sample data stored in the data storage module to obtain a more matching floor plan decoration sample data. Data storage module: used to store decoration sample data for different apartment types; Central control module: Used for data processing and conversion between the apartment layout image processing module, data processing module, and data storage module.

2. The system for matching floor plans with multiple integrated decoration designs as described in claim 1, characterized in that, The floor plan processing module includes a data acquisition module and an image processing module. Both the data acquisition module and the image processing module are connected to the central control module. The data acquisition module is used to acquire the floor plan to be matched, and the image processing module is used to process the floor plan acquired by the data acquisition module to obtain the floor plan layout outline.

3. The system for matching floor plans with multiple integrated decoration designs as described in claim 2, characterized in that, The data processing module includes a data analysis module, a data matching module, a data sorting module, and a file association module. These modules are all communicatively connected to the central control module. The data analysis module analyzes and processes the floor plan outline, extracting its geometric features. The data matching module compares the geometric features obtained from the data analysis module with the floor plan decoration samples stored in the data storage module, matching suitable floor plan decoration samples. The data sorting module sorts the matched floor plan decoration samples according to their matching degree and presents the associated diagrams to the client. The file association module extracts all design drawings and related documents associated with the floor plan sample data; selecting the sample data allows downloading the associated design drawings. A system for matching floor plans with multiple integrated decoration designs as described in claim 1, characterized in that, The data storage module stores previous decoration data for the apartment layouts. When a customer modifies the decoration data, it can be updated in the data storage module.

5. A system for matching floor plans with multiple integrated decoration designs as described in claim 2, characterized in that, The acquisition module includes camera acquisition and mobile phone photography.

6. The system for matching floor plans with multiple integrated decoration designs as described in claim 3, characterized in that, The geometric features include outline, area, floor plan, and decoration style. The design drawings associated with the apartment decoration sample data include decoration renderings, construction drawings, material white papers, bill of quantities, VR panoramas, and virtual tours.

7. A system for matching floor plans with multiple integrated decoration designs as described in claim 3, characterized in that, The data analysis module uses the TensorFlow deep learning framework for modeling. Known apartment decoration sample data are input into the model for training to obtain a pre-model. The apartment outline map is input into the pre-model to extract the geometric features of the layout outline map.

8. A system for matching floor plans with multiple integrated decoration designs as described in claim 7, characterized in that, The data matching module uses a pre-model to match the geometric feature data of the layout outline with the apartment decoration sample data stored in the data storage module.

9. A method for matching multiple complete home renovation designs with a floor plan, characterized in that, The specific steps of this method are as follows: S1: The floor plan image is acquired through the acquisition module; S2: The image processing module processes the acquired floor plan to obtain the floor plan outline, in order to meet the application requirements of the data processing module; S3: The data analysis module is used to analyze and process the apartment layout outline and extract geometric feature data; S4: The data matching module compares the geometric feature data obtained by the data analysis module with the data of the type decoration samples stored in the data storage module to match a more suitable type decoration sample. S5: The data sorting module sorts the matched apartment decoration samples according to their matching degree, and presents the sorted samples to the client. S6: The file association module is used to extract all design drawings and related files associated with the sorted apartment type samples; S7: Data storage module: Used to store decoration sample data for different apartment types. The apartment decoration sample data includes decoration renderings, construction drawings, material white papers, bill of quantities, VR panoramas, and virtual tours.

10. The method for matching multiple complete decoration designs with a floor plan as described in claim 9, characterized in that, The image processing module includes the following steps: S21: Use OpenCV technology to process the acquired images to obtain a grayscale image of the apartment layout; S22: Perform OTSU binarization on the grayscale image of the apartment layout to remove the image background; S23: Use the Sobel operator technique to obtain the edge image of the image after removing the background, and then cut the shape layout outline map from the edge image; S24: The wall threshold segmentation method is used to process the apartment layout outline and perform door and window recognition.

Images