Methods and Systems for Resilience Evaluation of Towns and Villages on the Edge of Large Cities

Abstract

This invention discloses a method and platform for evaluating the resilience of towns and villages on the outskirts of large cities. The method includes steps such as constructing a multi-level evaluation index system, acquiring and processing evaluation data, calculating index weights, and obtaining evaluation results. It establishes a multi-level index system encompassing economic resilience, social resilience, ecological resilience, and infrastructure resilience. Relevant literature data is acquired using web crawling technology and semantic analysis models. The final indicators are selected using the TF-IDF algorithm, and the index weights are calculated using the information entropy method. Finally, the evaluation results are obtained using the fuzzy comprehensive evaluation method. This method automates the evaluation process, enabling rapid and accurate assessment of the resilience level of towns and villages on the outskirts of large cities, providing a scientific basis for urban planning and management decisions.

Description

Technical Field

[0001] This invention belongs to the field of urban planning and management technology, specifically relating to a method for evaluating the resilience of towns and villages on the outskirts of large cities. Background Technology

[0002] As a transitional zone between urban and rural areas, the outskirts of large cities face both pressure from urban expansion and the important mission of integrated urban-rural development. Traditional resilience assessment methods have obvious limitations. Existing assessment systems are mostly focused on single-dimensional evaluation, which cannot comprehensively reflect the overall resilience level of towns and villages in multiple aspects such as economy, society, ecology and infrastructure. At the same time, the selection of evaluation indicators is often highly subjective and lacks a scientific screening mechanism.

[0003] Existing evaluation methods primarily rely on manual data collection and processing, which is not only time-consuming and labor-intensive but also prone to data omissions and errors. Currently used methods often overlook the ambiguity and uncertainty between indicators, leading to discrepancies between evaluation results and actual conditions. Furthermore, the determination of indicator weights largely depends on expert experience, lacking objective quantitative evidence. Additionally, current evaluation work is mostly fragmented, lacking unified evaluation standards and automated assessment tools, making it difficult to support large-scale, routine resilience evaluations. This severely restricts the practical application of evaluation results in urban planning and management decision-making.

[0004] These problems make it difficult to effectively conduct resilience assessments in towns and villages on the outskirts of large cities, hindering the provision of reliable decision-making support for regional sustainable development. Therefore, there is an urgent need to develop a scientific and efficient resilience assessment method and supporting platform to improve the quality and efficiency of the assessment work. Traditional assessment methods often lack systematicity and comprehensiveness. Summary of the Invention

[0005] The purpose of this invention is to provide a method and platform for evaluating the resilience of towns and villages in the fringe areas of large cities. By constructing a multi-level evaluation index system, calculating the weights of each level of index based on the initial index values ​​in the literature, constructing an index weight matrix, and using the fuzzy comprehensive evaluation method to calculate the town and village resilience evaluation results, a rapid and accurate evaluation of the town and village resilience of the target area can be achieved.

[0006] The specific plan is as follows:

[0007] A method for evaluating the resilience of towns and villages on the outskirts of large cities, the method comprising the following steps:

[0008] Step S1: Construct a multi-level evaluation index system. The multi-level evaluation index system includes a target layer, a criterion layer, and an indicator layer. The target layer is the evaluation result of town and village resilience, and the criterion layer includes four dimensions: economic resilience, social resilience, ecological resilience, and infrastructure resilience.

[0009] Step S2: Based on web crawling technology and semantic analysis model, relevant literature and data on town and village resilience evaluation are obtained, an initial set of indicators for the indicator layer is established, and the TF-IDF algorithm is used to filter the initial set of indicators to determine the final indicators for the indicator layer.

[0010] Step S3: Calculate the weights of each level of indicators based on the initial indicator values ​​in the literature, construct the indicator weight matrix, and use the fuzzy comprehensive evaluation method to calculate the town and village resilience evaluation results.

[0011] Furthermore, the initial indicator set for establishing the criterion layer and indicator layer in step S2 specifically involves:

[0012] Based on web crawling technology, publicly available literature related to resilience evaluation was obtained online, forming a literature set L, L={L1,L2,L3,…,L… n}, n>200, use a semantic analysis model to preprocess the document set L to extract the initial index set I, I={I1,I2,I3,…,I m}, m>16.

[0013] The document set L is segmented to remove stop words and filter words, forming a document segmentation set L'. The TF-IDF algorithm is then used to calculate each index I in the initial index set I. i The term frequency (TF) and inverse document frequency (IDF) in the document segmentation set are as follows:

[0014]

[0015] Wherein, N{I i ∈L'} represents the index I in the document segmentation set L'. i The number of times it appears, T L' M{I} represents the number of words in the document segmentation set; i ∈L'} is a group containing index I i The number of documents.

[0016] Calculation index I i The TF-IDF value is: TF-IDF = TF × IDF; the indicators in the initial indicator set I are sorted from high to low according to the TF-IDF value, and the top 15 are selected as the final indicators of the indicator layer. The final indicators of the indicator layer are classified according to four dimensions: economic resilience, social resilience, ecological resilience and infrastructure resilience, thus completing the correspondence between the indicator layer and the criterion layer.

[0017] Furthermore, the correspondence between the indicator layer and the criterion layer specifically includes:

[0018] Economic resilience: GDP per capita, fixed asset investment, and fiscal revenue;

[0019] Social resilience: population density, number of medical beds, coverage of educational facilities, and coverage of social security;

[0020] Ecological resilience: green coverage rate, air quality index, water quality compliance rate, and waste disposal rate;

[0021] Infrastructure resilience: road network density, water supply network density, communication network coverage, and power facility density.

[0022] Furthermore, the calculation of indicator weights at each level based on the initial indicator values ​​in the literature, and the construction of the indicator weight matrix, includes:

[0023] Collect the raw data for each indicator and construct the evaluation matrix R: Where rij is the value of the j-th initial index in the i-th document, 1≤i≤n, 1≤j≤m, n is the number of documents, and m is the number of initial indicators; the evaluation matrix R is normalized to obtain the standardized matrix P, where the element p ij The formula for calculation is: Calculate the information entropy e of the j-th indicator j : Where k is the entropy coefficient. element p ij Let be the value of the j-th initial index in the i-th document after standardization.

[0024] Calculate the difference coefficient d of the j-th indicator. j :d j =1-e j Then, based on the final indicators of the indicator layer, construct the indicator weight vector W: W = (w1, w2, ..., w 15 ), where the weight w of the j-th indicator. j The calculation formula is:

[0025] Furthermore, the step of calculating the town and village resilience evaluation results using the fuzzy comprehensive evaluation method includes:

[0026] Establish an evaluation level set V: V = {V1, V2, V3, V4, V5}, where V1 represents high toughness, V2 represents relatively high toughness, V3 represents medium toughness, V4 represents relatively low toughness, and V5 represents low toughness.

[0027] Construct the relation matrix Q:

[0028] Where: q sk This indicates that the s-th final indicator corresponds to the k-th evaluation level V. k The membership degree is 1≤s≤15, 1≤k≤5. Calculate the comprehensive evaluation result B: B=WQ=(b1,b2,b3,b4,b5), bk , 1≤k≤5, is the membership value of the kth evaluation level.

[0029] Furthermore, the normalized intervals of the evaluation level set V are divided as follows: V1 = [0.8, 1.0], V2 = [0.6, 0.8], V3 = [0.4, 0.6], V4 = [0.2, 0.4], V5 = [0, 0.2].

[0030] Furthermore, the elements q in the relation matrix Q sk The calculation method is as follows:

[0031] Calculate the average value for each column j of the standardized matrix P. The average value of the column corresponding to the final indicator is then expressed as: element q sk Includes: q s1 q s2 q s3 q s4 q s5 ,according to The correspondence between the value and the evaluation level is used to obtain the element q. sk The value;

[0032]

[0033] Furthermore, the fuzzy comprehensive evaluation method includes:

[0034] Calculate the membership value of the k-th evaluation level:

[0035] Among them, b k Let k be the k-th component in evaluation result B; after obtaining all 5 evaluation result components, calculate the maximum value of each component:

[0036] b max =max{b1,b2,b3,b4,b5}, then the evaluation level corresponding to the maximum value is the town / village resilience evaluation result.

[0037] The present invention also provides a resilience evaluation platform for towns and villages on the outskirts of large cities. The platform is used to execute the method of the present invention. The platform includes: a resilience evaluation platform for towns and villages on the outskirts of large cities, characterized in that the platform includes a data acquisition module, a preprocessing module, an indicator screening module, a weight calculation module, an evaluation result calculation module, and a result display module connected in sequence.

[0038] Furthermore, the data acquisition module is used to obtain publicly available literature on resilience evaluation from the internet based on web crawling technology, forming a literature collection.

[0039] Furthermore, the preprocessing module is used to perform semantic analysis and word segmentation on the document set and extract an initial index set.

[0040] Furthermore, the indicator screening module is used to calculate the TF-IDF value of each indicator in the initial indicator set using the TF-IDF algorithm, and select the final indicator based on the sorting of the TF-IDF values.

[0041] Furthermore, the weight calculation module is used to construct an evaluation matrix and calculate the weight of each indicator using the information entropy method.

[0042] Furthermore, the evaluation result calculation module is used to establish an evaluation level set, construct a relationship matrix, and use the fuzzy comprehensive evaluation method to calculate the town and village resilience evaluation results.

[0043] Furthermore, the results display module is used to display the final rating of the town and village resilience assessment.

[0044] The present invention also provides a computer-readable storage medium storing a computer program, the computer program being executed by a processor using the method for evaluating the resilience of towns and villages in the fringe areas of large cities according to the present invention.

[0045] The beneficial effects of this invention are as follows:

[0046] This invention establishes a multi-level evaluation index system, comprehensively assessing town and village resilience from four dimensions: economic, social, ecological, and infrastructure, thereby improving the scientific rigor and systematic nature of the evaluation. It utilizes web crawling technology and semantic analysis models to automatically acquire and process relevant literature data, and combines this with the TF-IDF algorithm to screen key indicators, improving data acquisition and processing efficiency. The invention employs the information entropy method to determine indicator weights, combined with fuzzy comprehensive evaluation, achieving objectivity and standardization in the evaluation process. Furthermore, it develops a supporting evaluation platform, automating the entire process from data collection to result display, thus improving the efficiency and accuracy of the evaluation work. Attached Figure Description

[0047] Figure 1 This is a flowchart of the method for evaluating the resilience of towns and villages on the outskirts of large cities according to the present invention;

[0048] Figure 2 This is a schematic diagram of the components of the urban fringe town and village resilience evaluation platform of the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention are described clearly and completely below. Obviously, the described embodiments are only some embodiments of this invention, not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0050] It should be noted that a large city refers to a city that meets the following conditions: (1) Scale condition: The urban resident population is more than 3 million; (2) Economic condition: The regional GDP reaches more than 300 billion yuan; (3) Administrative condition: It is a provincial capital, a municipality directly under the central government, a city with independent planning status, or a sub-provincial city; (4) Spatial condition: The built-up area reaches more than 200 square kilometers; (5) Functional condition: It has a complete urban infrastructure system, has multiple urban sub-centers, forms a metropolitan regional economic center, has a significant industrial agglomeration effect, and has regional comprehensive service functions; (6) Radiation condition: It has a strong economic, social and cultural radiation to the surrounding areas and can drive regional coordinated development.

[0051] Towns and villages on the outskirts of large cities refer to towns and their subordinate administrative villages located within the administrative area of ​​large cities and within 15-50 kilometers of the central urban area. They have the following characteristics: (1) Spatial characteristics: They are located in the urban-rural transition zone and are spatially continuous with the central urban area, but the density of construction land is significantly lower than that of the central urban area; (2) Functional characteristics: They undertake the node function of urban-rural factor flow, including population flow, material transportation, information exchange, etc.; (3) Industrial characteristics: They have a composite industrial structure with the coexistence of secondary and tertiary industry agglomeration and agricultural functions; (4) Social characteristics: The permanent population consists of local agricultural population, non-agricultural employment population and urban spillover population; (5) Infrastructure characteristics: Infrastructure and public service facilities are between urban and rural areas, showing obvious transitional characteristics.

[0052] Example 1

[0053] like Figure 1 The figure shows the resilience evaluation method for towns and villages on the outskirts of large cities according to the present invention. The method includes the following steps:

[0054] Step S1: Construct a multi-level evaluation index system. The multi-level evaluation index system includes a target layer, a criterion layer, and an indicator layer. The target layer is the evaluation result of town and village resilience, and the criterion layer includes four dimensions: economic resilience, social resilience, ecological resilience, and infrastructure resilience.

[0055] This multi-level evaluation system draws on the principles of the Analytic Hierarchy Process (AHP). For example, when assessing the resilience of a town on the outskirts of a major city, economic resilience can be examined by considering the degree of diversification of its industrial structure; social resilience by assessing the allocation of its medical and educational resources; ecological resilience by focusing on its environmental quality; and infrastructure resilience by examining the completeness of its municipal infrastructure. This multi-dimensional evaluation can comprehensively reflect the development status of towns and villages.

[0056] Step S2: Based on web crawling technology and semantic analysis model, relevant literature and data on town and village resilience evaluation are obtained, an initial set of indicators for the indicator layer is established, and the TF-IDF algorithm is used to filter the initial set of indicators to determine the final indicators for the indicator layer.

[0057] In practice, the Python Scrapy framework can be used for web crawling to retrieve relevant literature from academic databases such as CNKI and Wanfang. For example, using keywords such as "urban resilience" and "rural resilience," more than 200 core journal papers published in the past five years can be obtained. Using the Natural Language Processing (NLTK) toolkit for semantic analysis, evaluation indicators including "industry diversity index" and "medical resource density" can be extracted from these documents.

[0058] Based on web crawling technology, publicly available literature related to resilience evaluation was obtained online, forming a literature set L, L={L1,L2,L3,…,L… n}, n>200, use a semantic analysis model to preprocess the document set L to extract the initial index set I, I={I1,I2,I3,…,I m}, m>16.

[0059] The document set L is segmented to remove stop words and filter words, forming a document segmentation set L'. The TF-IDF algorithm is then used to calculate each index I in the initial index set I. i The term frequency (TF) and inverse document frequency (IDF) in the document segmentation set are as follows:

[0060]

[0061] Wherein, N{I i ∈L'} represents the index I in the document segmentation set L'. i The number of times it appears, T L' M{I} represents the number of words in the document segmentation set; i ∈L'} is a group containing index I i The number of documents.

[0062] Calculation index I iThe TF-IDF value is: TF-IDF = TF × IDF; the indicators in the initial indicator set I are sorted from high to low according to the TF-IDF value, and the top 15 are selected as the final indicators of the indicator layer. The final indicators of the indicator layer are classified according to four dimensions: economic resilience, social resilience, ecological resilience and infrastructure resilience, thus completing the correspondence between the indicator layer and the criterion layer.

[0063] The correspondence between the indicator layer and the criterion layer specifically includes:

[0064] Economic resilience: GDP per capita, fixed asset investment, and fiscal revenue;

[0065] Social resilience: population density, number of medical beds, coverage of educational facilities, and coverage of social security;

[0066] Ecological resilience: green coverage rate, air quality index, water quality compliance rate, and waste disposal rate;

[0067] Infrastructure resilience: road network density, water supply network density, communication network coverage, and power facility density.

[0068] These indicators are highly practical and feasible in real-world applications. Taking a town on the outskirts of a major city as an example: In terms of economic resilience, in 2023, the town's per capita GDP reached 85,000 yuan, fixed asset investment reached 1.5 billion yuan, and annual fiscal revenue reached 280 million yuan, demonstrating strong economic development potential. In terms of social resilience, the population density is 2,800 people per square kilometer, with 3 community health service centers providing a total of 120 medical beds, 15 primary and secondary schools and kindergartens covering 95% of the school-age population, and a social security coverage rate of 92%. In terms of ecological resilience, the green space coverage rate is 35%, the proportion of days with good air quality is 78%, the water quality compliance rate is 85%, and the harmless treatment rate of domestic waste is 99%. In terms of infrastructure resilience, the road network density is 4.2 kilometers per square kilometer, the water supply network density is 3.8 kilometers per square kilometer, the 5G network coverage rate is 95%, and the power distribution facility density is 2.5 distribution rooms per square kilometer.

[0069] Step S3: Calculate the weights of each level of indicators based on the initial indicator values ​​in the literature, construct the indicator weight matrix, and use the fuzzy comprehensive evaluation method to calculate the town and village resilience evaluation results.

[0070] Collect the raw data for each indicator and construct the evaluation matrix R: Where rij is the value of the j-th initial index in the i-th document, 1≤i≤n, 1≤j≤m, n is the number of documents, and m is the number of initial indicators; the evaluation matrix R is normalized to obtain the standardized matrix P, where the element p ij The formula for calculation is: Calculate the information entropy e of the j-th indicator j: Where k is the entropy coefficient. element p ij Let be the value of the j-th initial index in the i-th document after standardization.

[0071] Calculate the difference coefficient d of the j-th indicator. j :d j =1-e j Then, based on the final indicators of the indicator layer, construct the indicator weight vector W: W = (w1, w2, ..., w 15 ), where the weight w of the j-th indicator. j The calculation formula is:

[0072] The steps for calculating the town and village resilience evaluation results using the fuzzy comprehensive evaluation method include:

[0073] Establish an evaluation level set V: V = {V1, V2, V3, V4, V5}, where V1 represents high toughness, V2 represents relatively high toughness, V3 represents medium toughness, V4 represents relatively low toughness, and V5 represents low toughness.

[0074] Construct the relation matrix Q:

[0075] Where: q sk This indicates that the s-th final indicator corresponds to the k-th evaluation level V. k The membership degree is 1≤s≤15, 1≤k≤5. Calculate the comprehensive evaluation result B: B=WQ=(b1,b2,b3,b4,b5), b k , 1≤k≤5, is the membership value of the kth evaluation level.

[0076] The normalized intervals of the evaluation level set V are divided as follows: V1 = [0.8, 1.0], V2 = [0.6, 0.8], V3 = [0.4, 0.6], V4 = [0.2, 0.4], V5 = [0, 0.2].

[0077] Elements q in relation matrix Q sk The calculation method is as follows:

[0078] Calculate the average value for each column j of the standardized matrix P. The average value of the column corresponding to the final indicator is then expressed as: Assuming the standardized values ​​for the indicator "fixed asset investment" in the five studies are 0.75, 0.82, 0.68, 0.71, and 0.79, calculate the average value. Since 0.75 falls within the range [0.6, 0.8], it indicates that the indicator belongs to a relatively high level of resilience. This method of calculating the average value can eliminate the influence of individual extreme values ​​and more objectively reflect the overall level of the indicator.

[0079] element q sk Includes: q s1 q s2 q s3 q s4 q s5 ,according to The correspondence between the value and the evaluation level is used to obtain the element q. sk The value;

[0080]

[0081]

[0082] The fuzzy comprehensive evaluation method includes calculating the membership value of the k-th evaluation level:

[0083] Among them, b k Let k be the k-th component in evaluation result B; after obtaining all 5 evaluation result components, calculate the maximum value of each component:

[0084] b max =max{b1,b2,b3,b4,b5}, then the evaluation level corresponding to the maximum value is the town / village resilience evaluation result.

[0085] Example 2

[0086] like Figure 2 The diagram shows the composition of the urban periphery town and village resilience evaluation platform of the present invention. The platform is used to execute the method of Embodiment 1. The platform includes: an urban periphery town and village resilience evaluation platform, characterized in that the platform includes a data acquisition module, a preprocessing module, an indicator screening module, a weight calculation module, an evaluation result calculation module, and a result display module connected in sequence.

[0087] The data acquisition module is used to obtain publicly available literature on resilience evaluation based on web crawling technology, forming a literature collection.

[0088] The preprocessing module is used to perform semantic analysis and word segmentation on the document set and extract an initial index set.

[0089] The indicator screening module is used to calculate the TF-IDF value of each indicator in the initial indicator set using the TF-IDF algorithm, and select the final indicator based on the sorting of the TF-IDF values.

[0090] The weight calculation module is used to construct the evaluation matrix and calculate the weight of each indicator using the information entropy method.

[0091] The evaluation result calculation module is used to establish an evaluation level set, construct a relationship matrix, and use the fuzzy comprehensive evaluation method to calculate the town and village resilience evaluation results.

[0092] The results display module is used to show the final rating of the town and village resilience assessment.

[0093] This platform can be deployed on a local server or a cloud platform. Taking a practical application as an example: Data acquisition module: developed based on the Python Scrapy framework, capable of acquiring information from multiple data sources simultaneously; Preprocessing module: uses natural language processing tools such as NLTK for text cleaning and word segmentation; Indicator selection module: implements the TF-IDF algorithm using the scikit-learn library; Weight calculation module: performs matrix operations using NumPy; Evaluation result calculation module: implements fuzzy comprehensive evaluation based on Pandas; Result display module: uses the Django framework to build a web interface, combined with ECharts for visualization.

[0094] Example 3

[0095] The present invention also provides a computer-readable storage medium storing a computer program, the computer program being executed by a processor using the urban fringe town and village resilience evaluation method of Embodiment 1.

[0096] This computer program can be implemented in several forms: standalone software package: the Windows version is packaged as an .exe executable file, the Linux version is compiled as a .bin file, and the Mac version is packaged as an .app application; web application: the front-end uses the Vue.js framework to develop the interactive interface, the back-end uses the Spring Boot framework to provide a RESTful API, and the database uses MongoDB to store literature data and evaluation results; mobile application: the Android version is developed using Java / Kotlin, the iOS version is developed using Swift, and the cross-platform version is developed using the Flutter framework.

[0097] Deployment methods include local server deployment, cloud server deployment (such as Alibaba Cloud and Tencent Cloud), and containerized deployment (using Docker packaging).

[0098] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating the resilience of towns and villages on the outskirts of large cities, characterized in that, The method includes the following steps: Step S1: Construct a multi-level evaluation index system, which includes a target layer, a criterion layer, and an indicator layer. The target layer is the evaluation result of town and village resilience, and the criterion layer includes four dimensions: economic resilience, social resilience, ecological resilience, and infrastructure resilience. Step S2: Based on web crawling technology and semantic analysis models, relevant literature and data on town and village resilience evaluation are obtained, and an initial indicator set for the indicator layer is established. The TF-IDF algorithm is used to filter the initial indicator set to determine the final indicator layer indicators. Specifically, the initial indicator sets for the criterion layer and the indicator layer are established as follows: A collection of literature related to resilience evaluation was compiled by using web scraping technology to obtain publicly available online literature. , Using semantic analysis models to analyze document collections Preprocessing is performed to extract the initial indicator set. , ; For the collection of documents The process involves word segmentation to remove stop words and filter words, resulting in a document segmentation set. via TF IDF algorithm to calculate the initial indicator set Each indicator in The term frequency (TF) and inverse document frequency (IDF) in the document segmentation set are as follows: ； ； in, Document segmentation set medium indicators Number of times it appears This represents the number of words in the document segmentation set; For indicators Number of documents; calculation metrics TF-IDF value: The initial set of indicators was sorted from highest to lowest based on TF-IDF values. The indicators in the index are sorted, and the top 15 are selected as the final indicators of the indicator layer. The final indicators of the indicator layer are then classified according to four dimensions: economic resilience, social resilience, ecological resilience, and infrastructure resilience, thus completing the correspondence between the indicator layer and the criteria layer. Step S3: Calculate the weights of each level of indicators based on the initial indicator values ​​in the literature, construct the indicator weight matrix, and use the fuzzy comprehensive evaluation method to calculate the town and village resilience evaluation results. The steps for calculating the town and village resilience evaluation results using the fuzzy comprehensive evaluation method include: Establish evaluation level set : ,in Indicates high toughness Indicates high toughness Indicates medium toughness Indicates lower toughness Indicates low toughness; Constructing a relation matrix : ; in, Indicates the first The final indicator for the first rating levels membership degree Calculate the comprehensive evaluation results : , For the first Membership value of each evaluation level This is the indicator weight vector.

2. The method for evaluating the resilience of towns and villages on the outskirts of large cities according to claim 1, characterized in that, The correspondence between the indicator layer and the criterion layer specifically includes: Economic resilience: GDP per capita, fixed asset investment, and fiscal revenue; Social resilience: population density, number of medical beds, coverage of educational facilities, and coverage of social security; Ecological resilience: green coverage rate, air quality index, water quality compliance rate, and waste disposal rate; Infrastructure resilience: road network density, water supply network density, communication network coverage, and power facility density.

3. The method for evaluating the resilience of towns and villages on the outskirts of large cities according to claim 2, characterized in that, The process of calculating the weights of each level of indicators based on the initial indicator values ​​in the literature and constructing the indicator weight matrix includes: Collect the raw data for each indicator and construct the evaluation matrix R: ,in, Let j be the value of the initial index in the i-th document. , For the number of documents, The initial number of indicators; the evaluation matrix R is normalized to obtain the standardized matrix. , of which elements The formula for calculation is: Calculate the first Information entropy of each indicator : ,in The entropy coefficient, ,element The value of the j-th initial index in the i-th document after standardization; Calculate the first Coefficient of difference of each indicator : ; Then, based on the final indicators of the indicator layer, an indicator weight vector is constructed. : The weight of the j-th indicator is... The calculation formula is: .

4. The method for evaluating the resilience of towns and villages on the outskirts of large cities according to claim 3, characterized in that, The normalized interval of the evaluation level set V is divided as follows: , , , , .

5. The method for evaluating the resilience of towns and villages on the outskirts of large cities according to claim 4, characterized in that, Relationship matrix elements in The calculation method is as follows: For each column of the normalized matrix P Calculate the average value Then the average value of the column corresponding to the final indicator is expressed as: , ;element include: , , , , ,according to The correspondence between the value and the evaluation level is used to obtain the element. The value; ； ； ； ； 。 6. The method for evaluating the resilience of towns and villages on the outskirts of large cities according to claim 5, characterized in that, The fuzzy comprehensive evaluation method includes: Calculate the membership value of the k-th evaluation level: ,in, For the evaluation result B, the first Each of the five evaluation result components has five components; after obtaining all five evaluation result components, the maximum value of each component is calculated: The evaluation level corresponding to the maximum value is the town / village resilience evaluation result.

7. A resilience assessment platform for towns and villages on the outskirts of large cities, said platform being used to execute the method described in any one of claims 1-6, characterized in that, The platform includes: a resilience evaluation platform for towns and villages on the outskirts of large cities, characterized in that the platform comprises a data acquisition module, a preprocessing module, an indicator screening module, a weight calculation module, an evaluation result calculation module, and a result display module connected in sequence. The data acquisition module is used to obtain publicly available literature related to resilience evaluation on the Internet based on web crawling technology, and form a literature collection. The preprocessing module is used to perform semantic analysis and word segmentation on the document set and extract an initial index set; The indicator screening module is used to calculate the TF-IDF value of each indicator in the initial indicator set using the TF-IDF algorithm, and select the final indicators based on the sorting of the TF-IDF values. The weight calculation module is used to construct the evaluation matrix and calculate the weight of each indicator using the information entropy method. The evaluation result calculation module is used to establish an evaluation level set, construct a relationship matrix, and use the fuzzy comprehensive evaluation method to calculate the town and village resilience evaluation results. The results display module is used to show the final rating of the town and village resilience assessment.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method for evaluating the resilience of towns and villages in the fringe of large cities as described in any one of claims 1 to 6.

Images