Historical building stone facing repairing effect evaluation method and equipment

Abstract

The invention provides a historical building stone facing repairing effect evaluation method and equipment. The method comprises the following steps: calculating a third comprehensive weight of each index of a historical building stone facing repairing effect; and based on the image training set and the image test set of the historical building stone veneer and the scores of the indexes of the corresponding repairing effect, training a historical building stone veneer repairing effect scoring model, and inputting an image of the historical building stone veneer to be identified into the trained historical building stone veneer repairing effect scoring model. Obtaining the score of each index of the repairing effect corresponding to the image of the historical building stone veneer to be identified; based on the score of each index of the repairing effect corresponding to the image of the historical building stone veneer to be identified and the third comprehensive weight of each index of the repairing effect, obtaining a comprehensive score of the image of the historical building stone veneer to be identified; according to the method, the repairing effect of the historical building stone veneer can be efficiently and reliably evaluated.

Description

Technical Field

[0001] The present invention relates to a method and equipment for evaluating the repair effect of stone facings of historical buildings. Background Art

[0002] As an integral part of cultural heritage, historic buildings require regular restoration to preserve their unique historical value and cultural significance. Stone veneer, one of the most common exterior wall materials used in historic buildings, is often found in high-value, high-rise historic structures. Currently, well-established restoration practices are available, along with extensive case studies. However, research into the evaluation of restoration effectiveness is lacking. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and device for evaluating the repair effect of stone facings of historical buildings.

[0004] To solve the above problems, the present invention provides a method for evaluating the repair effect of stone facings of historical buildings, comprising:

[0005] The third comprehensive weight of various indicators for calculating the repair effect of the stone facing of historical buildings;

[0006] Based on the image training set and image test set of historical building stone facings and the corresponding scores of various indicators of the repair effect, a historical building stone facing repair effect scoring model is trained. The image training set and image test set both include: damaged image samples and undamaged image samples; the image samples in the image training set and image test set do not overlap with each other;

[0007] Input the image of the stone facing of the historical building to be identified into the trained scoring model for the repair effect of the stone facing of the historical building to obtain the score of various indicators of the repair effect corresponding to the image of the stone facing of the historical building to be identified;

[0008] Based on the scores of various indicators of the repair effect corresponding to the image of the stone facing of the historical building to be identified and the third comprehensive weight of each indicator of the repair effect, a comprehensive score of the image of the stone facing of the historical building to be identified is obtained.

[0009] Furthermore, in the above method, the scores of the image training set and the image test set and the corresponding indicators of the repair effect are divided into four levels, which are ranked according to the scores, namely, level 1 (excellent), level 2 (good), level 3 (qualified), and level 4 (unqualified);

[0010] Among them, the first-level excellent: the restoration of the stone veneer has restored the original historical appearance and addressed almost all visual and quality issues;

[0011] Level 2: Good; the restoration of the stone veneer has essentially restored its original historical appearance and addressed most of the visual and quality issues;

[0012] Level 3 qualified: The stone veneer is close to its original historical appearance after repair, and the quality problems of the veneer have been basically solved;

[0013] Level 4: Unqualified: The stone surface does not conform to its original historical appearance after repair, and there are many quality and appearance issues that have not been addressed.

[0014] Furthermore, in the above method, the third comprehensive weight of each indicator of the repair effect of the stone facing of the historical building is calculated, including:

[0015] The first comprehensive weight of each indicator of the repair effect is calculated using the hierarchical analysis method;

[0016] The entropy weight method is used to calculate the second comprehensive weight of each indicator of the repair effect;

[0017] Based on the first comprehensive weight and the second comprehensive weight, a third comprehensive weight is calculated.

[0018] Furthermore, in the above method, the analytic hierarchy process is used to calculate the first comprehensive weight of each indicator of the repair effect, including:

[0019] The historical building assessment system is divided into four levels from high to low: target level, criterion level, sub-criteria level and indicator level, where the next level is a sub-level of the previous level; each element in the indicator level is an indicator of the repair effect;

[0020] The hierarchical analysis method is used, and based on the four levels of target layer, criterion layer, sub-criterion layer and indicator layer, the first comprehensive weight of each indicator of the repair effect is calculated.

[0021] Furthermore, in the above method, each element in the indicator layer, i.e., an indicator, includes:

[0022] The elements of the lower indicator layer of the sub-criteria layer of remote stone repair quality include: surface pollution treatment-alkali efflorescence, surface pollution treatment-plant microbial coverage, surface pollution treatment-water spots, surface pollution treatment-rust spots, surface pollution treatment-white bloom, surface pollution treatment-paint coverage and damage treatment-cracking;

[0023] The elements of the lower indicator layer of the sub-criteria layer of the quality of remote joint repair include: shedding treatment;

[0024] The elements of the lower indicator layer of the sub-criteria layer of the remote stone repair appearance include: consistency of shape and size, overall color coordination, color difference of the new stone surface, local repair color difference and local stone yellowing and discoloration treatment;

[0025] The elements of the lower indicator layer of the sub-criteria layer of the close-range stone repair quality include: damage treatment-chipped edges, damage treatment-chipped corners, damage treatment-plate surface pits, damage treatment-holes, hollowing treatment and weathering treatment;

[0026] The elements of the lower indicator layer of the sub-criteria layer of the close-space joint repair quality include: aging and loosening treatment, defect treatment and plant and microbial coverage treatment;

[0027] The elements of the lower indicator layer of the sub-criteria layer of the close-range stone repair appearance include: polished stone brightness, polished stone texture, rough stone coarseness, rough stone texture form, rough stone texture, flatness - adjacent stone finish, flatness - finish within a certain range;

[0028] Among them, the elements of the lower criterion layer of the target layer include: remote evaluation, close evaluation;

[0029] The elements of the lower sub-criteria layer of the remote evaluation criterion layer include: remote stone repair quality, remote joint repair quality and remote stone repair appearance;

[0030] The elements of the sub-criteria layer of the close-range evaluation criterion layer include: close-range stone repair quality, close-range joint repair quality, close-range stone repair appearance and close-range joint repair appearance.

[0031] Furthermore, in the above method, the analytic hierarchy process is adopted, and based on the four levels of target layer, criterion layer, sub-criteria layer and indicator layer, the first comprehensive weight of each indicator of the repair effect is calculated, including:

[0032] By comparing the importance of the elements in each level in the target layer, criterion layer, sub-criteria layer, and indicator layer, an n*n comparison matrix A corresponding to each level is constructed, where n is the number of elements in each level and the factors in the comparison matrix A are a ij , represents the comparison value of the importance of the i-th element and the j-th element in each level; the comparison value of the importance is given using Santy's 1-9 scale method, where 1 represents equal importance, 3 represents slightly important, 5 represents quite important, 7 represents obviously important, 9 represents absolutely important, and 2, 4, 6, and 8 represent the middle values ​​of two adjacent judgments. 1 / 2, ... 1 / 9 represent the importance comparison of the two elements before and after the order is swapped;

[0033] Calculate the nth root of the product of the factors in each row i of the judgment matrix A, that is, the geometric mean, as follows:

[0034]

[0035] The j in the matrix A represents the column, and n is the number of elements at each level;

[0036] The geometric mean M i Normalize to get the weight ω of each element in each level i , the formula is as follows:

[0037]

[0038] Calculate the maximum eigenvalue of the judgment matrix for consistency testing:

[0039]

[0040] The consistency ratio CR test is used to determine whether each matrix A is reasonable:

[0041]

[0042] Among them, RI is the random consistency index, which is obtained by looking up the table; if CR < 0.1, it is reasonable and passes the consistency test; if it is unreasonable, the comparison value of the importance of the i-th element and the j-th element in each level is re-determined until it passes the consistency test;

[0043] Based on the weight ω of each element of the matrix A corresponding to each level through consistency check i , calculate the first comprehensive weight of each indicator of the repair effect, where the weight of the element corresponding to the indicator is ω i , the weight ω of the element corresponding to the subcriteria layer i and the corresponding element weight ω i The product of is used as the first comprehensive weight of each indicator of the repair effect.

[0044] Furthermore, in the above method, the entropy weight method is used to calculate the second comprehensive weight of each indicator of the repair effect, including:

[0045] Invite m experts to score n indicators in the established evaluation index system, and summarize and organize the scoring results to obtain the original data matrix X:

[0046]

[0047] The original data matrix X is standardized:

[0048] Normalization of positive indicators:

[0049] Negative indicator normalization:

[0050] Among them, the matrix y ij Where i represents the expert number, j represents the indicator number, i∈m=,j∈n, there are m experts and n indicators;

[0051] Determine the entropy value of the indicator:

[0052] The entropy value of the jth indicator e The calculation formula for j is as follows:

[0053]

[0054] Calculate the entropy weight u of the jth indicator j , as the second comprehensive weight:

[0055]

[0056] Furthermore, in the above method, the third comprehensive weight is calculated based on the first comprehensive weight and the second comprehensive weight, including:

[0057] The multiplier synthesis normalization method is used to couple the first comprehensive weight obtained by the hierarchical analysis method with the second comprehensive weight obtained by the entropy weight method to obtain the third comprehensive weight v of each indicator in the indicator layer. i ,

[0058]

[0059] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the processor is enabled to execute any one of the methods described above.

[0060] According to another aspect of the present invention, there is further provided a computer device, comprising:

[0061] processor; and

[0062] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0063] Compared with the existing technology, the present invention calculates the third comprehensive weight of various indicators of the repair effect of the stone finishes of historical buildings; based on the image training set and image test set of the historical building stone finishes and the scores of various indicators of the corresponding repair effect, trains a historical building stone finish repair effect scoring model; the image of the historical building stone finish to be identified is input into the trained historical building stone finish repair effect scoring model to obtain the scores of various indicators of the repair effect corresponding to the image of the historical building stone finish to be identified; based on the scores of various indicators of the repair effect corresponding to the image of the historical building stone finish to be identified and the third comprehensive weight of various indicators of the repair effect, obtains the comprehensive score of the image of the historical building stone finish to be identified; the present invention can perform efficient and reliable evaluation of the repair effect of the stone finishes of historical buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 The present invention is a flowchart of a method for evaluating the repair effect of stone facings of historical buildings according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The present invention is further described in detail below with reference to the accompanying drawings.

[0066] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPUs), input / output interfaces, network interfaces and memories.

[0067] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0068] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0069] like Figure 1 As shown, the present invention provides a method for evaluating the repair effect of stone facings of historical buildings, the method comprising:

[0070] Step S1, calculating the third comprehensive weight of various indicators of the repair effect of the stone facing of the historical building;

[0071] Step S2: Training a scoring model for the restoration effect of stone veneers on historical buildings based on a training set of images and a test set of images of stone veneers on historical buildings and scores of various indicators of the corresponding restoration effects, wherein both the training set and the test set include: damaged image samples and undamaged image samples; the image samples in the training set and the test set do not overlap; a higher score in the scoring model for the restoration effect of stone veneers on historical buildings indicates a better restoration effect of the stone veneers in the corresponding image;

[0072] Here, the score of the stone finishing repair effect of historical buildings (0 to 100 points) can be divided into 4 levels, and ranked according to the score, namely level 1 excellent (≥90), level 2 good (≥80), level 3 qualified (≥60), and level 4 unqualified (<60).

[0073] Specifically, to verify the rationality and feasibility of the constructed model, we selected an outstanding historical building with a stone facade in a certain city and conducted a scoring evaluation. The results are as follows: The higher the score after processing, the better the repair effect.

[0074] Level 1 Excellence: The restoration of the stone veneer has restored the original historical appearance and addressed almost all visual and quality issues.

[0075] Level 2, Good; the restoration of the stone finishes has basically restored the original historical appearance and addressed most of the visual and quality issues.

[0076] Level 3 qualified: The stone surface is close to its original historical appearance after repair, and the quality problems of the surface have been basically solved.

[0077] Level 4: Unqualified: The stone surface does not conform to its original historical appearance after repair, and there are many quality and appearance issues that have not been addressed.

[0078]

[0079]

[0080] The total score of the building is 85.45, which indicates that the stone surface repair effect is good. There are some defects, which have little impact on the overall effect and are in line with the actual situation.

[0081] A deep learning neural network model can be built to identify different damage types on stone surfaces through images, such as C01-C09 and C15-C23 in the index layer, facilitating rapid evaluation of corresponding indicators. Training is then performed to identify features, automatically assign scores based on these features, and then multiplying the scores by weights to generate a final score for a holistic assessment of the repair results.

[0082] Specifically, an image dataset can be established: high-definition images can be collected from multiple historical building projects using high-definition SLR cameras, damaged areas can be manually pre-labeled, and a variety of image data enhancement techniques can be used to expand the collected image sample dataset, such as image rotation, image flipping, image fusion, image filling, image stitching, image occlusion, image distortion, and random image erasure.

[0083] The image training set and image test set were established in a ratio of 8:2 (the image verification set and the image test set are the same). In order to reduce the false recognition rate, negative sample images (image samples without damage) were added to the image training set and image test set respectively.

[0084] Step S3: Input the image of the stone facing of the historical building to be identified into the trained scoring model for the repair effect of the stone facing of the historical building to obtain the score of various indicators of the repair effect corresponding to the image of the stone facing of the historical building to be identified;

[0085] Step S4: Obtain a comprehensive score for the image of the stone facing of the historical building to be identified based on the scores of the various indicators of the repair effect corresponding to the image of the stone facing of the historical building to be identified and the third comprehensive weight of the various indicators of the repair effect.

[0086] Here, the present invention can perform efficient and reliable evaluation of the repair effects of stone facings of historical buildings.

[0087] In one embodiment of the method for evaluating the repair effect of the stone facing of a historical building of the present invention, step S1 calculates the third comprehensive weight of various indicators of the repair effect of the stone facing of the historical building, including:

[0088] Step S11, using the analytic hierarchy process to calculate the first comprehensive weight of various indicators of the repair effect;

[0089] Step S12: using the entropy weight method to calculate the second comprehensive weight of each indicator of the repair effect;

[0090] Step S13: Calculate a third comprehensive weight based on the first comprehensive weight and the second comprehensive weight.

[0091] Here, the present invention adopts a combined weighting method combining AHP (analytic hierarchy process) and entropy weight method to calculate the third comprehensive weight.

[0092] In one embodiment of the method for evaluating the repair effect of stone facings of historical buildings of the present invention, step S11 uses the analytic hierarchy process to calculate the first comprehensive weight of various indicators of the repair effect, including:

[0093] Step S111: Divide the historical building evaluation system into four levels from high to low: target level, criterion level, sub-criterion level, and indicator level, wherein the next level is a sub-level of the previous level; each element in the indicator level is an indicator of the repair effect;

[0094] Here, we propose evaluation levels for observation distances, both near and far, for evaluating the effectiveness of stone veneer repairs. Based on the material characteristics of the stone veneer and the repair objectives, we identify repair quality and appearance as the primary evaluation dimensions.

[0095] The specific indicators are determined by the following methods:

[0096] 1) Extract indicators from relevant standards (national standards, local standards).

[0097] 2) Collect information on the repair of stone finishes, read a large amount of literature, and analyze the factors affecting the repair effect.

[0098] 3) Conduct research on historical buildings with stone facades to understand the condition of the buildings before and after renovation, the goals of the renovation, and any problems encountered during the renovation work.

[0099] Based on the above work, the historical building assessment system was finally determined. It is divided into four levels from high to low: target level, criterion level, sub-criteria level, and indicator level. The specific contents are shown in the following table:

[0100]

[0101] In step S112, the first comprehensive weight of each indicator of the repair effect is calculated based on the four levels of target layer, criterion layer, sub-criterion layer and indicator layer using the hierarchical analysis method.

[0102] In one embodiment of the method for evaluating the repair effect of stone facings of historical buildings of the present invention, the elements in the index layer, i.e., the indicators, include:

[0103] The elements of the lower indicator layer of the sub-criteria layer of remote stone repair quality include: surface pollution treatment-alkali efflorescence, surface pollution treatment-plant microbial coverage, surface pollution treatment-water spots, surface pollution treatment-rust spots, surface pollution treatment-white bloom, surface pollution treatment-paint coverage and damage treatment-cracking;

[0104] The elements of the lower indicator layer of the sub-criteria layer of the quality of remote joint repair include: shedding treatment;

[0105] The elements of the lower indicator layer of the sub-criteria layer of the remote stone repair appearance include: consistency of shape and size, overall color coordination, color difference of the new stone surface, local repair color difference and local stone yellowing and discoloration treatment;

[0106] The elements of the lower indicator layer of the sub-criteria layer of the close-range stone repair quality include: damage treatment-chipped edges, damage treatment-chipped corners, damage treatment-plate surface pits, damage treatment-holes, hollowing treatment and weathering treatment;

[0107] The elements of the lower indicator layer of the sub-criteria layer of the close-space joint repair quality include: aging and loosening treatment, defect treatment and plant and microbial coverage treatment;

[0108] The elements of the lower indicator layer of the sub-criteria layer of the close-range stone repair appearance include: polished stone brightness, polished stone texture, rough stone coarseness, rough stone texture form, rough stone texture, flatness - adjacent stone finish, flatness - finish within a certain range;

[0109] Among them, the elements of the lower criterion layer of the target layer include: remote evaluation, close evaluation;

[0110] The elements of the lower sub-criteria layer of the remote evaluation criterion layer include: remote stone repair quality, remote joint repair quality and remote stone repair appearance;

[0111] The elements of the sub-criteria layer of the close-range evaluation criterion layer include: close-range stone repair quality, close-range joint repair quality, close-range stone repair appearance and close-range joint repair appearance.

[0112] In one embodiment of the method for evaluating the restoration effect of stone facings of historical buildings of the present invention, step S112 uses the analytic hierarchy process to calculate the first comprehensive weight of each restoration effect indicator based on four levels: target level, criterion level, sub-criterion level, and indicator level, including:

[0113] Step S1121: By comparing the importance of the elements in each level of the target layer, criterion layer, sub-criteria layer, and indicator layer, an n*n comparison matrix A corresponding to each level is constructed, where n is the number of elements in each level and the factors in the comparison matrix A are a. ij , represents the comparison value of the importance of the i-th element and the j-th element in each level; the comparison value of the importance is given using Santy's 1-9 scale method, where 1 represents equal importance, 3 represents slightly important, 5 represents quite important, 7 represents obviously important, 9 represents absolutely important, and 2, 4, 6, and 8 represent the middle values ​​of two adjacent judgments. 1 / 2, ... 1 / 9 represent the importance of comparing the order of two elements before and after they are swapped.

[0114] Here, the weights of each element in each level are determined by comparing them pairwise. The relative scale of the same level is used when comparing to avoid the difficulty of comparing different factors in different levels and improve the accuracy. ijThe comparison result (comparison importance value) of the i-th factor of the elements at a certain level relative to the j-th factor is given using Santy's 1-9 scale method. The more important one is given a higher scale value.

[0115] Here, based on a ij , we can use the square root method to calculate the approximate value of the judgment matrix eigenvector. After normalizing the approximate value of the matrix eigenvector, we can get the weight vector;

[0116] Step S1122: Calculate the nth root of the product of the factors in each row i of the judgment matrix A, that is, the geometric mean, using the following formula:

[0117]

[0118] The j in the matrix A represents the column, n is the size of the matrix A n*n, and n is the number of elements at each level;

[0119] Step S1123, the geometric mean M i Normalize to get the weight ω of each element in each level i , the formula is as follows:

[0120]

[0121] Step S1124: Calculate the maximum eigenvalue of the judgment matrix for consistency check:

[0122]

[0123] Step S1125: Check whether each matrix A is reasonable by using the consistency ratio CR test:

[0124]

[0125] Among them, RI is the random consistency index, which is obtained by looking up the table; if CR < 0.1, it is reasonable and passes the consistency test; if it is unreasonable, the comparison value of the importance of the i-th element and the j-th element in each level is re-determined until the consistency test passes;

[0126] Step S1126: Based on the weights ω of each element corresponding to the matrix A at each level through the consistency check i , calculate the first comprehensive weight of each indicator of the repair effect, where the weight of the element corresponding to the indicator is ω i , the weight ω of the element corresponding to the subcriteria layer i and the corresponding element weight ω i The product of is used as the first comprehensive weight of each indicator of the repair effect.

[0127] Specifically, after the above calculation process and consistency check, the weights of indicators at each level and the first comprehensive weight are calculated.

[0128]

[0129]

[0130] As shown in the table above, the first comprehensive weight of the indicator surface pollution treatment - alkali efflorescence (C1) is 0.99%, and the weight of remote assessment (A1) is ω i =54.545%, weight of long-distance stone repair quality ω i =63.699% and the weight of surface contamination treatment-alkali alkali (C1) ω i =2.863% and so on.

[0131] In one embodiment of the method for evaluating the repair effect of stone facings of historical buildings of the present invention, step S12 uses the entropy weight method to calculate the second comprehensive weight of various indicators of the repair effect, including:

[0132] Step S121, constructing an evaluation matrix:

[0133] Invite m experts to score n indicators in the established evaluation index system, and summarize and organize the scoring results to obtain the original data matrix X:

[0134]

[0135] Here, the full score can be 10 points, with higher values ​​for important indicators;

[0136] Step S122: Standardization of evaluation matrix

[0137] The original data matrix X obtained above is standardized:

[0138] Normalization of positive indicators:

[0139] Negative indicator normalization:

[0140] Among them, the matrix y ij Where i represents the expert number, j represents the indicator number, i∈m=,j∈n, there are m experts and n indicators;

[0141] Step S123, determine the entropy value of the indicator:

[0142] The entropy value e of the jth indicator j The calculation formula is as follows:

[0143]

[0144] Step S124, calculate the j-th index entropy weight u j , as the second comprehensive weight:

[0145]

[0146] Here, based on the entropy weight method, each indicator u j The values ​​are as follows:

[0147]

[0148]

[0149] In one embodiment of the method for evaluating the repair effect of stone facings of historical buildings of the present invention, step S13, based on the first comprehensive weight and the second comprehensive weight, calculates a third comprehensive weight, including:

[0150] The multiplier synthesis normalization method is used to couple the first comprehensive weight obtained by the hierarchical analysis method with the second comprehensive weight obtained by the entropy weight method to obtain the third comprehensive weight v of each indicator in the indicator layer. i ,

[0151]

[0152]

[0153]

[0154] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the processor is enabled to execute any one of the methods described above.

[0155] According to another aspect of the present invention, there is further provided a computer device, comprising:

[0156] processor; and

[0157] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0158] The detailed contents of the various device embodiments of the present invention can be found in the corresponding parts of the various method embodiments, which will not be repeated here.

[0159] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

[0160] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0161] In addition, a portion of the present invention may be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The program instructions for calling the method of the present invention may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-carrying medium, and / or stored in a working memory of a computer device that operates according to the program instructions. Here, according to one embodiment of the present invention, a device is included, which includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to operate based on the aforementioned methods and / or technical solutions according to multiple embodiments of the present invention.

[0162] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the invention is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalents of the claims be encompassed within the present invention. Any figure marks in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. Words such as first and second are used to indicate names and do not indicate any particular order.

Claims

1. A method for evaluating the effect of stone veneer repair on historical buildings, characterized in that: include: The third comprehensive weight of various indicators for calculating the repair effect of the stone facing of historical buildings; Based on the image training set and image test set of historical building stone facings and the corresponding scores of various indicators of the repair effect, a historical building stone facing repair effect scoring model is trained. The image training set and image test set both include: damaged image samples and undamaged image samples; the image samples in the image training set and image test set do not overlap with each other; Input the image of the stone facing of the historical building to be identified into the trained scoring model for the repair effect of the stone facing of the historical building to obtain the score of various indicators of the repair effect corresponding to the image of the stone facing of the historical building to be identified; Based on the scores of various indicators of the repair effect corresponding to the image of the stone facing of the historical building to be identified and the third comprehensive weight of each indicator of the repair effect, a comprehensive score of the image of the stone facing of the historical building to be identified is obtained.

2. The method for evaluating the repair effect of stone facings of historical buildings according to claim 1, wherein: The scores of the image training set and the image test set and the corresponding indicators of the repair effect are divided into four levels, and are ranked according to the scores, namely level 1 excellent, level 2 good, level 3 qualified and level 4 unqualified; Among them, the first-level excellent: the restoration of the stone veneer has restored the original historical appearance and addressed almost all visual and quality issues; Level 2: Good; the restoration of the stone veneer has essentially restored its original historical appearance and addressed most of the visual and quality issues; Level 3 qualified: The stone veneer is close to its original historical appearance after repair, and the quality problems of the veneer have been basically solved; Level 4: Unqualified: The stone surface does not conform to its original historical appearance after repair, and there are many quality and appearance issues that have not been addressed.

3. The method for evaluating the repair effect of stone facings of historical buildings according to claim 1, wherein: The third comprehensive weight of various indicators used to calculate the restoration effect of stone veneers on historical buildings includes: The first comprehensive weight of each indicator of the repair effect is calculated using the hierarchical analysis method; The entropy weight method is used to calculate the second comprehensive weight of each indicator of the repair effect; Based on the first comprehensive weight and the second comprehensive weight, a third comprehensive weight is calculated.

4. The method for evaluating the repair effect of stone facings of historical buildings according to claim 3, wherein: The first comprehensive weight of each indicator of the repair effect is calculated using the hierarchical analysis method, including: The historical building assessment system is divided into four levels from high to low: target level, criterion level, sub-criteria level and indicator level, where the next level is a sub-level of the previous level; each element in the indicator level is an indicator of the repair effect; The hierarchical analysis method is used, and based on the four levels of target layer, criterion layer, sub-criterion layer and indicator layer, the first comprehensive weight of each indicator of the repair effect is calculated.

5. The method for evaluating the repair effect of stone facings of historical buildings according to claim 4, wherein: The various elements in the indicator layer, namely indicators, include: The elements of the lower indicator layer of the sub-criteria layer of remote stone repair quality include: surface pollution treatment-alkali efflorescence, surface pollution treatment-plant microbial coverage, surface pollution treatment-water spots, surface pollution treatment-rust spots, surface pollution treatment-white bloom, surface pollution treatment-paint coverage and damage treatment-cracking; The elements of the lower indicator layer of the sub-criteria layer of the quality of remote joint repair include: shedding treatment; The elements of the lower indicator layer of the sub-criteria layer of the remote stone repair appearance include: consistency of shape and size, overall color coordination, color difference of the new stone surface, local repair color difference and local stone yellowing and discoloration treatment; The elements of the lower indicator layer of the sub-criteria layer of the close-range stone repair quality include: damage treatment-chipped edges, damage treatment-chipped corners, damage treatment-plate surface pits, damage treatment-holes, hollowing treatment and weathering treatment; The elements of the lower indicator layer of the sub-criteria layer of the close-space joint repair quality include: aging and loosening treatment, defect treatment and plant and microbial coverage treatment; The elements of the lower indicator layer of the sub-criteria layer of the close-range stone repair appearance include: polished stone brightness, polished stone texture, rough stone coarseness, rough stone texture form, rough stone texture, flatness - adjacent stone finish, flatness - finish within a certain range; Among them, the elements of the lower criterion layer of the target layer include: remote evaluation, close evaluation; The elements of the lower sub-criteria layer of the remote evaluation criterion layer include: remote stone repair quality, remote joint repair quality and remote stone repair appearance; The elements of the sub-criteria layer of the close-range evaluation criterion layer include: close-range stone repair quality, close-range joint repair quality, close-range stone repair appearance and close-range joint repair appearance.

6. The method for evaluating the repair effect of stone facings of historical buildings according to claim 5, wherein: The analytic hierarchy process is used to calculate the first comprehensive weight of each indicator of the repair effect based on the four levels of target layer, criterion layer, sub-criteria layer and indicator layer, including: By comparing the importance of the elements in each level in the target layer, criterion layer, sub-criteria layer, and indicator layer, an n*n comparison matrix A corresponding to each level is constructed, where n is the number of elements in each level and the factors in the comparison matrix A are a ij , represents the comparison value of the importance of the i-th element and the j-th element in each level; the comparison value of the importance is given using Santy's 1-9 scale method, where 1 represents equal importance, 3 represents slightly important, 5 represents quite important, 7 represents obviously important, 9 represents absolutely important, and 2, 4, 6, and 8 represent the middle values ​​of two adjacent judgments. 1 / 2, ... 1 / 9 represent the importance comparison of the two elements before and after the order is swapped; Calculate the nth root of the product of the factors in each row i of the judgment matrix A, that is, the geometric mean, as follows: The j in the matrix A represents the column, and n is the number of elements at each level; The geometric mean M i Normalize to get the weight ω of each element in each level i , the formula is as follows: Calculate the maximum eigenvalue of the judgment matrix for consistency testing: The consistency ratio CR test is used to determine whether each matrix A is reasonable: Among them, RI is the random consistency index, which is obtained by looking up the table; if CR < 0.1, it is reasonable and passes the consistency test; if it is unreasonable, the comparison value of the importance of the i-th element and the j-th element in each level is re-determined until the consistency test passes; Based on the weight ω of each element of the matrix A corresponding to each level through consistency check i , calculate the first comprehensive weight of each indicator of the repair effect, where the weight of the element corresponding to the indicator is ω i , the weight ω of the element corresponding to the subcriteria layer i and the corresponding element weight ω i The product of is used as the first comprehensive weight of each indicator of the repair effect.

7. The method for evaluating the repair effect of stone facings of historical buildings according to claim 3, wherein: The entropy weight method is used to calculate the second comprehensive weight of various indicators of the repair effect, including: Invite m experts to score n indicators in the established evaluation index system, and summarize and organize the scoring results to obtain the original data matrix X: The original data matrix X is standardized: Normalization of positive indicators: Negative indicator normalization: Among them, the matrix y ij Where i represents the expert number, j represents the indicator number, i∈m=,j∈n, there are m experts and n indicators; Determine the entropy value of the indicator: The entropy value e of the jth indicator j The calculation formula is as follows: Calculate the entropy weight u of the jth indicator j , as the second comprehensive weight:

8. The method for evaluating the repair effect of stone facings of historical buildings according to claim 3, wherein: Based on the first comprehensive weight and the second comprehensive weight, a third comprehensive weight is calculated, including: The multiplier synthesis normalization method is used to couple the first comprehensive weight obtained by the hierarchical analysis method with the second comprehensive weight obtained by the entropy weight method to obtain the third comprehensive weight v of each indicator in the indicator layer. i , 9. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 8.

10. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: perform the method according to any one of claims 1 to 8.

Images