Ancient building restoration modeling reconstruction method based on digital technology

Abstract

The invention provides an ancient building restoration modeling reconstruction method based on a digital technology, and belongs to the technical field of artificial intelligence and building restoration. The method comprises the steps of obtaining three-dimensional structure information and plane structure information of a to-be-repaired target historic building, generating a three-dimensional structure chart and a target plane structure chart of the to-be-repaired target historic building, and performing matching retrieval in a preset plane structure chart database based on the target plane structure chart to obtain at least one matched plane structure chart, performing semantic analysis on the matched plane structure diagram to obtain a plurality of three-dimensional reconstruction cue words, and inputting the three-dimensional reconstruction cue words and the three-dimensional structure diagram of the to-be-repaired target historic building into a diagram-to-diagram artificial intelligence engine to output a plurality of three-dimensional structure repair effect candidate diagrams, and evaluating to obtain a three-dimensional structure repairing scheme diagram of the to-be-repaired target historic building and the like. According to the method, ancient building modeling reconstruction is realized based on a digital technology, and an artificial intelligence engine is assisted to obtain a plurality of candidate schemes, and then an optimal restoration scheme is obtained through evaluation.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence and building restoration technology, and in particular relates to a digital technology-based ancient building restoration modeling and reconstruction method, a computer-readable storage medium for implementing the method, a computer program product, and an electronic device. Background Art

[0002] As important ancient architectural relics, ancient buildings have witnessed the development of human civilization and history, and embodied the achievements of ancient working people in construction engineering, culture and art. These cultural relics have undergone thousands of years of changes in the times and have been destroyed and damaged to varying degrees by man and nature. Cultural inheritance and protection have become an important part of human cultural heritage protection. Ancient buildings are an important process in human development. Affected by time, environment, human factors and other factors for a long time, many ancient buildings have gradually withdrawn from the tide of history. Therefore, effective measures and artistic methods must be taken to maintain the original appearance of ancient buildings.

[0003] With the development of digital technology, artistic protection and product restoration in the field of ancient architecture have achieved remarkable results. For example: in the process of restoration and protection of ancient buildings, the corresponding model is established based on the original data of the ancient buildings, and the damaged parts of the current part are predicted through digital technology, and the restoration effect and adjustment are simulated in advance. Chinese invention patent application CN202411203655.9 proposes a digital restoration model design system and repair method for ancient buildings. By using deep learning algorithms to automatically detect damage to three-dimensional digital models, it can more accurately identify signs of damage and quantify the degree of damage, avoiding the problem of hidden damage that is difficult to find through manual surveys.

[0004] As digital technology evolves to the artificial intelligence stage, deeply evolved artificial intelligence engines can already replace human designers to complete various restoration simulation tasks. For example, the relevant drawings of the building to be restored are input into the artificial intelligence (AI) engine, and the artificial intelligence engine can derive recommended restoration simulation plans based on the big data model.

[0005] However, in actual applications, it was found that if the existing three-dimensional measurement data or drawings of the building to be repaired were simply input, the results output by the AI ​​engine (repair simulation effect) would not be ideal. Summary of the invention

[0006] In view of the above technical problems, the present invention proposes a method for ancient building restoration modeling and reconstruction based on digital technology, a computer-readable storage medium, a computer program product and an electronic device for implementing the method.

[0007] In the first aspect of the present invention, a method for modeling and reconstructing ancient building restoration based on digital technology is proposed, wherein the method is implemented based on electronic equipment, and the electronic equipment includes a three-dimensional laser scanning device, a computer image processing device, and a database combination device, etc.;

[0008] The method comprises the following steps:

[0009] S100: Acquire three-dimensional structural information and plane structural information of the target ancient building to be restored;

[0010] S200: generating a three-dimensional structural diagram of the target ancient building to be restored based on the three-dimensional structural information; and obtaining a target plane structural diagram of the target ancient building based on the plane structural information;

[0011] S300: performing a matching search in a preset plane structure diagram database based on the target plane structure diagram to obtain at least one matching plane structure diagram;

[0012] S400: performing semantic analysis on the matching plane structure graph to obtain a plurality of three-dimensional reconstruction prompt words;

[0013] S500: inputting the 3D reconstruction prompt words and the 3D structural diagram of the target ancient building to be restored into a graph generation and image artificial intelligence engine, and the graph generation and image artificial intelligence engine outputs a plurality of candidate graphs of the 3D structural restoration effect of the target ancient building to be restored;

[0014] S600: Evaluate the multiple three-dimensional structural restoration effect candidate images to obtain a three-dimensional structural restoration plan image of the target ancient building to be restored.

[0015] Step S100 obtains the three-dimensional structural information of the target ancient building to be restored, specifically including:

[0016] A laser scanner is used to scan the target ancient building to be restored from multiple angles to obtain a discrete three-dimensional point cloud data set;

[0017] The multiple angles include at least a first reference angle φ1, a second deviation angle φ2 that deviates from the first reference angle φ1 by a first preset arc θ1, and a third deviation angle φ3 that deviates from the first reference angle φ1 by a second preset arc θ2;

[0018] Perform Gaussian mapping on each discrete 3D point cloud data subset collected at the same angle to obtain a 3D point cloud data set after Gaussian mapping;

[0019] Each discrete 3D point cloud data subset collected at the same angle is processed by Gaussian mapping, including:

[0020] Assume angle φ iScan to obtain discrete 3D point cloud data subset D i , D i ={X i1 ,X i2 ,L,X iN},i=1,2,3;

[0021] For discrete 3D point cloud data subset D i Every element X in ij ,j=1,2,L,N; perform Gaussian mapping processing.

[0022] The three-dimensional structure information is obtained by performing splicing and fitting based on the three-dimensional point cloud data set processed by the Gaussian mapping.

[0023] Step S100 obtains the plane structure information of the target ancient building to be restored, which specifically includes:

[0024] Obtaining a BIM simulation model of the target ancient building;

[0025] Improve the BIM simulation model based on the discrete three-dimensional point cloud data set;

[0026] The plane structure information of the target ancient building to be restored is generated through the improved BIM simulation model.

[0027] Step S200 obtains a target plane structure diagram of the target ancient building based on the plane structure information, specifically including:

[0028] A standard CAD plan view can be quickly generated through the improved BIM simulation model.

[0029] The matching plane structure diagram obtained in step S300 is a complete plane structure diagram including the matching target building;

[0030] The step S400 performs semantic analysis on the matching plane structure diagram to obtain a plurality of three-dimensional reconstruction prompt words, specifically including:

[0031] Determine the difference between the complete plane structure diagram and the target plane structure diagram;

[0032] The difference part is analyzed to determine the plurality of three-dimensional reconstruction prompt words.

[0033] The analyzing the difference part and determining the plurality of three-dimensional reconstruction prompt words specifically includes:

[0034] Obtaining a difference plane structure diagram corresponding to the difference part;

[0035] Based on the difference plan structure diagram, determining the morphological data of the difference part, the morphological data including one of size, orientation, architectural style, axis, symmetry or any combination thereof;

[0036] Based on each of the morphological data, the three-dimensional reconstruction prompt word is determined.

[0037] Furthermore, after obtaining the three-dimensional structural restoration plan diagram of the target ancient building to be restored in step S600, the method further includes:

[0038] Obtaining a planar structure repair image corresponding to the three-dimensional structure repair image;

[0039] The plane structure repair diagram is updated into the preset plane structure diagram database.

[0040] Furthermore, after obtaining the three-dimensional structural restoration plan diagram of the target ancient building to be restored in step S600, the method further includes:

[0041] digitizing the three-dimensional structural repair plan diagram;

[0042] The three-dimensional structure repair plan diagram is associated with the target plane structure diagram and stored in the ancient building information database.

[0043] The aforementioned ancient building restoration modeling and reconstruction method based on digital technology can be automatically implemented through various forms of electronic devices through computer program instructions; the computer program instructions can be stored in different forms of storage media and loaded into computer electronic equipment for execution.

[0044] Therefore, in the second aspect of the present invention, a computer-readable storage medium is also provided for storing computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the ancient building restoration, modeling and reconstruction method based on digital technology according to the first aspect.

[0045] In the third aspect of the present invention, a computer device is also proposed, which includes a processor and a memory, the memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the computer device executes the ancient building restoration, modeling and reconstruction method based on digital technology in the first aspect mentioned above.

[0046] In the fourth aspect of the present invention, a computer program product is also proposed, which includes a computer program. When the computer program is executed, the ancient building restoration modeling and reconstruction method based on digital technology of the first aspect is implemented.

[0047] The present invention realizes the modeling and reconstruction of ancient buildings based on digital technology, and assists the artificial intelligence engine to obtain multiple candidate solutions and then evaluates and obtains the optimal restoration solution. In the technical solution of the present invention, the large model input of the AI ​​engine is no longer just the existing three-dimensional measurement data or drawing data of the building to be restored, but includes three-dimensional reconstruction prompt words and three-dimensional structure diagrams of the target ancient building to be restored. The three-dimensional reconstruction prompt words are obtained by matching and searching in a relatively complete preset plane structure diagram database, which conforms to the actual characteristics that the plane drawing database in the field of ancient buildings is relatively complete and the three-dimensional structure database is relatively lacking. Therefore, the method of the present invention is extensible, and the obtained AI prompt words can improve the pertinence of the candidate solutions output by the AI ​​engine, ensuring the standardization of the ancient building restoration modeling and reconstruction process.

[0048] Further advantages of the present invention will be further reflected in detail in the specific embodiments section in conjunction with the drawings of the specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 It is a main flow diagram of a method for restoration, modeling and reconstruction of ancient buildings based on digital technology according to an embodiment of the present invention;

[0051] Figure 2 yes Figure 1 A schematic diagram of a process of obtaining three-dimensional structural information of a target ancient building in the embodiment;

[0052] Figure 3 yes Figure 1 A schematic diagram of the process principle of obtaining the three-dimensional reconstruction prompt word in the embodiment;

[0053] Figure 4 yes Figure 1 The embodiment of the present invention is a schematic diagram of the optimization processing steps subsequent to the three-dimensional structure repair scheme diagram;

[0054] Figure 5 Is implemented Figure 1 A schematic diagram of the connection of the functional hardware combination modules of the method embodiment. DETAILED DESCRIPTION

[0055] First of all, it should be pointed out that the embodiments of the ancient building restoration modeling and reconstruction method based on digital technology mentioned in this section can be implemented through computer programs on electronic devices and systems equipped with memory and processors. The electronic devices and systems can be in the form of physical machines, virtual machines, servers, clusters or any combination thereof.

[0056] Preferably, the specific form of the electronic device may also be a human-computer interaction terminal, and the human-computer interaction terminal may be a desktop terminal, a smart handheld terminal, a mobile terminal, etc. with a human-computer interaction interface.

[0057] See first Figure 1 , Figure 1 It is a main flow chart of a method for restoration, modeling and reconstruction of ancient buildings based on digital technology according to an embodiment of the present invention.

[0058] Figure 1 The method is implemented based on three-dimensional laser scanning equipment, computer image processing equipment and database combination equipment, etc.

[0059] Figure 1 The method is shown to include the following steps:

[0060] S100: Acquire three-dimensional structural information and plane structural information of the target ancient building to be restored;

[0061] S200: generating a three-dimensional structural diagram of the target ancient building to be restored based on the three-dimensional structural information; and obtaining a target plane structural diagram of the target ancient building based on the plane structural information;

[0062] S300: performing a matching search in a preset plane structure diagram database based on the target plane structure diagram to obtain at least one matching plane structure diagram;

[0063] S400: performing semantic analysis on the matching plane structure graph to obtain a plurality of three-dimensional reconstruction prompt words;

[0064] S500: inputting the 3D reconstruction prompt words and the 3D structural diagram of the target ancient building to be restored into a graph generation and image artificial intelligence engine, and the graph generation and image artificial intelligence engine outputs a plurality of candidate graphs of the 3D structural restoration effect of the target ancient building to be restored;

[0065] S600: Evaluate the multiple three-dimensional structural restoration effect candidate images to obtain a three-dimensional structural restoration plan image of the target ancient building to be restored.

[0066] Next, combine Figure 2-Figure 4 ,right Figure 1 Each step of the method embodiment is adaptively described.

[0067] Based on existing literature records, 3D laser scanning technology has significant advantages in surveying and mapping the ground, walls, etc., which are as follows: First, it has strong adaptability and can be operated and applied in various environments; second, it can greatly improve the accuracy of surveying and mapping data, and can significantly shorten the surveying and mapping cycle, so that the efficiency and quality of surveying and mapping work are comprehensively improved. After the staff enters the acquired surveying and mapping data into a specific computer system, the system can automatically create a 3D model of the ancient building in accordance with the established process in combination with the existing data, providing important information support for the staff to formulate ancient building protection plans or programs. The most important thing is that the staff can directly restore the ancient buildings that can no longer return to the public's view through 3D laser scanning technology.

[0068] In practical applications, most buildings only consider one reference surface data when performing laser scanning, and perform Gaussian mapping fitting based on the reference surface data. At this time, by understanding the spatial layout of the point cloud and the surface form on which it is located, combined with mathematical formulas to identify the class and feature structure to improve the stitching accuracy and efficiency. Based on the Gaussian mapping data conditions, it is necessary to divide the actual reference surface fitting work of the point cloud into two steps: "shape type recognition" and "feature extraction".

[0069] However, when restoring and modeling ancient buildings, if only the point cloud data of one reference plane is considered, the subsequent fitting process needs to be divided into multiple steps and multiple modes, and the simulated three-dimensional structure effect is relatively simple. Even if the shape type and features can be identified through the Gaussian mapping processing mentioned above, the subsequent splicing process also requires a full understanding of the data type contained in the point cloud data to determine which point cloud processing solution to use to complete the research.

[0070] For this purpose, as a first improvement of the present invention, see Figure 2 Step S100 obtains the three-dimensional structural information of the target ancient building to be restored, specifically including:

[0071] A laser scanner is used to scan the target ancient building to be restored from multiple angles to obtain a discrete three-dimensional point cloud data set;

[0072] The multiple angles include at least a first reference angle φ1, a second deviation angle φ2 that deviates from the first reference angle φ1 by a first preset arc θ1, and a third deviation angle φ3 that deviates from the first reference angle φ1 by a second preset arc θ2;

[0073] Perform multi-angle Gaussian mapping processing on each discrete 3D point cloud data subset collected at the same angle to obtain a 3D point cloud data set after multi-angle Gaussian mapping processing;

[0074] The three-dimensional structure information is obtained by performing splicing and fitting based on the three-dimensional point cloud data set processed by the multi-angle Gaussian mapping.

[0075] As one of the improvements of the present invention, in this embodiment, a multi-angle Gaussian mapping process is performed on each discrete 3D point cloud data subset collected at the same angle, specifically including:

[0076] Assume angle φ i Scan to obtain discrete 3D point cloud data subset D i , D i ={X i1 ,X i2 ,L,X iN},i=1,2,3;

[0077] For discrete 3D point cloud data subset D i Every element X in ij ,j=1,2,L,N;N>1;Perform the following Gaussian mapping process:

[0078]

[0079] ω1=1,

[0080] in, X for the elements ij The result after Gaussian mapping processing.

[0081] It can be seen that the above process takes into account the offset of the current angle relative to the reference angle as a weight influence value when performing Gaussian mapping for discrete 3D point cloud data subsets at different angles, thereby obtaining the corresponding Gaussian mapping data at each angle. On this basis, the existing reference plane fitting method of the prior art mentioned above is used, that is, the Gaussian mapping data of three different angles are all used as new "reference plane" data, which can ensure that the subsequent stitching process does not need to consider the data type contained in each point cloud data, and the data fitting stitching process can be directly carried out, thereby improving the efficiency of the entire 3D reconstruction and stitching.

[0082] Of course, in practical applications, if the ordinary Gaussian mapping process of the prior art is actually adopted, after ordinary Gaussian mapping is performed on the discrete three-dimensional point cloud data subset at each angle, the subsequent fitting and splicing process can be continued, and the technical solution of the present application can also be implemented, but the effect is not as good as the embodiment of the present application. Therefore, this process (multi-angle Gaussian mapping) is the preferred technical solution.

[0083] Furthermore, step S100 obtains the plane structure information of the target ancient building to be restored, which specifically includes:

[0084] Obtaining a BIM simulation model of the target ancient building;

[0085] Improve the BIM simulation model based on the discrete three-dimensional point cloud data set;

[0086] The plane structure information of the target ancient building to be restored is generated through the improved BIM simulation model.

[0087] The floor plan can be viewed using CAD software, and the BIM 3D model can be viewed using Revit;

[0088] Preferably, step S200 obtains a target plane structure diagram of the target ancient building based on the plane structure information, specifically including:

[0089] A standard CAD plan view can be quickly generated through the improved BIM simulation model.

[0090] Improving the BIM simulation model based on the discrete three-dimensional point cloud data set specifically includes:

[0091] Based on software such as Revit, we have developed a variety of interfaces to diversify the types of exported files. For example, in addition to .rvt, the exported file formats in Revit can also be exported to CAD formats (.dwg / .dxf / .dgn / .acis), DWF format, ODBC development database link format, image file format (.png / jpeg / jpg), etc. Of course, the above file formats can also be received, and point cloud data in formats such as .DPI / .RCP have been allowed to be imported, which greatly improves the scalability of BIM model data files.

[0092] On this basis, the point cloud model has the advantage of being able to observe the measured object in all directions. At the same time, the BIM simulation model based on the point cloud model can also be used in Revit to quickly generate standard CAD floor plans, cut the model at will as needed, and restore the missing drawings in all directions more quickly and accurately.

[0093] The matching plane structure diagram obtained in step S300 is a complete plane structure diagram including the matching target building.

[0094] In the field of ancient architecture, due to historical reasons and limitations of the development of technological conditions, the number, perfection, and completeness of the plane structure drawings corresponding to a target ancient building are, in most cases, significantly better than the number, perfection, and completeness of the corresponding three-dimensional structure drawings.

[0095] Taking this into consideration, a plane structure diagram database D containing the complete or partial structures of various target buildings can be pre-constructed. For a target ancient building A to be restored, its target plane structure diagram Aa is matched and retrieved in the preset plane structure diagram database D, and at least one matching plane structure diagram A'a can be obtained.

[0096] The obtained matching plane structure diagram A'a is a complete plane structure diagram of some other main building A' that includes all or part of the structure of the matching target building A.

[0097] See next Figure 3 .

[0098] The step S400 performs semantic analysis on the matching plane structure diagram to obtain a plurality of three-dimensional reconstruction prompt words, specifically including:

[0099] Determine the difference between the complete plane structure diagram and the target plane structure diagram;

[0100] The difference part is analyzed to determine the plurality of three-dimensional reconstruction prompt words.

[0101] Preferably, the analyzing the difference portion and determining the plurality of three-dimensional reconstruction prompt words specifically includes:

[0102] Obtaining a difference plane structure diagram corresponding to the difference part;

[0103] Based on the difference plan structure diagram, determining the morphological data of the difference part, the morphological data including one of size, orientation, architectural style, axis, symmetry or any combination thereof;

[0104] Based on each of the morphological data, the three-dimensional reconstruction prompt word is determined.

[0105] Continuing with the above example, the target ancient building A is an ancient building to be repaired, and there are some missing parts or damaged parts. Therefore, its corresponding target plane structure diagram Aa (derived through the BIM model based on the actual three-dimensional scanning data) must also have some missing parts or damaged parts, that is, the target plane structure diagram Aa is incomplete, and the resulting matching plane structure diagram A'a is a complete plane structure diagram of another main building A' that contains all or part of the structure of the matching target building A. Therefore, there must be differences between the two (including differences caused by missing parts or damaged parts to be repaired and other differences).

[0106] For these difference parts, the difference plane structure diagrams corresponding to the difference parts can be further determined, thereby obtaining the morphological data of the difference parts, wherein the morphological data includes one of size, orientation, architectural style, axis, symmetry or any combination thereof.

[0107] As an example, if the morphological data characterizes the architectural style as "European style, pointed roof" and the orientation is "missing in the northeast direction", the corresponding 3D reconstruction prompt word can be "the part to be repaired is in the northeast direction, and the repair options include European style and pointed roof".

[0108] The output of the three-dimensional reconstruction prompt word can be obtained by querying a pre-established morphological data-prompt word mapping database, or a prompt word generation model can be pre-trained, and the training samples include morphological data-prompt word associated data pairs. By inputting morphological data, the generation model can output prompt words, etc. This embodiment does not make specific restrictions on this. The generation of prompt words can also refer to the prior art.

[0109] On this basis, steps S500-S600 are performed:

[0110] S500: inputting the 3D reconstruction prompt words and the 3D structural diagram of the target ancient building to be restored into a graph generation and image artificial intelligence engine, and the graph generation and image artificial intelligence engine outputs a plurality of candidate graphs of the 3D structural restoration effect of the target ancient building to be restored;

[0111] S600: Evaluate the multiple three-dimensional structural restoration effect candidate images to obtain a three-dimensional structural restoration plan image of the target ancient building to be restored.

[0112] As mentioned above, the deeply evolved artificial intelligence engines in the existing technology can already replace human designers to complete various restoration simulation tasks. For example, the relevant drawings of the building to be restored are input into the artificial intelligence (AI) engine, and the artificial intelligence engine can derive recommended restoration simulation plans based on the big data model.

[0113] However, due to the lack of effective prompt words, the output of the AI ​​engine in the above-mentioned input-output process is mostly empty and lacks effectiveness. This is related to the lack of historical three-dimensional data in the field of ancient architecture and the insufficient expectations of the three-dimensional modeling database.

[0114] Based on this, the improvement of the present application lies in inputting the three-dimensional reconstruction prompt words and the three-dimensional structural diagram of the target ancient building to be restored into the image generation artificial intelligence engine, thereby giving the AI ​​engine more guidance and correction capabilities.

[0115] As an example, the image-generating AI engine uses the partial image description text and a picture input by the user as the prompt word input to intelligently generate preliminary design pictures. The most typical examples are the Stable Diffusion tool released by Stability AI in August 2022 and the FUgenerator tool released by Tongji CAUP in March 2023. It can be understood that the general large model of the image-generating industry configured by the general image-generating AI engine can also have the functions of text-generating text, text-generating picture, and image-generating picture at the same time.

[0116] Therefore, as Example 1, when the 3D reconstruction prompt word and the 3D structural diagram of the target ancient building to be restored are input into the image generation artificial intelligence engine, the image generation artificial intelligence engine may first use the 3D reconstruction prompt word to generate further 3D reconstruction restoration components, and then splice and fuse them with the 3D structural diagram of the target ancient building to be restored to obtain a candidate diagram of the 3D structural restoration effect;

[0117] As another example 2, when the 3D reconstruction prompt words and the 3D structure diagram of the target ancient building to be restored are input into the image generation artificial intelligence engine, the image generation artificial intelligence engine may also directly generate a plurality of preliminary 3D structure restoration effect candidate images first, and then perform deviation correction considering the 3D reconstruction prompt words, so as to obtain the 3D structure restoration effect candidate images;

[0118] Of course, the image-generated artificial intelligence engine can also adopt other methods. The above description is only an example. The working principles of each image-generated artificial intelligence engine may be somewhat different, but based on the above introduction, it can be seen that the purpose of outputting multiple three-dimensional structure repair effect candidate images in this application can be achieved.

[0119] For example, Example 2 may also include using the 3D reconstruction prompt words to generate further 3D reconstruction repair parts, and then splicing and fusing them with the 3D structure diagram of the target ancient building to be repaired to obtain a candidate diagram of the 3D structure repair effect, that is, the process of fusing Example 1 and Example 2, and so on.

[0120] Step S600 evaluates the multiple three-dimensional structure repair effect candidate images, which can be computer automatic scoring evaluation, expert experience scoring evaluation, or a combination of the two. The evaluation and scoring belong to the existing technology and will not be described in detail in this embodiment.

[0121] Based on the above embodiments, see Figure 4 , Figure 4 yes Figure 1 The embodiment provides a schematic diagram of subsequent optimization processing steps for obtaining a three-dimensional structure repair solution diagram.

[0122] Specifically, after obtaining the three-dimensional structural restoration plan diagram of the target ancient building to be restored in step S600, the method further includes:

[0123] Obtaining a planar structure repair image corresponding to the three-dimensional structure repair image;

[0124] The plane structure repair diagram is updated into the preset plane structure diagram database.

[0125] The above preferred embodiments can realize standardized data utilization of the method, thereby realizing closed-loop learning and updating of the entire process of the database.

[0126] Furthermore, after obtaining the three-dimensional structural restoration plan diagram of the target ancient building to be restored in step S600, the method further includes:

[0127] digitizing the three-dimensional structural repair plan diagram;

[0128] The three-dimensional structure repair plan diagram is associated with the target plane structure diagram and stored in the ancient building information database.

[0129] In the above example, by creating an ancient building information database, digital recording and preservation of ancient building information is achieved, making it easier for staff from various departments to quickly and accurately retrieve and apply the required ancient building information, thereby promoting the efficient and safe development of ancient building protection work.

[0130] Preferably, creating an ancient building information database specifically includes:

[0131] First, we need to combine the purpose of database construction and data content (such as the name, age, style of ancient buildings).

[0132] etc.), data characteristics, etc. to reasonably determine the structure and fields of the database to ensure that the collected ancient building information is accurate and comprehensive; secondly, technical personnel should select a suitable ancient building information database management system according to needs, such as MySQL, Oracle, etc. Different database management systems have different functions and characteristics, and technical personnel can choose according to specific circumstances; thirdly, designers need to create table indexes according to the ancient building information query needs of relevant departments to further improve the operational efficiency of data retrieval; finally, technical personnel need to perform database backup operations regularly to prevent data loss, ensure the safe storage of backup files, and test the recovery process of backup files to ensure that data information can be successfully restored after deletion.

[0133] Preferably, when entering and managing ancient building data information, it also includes:

[0134] First, the collected ancient building information will be timely entered into the ancient building information database through manual or digital scanning, so as to facilitate people to understand and call up ancient buildings; secondly, the database will be managed and organized, and basic functions such as adding, modifying and deleting will be added to support operations such as classification and labeling of data information, and accurate retrieval and quick access to ancient building information will be achieved by creating indexes; finally, authority management will be strengthened to ensure data security, that is, staff will ensure the confidentiality and integrity of ancient building information in the database by setting security measures and setting access rights for people with different identities.

[0135] The aforementioned cloud-based digital technology-based ancient building restoration modeling and reconstruction method can be automatically implemented through various forms of electronic devices through computer-readable program instructions; the computer-readable program instructions can be stored in different forms of storage media and loaded into computer electronic devices for execution.

[0136] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0137] In the introduction Figure 1-Figure 4 Based on the principle of the method embodiment involved, Figure 5 Show implementation Figure 1 A schematic diagram of the connection of the functional hardware combination modules of the method embodiment.

[0138] exist Figure 5 In the example, the implementation is shown Figure 1 The method includes the following hardware components:

[0139] 3D laser scanning equipment to obtain 3D structural information of the target ancient building to be restored;

[0140] BIM simulation model, based on the BIM simulation model improved by the point cloud model, quickly generates a standard CAD plan;

[0141] Computer image processing equipment is used to build three-dimensional models of ancient buildings and reproduce the models; data resources are acquired to form a comprehensive database; comparison technology is implemented to compare the acquired images of the shape, color, texture, etc. of the ancient buildings, and an accurate and comprehensive evaluation is given based on the comparison results, providing an important reference for the creation of ancient building protection plans.

[0142] Specifically, based on the three-dimensional structure information, a three-dimensional structure diagram of the target ancient building to be restored is generated; based on the plane structure information, a computer image processing device uses a BIM simulation model to obtain a target plane structure diagram of the target ancient building;

[0143] Figure 5 It also shows Figure 1 The functions of the preset plane structure diagram database, ancient building information database and image-generating artificial intelligence engine utilized in the method embodiment have been introduced in the aforementioned method embodiment and will not be repeated here.

[0144] For other technologies, principles, algorithms or models not elaborated in detail in this application, please refer to the prior art.

[0145] The present invention realizes the modeling and reconstruction of ancient buildings based on digital technology, and assists the artificial intelligence engine to obtain multiple candidate solutions and then evaluates and obtains the optimal restoration solution. In the technical solution of the present invention, the large model input of the AI ​​engine is no longer just the existing three-dimensional measurement data or drawing data of the building to be restored, but includes three-dimensional reconstruction prompt words and three-dimensional structure diagrams of the target ancient building to be restored. The three-dimensional reconstruction prompt words are obtained by matching and searching in a relatively complete preset plane structure diagram database, which conforms to the actual characteristics that the plane drawing database in the field of ancient buildings is relatively complete and the three-dimensional structure database is relatively lacking. Therefore, the method of the present invention is extensible, and the obtained AI prompt words can improve the pertinence of the candidate solutions output by the AI ​​engine, ensuring the standardization of the ancient building restoration modeling and reconstruction process.

[0146] In the above-mentioned embodiment section, the present invention provides multiple embodiments, each of which can constitute an independent technical solution and may contribute to the prior art and solve corresponding technical problems. However, it should be pointed out that different embodiments can be combined with each other without violating logic; at the same time, each embodiment can solve at least one technical problem, but it is not required that each individual embodiment solves multiple or all technical problems.

[0147] At the same time, in the specific implementation of this application, if user-related data is involved, when the embodiment of this application is applied to a specific product or technology, the user's permission or consent must be obtained, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0148] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A digital technology-based ancient building restoration modeling and reconstruction method, the method is implemented based on electronic equipment, characterized in that: The method comprises the following steps: S100: Acquire three-dimensional structural information and plane structural information of the target ancient building to be restored; S200: generating a three-dimensional structural diagram of the target ancient building to be restored based on the three-dimensional structural information; Based on the plane structure information, a target plane structure diagram of the target ancient building is obtained; S300: performing a matching search in a preset plane structure diagram database based on the target plane structure diagram to obtain at least one matching plane structure diagram; S400: performing semantic analysis on the matching plane structure graph to obtain a plurality of three-dimensional reconstruction prompt words; S500: inputting the 3D reconstruction prompt words and the 3D structural diagram of the target ancient building to be restored into a graph generation and image artificial intelligence engine, and the graph generation and image artificial intelligence engine outputs a plurality of candidate graphs of the 3D structural restoration effect of the target ancient building to be restored; S600: Evaluate the multiple three-dimensional structural restoration effect candidate images to obtain a three-dimensional structural restoration plan image of the target ancient building to be restored.

2. The ancient building restoration modeling and reconstruction method based on digital technology as claimed in claim 1 is characterized in that: The matching plane structure diagram obtained in step S300 is a complete plane structure diagram including the matching target building; The step S400 performs semantic analysis on the matching plane structure diagram to obtain a plurality of three-dimensional reconstruction prompt words, specifically including: Determine the difference between the complete plane structure diagram and the target plane structure diagram; The difference part is analyzed to determine the plurality of three-dimensional reconstruction prompt words.

3. The ancient building restoration modeling and reconstruction method based on digital technology as claimed in claim 1 is characterized in that: Step S100 obtains the three-dimensional structural information of the target ancient building to be restored, specifically including: A laser scanner is used to scan the target ancient building to be restored from multiple angles to obtain a discrete three-dimensional point cloud data set; Perform Gaussian mapping on each discrete 3D point cloud data subset collected at the same angle to obtain a 3D point cloud data set after Gaussian mapping; The three-dimensional structure information is obtained by performing splicing and fitting based on the three-dimensional point cloud data set processed by the Gaussian mapping.

4. The ancient building restoration modeling and reconstruction method based on digital technology as claimed in claim 3 is characterized in that: The multiple angles include at least a first reference angle φ1, a second deviation angle φ2 that deviates from the first reference angle φ1 by a first preset arc θ1, and a third deviation angle φ3 that deviates from the first reference angle φ1 by a second preset arc θ2; Each discrete 3D point cloud data subset collected at the same angle is processed by Gaussian mapping, including: Assume angle φ i Scan to obtain discrete 3D point cloud data subset D i , D i ={X i1 ,X i2 ,L,X iN },i=1,2,3; ， For discrete 3D point cloud data subset D i Every element X in ij ,j=1,2,L,N;N>1;perform Gaussian mapping processing.

5. The ancient building restoration modeling and reconstruction method based on digital technology as claimed in claim 3 is characterized in that: Step S100 obtains the plane structure information of the target ancient building to be restored, which specifically includes: Obtaining a BIM simulation model of the target ancient building; Improve the BIM simulation model based on the discrete three-dimensional point cloud data set; The plane structure information of the target ancient building to be restored is generated through the improved BIM simulation model.

6. The ancient building restoration modeling and reconstruction method based on digital technology as claimed in claim 5 is characterized in that: Step S200 obtains a target plane structure diagram of the target ancient building based on the plane structure information, specifically including: A standard CAD plan view can be quickly generated through the improved BIM simulation model.

7. The ancient building restoration modeling and reconstruction method based on digital technology as claimed in claim 2 is characterized in that: The analyzing the difference part and determining the plurality of three-dimensional reconstruction prompt words specifically includes: Obtaining a difference plane structure diagram corresponding to the difference part; Based on the difference plan structure diagram, determining the morphological data of the difference part, the morphological data including one of size, orientation, architectural style, axis, symmetry or any combination thereof; Based on each of the morphological data, the three-dimensional reconstruction prompt word is determined.

8. The ancient building restoration modeling and reconstruction method based on digital technology as claimed in claim 1 is characterized in that: After the three-dimensional structural restoration plan diagram of the target ancient building to be restored is obtained in step S600, the method further includes: Obtaining a planar structure repair image corresponding to the three-dimensional structure repair image; The plane structure repair diagram is updated into the preset plane structure diagram database.

9. The ancient building restoration modeling and reconstruction method based on digital technology as claimed in claim 1, characterized in that: After the three-dimensional structural restoration plan diagram of the target ancient building to be restored is obtained in step S600, the method further includes: digitizing the three-dimensional structural repair plan diagram; The three-dimensional structure repair plan diagram is associated with the target plane structure diagram and stored in the ancient building information database.

10. A computer program product, comprising a computer program or computer executable instructions, which, when executed by a processor, implements the ancient building restoration, modeling and reconstruction method based on digital technology as described in any one of claims 1 to 9.

Images