Method, system, device and storage medium for evaluating the quality of public commemorative space

Abstract

The present invention discloses a method, system, device and storage medium for evaluating the quality of a public memorial space. The method includes: obtaining relevant data within the evaluation area; constructing a public memorial space quality evaluation system, which includes three first-level indicators of publicity, memoriality, and narrativity and corresponding second-level indicators; measuring the data of the second-level indicators corresponding to publicity, memoriality, and narrativity according to the relevant data within the evaluation area, and performing normalization processing; determining the weights of each second-level indicator; superimposing the weights of each second-level indicator data for summarization, and calculating the final evaluation result of the public memorial space quality. Based on multi-source data, starting from the characteristics of the public memorial space, the present invention evaluates from three aspects of publicity, memoriality, and narrativity, determines quantitative evaluation indicators, comprehensively evaluates the quality of the commercial space, makes the evaluation result more in line with the objective reality, and also provides a reference for improving the quality of the public memorial space.

Description

Technical Field

[0001] The present invention relates to a method, a system, a computer device and a storage medium for evaluating the quality of a public memorial space, and belongs to the field of urban planning. Background Art

[0002] A public memorial space is an important type of space, referring to a space with memorial functions or behaviors, which can carry urban memories, meet the spiritual needs of the public, and provide a place for memory inheritance and emotional sustenance for people. Compared with other types of spaces, it has stronger spirituality, richer historical value and deeper cultural connotations. Most of the existing research on public memorial spaces focuses on design strategies and design techniques, etc., lacking quantitative evaluation research on the quality of public memorial spaces, and no complete comprehensive evaluation system has been formed yet. Summary of the Invention

[0003] In view of this, the present invention provides a method, a system, a computer device and a storage medium for evaluating the quality of a public memorial space. Based on multi-source data, starting from the characteristics of the public memorial space, it evaluates from three aspects: publicity, memoriality, and narrativity, determines quantitative evaluation indicators, comprehensively evaluates the quality of the commercial space, makes the evaluation results more in line with the objective reality, and also provides a reference for improving the quality of the public memorial space.

[0004] The first object of the present invention is to provide a method for evaluating the quality of a public memorial space.

[0005] The second object of the present invention is to provide a system for evaluating the quality of a public memorial space.

[0006] The third object of the present invention is to provide a computer device.

[0007] The fourth object of the present invention is to provide a storage medium.

[0008] The first object of the present invention can be achieved by adopting the following technical solutions:

[0009] A method for evaluating the quality of a public memorial space, the method comprising:

[0010] Obtaining relevant data within the evaluation area, the relevant data including SDK population portrait data, POI location interest point data, road data, high-resolution satellite remote sensing images and network photos;

[0011] Constructing a public memorial space quality evaluation system, the public memorial space quality evaluation system including three first-level indicators of publicity, memoriality, and narrativity and corresponding second-level indicators;

[0012] Measure the secondary index data corresponding to publicity, monumentality, and narrativity based on the relevant data within the evaluation area, and perform normalization processing;

[0013] Determine the weights of each secondary index according to the secondary index data after normalization processing;

[0014] Overlay the weights of each secondary index data for aggregation, and calculate the final evaluation result of the public monumentality space quality.

[0015] Furthermore, the secondary indexes corresponding to publicity include the number of people flow, the integrity of facilities, and the traffic convenience. The secondary indexes corresponding to monumentality include the spatial sequence and the visual field sensitivity. The secondary indexes corresponding to narrativity include the richness of elements and the visual directness;

[0016] The measuring of the secondary index data corresponding to publicity, monumentality, and narrativity based on the relevant data within the evaluation area and the normalization processing specifically include:

[0017] Calculate the number of people moving within the unit area according to the population quantity in the SDK population portrait data to represent the people flow index;

[0018] Obtain the spatial distribution of service facilities according to the POI location interest point data, and calculate the facility integrity index using Shannon entropy;

[0019] Obtain the spatial distribution of bus stops, subway stations, and parking lots and the number of parking spaces inside each parking lot according to the POI location interest point data, and calculate the traffic convenience index;

[0020] Based on the road data, combine with high-resolution satellite remote sensing images for correction and adjustment, measure the length of the sections between each memorial node, and calculate the spatial sequence index;

[0021] Based on the road data, combine with high-resolution satellite remote sensing images for correction and adjustment, measure the total length of the tour path and the length of the sections where memorial structures can be seen, and calculate the visual field sensitivity index;

[0022] Use a machine learning model to measure the network photos and evaluate the richness of elements index and the visual directness index;

[0023] Apply the range normalization method to perform normalization processing on the secondary index data.

[0024] Furthermore, the use of a machine learning model to measure the network photos and evaluate the richness of elements index and the visual directness index specifically includes:

[0025] Randomly select a part of street view photos from online photos as scoring sample photos, and construct a richness evaluation scoring table. The richness evaluation scoring table includes three categories: human - type elements, event - type elements, and spatial - type elements. If a scoring sample photo shows any one of the indicators of human - type elements, event - type elements, and spatial - type elements, it is counted as 1 point; if not, it is counted as 0 point. The richness score of each scoring sample photo is obtained by accumulation;

[0026] Based on the random forest model, use the scoring sample photos for machine deep learning to obtain a trained random forest machine learning model;

[0027] Use the trained random forest machine learning model to score the remaining online photos to obtain the evaluation results of the richness index;

[0028] Identify the online photos through visual image semantic segmentation of the deep learning fully convolutional network, and count the area occupied by narrative elements in the photos to obtain the evaluation results of the visual accessibility index.

[0029] Furthermore, calculate the facility integrity index using Shannon entropy as follows:

[0030]

[0031] Among them, P i represents the facility integrity index, m is the number of types of supporting service facilities; T j is the proportion of the number of POIs of the j - type service facility type to the total number of service facility POIs within the range.

[0032] Furthermore, calculate the traffic convenience index as follows:

[0033]

[0034] Among them, K i represents the traffic convenience index, Q i is the number of bus stops and subway stations within the i - th grid range, Q max is the number of bus and subway stations within the public memorial space and its 500 - m buffer zone, R i is the number of parking spaces within the grid range, R max is the number of parking spaces within the public memorial space and its 500 - m buffer zone; Use an online questionnaire to survey the importance weight values of bus and subway stations and parking lots within the public memorial space. a and b represent the importance weight values of bus stops and parking lots respectively.

[0035] Furthermore, use the range normalization method to normalize the secondary - index data, which specifically includes:

[0036] Find the maximum and minimum values of the secondary indicators, and calculate the range;

[0037] Subtract the minimum value of the secondary indicator from each observation value, and divide by the range to obtain the standardized secondary indicator, as shown in the following formula:

[0038] X′ = (X - X min ) / R

[0039] where X′ is the standardized secondary indicator, 0 ≤ X′ ≤ 1, X is the observation value, X max is the maximum value of the secondary indicator, X min is the minimum value of the secondary indicator, and R is the range, R = X max - X min .

[0040] Furthermore, determining the weights of the secondary indicators according to the normalized secondary indicator data specifically includes:

[0041] Assume there are n samples to be evaluated and p secondary indicators, and construct the original indicator matrix, as shown in the following formula:

[0042]

[0043] Perform positive normalization - standardization processing on the original indicator matrix, as shown in the following formula:

[0044]

[0045] where x max is the maximum value under the same secondary indicator;

[0046] Calculate the expected value of the samples to be evaluated as the entropy value, as shown in the following formula:

[0047]

[0048] Define the weights of the secondary indicators. The larger the entropy weight coefficient, the greater the amount of information represented by the secondary indicator, indicating that the secondary indicator plays a greater role in the comprehensive evaluation, as shown in the following formula:

[0049]

[0050] where w j represents the weight of the jth secondary indicator, d j is the entropy weight coefficient, d j = 1 - e j ;

[0051] Perform standardization processing on the matrix indicators so that each column element is divided by the cosine distance of the current column vector, as shown in the following formula:

[0052]

[0053] Construct a standardized weighted matrix and attach the weights of each secondary index to the matrix indexes after standardization:

[0054]

[0055]

[0056] where z ij represents the matrix indexes after standardization, represents the standardized matrix indexes attached with weights;

[0057] Find the optimal and the worst solutions as follows:

[0058]

[0059]

[0060] Construct the relative closeness as follows:

[0061]

[0062]

[0063] where is the distance between the i-th evaluation object and the maximum value, is the distance between the i-th evaluation object and the minimum value, and C i is the relative closeness;

[0064] Sort the weights of the secondary indexes according to the size of the relative closeness C i The larger the relative closeness C i is, the closer the evaluation object is to the optimal value, and the higher the weight of the corresponding secondary index is.

[0065] The second object of the present invention can be achieved by adopting the following technical solutions:

[0066] A public commemorative space quality evaluation system, the system comprising:

[0067] An acquisition module, configured to acquire relevant data within the evaluation area, the relevant data including SDK population portrait data, POI location interest point data, road data, high-resolution satellite remote sensing images, and network photos;

[0068] A construction module, configured to construct a public commemorative space quality evaluation system, the public commemorative space quality evaluation system including three first-level indexes of publicity, commemorativeness, and narrativeness and corresponding secondary indexes;

[0069] A measurement module, configured to measure the secondary index data corresponding to publicity, monumentality, and narrativeness according to relevant data within an evaluation area, and perform normalization processing;

[0070] A determination module, configured to determine the weights of the secondary indexes according to the normalized secondary index data;

[0071] A calculation module, configured to sum up the secondary index data with weights superimposed, and calculate the final evaluation result of the public monumentality space quality.

[0072] The third object of the present invention can be achieved by adopting the following technical solutions:

[0073] A computer device includes a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the above-mentioned public monumentality space quality evaluation method is implemented.

[0074] The fourth object of the present invention can be achieved by adopting the following technical solutions:

[0075] A storage medium stores a program, and when the program is executed by a processor, the above-mentioned public monumentality space quality evaluation method is implemented.

[0076] The present invention has the following beneficial effects compared with the prior art:

[0077] Based on the data mined from open sources and considering the characteristics of public monumentality spaces different from other types of spaces, the present invention constructs an evaluation system for the quality of public monumentality spaces, measures the secondary index data corresponding to publicity, monumentality, and narrativeness, determines the weights of the secondary indexes, and thus calculates the final evaluation result of the quality of public monumentality spaces, which can effectively evaluate the quality of public monumentality spaces, provide guidance for optimizing functional configuration and improving environmental quality, and provide assistance and reference for the efficient and accurate implementation of urban planning work. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the structures shown in these drawings without creative efforts.

[0079] Figure 1 It is a flowchart of the public monumentality space quality evaluation method according to Embodiment 1 of the present invention.

[0080] Figure 2 It is a scoring table for evaluating the richness of narrative elements according to Embodiment 2 of the present invention.

[0081] Figure 3 Schematic diagram of the publicity evaluation result of Embodiment 2 of the present invention.

[0082] Figure 4 Schematic diagram of the commemorative evaluation result of Embodiment 2 of the present invention.

[0083] Figure 5 Schematic diagram of the narrative evaluation result of Embodiment 2 of the present invention.

[0084] Figure 6 Schematic diagram of the evaluation result of the public commemorative space quality of Embodiment 2 of the present invention.

[0085] Figure 7 Block diagram of the structure of the public commemorative space quality evaluation system of Embodiment 3 of the present invention.

[0086] Figure 8 Block diagram of the structure of the computer device of Embodiment 4 of the present invention. Detailed implementation manners

[0087] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0088] Embodiment 1:

[0089] As Figure 1 shown, this embodiment provides a method for evaluating the quality of a public commemorative space. The public commemorative space refers to a space with commemorative functions or behaviors. This method uses multi-source data and conducts a comprehensive evaluation considering the characteristics of the public commemorative space, including the following steps:

[0090] S101. Obtain relevant data within the evaluation area.

[0091] In this embodiment, the relevant data includes SDK (Software Development Kit) population portrait data, POI (Point of Interest) location interest point data, road data, high-resolution satellite remote sensing images, and network photos.

[0092] Furthermore, the SDK population portrait data is sourced from the Aurora Big Data Platform, and the monthly population quantity within the research area is counted within the geohash level 7 (approx. 150m * 150m in size) grid range.

[0093] Further, the POI (Point of Interest) data is sourced from Baidu Maps. A Python web crawler is programmed to obtain specific location, category, and quantity information of toilets, parking lots, activity facilities, rest facilities, etc. within the research scope through the API interface, accurate to the interior of the evaluated space.

[0094] Further, the road data is sourced from the Open Street Map open platform. A Python web crawler is programmed to batch obtain vector road network data within the research scope through the API interface, which has fields such as road location, total road length, and sectional lengths of roads at all levels.

[0095] Further, the high-resolution satellite remote sensing images are sourced from the Geo-remote Sensing Ecosystem Network platform, with a resolution of 50m, capable of accurately reflecting the planar position and height of ground features.

[0096] Further, the network photos are sourced from Baidu Images, obtained through the Octopus crawler software. Baidu Images come from major search engines and private sharing social media platforms, etc., and can reflect spatial characteristics and urban environment from the perspectives of multiple platforms and users.

[0097] S102. Construct a quality evaluation system for public commemorative spaces.

[0098] In this embodiment, according to the characteristics of public commemorative spaces, referring to relevant content such as the spatial quality quantification evaluation system and index calculation methods in existing literature, and combining the definition of commemorative buildings (spaces) in the "Encyclopedia of China" (Architecture, Landscape Architecture, Urban Planning Volume), a targeted and innovative quality evaluation system for public commemorative spaces is constructed. The constructed quality evaluation system for public commemorative spaces includes three first-level indicators: publicity, monumentality, and narrativity, as well as corresponding second-level indicators.

[0099] Further, the second-level indicators corresponding to publicity include pedestrian flow, facility integrity, and traffic convenience, reflecting the crowd activity characteristics of the space. The pedestrian flow reflects the activity level of the space, the facility integrity focuses on the completeness of the space's infrastructure, and the traffic convenience emphasizes the accessibility of the space.

[0100] Further, the second-level indicators corresponding to monumentality include spatial sequence and visual sensitivity, reflecting the landscape construction effect of commemorative spaces. The spatial sequence emphasizes the orderly organization of spatial elements, and the visual sensitivity focuses on how to effectively guide people's perception of the space.

[0101] Further, the second-level indicators corresponding to narrativity include element richness and visual directness, reflecting the cultural connotation expression of commemorative spaces. The element richness emphasizes the diversity of elements in the space, and the visual directness emphasizes people's intuitive perception ability of the space.

[0102] S103. Measure the secondary index data corresponding to publicity, monumentality, and narrativity based on the relevant data within the evaluation area, and perform normalization processing.

[0103] In this embodiment, the SDK population portrait data, POI location interest point data, road data, high-resolution satellite remote sensing images, and network photos within the target area are processed, and the obtained secondary index data is normalized. Specifically, it includes:

[0104] S1031. Create a fishnet tool to divide the evaluation area into multiple N*N grids.

[0105] Specifically, use the fishnet creation tool in ArcGIS software to create 50*50m grids on the map within the evaluated range. Use the spatial join tool to assign the index calculation results in the unit area to the grid attribute table, and use the natural breaks classification method to divide the calculation results into five categories for visual expression. The darker the color, the higher the evaluation score.

[0106] In this embodiment, when measuring the publicity index, the population quantity in the SDK population portrait data is used to reflect the pedestrian flow index of the public memorial space. The POI location interest point data is combined with high-resolution satellite remote sensing images to evaluate the facility integrity index and traffic convenience index within the public memorial space. For specific descriptions, refer to steps S1032 to S0134.

[0107] In this embodiment, when measuring the monumentality index, the road data and high-resolution satellite remote sensing images are used to evaluate the spatial sequence index and view sensitivity index within the public memorial space. For specific descriptions, refer to steps S1035 to S1036.

[0108] In this embodiment, when measuring the narrativity index, network photos are used and the method of machine learning is applied to evaluate the element richness index and visual directness index within the public memorial space. For specific descriptions, refer to step S1037.

[0109] S1032. Measure the pedestrian flow index: According to the population quantity in the SDK population portrait data, calculate the number of people active per unit area to represent the pedestrian flow index.

[0110] Specifically, convert the SDK data table to csv format and import it into ArcGIS software. Use the spatial join tool to connect it with the attribute table of the created grid so that the grid can correspondingly reflect the population data to represent the pedestrian flow index.

[0111] S1033. Measure the facility integrity index: According to the POI location interest point data, obtain the spatial distribution of service facilities, and use Shannon entropy to calculate the facility integrity index.

[0112] Specifically, first, summarize the POI data of toilets, parking lots, activity facilities, rest facilities, etc. within the evaluation scope. In the ArcGIS software, set the X field as longitude and the Y field as latitude, display the POI points according to the longitude and latitude location data, use the spatial join tool to connect the POI data information with the attribute table of the created grid, and then calibrate the location by comparing with the high-resolution satellite remote sensing image. Calculate the facility integrity index using the Shannon entropy, as shown in the following formula:

[0113]

[0114] Among them, P i represents the facility integrity index, m is the number of types of supporting service facilities, and the facility types include toilets, parking lots, activity facilities, and rest facilities; T j is the proportion of the number of POIs of the jth type of service facility to the total number of service facility POIs within the scope.

[0115] S1034. Measure the traffic convenience index: According to the POI location interest point data, obtain the spatial distribution of bus stops, subway stations, and parking lots, as well as the number of parking spaces inside each parking lot, and calculate the traffic convenience index.

[0116] Specifically, first, summarize the number of bus stops, subway stations, and the number of parking spaces within the evaluation scope and the 500m buffer zone. In the ArcGIS software, set the X field as longitude and the Y field as latitude, display the POI points according to the longitude and latitude location data, use the spatial join tool to connect the POI data information with the attribute table of the created grid, and calculate the traffic convenience index, as shown in the following formula:

[0117]

[0118] Among them, K i represents the traffic convenience index, Q i is the number of bus stops and subway stations within the i-th grid range, Q max is the number of bus and subway stations within the public memorial space and the 500m buffer zone, R i is the number of parking spaces within the grid range, R max is the number of parking spaces within the public memorial space and the 500m buffer zone; Use an online questionnaire to survey the importance weight values of bus and subway stations and parking lots within the public memorial space. a and b respectively represent the importance weight values of bus stops and parking lots, and a:b = 0.6:0.4.

[0119] S1035. Measure the spatial sequence index: According to the road data, combine with the high-resolution satellite remote sensing image for correction and adjustment, measure the length of the sections between each memorial node, and calculate the spatial sequence index.

[0120] Specifically, first download road data from the Open Street Map open platform. After downloading, clean and filter the data, retaining fields such as road length. Then, perform road segmentation and map distance measurement on the map platform to measure the road length within the space and the distances between main nodes to verify the accuracy of the road data. Use uniformity to calculate the spatial sequence index as follows:

[0121] S i =D i / L

[0122] Where S i is the spatial sequence index, D i is the minimum value of the segment length, and L is the average value of the road segment length. The closer S i is to 1, the more uniform it is, indicating a better commemorative rhythm and tour experience.

[0123] S1036. Measure the visual field sensitivity index: According to the road data, combine it with high-resolution satellite remote sensing images for correction and adjustment, measure the total length of the tour path and the length of the sections where commemorative structures can be seen, and calculate the visual field sensitivity index.

[0124] Specifically, first download road data from the Open Street Map open platform. After downloading, clean and filter the data, retaining fields such as road length. Then, perform road segmentation and map distance measurement on the map platform to measure the road length within the space and the distances between main nodes to verify the accuracy of the road data, and use the spatial join tool to connect the road attribute data with the attribute table of the created grid as follows:

[0125] M i =A i / N

[0126] Where M i is the visual field sensitivity index, N is the total length of the sections of the subjective view line within a certain area, and A i is the length of the section where a certain landscape can be seen. The closer M i is to 1, the greater the probability that the landscape can be seen.

[0127] S1037. Measure the richness index and visual directness index: Use a machine learning model to measure network photos and evaluate the richness index of evaluation elements and the visual directness index.

[0128] S10371. Randomly select a part of the street view photos from the network photos as the scoring sample photos and construct a richness evaluation scoring table for evaluation elements.

[0129] In this embodiment, 550 street view photos are randomly selected as the sample photos for scoring, and are evenly distributed to five experts for scoring according to the evaluation form of element richness. The evaluation form of element richness includes three categories: character elements, event elements, and spatial elements, and is subdivided into ten narrative element types (ten indicators) in total. The richness of elements is reflected by the number of commemorative elements contained in the sample photos. If any of the ten indicators is shown in the sample photo for scoring, it is counted as 1 point; if not, it is counted as 0 point. The element richness score of each sample photo for scoring is obtained by accumulation, ranging from 0 to 12 points from poor to good.

[0130] S10372. Based on the random forest model, machine deep learning is carried out using the sample photos for scoring to obtain a trained random forest machine learning model.

[0131] In this embodiment, 80% of the sample photos for scoring are randomly selected as the training set, and 20% are used as the test set. The model parameters are adjusted to make the random forest machine learning model have a higher model score on the test set, and a more accurate machine scoring value is obtained. Finally, a trained random forest machine learning model is obtained.

[0132] S10373. Use the trained random forest machine learning model to score the remaining network photos to obtain the evaluation result of the element richness index.

[0133] S10374. Identify the network photos through the visual image semantic segmentation of the deep learning fully convolutional network, and count the area occupied by the narrative elements in the photos to obtain the evaluation result of the visual directness index.

[0134] Specifically, the network photos are identified through the visual image semantic segmentation of the deep learning fully convolutional network, and the area occupied by the narrative elements in the photos is counted. Through the visual image semantic segmentation software, the network photos are element-identified to obtain the proportion results of 150 types of built environment elements in the image, and a CSV table file and the network photos after semantic segmentation are obtained. The visual directness index is calculated as follows:

[0135]

[0136] Among them, E i is the visual directness index, F i is the area of commemorative buildings and structures in the network photo image, and G is the field of view area of the network photo.

[0137] S1038. Use the range normalization method to normalize the secondary index data.

[0138] S1038. Find the maximum and minimum values of the secondary index and calculate the range.

[0139] S1039. Subtract the minimum value of the secondary index from each observation value and divide by the range to obtain the standardized secondary index, as shown in the following formula:

[0140] X′ = (X - X min ) / R

[0141] where X′ is the standardized secondary index, 0 ≤ X′ ≤ 1, X is the observation value, X max is the maximum value of the secondary index, X min is the minimum value of the secondary index, and R is the range, R = X max - X min .

[0142] S104. Determine the weights of each secondary index according to the normalized secondary index data.

[0143] In this embodiment, the entropy weight TOPSIS method is used to calculate the weights of each secondary index. The specific process is as follows:

[0144] 1) Assume there are n samples to be evaluated and p secondary indicators, and construct the original indicator matrix, as shown in the following formula:

[0145]

[0146] 2) Perform positive normalization - standardization processing on the original indicator matrix, as shown in the following formula:

[0147]

[0148] where x max is the maximum value under the same secondary index;

[0149] 3) Calculate the expected value of the samples to be evaluated as the entropy value, as shown in the following formula:

[0150]

[0151] 4) Define the weights of each secondary index. The larger the entropy weight coefficient, the greater the amount of information represented by the secondary index, indicating that the secondary index has a greater role in the comprehensive evaluation, as shown in the following formula:

[0152]

[0153] where w j represents the weight of the jth secondary index, d j is the entropy weight coefficient, d j = 1 - e j ;

[0154] 5) Perform standardization processing on the matrix indicators so that each column element is divided by the cosine distance of the current column vector, as shown in the following formula:

[0155]

[0156] 6) Construct a standardized weighted matrix, and attach the weights of each secondary index to the matrix indexes after standardization:

[0157]

[0158]

[0159] Among them, z ij represents the matrix indexes after standardization, represents the standardized matrix indexes with weights attached;

[0160] 7) Find the optimal and worst solutions, as shown in the following formula:

[0161]

[0162]

[0163] 8) Construct the relative closeness, as shown in the following formula:

[0164]

[0165]

[0166] Among them, is the distance between the i-th evaluation object and the maximum value, is the distance between the i-th evaluation object and the minimum value, and C i is the relative closeness.

[0167] 9) Sort the weights of the secondary indexes according to the size of the relative closeness C i The larger the relative closeness C i , the closer the evaluation object is to the optimal value, and the higher the weight of the corresponding secondary index.

[0168] S105. Stack the data of each secondary index with weights for summarization, and calculate the final evaluation result of the public memorial space quality.

[0169] After obtaining the final evaluation result of the public memorial space quality in this embodiment, import the final evaluation result of the public memorial space quality into the ArcGIS software for visual expression, and sort the final evaluation result of the public memorial space quality; modify the symbol system in the ArcGIS layer properties to classify and visually express the data, and divide the comprehensive potential evaluation value into five categories based on the natural breakpoint grading method, which are marked as low level, medium-low level, medium level, medium-high level, and high level from small to large.

[0170] Example 2:

[0171] To verify the implementation effect of the public commemorative space quality evaluation method in the above Example 1, this example uses a cemetery as an application example for verification. The cemetery covers an area of 26 hectares and belongs to a typical public commemorative space. The specific implementation can be achieved through the following steps:

[0172] S1. Obtain relevant data within the evaluation area.

[0173] In this example, the relevant data includes SDK population portrait data, POI location interest point data, road data, high-resolution satellite remote sensing image data, and network photo data within the cemetery and within a 500m buffer zone around it. Among them, the SDK population portrait data comes from the Aurora Big Data Platform and reflects the population quantity in the research area on a monthly basis. The POI location interest point data comes from Baidu Maps. A Python web crawler is written to obtain POI data such as toilets, parking lots, activity facilities, and rest facilities within the research scope through the API interface, including information such as names, addresses, and coordinates. The road data comes from the Open StreetMap open platform. A Python web crawler is written to batch obtain the vector road network data within the research scope through the API interface. After downloading, the data is cleaned and filtered, and fields such as road location, total road length, and segmented lengths of roads at all levels are retained. The high-resolution satellite remote sensing images come from the Geo-remote Sensing Ecosystem Network Platform with a resolution of 50m, which can accurately reflect the planar position and height of ground objects. The network photos come from Baidu Images and are obtained through the Octopus crawler software. Baidu Images come from major search engines and private sharing social media platforms, etc., and can reflect the spatial characteristics and urban environment from the perspectives of multiple platforms and multiple users.

[0174] S2. Construct a public commemorative space quality evaluation system.

[0175] In this example, according to the characteristics of the public commemorative space, referring to relevant content such as the spatial quality quantification evaluation system and index calculation methods in existing literature, and combining the definition of commemorative buildings (spaces) in the "Encyclopedia of China" (Architecture, Landscape Architecture, Urban Planning Volume), a public commemorative space quality evaluation system with pertinence and innovation is constructed. The constructed public commemorative space evaluation system includes three first-level indicators and corresponding second-level indicators.

[0176] Among them, the publicity is evaluated by three indicators: the pedestrian flow, the integrity of facilities, and the traffic convenience, which reflect the characteristics of crowd activities in the space. The pedestrian flow reflects the activity level of the space, the integrity of facilities focuses on the completeness of the space's infrastructure, and the traffic convenience emphasizes the accessibility of the space; the monumentality is evaluated by two indicators: the spatial sequence and the visual field sensitivity, which reflect the landscape construction effect of the memorial space. The spatial sequence emphasizes the orderly organization of spatial elements, and the visual field sensitivity focuses on how to effectively guide people's perception of the space; the narrativity is evaluated by two indicators: the richness of elements and the visual directness, which reflect the cultural connotation expression of the memorial space. The richness of elements emphasizes the diversity of elements in the space, and the visual directness emphasizes people's intuitive perception ability of the space.

[0177] S3. According to the relevant data within the evaluation area, measure the data of the secondary indicators corresponding to publicity, monumentality, and narrativity, and perform normalization processing.

[0178] 1) Evaluate the pedestrian flow indicator using the population quantity in the SDK population portrait data. Convert the SDK data table to the csv format and import it into the ArcGIS software, and connect it to the attribute table of the created grid so that the grid can correspondingly reflect the population data.

[0179] 2) Summarize the POI interest point data such as toilets, parking lots, activity facilities, and rest facilities within the evaluation scope. In the ArcGIS software, set the X field as the longitude and the Y field as the latitude, display the POI points according to the longitude and latitude position data, then calibrate the position by referring to the high-resolution satellite remote sensing image, use the spatial join tool to connect the POI data information to the attribute table of the created grid, and calculate the facility integrity indicator using the Shannon entropy.

[0180] 3) Summarize the number of bus stops, subway stations, and the number of parking spaces in the parking lots within the evaluation scope and the 500m buffer zone. In the ArcGIS software, set the X field as the longitude and the Y field as the latitude, display the POI points according to the longitude and latitude position data, then calibrate the position by referring to the high-resolution satellite remote sensing image, use the spatial join tool to connect the POI data information to the attribute table of the created grid, and calculate the traffic convenience indicator.

[0181] 4) Download the road data within the evaluation scope from the Open Street Map open platform. After downloading, clean and filter the data, retain fields such as the road length, then perform map ranging on the map platform, measure the road length and the distance between the main nodes in the space to verify the accuracy of the road data, and use the spatial join tool to connect the road attribute data to the attribute table of the created grid, and calculate the spatial sequence indicator using the uniformity.

[0182] 5) Download road data from the Open Street Map open platform. After downloading, clean and filter the data, retain fields such as road length, and then perform map distance measurement on the map platform to measure the road length within the said space and the distances between main nodes to verify the accuracy of the road data. Then use the spatial join tool to connect the road attribute data with the attribute table of the created grid and calculate the visibility sensitivity index.

[0183] 6) Randomly select 550 street view photos from the network photos as sample photos for scoring, and construct an evaluation form for element richness, as Figure 2 shown, including three categories of elements: human elements, event elements, and spatial elements, which are further divided into ten narrative element types in total. The richness of elements is reflected by the number of commemorative elements contained in the photo. If a certain item among the ten indicators is shown in the sample photo, it is counted as 1 point; if not, it is counted as 0 point. The element richness score of each network photo is obtained by accumulation.

[0184] 7) Perform machine deep learning on the sample photos for scoring through a random forest model. Randomly select 80% of the sample photos for scoring as the training set and 20% as the test set, adjust the model parameters to make the random forest machine learning model have a higher model score on the test set, obtain a more accurate machine scoring value, and finally obtain a trained random forest machine learning model. Use the trained model to score the remaining photos to obtain the evaluation result of the element richness index.

[0185] 8) Identify the network photos through semantic segmentation of visual images of the deep learning fully convolutional network, count the area occupied by narrative elements in the photos, use the semantic segmentation software for visual images to identify elements in the network photos, obtain the proportion results of 150 types of built environment elements in the image, obtain a CSV table file and the network photos after semantic segmentation, and calculate the visual directness index.

[0186] 9) Find the maximum value (X max ) and the minimum value (X min ) of this index, and calculate the range (R = X max - C min ). Then subtract the minimum value (X min ) from each observation value (X) of this variable, and divide by the range (R) to obtain the standardized index X′, and the numerical change range satisfies 0 ≤ X′ ≤ 1.

[0187] S4. Determine the weights of each secondary index according to the normalized secondary index data.

[0188] In this embodiment, the entropy weight TOPSIS method is used to determine the weights of evaluation indicators. The final weight calculation results are as follows: pedestrian flow 0.11351, facility integrity 0.08532, traffic convenience 0.02412, spatial sequence 0.43596, view sensitivity 0.25567, element richness 0.05250, and visual directness 0.03292.

[0189] S5. Superimpose the weights on the data of each secondary indicator and summarize to calculate the final evaluation result of the public memorial space quality.

[0190] In this embodiment, the evaluation results of the three primary indicators of publicity, monumentality, and narrativeness are calculated by superimposing weights respectively, and two-dimensional graphical visualization and vectorization output are performed using ArcGIS software, as Figures 3 to 5 shown.

[0191] Superimpose the weights to calculate the final evaluation result of the public memorial space quality, sort the evaluation results, and label them as low level 0 - 0.000001, medium - low level 0.000002 - 0.526612, medium level 0.526613 - 0.563115, medium - high level 0.563116 - 0.865216, and high level 0.865217 - 0.096612 in ascending order. Two-dimensional graphical visualization and vectorization output are performed using ArcGIS software, as Figure 6 shown.

[0192] It should be noted that although the method operations of the above embodiments are described in a specific order, this does not require or imply that these operations must be performed in that specific order, or that all the shown operations must be performed to achieve the desired result. On the contrary, the described steps can be executed in a changed order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution.

[0193] Embodiment 3:

[0194] As Figure 7 shown, this embodiment provides a public memorial space quality evaluation system, which includes an acquisition module 701, a construction module 702, a measurement module 703, a determination module 704, and a calculation module 705. The specific functions of each module are as follows:

[0195] The acquisition module 701 is used to acquire relevant data within the evaluation area, and the relevant data includes SDK population portrait data, POI location interest point data, road data, high - resolution satellite remote sensing images, and network photos.

[0196] A construction module 702 for constructing a public memorial space quality evaluation system, where the public memorial space quality evaluation system includes three first-level indicators of publicity, memoriality, and narrativity and corresponding second-level indicators.

[0197] A measurement module 703 for measuring the data of the second-level indicators corresponding to publicity, memoriality, and narrativity based on the relevant data within the evaluation area and performing normalization processing.

[0198] A determination module 704 for determining the weights of the second-level indicators according to the normalized data of the second-level indicators.

[0199] A calculation module 705 for summing up the data of the second-level indicators by superimposing the weights to calculate the final evaluation result of the public memorial space quality.

[0200] It should be noted that the system provided in this embodiment is only illustrated by the above division of each functional module. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure is divided into different functional modules to complete all or part of the functions described above.

[0201] Example 4:

[0202] This embodiment provides a computer device, as Figure 8 shown, which includes a processor 802, a memory, an input device 803, a display device 804, and a network interface 805 connected through a system bus 801. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium 806 and an internal memory 807. The non-volatile storage medium 806 stores an operating system, a computer program, and a database. The internal memory 807 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the processor 802 executes the computer program stored in the memory, the public memorial space quality evaluation method of the above Embodiment 1 is implemented as follows:

[0203] Obtain relevant data within the evaluation area, where the relevant data includes SDK population portrait data, POI location interest point data, road data, high-resolution satellite remote sensing images, and network photos;

[0204] Construct a public memorial space quality evaluation system, where the public memorial space quality evaluation system includes three first-level indicators of publicity, memoriality, and narrativity and corresponding second-level indicators;

[0205] Measure the data of the second-level indicators corresponding to publicity, memoriality, and narrativity based on the relevant data within the evaluation area and perform normalization processing;

[0206] Determine the weights of each secondary index based on the normalized secondary index data;

[0207] Sum up the secondary index data after superimposing the weights to calculate the final evaluation result of the public commemorative space quality.

[0208] Example 5:

[0209] This example provides a storage medium, which is a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the public commemorative space quality evaluation method of the above Example 1 as follows:

[0210] Obtain relevant data within the evaluation area, where the relevant data includes SDK population portrait data, POI location interest point data, road data, high-resolution satellite remote sensing images, and network photos;

[0211] Construct a public commemorative space quality evaluation system, where the public commemorative space quality evaluation system includes three first-level indicators of publicity, commemorativeness, and narrativeness and corresponding secondary indicators;

[0212] Measure the secondary index data corresponding to publicity, commemorativeness, and narrativeness based on the relevant data within the evaluation area, and perform normalization processing;

[0213] Determine the weights of each secondary index based on the normalized secondary index data;

[0214] Sum up the secondary index data after superimposing the weights to calculate the final evaluation result of the public commemorative space quality.

[0215] It should be noted that the computer-readable storage medium in this example can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0216] In this embodiment, a computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In this embodiment, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0217] The above computer-readable storage medium can be written in one or more programming languages or combinations thereof for executing the computer program of this embodiment. The above programming languages include object-oriented programming languages - such as Java, Python, C++, and also include conventional procedural programming languages - such as C language or similar programming languages. The program can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0218] In summary, based on the data of open-source data mining and considering the characteristics of public memorial spaces different from other types of spaces, the present invention constructs a quality evaluation system for public memorial spaces, measures the secondary index data corresponding to publicity, memoriality, and narrativity, determines the weights of each secondary index, and thus calculates the final evaluation result of the quality of public memorial spaces, which can effectively evaluate the quality of public memorial spaces, provide guidance for optimizing functional configuration and improving environmental quality, and provide assistance and reference for the efficient and accurate implementation of urban planning work.

[0219] The above are only the preferred embodiments of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention.

Claims

1. A method for evaluating the quality of a public memorial space, characterized in that: The method comprises: Acquire relevant data in the evaluation area, including SDK crowd portrait data, POI location point of interest data, road data, high-resolution satellite remote sensing images and network photos; Construct a quality evaluation system for public memorial spaces, which includes three primary indicators, namely publicity, memorial and narrative, and corresponding secondary indicators. The secondary indicators corresponding to publicity include passenger flow, facility completeness and traffic convenience, the secondary indicators corresponding to memorial include spatial sequence and visual sensitivity, and the secondary indicators corresponding to narrative include element richness and visual directness. According to the relevant data in the evaluation area, the secondary indicator data corresponding to publicity, commemoration and narrative are measured and normalized; According to the normalized secondary indicator data, the weight of each secondary indicator is determined, and the weight is calculated using the entropy weight TOPSIS method; The weights of each secondary indicator are added together to calculate the final evaluation results of the quality of the public memorial space; The secondary indicator data corresponding to publicity, commemoration and narrative are measured based on the relevant data in the evaluation area, and normalized, specifically including: According to the population in the SDK crowd portrait data, calculate the number of people active in a unit area to represent the flow of people index; According to the POI location data, the spatial distribution of service facilities is obtained, and the Shannon entropy is used to calculate the facility completeness index. Specifically, the POI points are displayed according to the longitude and latitude location data, and the POI data information is connected to the attribute table of the created grid using the spatial connection tool. The location is calibrated against the high-resolution satellite remote sensing image, and the Shannon entropy is used to calculate the facility completeness index, as shown in the following formula: Among them, P i represents the facility completeness index, m is the number of supporting service facilities, including toilets, parking lots, activity facilities, and rest facilities; T j is the ratio of the number of POIs of service facility type j to the number of all service facility POIs within the grid; According to the POI location data, the spatial distribution of bus stations, subway stations and parking lots and the number of parking spaces in each parking lot are obtained, and the traffic convenience index is calculated. Specifically, the POI points are displayed according to the latitude and longitude location data, and the POI data information is connected with the attribute table of the created grid using the spatial connection tool to calculate the traffic convenience index as follows: Among them, K i represents the traffic convenience index, Q i is the number of bus stops and subway stations within the i-th grid, Q max The number of public memorial spaces and bus and subway stations within the 500m buffer zone, R i is the number of parking spaces within the grid, R max is the number of parking spaces within the public memorial space and the 500m buffer zone; an online questionnaire was used to investigate the importance weights of bus and subway stations and parking lots in the public memorial space, where a and b represent the importance weights of bus stops and parking lots, respectively; According to the road data, combined with high-resolution satellite remote sensing images, corrections and adjustments are made, the length of the road section between each memorial node is measured, and the spatial sequence index is calculated. Specifically, the road data is cleaned and screened, the road segmentation and map distance measurement are performed, the road length in space and the distance between the main nodes are measured to verify the accuracy of the road data, and the uniformity is used to calculate the spatial sequence index, as shown in the following formula: S i =D i / L Among them, S i is the spatial sequence index, D i is the minimum length of the segment, and L is the average length of the road segment; According to the road data, combined with high-resolution satellite remote sensing images, corrections and adjustments are made, the total length of the tour path and the length of the road section where the monumental structures can be seen are measured, and the viewshed sensitivity index is calculated. Specifically, the road data is cleaned and screened, road segmentation and map distance measurement are performed, the road length in space and the distance between the main nodes are measured to verify the accuracy of the road data, and the road attribute data is connected to the attribute table of the created grid using the spatial connection tool to calculate the viewshed sensitivity index, as shown in the following formula: M i =A i / N Among them, M i is the visual sensitivity index, N is the total length of the road section of the subjective view line in a certain area, and A i The length of the road section where a certain landscape can be seen; Use machine learning models to measure online photos and evaluate feature richness and visual directness indicators; The range standardization method is used to normalize the secondary indicator data.

2. The method for evaluating the quality of public memorial space according to claim 1, characterized in that: The machine learning model is used to measure online photos and evaluate the element richness index and visual directness index, specifically including: A portion of street view photos are randomly selected from online photos as scoring sample photos, and an element richness evaluation scoring table is constructed. The element richness evaluation scoring table includes three categories: human elements, event elements, and space elements. If the scoring sample photos show any one of the indicators of human elements, event elements, and space elements, it is scored as 1 point, otherwise it is scored as 0 point, and the element richness score of each scoring sample photo is accumulated; Based on the random forest model, the scored sample photos are used for machine deep learning to obtain a trained random forest machine learning model; The trained random forest machine learning model was used to score the remaining online photos and obtain the evaluation results of the feature richness index; Through the visual image semantic segmentation of the deep learning fully convolutional network, online photos are recognized, the area occupied by narrative elements in the photos is counted, and the evaluation results of the visual directness index are obtained.

3. The method for evaluating the quality of public memorial space according to claim 1, characterized in that: The use of the range standardization method to normalize the secondary index data specifically includes: Find the maximum and minimum values ​​of the secondary index and calculate the range; Subtract the minimum value of the secondary index from each observation value and divide it by the range to obtain the standardized secondary index, as shown in the following formula: X′=(X-X min ) / R Among them, X′ is the secondary index after standardization, 0≤X′≤1, X is the observed value, X max is the maximum value of the secondary index, X min is the minimum value of the secondary index, R is the range, R = X max -X min .

4. The method for evaluating the quality of a public memorial space according to any one of claims 1 to 3, characterized in that: Determining the weight of each secondary indicator according to the normalized secondary indicator data specifically includes: Assuming there are n samples to be evaluated and p secondary indicators, the original indicator matrix is ​​constructed as follows: The original indicator matrix is ​​normalized and standardized as follows: Among them, x max It is the maximum value under the same secondary indicator; Calculate the expected value of the sample to be evaluated as the entropy value, as follows: Define the weight of each secondary indicator. The larger the entropy weight coefficient, the greater the amount of information represented by the secondary indicator, which means that the secondary indicator has a greater impact on the comprehensive evaluation, as shown in the following formula: Among them, w j represents the weight of the jth secondary indicator, d j is the entropy weight coefficient, d j =1-e j ; The matrix index is normalized so that each column element is divided by the cosine distance of the current column vector, as follows: Construct a standardized weighted matrix and attach the weights of each secondary indicator to the standardized matrix indicator: Among them, z ij represents the matrix index after normalization, It represents the standardized matrix index with weights attached; Find the best and worst solutions as follows: Construct relative proximity as follows: in, is the distance between the i-th evaluation object and the maximum value, is the distance between the i-th evaluation object and the minimum value, C i is the relative proximity; Sort the weights of the secondary indicators according to the relative proximity C i The size of the sorting, relative proximity C i The larger it is, the closer the evaluation object is to the optimal value, and the higher the weight of the corresponding secondary indicator.

5. A public memorial space quality evaluation system, characterized in that: The system comprises: An acquisition module is used to acquire relevant data in the evaluation area, including SDK crowd portrait data, POI location point of interest data, road data, high-resolution satellite remote sensing images and network photos; A construction module is used to construct a public memorial space quality evaluation system, which includes three primary indicators of publicity, memorial and narrative, and corresponding secondary indicators. The secondary indicators corresponding to publicity include passenger flow, facility completeness and traffic convenience, the secondary indicators corresponding to memorial include spatial sequence and visual sensitivity, and the secondary indicators corresponding to narrative include element richness and visual directness. The measurement module is used to measure the secondary indicator data corresponding to publicity, commemoration, and narrative according to the relevant data in the evaluation area, and perform normalization processing; A determination module is used to determine the weight of each secondary indicator according to the normalized secondary indicator data, and the weight is calculated using the entropy weight TOPSIS method; The calculation module is used to aggregate the weights of the secondary indicator data and calculate the final evaluation results of the quality of the public memorial space; The secondary indicator data corresponding to publicity, commemoration and narrative are measured based on the relevant data in the evaluation area, and normalized, specifically including: According to the population in the SDK crowd portrait data, calculate the number of people active in a unit area to represent the flow of people index; According to the POI location data, the spatial distribution of service facilities is obtained, and the Shannon entropy is used to calculate the facility completeness index. Specifically, the POI points are displayed according to the longitude and latitude location data, and the POI data information is connected to the attribute table of the created grid using the spatial connection tool. The location is calibrated against the high-resolution satellite remote sensing image, and the Shannon entropy is used to calculate the facility completeness index, as shown in the following formula: Among them, P i represents the facility completeness index, m is the number of supporting service facilities, including toilets, parking lots, activity facilities, and rest facilities; T j is the ratio of the number of POIs of service facility type j to the number of all service facility POIs within the grid; According to the POI location data, the spatial distribution of bus stations, subway stations and parking lots and the number of parking spaces in each parking lot are obtained, and the traffic convenience index is calculated. Specifically, the POI points are displayed according to the latitude and longitude location data, and the POI data information is connected with the attribute table of the created grid using the spatial connection tool to calculate the traffic convenience index as follows: Among them, K i represents the traffic convenience index, Q i is the number of bus stops and subway stations within the i-th grid, Q max The number of public memorial spaces and bus and subway stations within the 500m buffer zone, R i is the number of parking spaces within the grid, R max is the number of parking spaces within the public memorial space and the 500m buffer zone; an online questionnaire was used to investigate the importance weights of bus and subway stations and parking lots in the public memorial space, where a and b represent the importance weights of bus stops and parking lots, respectively; According to the road data, combined with high-resolution satellite remote sensing images, corrections and adjustments are made, the length of the road section between each memorial node is measured, and the spatial sequence index is calculated. Specifically, the road data is cleaned and screened, the road segmentation and map distance measurement are performed, the road length in space and the distance between the main nodes are measured to verify the accuracy of the road data, and the uniformity is used to calculate the spatial sequence index, as shown in the following formula: S i =D i / L Among them, S i is the spatial sequence index, D i is the minimum length of the segment, and L is the average length of the road segment; According to the road data, combined with high-resolution satellite remote sensing images, corrections and adjustments are made, the total length of the tour path and the length of the road section where the monumental structures can be seen are measured, and the viewshed sensitivity index is calculated. Specifically, the road data is cleaned and screened, road segmentation and map distance measurement are performed, the road length in space and the distance between the main nodes are measured to verify the accuracy of the road data, and the road attribute data is connected to the attribute table of the created grid using the spatial connection tool to calculate the viewshed sensitivity index, as shown in the following formula: M i =A i / N Among them, M i is the visual sensitivity index, N is the total length of the road section of the subjective view line in a certain area, and A i The length of the road section where a certain landscape can be seen; Use machine learning models to measure online photos and evaluate feature richness and visual directness indicators; The range standardization method is used to normalize the secondary indicator data.

6. A computer device comprising a processor and a memory for storing a program executable by the processor, characterized in that: When the processor executes the program stored in the memory, the method for evaluating the quality of a public memorial space as described in any one of claims 1 to 4 is implemented.

7. A storage medium storing a program, characterized in that: When the program is executed by a processor, the method for evaluating the quality of a public memorial space as described in any one of claims 1 to 4 is implemented.

Images