Traditional village toughness comprehensive evaluation system

Abstract

The invention discloses a comprehensive evaluation system for toughness of a traditional village, and the system carries out the semantic coding of the toughness data of a to-be-evaluated traditional village through employing a neural network model based on deep learning, so as to extract the semantic description coding features of the multi-dimensional data of the toughness of the to-be-evaluated traditional village. The method comprises the following steps: calling village toughness aspect data marked as a first toughness evaluation label from a background database as a reference feature, and performing semantic query matching analysis based on toughness aspect multi-source data on a to-be-evaluated traditional village and each village marked as the first toughness evaluation label; therefore, whether the to-be-evaluated traditional village has the toughness level matched with the first toughness evaluation label or not is intelligently evaluated. Therefore, the accuracy of evaluating the comprehensive toughness of the to-be-evaluated traditional villages can be effectively improved by comparing and analyzing the to-be-evaluated traditional villages and the labeled villages.

Description

Technical Field

[0001] This application relates to the field of intelligent evaluation, and more specifically, to a comprehensive evaluation system for the resilience of traditional villages. Background Art

[0002] Traditional villages are not only symbols of regional culture but also important heritages of the development of human civilization. However, in the rapidly developing modern society, traditional villages are facing a series of challenges, such as frequent natural disasters, declining economic activities, population outflows, and imperfect management mechanisms. These problems seriously threaten the survival and development of traditional villages. Therefore, the resilience evaluation of traditional villages has become the key to protecting and developing traditional villages.

[0003] The existing resilience evaluation methods for traditional villages mainly include qualitative evaluation and quantitative evaluation. Qualitative evaluation methods mainly rely on expert knowledge and experience to draw evaluation conclusions in a qualitative way. Although this method can reveal the internal characteristics and potential advantages of villages to a certain extent, its subjectivity is strong and it is difficult to quantitatively compare the differences between different villages. Quantitative evaluation methods measure the resilience of villages by constructing mathematical models or statistical index systems. This method can provide relatively objective evaluation results, but there are also some limitations in practical applications, such as complex construction of index systems and insufficient generalization ability of models. Whether it is qualitative or quantitative evaluation, it is difficult to completely avoid the influence of human factors. Especially in the process of setting evaluation criteria and weight distribution, subjective judgment may lead to deviations in evaluation results.

[0004] Therefore, an optimized comprehensive evaluation system for the resilience of traditional villages is expected. Summary of the Invention

[0005] To solve the above technical problems, this application is proposed. The embodiments of this application provide a comprehensive evaluation system for the resilience of traditional villages, which performs semantic encoding on the data related to the resilience aspects of the traditional village to be evaluated by using a neural network model based on deep learning to extract the semantic description coding features of multi-dimensional data related to the resilience aspects of the traditional village to be evaluated. At the same time, the data related to the resilience aspects of the villages labeled with the first resilience evaluation label are retrieved from the background database as reference features, and through semantic query matching analysis based on multi-source data related to the resilience aspects of the traditional village to be evaluated and each village labeled with the first resilience evaluation label, the resilience level of the traditional village to be evaluated that matches the first resilience evaluation label is intelligently evaluated. In this way, by comparing and analyzing the traditional village to be evaluated with the labeled villages, the accuracy of the evaluation of the comprehensive resilience of the traditional village to be evaluated can be effectively improved.

[0006] According to one aspect of this application, a comprehensive evaluation system for the resilience of traditional villages is provided, which includes:

[0007] A data acquisition module, configured to acquire a dataset of the resilience aspects of a traditional village to be evaluated;

[0008] A semantic encoding module, configured to perform semantic encoding and structured processing on the dataset of the resilience aspects of the traditional village to be evaluated to obtain a multi-source semantic aggregation matrix of the resilience aspects of the village to be evaluated;

[0009] A first resilience evaluation label extraction module, configured to extract a set of multi-source semantic aggregation reference matrices of the resilience aspects of villages labeled with a first resilience evaluation label from a background database;

[0010] A semantic association encoding module, configured to perform semantic association encoding on the multi-source semantic aggregation matrix of the resilience aspects of the village to be evaluated and the set of multi-source semantic aggregation reference matrices of the resilience aspects of the village respectively to obtain a multi-source semantic aggregation implicit feature vector of the resilience aspects of the village to be evaluated and a set of multi-source semantic aggregation implicit reference feature vectors of the resilience aspects of the village;

[0011] A query encoding module, configured to perform cross-domain query encoding on the multi-source semantic aggregation implicit feature vector of the resilience aspects of the village to be evaluated relative to the set of multi-source semantic aggregation implicit reference feature vectors of the resilience aspects of the village based on the essential features of the set of multi-source semantic aggregation implicit reference feature vectors of the resilience aspects of the village to obtain a semantic query response representation vector of the resilience aspects of the village to be evaluated;

[0012] A resilience evaluation module, configured to determine whether to label the resilience of the traditional village to be evaluated with a first resilience evaluation label based on the semantic query response representation vector of the resilience aspects of the village to be evaluated.

[0013] Compared with the prior art, a comprehensive evaluation system for the resilience of traditional villages provided by the present application performs semantic encoding on the data of the resilience aspects of a traditional village to be evaluated by using a neural network model based on deep learning to extract semantic description encoding features of multi-dimensional data of the resilience aspects of the traditional village to be evaluated. At the same time, data of the resilience aspects of villages labeled with a first resilience evaluation label are retrieved from a background database as reference features, and through semantic query matching analysis based on multi-source data of the resilience aspects for the traditional village to be evaluated and each village labeled with a first resilience evaluation label, it is thus possible to intelligently evaluate whether the traditional village to be evaluated has a resilience level matching the first resilience evaluation label. In this way, by comparing and analyzing the traditional village to be evaluated and the already labeled villages, the accuracy of the evaluation of the comprehensive resilience of the traditional village to be evaluated can be effectively improved. Description of the Drawings

[0014] The above and other objects, features, and advantages of the present application will become more apparent by describing the embodiments of the present application in more detail with reference to the accompanying drawings. The drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0015] Figure 1 It is a block diagram of a comprehensive evaluation system for the resilience of traditional villages according to an embodiment of the present application;

[0016] Figure 2 It is a schematic diagram of data flow of a comprehensive evaluation system for the resilience of traditional villages according to an embodiment of the present application;

[0017] Figure 3 It is a block diagram of a query coding module in a comprehensive evaluation system for the resilience of traditional villages according to an embodiment of the present application. Detailed implementation manners

[0018] Next, exemplary embodiments according to the present application will be described in detail with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0019] As shown in the present application and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "including" and "comprising" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0020] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0021] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in order. On the contrary, as needed, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0022] Next, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0023] Existing traditional village resilience evaluation methods mainly include qualitative evaluation and quantitative evaluation. Qualitative evaluation methods mainly rely on expert knowledge and experience to draw evaluation conclusions in a qualitative manner. Although this method can reveal the internal characteristics and potential advantages of villages to a certain extent, its strong subjectivity makes it difficult to quantitatively compare the differences between different villages. Quantitative evaluation methods measure the resilience of villages by constructing mathematical models or statistical index systems. This method can provide relatively objective evaluation results, but there are also some limitations in practical applications, such as the complex construction of the index system and the insufficient generalization ability of the model. Whether it is qualitative or quantitative evaluation, it is difficult to completely avoid the influence of human factors. Especially in the process of setting evaluation criteria and weight allocation, subjective judgment may lead to deviations in evaluation results. Therefore, an optimized comprehensive evaluation system for traditional village resilience is expected.

[0024] In the technical solution of the present application, a comprehensive evaluation system for traditional village resilience is proposed. Figure 1 FIG. is a block diagram of a comprehensive evaluation system for traditional village resilience according to an embodiment of the present application. Figure 2 FIG. is a schematic diagram of data flow of a comprehensive evaluation system for traditional village resilience according to an embodiment of the present application. As Figure 1 and Figure 2As shown, the traditional village resilience comprehensive evaluation system 300 according to an embodiment of the present application includes: a data acquisition module 310 for acquiring a dataset of the resilience aspects of the traditional village to be evaluated; a multi-source semantic aggregation module 320 for the resilience aspects of the village to be evaluated, which is used to perform semantic encoding and structured processing on the dataset of the resilience aspects of the traditional village to be evaluated to obtain a multi-source semantic aggregation matrix for the resilience aspects of the village to be evaluated; a first resilience evaluation label extraction module 330 for extracting, from the background database, a set of multi-source semantic aggregation reference matrices for the resilience aspects of the village labeled with the first resilience evaluation label; a semantic association encoding module 340 for performing semantic association encoding on the multi-source semantic aggregation matrix for the resilience aspects of the village to be evaluated and the set of multi-source semantic aggregation reference matrices for the resilience aspects of the village respectively to obtain a multi-source semantic aggregation implicit feature vector for the resilience aspects of the village to be evaluated and a set of multi-source semantic aggregation implicit reference feature vectors for the resilience aspects of the village; a query encoding module 350 for performing cross-domain query encoding on the multi-source semantic aggregation implicit feature vector for the resilience aspects of the village to be evaluated with respect to the set of multi-source semantic aggregation implicit reference feature vectors for the resilience aspects of the village based on the essential features of the set of multi-source semantic aggregation implicit reference feature vectors for the resilience aspects of the village to obtain a semantic query response representation vector for the resilience aspects of the village to be evaluated; and a resilience evaluation module 360 for determining whether to label the resilience of the traditional village to be evaluated with the first resilience evaluation label based on the semantic query response representation vector for the resilience aspects of the village to be evaluated.

[0025] In particular, the data acquisition module 310 is used to acquire a dataset on the resilience aspects of the traditional villages to be evaluated. Among them, the resilience aspect data includes descriptions of the physical environment, economic conditions, social culture, and management mechanisms. It should be understood that the resilience of traditional villages is affected by multiple factors, and these factors interact with each other to jointly determine the village's resistance and recovery capabilities. In one example, the physical environment is the basis for the survival and development of traditional villages, including geographical location, natural landscape, ecological environment, infrastructure, etc. By evaluating the physical environment of the village to be evaluated, we can understand the village's ability to resist natural disasters, the health status of the ecological environment, and the improvement degree of infrastructure, providing a basis for improving the physical environment. The economic condition reflects the economic vitality and development potential of the village, including income level, industrial structure, employment opportunities, etc. By evaluating the economic condition of the village to be evaluated, we can identify the economic advantages and disadvantages of the village. The quality of the economic condition directly affects the living quality of residents and the sustainable development of the village. Social culture is the unique charm of traditional villages, including historical inheritance, folk customs, community relations, etc. By evaluating the social culture of the village to be evaluated, we can understand the status of cultural heritage protection, community cohesion, and residents' sense of identity in the village. The management mechanism is the key to ensuring the orderly operation and sustainable development of the village, including governance structure, rules and regulations, community participation, etc. By evaluating the management mechanism of the village to be evaluated, we can discover problems and shortcomings in governance, so as to optimize the management structure and improve governance efficiency. In the technical solution of this application, by analyzing data from multiple dimensions, we can more comprehensively reflect the actual situation of traditional villages, avoiding one-sidedness and limitations caused by single-dimensional evaluation.

[0026] Data on the physical environment mainly comes from Geographic Information System (GIS) data, remote sensing image data, environmental monitoring data, and disaster history records. These data can help us understand the geographical location, topography, climate conditions, natural landscape, vegetation cover, water body distribution, air quality, water quality, soil quality, and past natural disaster situations of the village. In one example, first, relevant data is collected through various means such as on-site inspections, questionnaires, remote sensing technology, and environmental monitoring equipment. For example, drones can be used for aerial photography to obtain high-resolution terrain and vegetation images; environmental monitoring stations can be installed to regularly collect air and water quality data. Secondly, the collected data is cleaned and standardized to ensure the consistency and comparability of the data. The specific steps include deduplication, filling missing values, and outlier processing. Finally, the processed data is stored in a database for subsequent analysis and retrieval. A database table containing fields such as geographical location, topography, climate conditions, environmental monitoring data, and disaster history records can be designed to ensure the efficient management and query of data.

[0027] Data on economic conditions mainly come from economic statistics provided by statistical bureaus and local governments, information on the number, scale, and industry distribution of enterprises within the village, as well as villagers' economic activities and consumption habits learned through questionnaires, interviews, etc. In one example, first, obtain economic statistics through official channels and conduct a census or sample survey of enterprises within the village. For example, the latest economic census data can be downloaded from the statistical bureau, or the household income and expenditure of villagers can be collected through questionnaires. Second, conduct statistical analysis on the collected economic data to identify the economic advantages and disadvantages of the village. Statistical software (such as SPSS, R language) can be used for data analysis to generate charts and reports to visually display the economic situation. Finally, integrate economic data from different sources to form a complete description of the economic situation. A database table containing fields such as per capita income, employment rate, number of enterprises, and industrial structure can be designed to ensure the integrity and consistency of the data.

[0028] Data on social culture mainly come from information such as the historical evolution, cultural heritage, and traditional festivals of the village, villagers' social relations, community cohesion, cultural identity learned through questionnaires, interviews, etc., as well as documentary materials such as local chronicles, academic papers, and news reports consulted. In one example, first, collect social culture data through various methods such as on-site inspections, literature reviews, and community surveys. For example, local elders can be visited to record their oral history; local chronicles can be consulted to understand the historical changes of the village; through questionnaires, villagers' understanding and participation in traditional culture can be learned. Second, classify and organize the collected data to ensure the integrity and accuracy of the data. A database table containing fields such as historical evolution, cultural heritage, traditional festivals, and community cohesion can be designed to ensure the efficient management and query of the data. Finally, store the organized data in the database for subsequent analysis and retrieval. A relational database (such as MySQL, PostgreSQL) can be used to store the data to ensure the security and integrity of the data.

[0029] Data on management mechanisms mainly come from local government policy documents and regulations on village management, community management records of villages (such as meeting minutes and activity records), as well as villagers' satisfaction and suggestions on community management obtained through questionnaires, interviews, etc. In one example, first, obtain government documents through official channels, organize community management records, and conduct resident surveys. For example, the latest policy documents can be downloaded from the local government website, and community meeting minutes and activity records can be collected; through questionnaires, understand villagers' satisfaction and suggestions on community management. Secondly, analyze the collected management mechanism data to identify problems and shortcomings in management. Text analysis tools (such as the NLTK library in Python) can be used to perform sentiment analysis on the text data to understand villagers' attitudes and opinions on community management. Finally, integrate management mechanism data from different sources to form a complete description of the management mechanism. A database table containing fields such as policy documents, community management records, and resident satisfaction can be designed to ensure the integrity and consistency of the data.

[0030] Specifically, the multi-source semantic aggregation module 320 for the resilience aspects of the village to be evaluated is used to perform semantic encoding and structured processing on the dataset of the resilience aspects of the traditional village to be evaluated to obtain the multi-source semantic aggregation matrix for the resilience aspects of the village to be evaluated. In a specific example of the present application, first, semantic encoding is respectively performed on the description of the physical environment aspect, the description of the economic situation aspect, the description of the social culture aspect, and the description of the management mechanism aspect to obtain a set of semantic encoding vectors for the description of the resilience aspects of the traditional village to be evaluated, where the set of semantic encoding vectors for the description of the resilience aspects of the traditional village to be evaluated includes the semantic encoding vector for the description of the physical environment aspect, the semantic encoding vector for the description of the economic situation aspect, the semantic encoding vector for the description of the social culture aspect, and the semantic encoding vector for the description of the management mechanism aspect. Here, considering that the description of the physical environment aspect, the description of the economic situation aspect, the description of the social culture aspect, and the description of the management mechanism aspect all exist in the form of natural language, the computer cannot directly understand and process them. Therefore, in the technical solution of the present application, semantic encoding is respectively performed on the description of the physical environment aspect, the description of the economic situation aspect, the description of the social culture aspect, and the description of the management mechanism aspect by using natural language processing technology, so as to effectively extract and process the semantic information in the text description of the resilience aspects to obtain the semantic encoding vector for the description of the physical environment aspect, the semantic encoding vector for the description of the economic situation aspect, the semantic encoding vector for the description of the social culture aspect, and the semantic encoding vector for the description of the management mechanism aspect. Then, the set of semantic encoding vectors for the description of the resilience aspects of the traditional village to be evaluated is arranged in a matrix to organically combine the data from different fields (physical environment, economic situation, social culture, management mechanism) of the resilience aspects of the village to be evaluated, forming a comprehensive representation of the multi-source data of the resilience aspects of the village to be evaluated, so as to obtain the multi-source semantic aggregation matrix for the resilience aspects of the village to be evaluated, which is convenient for comprehensive analysis and evaluation.

[0031] Specifically, the first resilience evaluation label extraction module 330 is configured to extract, from the background database, a set of multi-source semantic aggregation reference matrices for the resilience aspects of villages labeled with the first resilience evaluation label. That is, by obtaining, from the background database, a dataset for the resilience aspects of villages labeled with the first resilience evaluation label; similarly, performing semantic encoding and structuring processing on the dataset for the resilience aspects of villages labeled with the first resilience evaluation label to obtain a set of multi-source semantic aggregation reference matrices for the resilience aspects of villages labeled with the first resilience evaluation label. Among them, a large amount of village resilience evaluation data is stored in the background database. These data have been verified by a large amount of historical experience and data and have reference value for village resilience assessment. Therefore, in the technical solution of this application, the resilience aspect data (physical environment, economic status, social culture, management mechanism) of each village labeled with the first resilience evaluation label can be used as reference data. After the above-mentioned semantic encoding and matrix arrangement processing, a set of multi-source semantic aggregation reference matrices for the resilience aspects of villages is formed, so as to provide a comprehensive resilience evaluation benchmark, thereby improving the accuracy of the resilience evaluation of the traditional villages to be evaluated.

[0032] Specifically, the semantic association encoding module 340 is configured to perform semantic association encoding on the multi-source semantic aggregation matrix for the resilience aspects of the village to be evaluated and the set of multi-source semantic aggregation reference matrices for the resilience aspects of the village to obtain a set of multi-source semantic aggregation implicit feature vectors for the resilience aspects of the village to be evaluated and a set of multi-source semantic aggregation implicit reference feature vectors for the resilience aspects of the village. It should be understood that village resilience assessment needs to consider data in multiple dimensions, including physical environment, economic status, social culture, governance ability, etc. Single-dimensional assessment is difficult to comprehensively reflect the overall situation of the village, thus affecting the accuracy of the model's resilience analysis of the village. Therefore, in the technical solution of this application, the multi-source semantic aggregation matrix for the resilience aspects of the village to be evaluated is input into the multi-source data semantic association feature encoder based on the text convolutional neural network model to realize the semantic association fusion of the multi-source data for the resilience aspects of the village to be evaluated, so as to extract the multi-source semantic aggregation implicit features for the resilience aspects of the traditional village to be evaluated and obtain the multi-source semantic aggregation implicit feature vectors for the resilience aspects of the village to be evaluated. Similarly, the set of multi-source semantic aggregation reference matrices for the resilience aspects of the village is input into the multi-source data semantic association feature encoder based on the text convolutional neural network model to respectively extract the semantic association aggregation features between the multi-source data in each multi-source semantic aggregation reference matrix for the resilience aspects of the village, and obtain a set of multi-source semantic aggregation implicit reference feature vectors, so as to improve the accuracy of the reference data. Specifically, through the sliding convolution operation, the text convolutional neural network can effectively process and integrate multi-source data, capture the complex associations between the multi-source data for the resilience aspects of the village, and thus achieve deeper semantic association fusion in the feature space, providing a more accurate basis for resilience assessment.

[0033] In particular, the query encoding module 350 is configured to perform cross-domain query encoding on the multi-source semantic aggregation implicit feature vectors of the village resilience aspect to be evaluated with respect to the set of multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect based on the essential features of the set of multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect, so as to obtain the semantic query response representation vectors of the village resilience aspect to be evaluated. Since the evaluation of village resilience involves multi-dimensional and multi-modal data, and different multi-source semantic aggregation features of village resilience evaluation have different feature distributions, traditional methods often have difficulty in effectively integrating these diverse resilience features. Therefore, in the technical solution of this application, in order to reduce the noise interference between different village resilience features, this application proposes a cross-domain query encoding method based on essential features. By learning the essential features of the set of multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect, and using this to perform differential reinforcement hierarchical modulation on each multi-source semantic aggregation implicit feature of the village resilience aspect, the distinctiveness between the resilience features of different villages is enhanced, thereby avoiding noise interference and improving the ability to evaluate village resilience. In a specific example of this application, as Figure 3 shown, the query encoding module 350 includes: an essential feature extraction unit 351, configured to input the set of multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect into an essential feature capture network to obtain a multi-source semantic aggregation reference essential feature representation vector of the village resilience aspect; a semantic expression hierarchical modulation unit 352, configured to perform semantic expression hierarchical modulation on each multi-source semantic aggregation implicit reference feature vector in the set of multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect based on the multi-source semantic aggregation reference essential feature representation vector of the village resilience aspect to obtain a set of modulated multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect; a cross-domain query encoding unit 353, configured to perform cross-domain query encoding on the multi-source semantic aggregation implicit feature vectors of the village resilience aspect to be evaluated and the set of modulated multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect to obtain the semantic query response representation vectors of the village resilience aspect to be evaluated.

[0034] Specifically, the essential feature extraction unit 351 is configured to input the set of multi-source semantic aggregation implicit reference feature vectors in terms of village resilience into an essential feature capture network to obtain a multi-source semantic aggregation reference essential feature representation vector in terms of village resilience. That is, the set of multi-source semantic aggregation implicit reference feature vectors in terms of village resilience is input into an essential feature capture network designed to extract intrinsic attributes or core structures from data. The essential feature capture network is adapted to learn and extract complex reference state parameter multi-modal temporal correlation patterns from the set of multi-source semantic aggregation implicit reference feature vectors in terms of village resilience, and compress them into a fixed-length reference state parameter essential feature representation vector, so as to retain important information, reduce noise, and provide a reference anchor for subsequent processing. In the technical solution of this application, through the essential feature capture network, the features that can best reflect the essence of village resilience can be extracted from multi-source data, and these features can more accurately describe the resilience level of the village, thereby improving the quality and credibility of the evaluation, so as to obtain a multi-source semantic aggregation reference essential feature representation vector in terms of village resilience.

[0035] More specifically, in the embodiments of this application, the specific steps of inputting the set of multi-source semantic aggregation implicit reference feature vectors in terms of village resilience into the essential feature capture network include: First, calculate the semantic difference coefficient of each multi-source semantic aggregation implicit reference feature vector in terms of village resilience in the set of multi-source semantic aggregation implicit reference feature vectors in terms of village resilience relative to other multi-source semantic aggregation implicit reference feature vectors in terms of village resilience to obtain a set of multi-source semantic aggregation reference semantic difference coefficients; Then, take the opposite number of each multi-source semantic aggregation reference semantic difference coefficient in the set of multi-source semantic aggregation reference semantic difference coefficients and perform normalization processing based on the Softmax function to obtain a set of multi-source semantic aggregation reference essential semantic correlation factors; Then, using the set of multi-source semantic aggregation reference essential semantic correlation factors as the set of weights, calculate the position-weighted sum of the set of multi-source semantic aggregation implicit reference feature vectors in terms of village resilience to obtain the multi-source semantic aggregation reference essential feature representation vector in terms of village resilience.

[0036] Among them, the specific steps for calculating the semantic difference coefficient of each multi-source semantic aggregation implicit reference feature vector in the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect relative to other multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect are as follows: Calculate the mean of the first norm of the position-wise difference vectors between the multi-source semantic aggregation implicit reference feature vector for the village resilience aspect and each of the other multi-source semantic aggregation implicit reference feature vectors in the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect as the multi-source semantic aggregation reference semantic difference coefficient of this multi-source semantic aggregation implicit reference feature vector for the village resilience aspect.

[0037] In the above embodiment, the following essential feature extraction formula is used to perform essential feature extraction on the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect to obtain the multi-source semantic aggregation reference essential feature representation vector; among them, the essential feature extraction formula is:

[0038] X = {v 1 , v 2 ,..., v i ,..., v n}

[0039]

[0040] Among them, X represents the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect, v 1 , v 2 , v i and v n respectively represent the first, second, i-th, and n-th multi-source semantic aggregation implicit reference feature vectors in the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect, n is the number of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect, exp(·) represents the exponential operation, ‖·‖ 1 represents the first norm of the vector, D i represents the multi-source semantic aggregation reference semantic difference coefficient corresponding to the i-th multi-source semantic aggregation implicit reference feature vector for the village resilience aspect, and P k represents the multi-source semantic aggregation reference essential feature representation vector.

[0041] Specifically, the semantic expression hierarchical modulation unit 352 is configured to perform semantic expression hierarchical modulation on each multi-source semantic aggregation implicit reference feature vector in the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect based on the multi-source semantic aggregation reference essential feature representation vector for the village resilience aspect, so as to obtain a set of modulated multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect. That is, in the embodiments of the present application, first, calculate the multi-source semantic aggregation reference semantic contribution coefficients between each multi-source semantic aggregation implicit reference feature vector in the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect and the multi-source semantic aggregation reference essential feature representation vector for the village resilience aspect, to determine the specific contribution degree of each multi-source semantic aggregation implicit reference feature vector to the overall multi-source semantic aggregation expression for the resilience aspect, so as to obtain a set of multi-source semantic aggregation reference semantic contribution coefficients for the village resilience aspect. Furthermore, based on the set of multi-source semantic aggregation reference semantic contribution coefficients for the village resilience aspect, perform hierarchical modulation on the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect to widen the semantic essential expression differences between the multi-source semantic aggregation implicit reference feature vectors in the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect, and obtain the set of modulated multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect. By performing hierarchical modulation on the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect, the important resilience features in the multi-source semantic aggregation implicit reference features for the village resilience aspect will be assigned higher weights, so as to enhance the expressiveness of the important resilience features, and at the same time suppress the influence of the secondary resilience features. By enhancing the expressiveness of the important resilience features, the discrimination between different resilience features can be improved, making it easier for the model to identify and distinguish different village resilience features. In this way, the model can better focus on the features that are crucial for the final decision, thereby improving the robustness and generalization ability.

[0042] Among them, the specific steps of calculating the multi-source semantic aggregation reference semantic contribution coefficients between each multi-source semantic aggregation implicit reference feature vector in the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect and the multi-source semantic aggregation reference essential feature representation vector for the village resilience aspect include: calculating the Mahalanobis distance between each multi-source semantic aggregation implicit reference feature vector in the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect and the multi-source semantic aggregation reference essential feature representation vector for the village resilience aspect to obtain the set of multi-source semantic aggregation reference semantic contribution coefficients.

[0043] More specifically, based on the set of multi-source semantic aggregation reference semantic contribution coefficients for the village resilience aspects, the specific steps for hierarchical modulation of the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspects are as follows: Set a first mask threshold and a second mask threshold, where the second mask threshold is twice the first mask threshold; if the eigenvalue in the multi-source semantic aggregation implicit reference feature vector for the village resilience aspect is greater than the second mask threshold, perform a two-fold amplification process on it; if the eigenvalue in the multi-source semantic aggregation implicit reference feature vector for the village resilience aspect is greater than the first mask threshold and less than or equal to the second mask threshold, keep it unchanged; if the eigenvalue in the multi-source semantic aggregation implicit reference feature vector for the village resilience aspect is less than or equal to the first mask threshold, perform a two-fold reduction process on it, thereby obtaining the set of modulated multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect.

[0044] In the above embodiment, based on the multi-source semantic aggregation reference essential feature representation vector for the village resilience aspect, semantic expression hierarchical modulation is performed on each multi-source semantic aggregation implicit reference feature vector in the set of multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect to obtain the set of modulated multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect; where the semantic expression hierarchical modulation formula is:

[0045]

[0046] where S represents the covariance matrix, C i represents the multi-source semantic aggregation reference semantic contribution coefficient corresponding to the i-th multi-source semantic aggregation implicit reference feature vector for the village resilience aspect, mask(·) is the masking process, θ is a predetermined threshold, and v i ’ represents the set of modulated multi-source semantic aggregation implicit reference feature vectors for the village resilience aspect.

[0047] Specifically, the cross-domain query encoding unit 353 is used to perform cross-domain query encoding on the set of the multi-source semantic aggregation implicit feature vectors of the village resilience aspect to be evaluated and the modulated multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect, so as to obtain the semantic query response representation vector of the village resilience aspect to be evaluated. That is, in the embodiment of the present application, first, each of the modulated multi-source semantic aggregation implicit reference feature vectors in the set of the multi-source semantic aggregation implicit feature vectors of the village resilience aspect to be evaluated and the modulated multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect is input into the cross-domain query encoding attention network to generate attention scores according to the interaction between the multi-source semantic aggregation implicit feature vectors of the village resilience aspect to be evaluated and the modulated multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect, reflecting the correlation of different resilience feature combinations, so as to obtain a set of cross-domain query attention coefficients of the multi-source semantic aggregation of the village resilience aspect to be evaluated. Then, to ensure the numerical stability of the cross-domain query attention weights of the multi-source semantic aggregation of the village resilience aspect to be evaluated and make it a smooth and interpretable probability distribution, further, the set of cross-domain query attention coefficients of the multi-source semantic aggregation of the village resilience aspect to be evaluated is input into the weight conversion network based on the Sigmoid activation function to convert it into weight values within the normalized range, so as to obtain a set of cross-domain query attention weights of the multi-source semantic aggregation of the village resilience aspect to be evaluated. In this way, it can be ensured that the features in each of the modulated multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect are properly considered, and at the same time, the problem of gradient disappearance or explosion in extreme cases is avoided. Subsequently, using the set of cross-domain query attention weights of the multi-source semantic aggregation of the village resilience aspect to be evaluated as the set of weights, perform an element-wise product and then accumulation operation on the set of the multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect, so as to obtain the semantic query response representation vector of the village resilience aspect to be evaluated. Here, through the attention weights, the correlation between the multi-source semantic aggregation features of the village to be evaluated and the labeled village can be enhanced, the query feature representation of the real-time state optimization can be optimized, and the classification accuracy of the subsequent classifier can be improved.

[0048] In the above embodiment, the following cross-domain query encoding formula is used to perform cross-domain query encoding on the set of the multi-source semantic aggregation implicit feature vectors of the village resilience aspect to be evaluated and the modulated multi-source semantic aggregation implicit reference feature vectors of the village resilience aspect, so as to obtain the semantic query response representation vector of the village resilience aspect to be evaluated; wherein, the cross-domain query encoding formula is:

[0049]

[0050] Among them, v a represents the multi-source semantic aggregation implicit feature vector of the village resilience aspect to be evaluated, wi represents the cross - domain query attention coefficient of the multi - source semantic aggregation of the resilience aspect of the \(i\) - th modulated village resilience multi - source semantic aggregation implicit reference feature vector, \(a\) i represents the \(i\) - th cross - domain query attention weight of the multi - source semantic aggregation of the resilience aspect of the village to be evaluated in the set of cross - domain query attention weights of the multi - source semantic aggregation of the resilience aspect of the village to be evaluated, sigmoid(·) is the sigmoid function, \(V\) f represents the semantic query response representation vector of the resilience aspect of the village to be evaluated.

[0051] Specifically, the resilience evaluation module 360 is used to determine whether to label the resilience of the traditional village to be evaluated as the first resilience evaluation label based on the semantic query response representation vector of the resilience aspect of the village to be evaluated. In a specific example of the present application, the semantic query response representation vector of the resilience aspect of the village to be evaluated is input into the resilience comprehensive evaluation module based on a classifier to obtain an evaluation result, and the evaluation result is used to represent whether to label the resilience of the traditional village to be evaluated as the first resilience evaluation label. Specifically, the classifier mainly uses machine learning and statistical methods to learn the features of different evaluation category labels from the training data and classify the semantic query response representation vector of the resilience aspect of the village to be evaluated. Specifically, in the technical solution of the present application, the labels of the classifier include labeling the resilience of the traditional village to be evaluated as the first resilience evaluation label (the first classification label), and not labeling the resilience of the traditional village to be evaluated as the first resilience evaluation label (the second classification label). Among them, the classifier uses the softmax function to determine which classification label the semantic query response representation vector of the resilience aspect of the village to be evaluated belongs to. It should be noted that the first classification label \(p1\) and the second classification label \(p2\) here do not contain the concept set by humans. In fact, during the training process, the computer model does not have the concept of "whether to label the resilience of the traditional village to be evaluated as the first resilience evaluation label". It only has two classification labels and outputs the probabilities of the output features under these two classification labels, that is, the sum of \(p1\) and \(p2\) is one. Therefore, the evaluation result of whether to label the resilience of the traditional village to be evaluated as the first resilience evaluation label is actually transformed into a binary classification probability distribution that conforms to natural laws through the classification labels. Substantially, the physical meaning of the natural probability distribution of the labels is used, rather than the language text meaning of "whether to label the resilience of the traditional village to be evaluated as the first resilience evaluation label". In this way, a multi - dimensional comprehensive evaluation of the resilience of the traditional village to be evaluated can be realized, ensuring the scientificity and reliability of the evaluation result, achieving classification and labeling management, and providing a scientific basis and support for policy making and resource allocation.

[0052] In the technical solution of this application, the set of multi-source semantic aggregation implicit feature vectors for the resilience aspects of the village to be evaluated and the set of multi-source semantic aggregation implicit reference feature vectors for the resilience aspects of the village respectively represent the semantic association features of the resilience aspect data of the traditional village to be evaluated and the set of multi-source semantic association features for the resilience aspects of the village labeled with the first resilience evaluation label. However, considering that there may be interference signals or noise components in the set of multi-source semantic aggregation reference matrices for the resilience aspects of the village labeled with the first resilience evaluation label, when performing cross-domain query encoding based on essential feature hierarchical modulation on the set of multi-source semantic aggregation implicit feature vectors for the resilience aspects of the village to be evaluated and the set of multi-source semantic aggregation implicit reference feature vectors for the resilience aspects of the village, the resulting semantic query response representation vector for the resilience aspects of the village to be evaluated may be mixed with interference components. This interference component will cause a dynamic deviation in the overall feature of the semantic query response representation vector for the resilience aspects of the village to be evaluated in the high-dimensional feature space towards the class target probability mapping, affecting the convergence consistency of the classifier and the accuracy of the evaluation result obtained by inputting the semantic query response representation vector for the resilience aspects of the village to be evaluated into the resilience comprehensive evaluation module based on the classifier.

[0053] In the technical solution of this application, inputting the semantic query response representation vector for the resilience aspects of the village to be evaluated into the resilience comprehensive evaluation module based on the classifier to obtain an evaluation result includes:

[0054] Determine the semantic query response probability value p for the resilience aspects of the village to be evaluated obtained by inputting the semantic query response representation vector for the resilience aspects of the village to be evaluated into the resilience comprehensive evaluation module based on the classifier. The semantic query response probability value for the resilience aspects of the village to be evaluated represents the probability of labeling the resilience of the traditional village to be evaluated with the first resilience evaluation label;

[0055] Multiply the feature mean of the semantic query response representation vector for the resilience aspects of the village to be evaluated by the semantic query response probability value for the resilience aspects of the village to be evaluated to obtain the semantic query response statistical field value n = μp for the resilience aspects of the village to be evaluated, where μ represents the feature mean of the semantic query response representation vector for the resilience aspects of the village to be evaluated;

[0056] Subtract one from the semantic query response statistical field value for the resilience aspects of the village to be evaluated and then divide it by the semantic query response statistical field value for the resilience aspects of the village to be evaluated to obtain the semantic query response partial probability value ρ = (n - 1) / n for the resilience aspects of the village to be evaluated;

[0057] Calculate the power function V of the semantic query response representation vector for the resilience aspects of the village to be evaluated with the semantic query response partial probability value as the exponent ⊙ρ, and multiply it by the partial probability value point of the semantic query response in terms of the resilience of the village to be evaluated to obtain the microscopic representation vector V of the semantic query response in terms of the resilience of the village to be evaluated 1 = ρ ⊙ V ⊙ρ , where ⊙ represents dot product;

[0058] After dot multiplying the representation vector of the semantic query response in terms of the resilience of the village to be evaluated and the partial probability value of the semantic query response in terms of the resilience of the village to be evaluated, calculate the exponential function with the natural constant as the base to obtain the macroscopic mapping vector V of the semantic query response in terms of the resilience of the village to be evaluated 2 = exp(V ⊙ ρ);

[0059] After calculating the logarithm with base 2 of the microscopic representation vector of the semantic query response in terms of the resilience of the village to be evaluated, perform weighted summation with the macroscopic mapping vector of the semantic query response in terms of the resilience of the village to be evaluated to obtain the optimized representation vector of the semantic query response in terms of the resilience of the village to be evaluated where α and β represent weighted hyperparameters, represents point addition;

[0060] Input the optimized representation vector of the semantic query response in terms of the resilience of the village to be evaluated into the resilience comprehensive evaluation module based on a classifier to obtain the evaluation result.

[0061] Therefore, through the partial low-order derivative of the statistical distribution field corresponding to the representation vector of the semantic query response in terms of the resilience of the village to be evaluated, as the non-overlapping macroscopic feature representation behavior patch of the representation vector of the semantic query response in terms of the resilience of the village to be evaluated, based on the different macroscopic behavior patch organization spaces under the non-isotropic backbone structure of the representation vector of the semantic query response in terms of the resilience of the village to be evaluated, to strengthen the dynamic sensitivity of the long-sequence microscopic complex information distribution of the representation vector of the semantic query response in terms of the resilience of the village to be evaluated to the macroscopic representation behavior of the class probability, thereby promoting the iterative dynamic consistency of the class target between the classification target and the extracted features during the feature space-class probability mapping, so as to improve the accuracy of the evaluation result obtained by inputting the representation vector of the semantic query response in terms of the resilience of the village to be evaluated into the resilience comprehensive evaluation module based on a classifier.

[0062] As described above, the traditional village resilience comprehensive evaluation system 300 according to the embodiments of the present application can be implemented in various wireless terminals, such as a server with a traditional village resilience comprehensive evaluation algorithm. In a possible implementation manner, the traditional village resilience comprehensive evaluation system 300 according to the embodiments of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the traditional village resilience comprehensive evaluation system 300 can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the traditional village resilience comprehensive evaluation system 300 can also be one of the many hardware modules of the wireless terminal.

[0063] Alternatively, in another example, the traditional village resilience comprehensive evaluation system 300 and the wireless terminal can also be separate devices, and the traditional village resilience comprehensive evaluation system 300 can be connected to the wireless terminal through a wired and / or wireless network and transmit interaction information in accordance with a predefined data format.

[0064] The embodiments of the present disclosure have been described above. The above description is exemplary and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art in the technical field without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technologies in the market, or to enable other ordinary technical personnel in the technical field to understand the embodiments disclosed herein.

Claims

1. A comprehensive evaluation system for the resilience of traditional villages, characterized by: include: The data acquisition module is used to obtain the resilience dataset of the traditional villages to be evaluated; A multi-source semantic aggregation module for the resilience of the village to be evaluated, used for semantically encoding and structurally processing the resilience dataset of the traditional village to be evaluated to obtain a multi-source semantic aggregation matrix for the resilience of the village to be evaluated; A first resilience evaluation label extraction module is used to extract a set of multi-source semantic aggregation reference matrices of village resilience labeled as the first resilience evaluation label from a background database; A semantic association coding module, used for performing semantic association coding on the set of the multi-source semantic aggregation matrix of the village resilience to be evaluated and the set of the multi-source semantic aggregation reference matrix of the village resilience to obtain a set of multi-source semantic aggregation implicit feature vectors of the village resilience to be evaluated and a set of multi-source semantic aggregation implicit reference feature vectors of the village resilience; A query encoding module, for performing cross-domain query encoding of the multi-source semantically aggregated implicit feature vector of the village resilience to be evaluated relative to the set of multi-source semantically aggregated implicit reference feature vectors of the village resilience to obtain a semantic query response representation vector of the village resilience to be evaluated based on the essential characteristics of the set of multi-source semantically aggregated implicit reference feature vectors of the village resilience; The resilience assessment module is used to determine whether to mark the resilience of the traditional village to be assessed as a first resilience evaluation label based on the semantic query response representation vector of the resilience of the village to be assessed.

2. The comprehensive evaluation system for the resilience of traditional villages according to claim 1 is characterized in that: The resilience data include descriptions of the physical environment, economic conditions, social culture and management mechanisms.

3. The comprehensive evaluation system for the resilience of traditional villages according to claim 2 is characterized in that: The multi-source semantic aggregation of the village resilience to be evaluated includes: A semantic coding unit, used for semantically coding the description of the physical environment, the description of the economic situation, the description of the social culture and the description of the management mechanism to obtain a set of semantic coding vectors describing the resilience of the traditional village to be evaluated, wherein the set of semantic coding vectors describing the resilience of the traditional village to be evaluated includes a semantic coding vector describing the physical environment, a semantic coding vector describing the economic situation, a semantic coding vector describing the social culture and a semantic coding vector describing the management mechanism; A matrix arrangement unit is used to arrange the set of semantic coding vectors describing the resilience of the traditional village to be evaluated into a matrix to obtain a multi-source semantic aggregation matrix of the resilience of the village to be evaluated.

4. The comprehensive evaluation system for the resilience of traditional villages according to claim 3 is characterized in that: The semantic association encoding module is used to: Use a semantic association feature encoder for multi-source data on resilience based on a text convolutional neural network model to perform semantic association encoding on the set of multi-source semantic aggregation matrices for the resilience of the village to be evaluated and the set of multi-source semantic aggregation reference matrices for the resilience of the village to be evaluated, so as to obtain a set of multi-source semantic aggregation implicit feature vectors for the resilience of the village to be evaluated and a set of multi-source semantic aggregation implicit reference feature vectors for the resilience of the village.

5. The comprehensive evaluation system for the resilience of traditional villages according to claim 4 is characterized in that: The query encoding module comprises: An essential feature extraction unit is used to input the set of multi-source semantically aggregated implicit reference feature vectors of village resilience into an essential feature capture network to obtain a multi-source semantically aggregated reference essential feature representation vector of village resilience; A semantic expression hierarchical modulation unit is used to perform semantic expression hierarchical modulation on each village resilience multi-source semantic aggregation implicit reference feature vector in the set of village resilience multi-source semantic aggregation implicit reference feature vectors based on the village resilience multi-source semantic aggregation reference essential feature representation vector to obtain a set of village resilience multi-source semantic aggregation implicit reference feature vectors after modulation; A cross-domain query encoding unit is used to perform cross-domain query encoding on the set of multi-source semantically aggregated implicit feature vectors of the village resilience to be evaluated and the modulated multi-source semantically aggregated implicit reference feature vectors of the village resilience to be evaluated to obtain a semantic query response representation vector of the village resilience to be evaluated.

6. The comprehensive evaluation system for the resilience of traditional villages according to claim 5 is characterized in that: The essential feature extraction unit is used to: Calculating the semantic difference coefficient of each village resilience multi-source semantic aggregation implicit reference feature vector in the set of village resilience multi-source semantic aggregation implicit reference feature vectors relative to other village resilience multi-source semantic aggregation implicit reference feature vectors to obtain a set of village resilience multi-source semantic aggregation reference semantic difference coefficients; Taking the inverse of each of the multi-source semantic aggregation reference semantic difference coefficients of village resilience in the set of multi-source semantic aggregation reference semantic difference coefficients of village resilience, and then performing normalization processing based on the Softmax function to obtain a set of multi-source semantic aggregation reference essential semantic correlation factors of village resilience; Taking the set of essential semantic relevance factors of the multi-source semantic aggregation reference of the village resilience as a set of weights, the position-weighted sum of the set of implicit reference feature vectors of the multi-source semantic aggregation of the village resilience is calculated to obtain the multi-source semantic aggregation reference essential feature representation vector of the village resilience.

7. The comprehensive evaluation system for the resilience of traditional villages according to claim 6 is characterized in that: The semantic expression hierarchical modulation unit comprises: A semantic contribution coefficient calculation subunit, used to calculate the village resilience multi-source semantic aggregation reference semantic contribution coefficient between each village resilience multi-source semantic aggregation implicit reference feature vector in the set of village resilience multi-source semantic aggregation implicit reference feature vectors and the village resilience multi-source semantic aggregation reference essential feature representation vector to obtain a set of village resilience multi-source semantic aggregation reference semantic contribution coefficients; The feature modulation subunit is used to hierarchically modulate the set of implicit reference feature vectors of the multi-source semantic aggregation in terms of village resilience based on the set of reference semantic contribution coefficients of the multi-source semantic aggregation in terms of village resilience to obtain the set of implicit reference feature vectors of the multi-source semantic aggregation in terms of village resilience after modulation.

8. The comprehensive evaluation system for the resilience of traditional villages according to claim 7 is characterized in that: The cross-domain query encoding unit includes: A cross-domain query attention coefficient calculation subunit is used to input each modulated village resilience multi-source semantic aggregation implicit reference feature vector in the set of the multi-source semantic aggregation implicit feature vector of the village resilience to be evaluated and the multi-source semantic aggregation implicit reference feature vector of the modulated village resilience into a cross-domain query encoding attention network to obtain a set of multi-source semantic aggregation cross-domain query attention coefficients of the village resilience to be evaluated; A weight conversion subunit, used for inputting the set of multi-source semantic aggregation cross-domain query attention coefficients of the village resilience to be evaluated into a weight conversion network based on a Sigmoid activation function to obtain a set of multi-source semantic aggregation cross-domain query attention weights of the village resilience to be evaluated; The query optimization sub-unit is used to calculate the position-weighted sum of the set of multi-source semantically aggregated cross-domain query attention weights of the village resilience to be evaluated as a set of weights, so as to obtain the semantic query response representation vector of the village resilience to be evaluated.

9. The comprehensive evaluation system for the resilience of traditional villages according to claim 8 is characterized in that: The resilience assessment module is used to: The semantic query response representation vector of the resilience of the village to be evaluated is input into the classifier-based comprehensive resilience evaluation module to obtain an evaluation result, and the evaluation result is used to indicate whether the resilience of the traditional village to be evaluated is marked as the first resilience evaluation label.

Images