Data Processing Method and Device for the Knowledge Graph of Regional Sustainable Development Indicators

Abstract

The present invention provides a data processing method and device for a knowledge graph of regional sustainable development indicators, which relates to the technical fields of big data analysis and knowledge graph construction. The specific steps include: Firstly, continuously collect the sustainable development indicator data of economy, environment, and society in the same region for multiple historical years. After standardization processing, calculate the multivariate coordination index to evaluate the coordinated development degree of the three major fields. Based on these data, construct a knowledge graph and extract time series data. With the help of a long short-term memory network, construct a sustainable development prediction model, and use the time series data of the previous year as input and the data of the next year as output for training. After that, extract data from the current knowledge graph and input it into the trained model to obtain the predicted value of the next year, and accordingly construct the knowledge graph of the next year. The present invention integrates multi-domain data, calculates the coordination index, constructs a model, analyzes the regional development relationship, and provides evaluation and forward-looking prediction for regional sustainable development.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis and knowledge graph construction, and specifically provides a data processing method and device for a knowledge graph of regional sustainable development indicators. Background Art

[0002] Driven by the digital wave, the field of urban and regional development research has witnessed profound changes. As a key support for understanding the laws of regional development and formulating scientific development strategies, the data processing method has become increasingly important. Regional sustainable development is related to the rational allocation of resources, the protection of the ecological environment, and the improvement of people's livelihood, and is the core issue for achieving the long-term prosperity of human society.

[0003] Under this background, the data processing method based on the knowledge graph of big data urban indicators disclosed in the prior art with the publication number of CN117708192A includes the following steps: obtaining the urban macro big data of a target area in multiple historical years to generate an original indicator set; selecting the first urban indicator with the highest priority from the original indicator set, and determining each second urban indicator with the first urban indicator as a precondition indicator, so as to generate an available indicator set; sequentially extracting multiple indicator combinations within the available indicator set, respectively learning the data relationship between each indicator combination and the first urban indicator in the same year, and determining the best indicator combination and the best data model; returning to the operation of selecting the first urban indicator until all the urban indicators in the original indicator set are selected; constructing a knowledge graph with each urban indicator as a node according to the best indicator combination and the best data model corresponding to each urban indicator. This method clearly defines the complex data relationships between a large number of urban indicators in a quantitative form.

[0004] However, there are still the following deficiencies. From the above statements, on the one hand, the existing methods mainly focus on sorting out the data relationships between urban indicators, but lack sufficient consideration of the coordination of the three major systems of economy, environment and society involved in regional sustainable development. Regional sustainable development is by no means a single-dimensional growth, but a process of coordinating multiple goals such as economic growth, environmental protection, and social fairness and justice. Since the existing methods fail to systematically integrate and deeply analyze environmental monitoring data and social development indicators, it is difficult to generate key indicators for evaluating regional sustainable development such as the multi-dimensional coordination index, resulting in the inability to comprehensively and objectively measure the overall level of regional sustainable development. On the other hand, the existing methods have major defects in the analysis of the time dimension and fail to use time series data to deeply predict the regional development trend. In the dynamic process of regional development, the evolution trend of each indicator over time has irreplaceable value for predicting future development directions and formulating response strategies in advance. However, the existing methods only focus on the data relationships between indicators within the same year and ignore the development laws of indicators in the time dimension, and thus cannot provide strong prediction support for the long-term planning and scientific decision-making of the region.

[0005] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a data processing method and device for a knowledge graph of regional sustainable development indicators to solve the problems raised in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] A data processing method for a knowledge graph of regional sustainable development indicators, the specific steps include:

[0009] S1. Continuously collect sustainable development indicator data of the same region for multiple historical years. The sustainable development indicator data includes economic statistical data, environmental monitoring data, and social development indicator data, and perform standardization processing on the economic statistical data, environmental monitoring data, and social development indicator data;

[0010] S2. Calculate the standardized economic statistical data, environmental monitoring data, and social development indicator data to generate a multi-dimensional coordination index for evaluating the coordinated development degree of the economy, environment, and society;

[0011] S3. Based on the sustainable development indicator data and the multi - element coordination index data of multiple historical years in the same region, construct the knowledge graph of sustainable development indicators for each historical year in the same region, and extract time - series data from the constructed knowledge graph of sustainable development indicators. The time - series data includes the sustainable development indicator data and the multi - element coordination index data of each historical year in the same region;

[0012] S4. Construct a sustainable development prediction model based on the long - short - term memory network. Use the time - series data of the previous year among multiple historical years as input, and use the sustainable development indicator data and the coordination index data of the subsequent year among multiple historical years as the labeled output to train the sustainable development prediction model;

[0013] S5. Extract the time - series data of the current year from the current knowledge graph, input it into the trained sustainable development prediction model, and obtain the predicted values of the sustainable development indicator data and the multi - element coordination index data of the next year in this region;

[0014] S6. Based on the predicted values of the sustainable development indicator data and the multi - element coordination index data of the next year in this region, construct the knowledge graph of sustainable development indicators for the next year.

[0015] Furthermore, the economic statistical data includes per capita GDP and employment growth rate, the environmental monitoring data includes air quality index and forest coverage rate, and the social development indicator data includes average years of education per capita and energy consumption per unit of GDP.

[0016] Furthermore, calculate the economic statistical data, environmental monitoring data, and social development indicator data after standardization processing to generate a multi - element coordination index. The formula is as follows:

[0017] ;

[0018] Among them, is the multi - element coordination index of the th historical year in the same region, is the per capita GDP of the th historical year in the same region, is the energy consumption per unit of GDP of the th historical year in the same region, is the average years of education per capita of the th historical year in the same region, is the air quality index of the th historical year in the same region, is the forest coverage rate of the th historical year in the same region, is the employment growth rate of the th historical year in the same region;

[0019] Wherein, is the weight coefficient of the ratio of per capita GDP to energy consumption per unit GDP, is the weight coefficient of three indicators, namely per capita GDP, the ratio of energy consumption per unit GDP, and the average years of education per capita, when comprehensively evaluating the coordinated development degree of economy, environment and society, is the weight coefficient of two indicators, namely per capita GDP and air quality index, when comprehensively evaluating the coordinated development degree of economy, environment and society, is the weight coefficient of forest coverage rate and the ratio of energy consumption per unit GDP, is the weight coefficient of two indicators, namely employment growth rate and air quality index, when comprehensively evaluating the coordinated development degree of economy, environment and society. On the basis of let .

[0020] Furthermore, based on the regional sustainable development indicator data of multiple historical years in the same region, a knowledge graph of regional sustainable development indicators for each historical year is constructed. The specific process is as follows:

[0021] Data association: Taking the region and time as indexes, integrating economic statistical data, environmental monitoring data and social development indicator data, and associating the per capita GDP, air quality index and average years of education per capita data in the same region in the same year;

[0022] Knowledge extraction: Extracting entities, entity relationships, entity attributes and relationship attributes from the original data;

[0023] Graph construction: Selecting a storage scheme according to the data scale. For less data volume, use the Neo4j database; for large data volume, select a distributed database. Setting the extracted entities as nodes, entity relationships as edges, and adding attributes to nodes and edges;

[0024] Setting nodes: Setting "economic development representation entity" and "ecological environment quality entity" as nodes. The former includes per capita GDP data, and the latter includes air quality index;

[0025] Defining edges and relationships: Establishing a directed edge between the two with "the impact of economic activities on the ecological environment", and the direction is from the former to the latter;

[0026] Adding node attributes: Adding per capita GDP attribute to the "economic development representation entity";

[0027] Adding edge attributes: Adding an "impact degree" attribute to the edge, and determining the impact intensity through expert evaluation;

[0028] Graph optimization and verification: Conducting consistency check, knowledge reasoning and visualization verification.

[0029] Further, construct a knowledge graph of regional sustainable development indicators for the next year. The specific process is as follows:

[0030] Refer to the method of constructing the knowledge graph of historical years in the same region before. Based on the predicted values, construct a knowledge graph of regional sustainable development indicators for the next year. In the new knowledge graph, add nodes for the next year, and according to the logical relationships and influence mechanisms between the indicators, add corresponding edges, so as to form a knowledge graph that can reflect the regional sustainable development situation in the next year.

[0031] To achieve the above object, the present invention also provides the following technical solutions:

[0032] A data processing device for a knowledge graph of regional sustainable development indicators. The device is used to execute the data processing method of a knowledge graph of regional sustainable development indicators described in any one of the above, including:

[0033] A data collection module, which is used to continuously collect data on regional sustainable development indicators for multiple historical years in the same region, including economic statistical data, environmental monitoring data, and social development indicator data, and perform standardization processing on the economic statistical data, environmental monitoring data, and social development indicator data;

[0034] A data calculation module, which is used to calculate the standardized economic statistical data, environmental monitoring data, and social development indicator data to generate a multivariate coordination index for evaluating the coordinated development degree of economy, environment, and society;

[0035] A graph construction module, which is used to construct a knowledge graph of sustainable development indicators for each historical year in the same region based on the sustainable development indicator data and multivariate coordination index data for multiple historical years in the same region, and extract time series data from the constructed knowledge graph of regional sustainable development indicators. The time series data includes sustainable development indicator data and multivariate coordination index data for each year in the same region;

[0036] A prediction model construction module, which is used to construct a sustainable development prediction model based on a long short-term memory network, use the time series data of the previous year in multiple historical years as input, and use the regional sustainable development indicator data and coordination index data of the next year in multiple historical years as label output to train the regional sustainable development prediction model;

[0037] A simulation module, which is used to extract the time series data of the current year from the current knowledge graph, input it into the trained sustainable development prediction model, and obtain the predicted values of the regional sustainable development indicator data and multivariate coordination index data for the next year of the region;

[0038] The atlas prediction module is used to construct the knowledge atlas of sustainable development indicators for the next year based on the predicted values of the sustainable development indicator data and the multivariate coordination index data in the next year for this region.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0040] The present invention continuously collects regional economic statistical data, environmental monitoring data, and social development indicator data, performs standardized processing, calculates the multivariate coordination index, and conducts a multi-dimensional comprehensive assessment of the regional sustainable development level, breaking through the limitation of only focusing on a single field in the traditional method, clearly presenting the coordinated state of regional development, integrating the key data of the economic, environmental, and social systems through a unique algorithm, accurately measuring the coordination degree of the three systems, quantifying the coordinated development status among the three, and helping researchers and decision-makers comprehensively and intuitively understand the coordination of regional development.

[0041] By means of a long short-term memory network, in-depth modeling is performed on the time series data of regional sustainable development indicators. The model can automatically learn the complex evolution laws of each indicator in the time dimension, capture the periodic changes of economic, environmental, and social indicators, discover the long-term dependence relationships between data. Through this comprehensive and in-depth modeling and analysis, the model forms a thorough understanding of the complex relationships among the regional economic, environmental, and social systems, provides a highly forward-looking prediction for regional sustainable development, helps regional managers plan the development path in advance, fully consider the impacts on the environment and society when formulating economic development strategies, rationally allocate resources, coordinate the relationship between economic growth and environmental protection and social development, and effectively respond to potential challenges in multiple aspects such as population, resources, and environment, so as to achieve the long-term goal of regional sustainable development. Description of the Drawings

[0042] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0043] Figure 2 It is a block diagram of the module composition of the present invention. Specific Embodiments

[0044] In order to make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the following further elaborates on the present invention in conjunction with specific embodiments.

[0045] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0046] Embodiment 1:

[0047] Please refer to Figure 1 , the present invention provides a technical solution:

[0048] A data processing method for a knowledge graph of regional sustainable development indicators, the specific steps include:

[0049] S1. Continuously collect the sustainable development indicator data of the same region in multiple historical years. The sustainable development indicator data includes economic statistical data, environmental monitoring data and social development indicator data, and standardize the economic statistical data, environmental monitoring data and social development indicator data;

[0050] On the basis of the above embodiment, the economic statistical data includes per capita GDP and employment growth rate;

[0051] The environmental monitoring data includes air quality index and forest coverage rate;

[0052] The social development indicator data includes average years of education per capita and energy consumption per unit of GDP.

[0053] On the basis of the above embodiment, the collection methods of the economic statistical data, environmental monitoring data and social development indicator data are as follows:

[0054] The per capita GDP is usually calculated by the national or local statistical department according to the gross domestic product (GDP) and the number of permanent residents at the end of the year. Per capita GDP = gross domestic product / number of permanent residents at the end of the year.

[0055] The employment growth rate obtains the employment number data through methods such as labor force surveys and employment registrations. The statistical department calculates the employment growth rate according to the employment numbers in different periods. Using the formula, employment growth rate = (employment number in the next period - employment number in the previous period) / employment number in the previous period × 100%.

[0056] The air quality index is monitored in real time through air quality monitoring stations distributed in different regions. The monitoring stations are equipped with professional monitoring instruments to continuously monitor the concentrations of pollutants such as sulfur dioxide, nitrogen dioxide, particulate matter, carbon monoxide, and ozone in the air. Based on the concentration values of these pollutants, the air quality index is calculated.

[0057] The forest coverage rate is calculated by combining remote sensing technology and ground surveys. Satellite remote sensing images or aerial photogrammetry are used to obtain the distribution information of forest resources. Through image processing and analysis techniques, forest-covered areas are identified and their areas are calculated. Vector boundary data of the study area are obtained from a professional geographic information database or the natural resources department. These data clearly define the scope of the area. The total land area of the area is calculated through GIS software, and the forest coverage rate is calculated through the formula: forest coverage rate = forest-covered area / total land area × 100%.

[0058] The average years of education per capita are usually obtained by conducting population censuses, sample surveys, etc. to obtain information on the education levels of residents, and then calculating the weighted average of the years of education at different education levels.

[0059] The energy consumption per unit of GDP is calculated by the statistical department based on the total energy consumption and GDP data. The formula is energy consumption per unit of GDP = total energy consumption / GDP data × 100%. The total energy consumption is obtained by statistically calculating the consumption amounts of various energy sources such as coal, oil, natural gas, and electricity.

[0060] S2. Calculate the standardized economic statistical data, environmental monitoring data, and social development indicator data to generate a multi-dimensional coordination index for evaluating the coordinated development degree of the economy, environment, and society;

[0061] Based on the above embodiments, calculate the standardized economic statistical data, environmental monitoring data, and social development indicator data to generate a multi-dimensional coordination index. The formula is as follows:

[0062] ;

[0063] Wherein, is the multi-dimensional coordination index of the th historical year in the same region. The multi-dimensional coordination index is used to comprehensively evaluate the coordinated development degree of the economy, environment, and society by combining six indicators: per capita GDP, employment growth rate, air quality index, forest coverage rate, energy consumption per unit of GDP, and average years of education per capita. And the larger the multi-dimensional coordination index, the better the coordinated development degree of the economy, environment, and society;

[0064] In the formula, is the The per capita GDP of a historical year, is the energy consumption per unit GDP of the th historical year in the same region, is the average years of education per capita of the th historical year in the same region, is the air quality index of the th historical year in the same region, is the forest coverage rate of the th historical year in the same region, is the employment growth rate of the th historical year in the same region;

[0065] On this basis, it should be noted that: when the ratio of per capita GDP to energy consumption per unit GDP increases, it indicates that while reducing energy consumption, the output and quality of products are improved, promoting the growth of per capita GDP. At the same time, the proportion of clean energy in the energy consumption structure increases, the energy utilization efficiency is enhanced, the energy consumption per unit GDP decreases accordingly, and the development of the clean energy industry drives the development of related industrial chains, promoting the growth of per capita GDP. Therefore, the degree of coordinated development of the economy and the environment is improved, and the multi-dimensional coordination index increases;

[0066] When the ratio of per capita GDP to energy consumption per unit GDP increases and the average years of education per capita increases, it means that the quality of the labor force is improved, providing strong intellectual support for technological innovation. During the production process, high-quality labor can introduce advanced technologies and management experiences, significantly improving production efficiency. Taking the manufacturing industry as an example, highly educated technical talents can optimize the production process, not only reducing the energy consumption per unit GDP, but also improving the quality and output of products, promoting the growth of per capita GDP, and further promoting the coordinated development of the economy and the environment, making the multi-dimensional coordination index increases;

[0067] When per capita GDP increases and the air quality index decreases, the consumption structure of residents gradually shifts towards a green and healthy direction, and the demand of consumers for environmentally friendly products increases significantly, prompting enterprises to adjust their production strategies and increase their R & D and production investment in green products. Taking the household appliance industry as an example, the preference of consumers for energy-saving and low-pollution household appliances drives enterprises to adopt more environmentally friendly materials and production processes, reducing the pollution emissions during product production. This not only improves the air quality, but also promotes the green transformation of the industry, and further improves the degree of coordinated development of the economy and the environment, making the multi-dimensional coordination index increases;

[0068] When the ratio of forest coverage rate to energy consumption per unit GDP When it increases, the ecological environment is improved, providing a basis for the development of green industries such as eco-tourism and forestry-based economy. These green industries consume relatively less energy while creating economic value, helping to reduce the energy consumption per unit of GDP, and thus enhancing the coordinated development degree of the economy and the environment, making the multi-factor coordination index increase;

[0069] When the employment growth rate increases and the air quality index decreases, the increase in the employment growth rate, especially in the field of green industries, indicates that the green industries are developing rapidly. The expansion of green industries not only creates a large number of employment opportunities but also plays a positive role in improving air quality. For example, the development of the environmental protection equipment manufacturing industry not only absorbs a large amount of labor, but the environmental protection equipment produced is applied in industrial production and environmental governance, effectively reducing pollutant emissions and lowering the air quality index. This virtuous cycle of economic growth and environmental improvement enhances the coordinated development degree of the economy and the environment, making the multi-factor coordination index increase.

[0070] Therefore, the multi-factor coordination index is positively correlated with per capita GDP, years of education per capita, forest coverage rate, and employment growth rate, and the multi-factor coordination index is negatively correlated with energy consumption per unit of GDP and air quality index.

[0071] In summary, the above form is used to express the functional relationship between the multi-factor coordination index and per capita GDP, years of education per capita, forest coverage rate, employment growth rate, energy consumption per unit of GDP, and air quality index.

[0072] In the formula, is the weight coefficient of the ratio of per capita GDP to energy consumption per unit of GDP, is the weight coefficient of three indicators, namely per capita GDP, the ratio of energy consumption per unit of GDP, and years of education per capita, when comprehensively evaluating the coordinated development degree of the economy, environment, and society, is the weight coefficient of two indicators, namely per capita GDP and air quality index, when comprehensively evaluating the coordinated development degree of the economy, environment, and society, is the weight coefficient of the ratio of forest coverage rate to energy consumption per unit of GDP, is the weight coefficient of two indicators, namely employment growth rate and air quality index, when comprehensively evaluating the coordinated development degree of the economy, environment, and society;

[0073] The ratio of per capita GDP to energy consumption per unit of GDP intuitively reflects the energy utilization efficiency in the process of economic development, which is crucial for measuring the initial coordination state of the economy and the environment. If a region can increase per capita GDP while reducing energy consumption per unit of GDP, it undoubtedly lays a good foundation for the coordinated development of the economy, environment, and society. Compared with other complex indicator combinations, this ratio can more directly reflect the quality of economic development. Therefore, it usually occupies a relatively large proportion in the weight system.

[0074] As the global economy transforms towards a knowledge-based economy, the quality of the labor force and the technological innovation ability have gradually become the core elements driving sustainable economic development. The combination of the three indicators of per capita GDP, the ratio of energy consumption per unit of GDP, and the average years of education per capita comprehensively reflects the impact of the quality of the labor force on economic growth and energy utilization efficiency. A high-quality labor force can not only promote technological innovation and improve production efficiency but also facilitate the optimization and upgrading of the industrial structure. In the long run, it has a profound impact on the coordinated development of the economy, environment, and society. Therefore, its weight is usually only second to .

[0075] The air quality index is directly related to the quality of life and health of residents and is an important indicator for measuring environmental quality. The combination of per capita GDP and the air quality index reflects the relationship between economic development and environmental quality. Ensuring good air quality while pursuing economic development is the key to achieving the coordinated development of the economy, environment, and society. In addition, the forest coverage rate and the ratio of energy consumption per unit of GDP reflect the mutual relationship between the ecological environment and economic development and are of great significance for maintaining ecological balance and sustainable development. Therefore, and have medium weights in the overall system, lower than ;

[0076] Moreover, the air quality index directly affects the respiratory health of residents. Good air quality can reduce the incidence of respiratory diseases and improve the quality of life of residents, while the forest coverage rate maintains the stability of the ecosystem through ecological functions such as regulating the climate, conserving water sources, and preventing soil erosion, which is crucial for the survival and reproduction of wild animals and plants. The correlation between per capita GDP and the air quality index focuses on the impact on residents' health during economic development; the relationship between the forest coverage rate and energy consumption per unit of GDP focuses on the role of economic activities in the ecosystem. One is related to human health and the other to ecological balance, both of which are equally important for the sustainable development of human society, making their importance in the coordinated development assessment system comparable. Therefore, ;

[0077] The combination of employment growth rate and air quality index reflects the dual impact of the development of green industries on employment and the environment. Although creating job opportunities and improving air quality have a positive effect on the coordinated development of the economy, environment, and society, compared with other indicators, their impact on overall coordinated development is relatively indirect. Therefore, has a relatively small weight under normal circumstances.

[0078] To sum up, on the basis of , let .

[0079] As an implementation method, ranges from 0.35 to 0.6, ranges from 0.25 to 0.45, ranges from 0.1 to 0.2, ranges from 0.1 to 0.2, ranges from 0.05 to 0.15, and the specific values are set by technicians according to the actual situation and are not limited here.

[0080] S3. Based on the sustainable development indicator data and multi - dimensional coordination index data of multiple historical years in the same region, construct the sustainable development indicator knowledge graph of each historical year in the same region, and extract time - series data from the constructed sustainable development indicator knowledge graph. The time - series data includes the sustainable development indicator data and multi - dimensional coordination index data of each historical year in the same region;

[0081] On the basis of the above - mentioned embodiment, based on the regional sustainable development indicator data of multiple historical years in the same region, construct the regional sustainable development indicator knowledge graph of each historical year in the same region. The specific process is as follows:

[0082] Data association: Using the region and time as indexes, integrate economic statistical data, environmental monitoring data, and social development indicator data. For example, associate the per capita GDP data, air quality index data, and average years of education per capita data of the current year in the same region;

[0083] Knowledge extraction: Extract entities, entity relationships, entity attributes, and relationship attributes from the original data to lay the foundation for constructing the knowledge graph, which means analyzing the objects (entities) existing in the data, the connections (relationships) between these objects, and determining the characteristics (attributes) of each object and connection;

[0084] Graph construction: Select a suitable knowledge graph storage scheme according to the scale of data of each historical year. When the data volume is small, use the Neo4j database; when the data volume is large, choose a distributed database;

[0085] Define the extracted entities as graph nodes, the relationships between entities as edges, and add attributes to the nodes and edges;

[0086] Set nodes: When constructing the knowledge graph of regional sustainable development indicators, set "economic development representation entities" and "ecological environment quality entities" as nodes. The former aggregates data such as per capita GDP and employment growth rate, intuitively reflecting the regional economic development level; the latter integrates information such as air quality index, water quality compliance rate, and forest coverage rate, comprehensively reflecting the regional ecological environment status;

[0087] Define edges and relationships: The two are associated through "the impact of economic activities on the ecological environment" to form a directed edge. This edge indicates that the economic development process will have an impact on the ecological environment, and the direction is from "economic development representation entities" to "ecological environment quality entities";

[0088] Add node attributes: For economic development representation, add attributes such as the specific value of per capita GDP, the percentage of employment growth rate, the specific value of air quality index, the percentage of forest coverage rate, the specific value of average years of education per capita, and the percentage of energy consumption per unit GDP;

[0089] Add edge attributes: For the edge of "the impact of economic activities on the ecological environment", add the attribute of "impact degree". This attribute determines the impact intensity of economic development on the ecological environment through quantitative analysis or expert evaluation;

[0090] Graph optimization and verification steps: Consistency check, knowledge reasoning, and visualization verification.

[0091] S4. Construct a sustainable development prediction model based on the long short-term memory network, using the time series data of the previous year in multiple historical years as input, and the sustainable development indicator data and coordination index data of the subsequent year in multiple historical years as label output, and train the sustainable development prediction model;

[0092] Based on the above embodiments, when building an LSTM (Long Short-Term Memory) model, it is necessary to select a deep learning framework such as Keras (a high-level neural network API written in Python). The LSTM model consists of one or more LSTM layers and a fully connected layer. The LSTM layer can effectively learn the long-term dependencies in time series data and capture the changing trends of data over time. The fully connected layer generates the final prediction results based on the output of the LSTM layer. During this process, it is necessary to determine the number of neurons in the LSTM layer, which will affect the learning ability and complexity of the model; determine the time step, that is, the number of consecutive time periods considered by the model when analyzing data; clarify the number of features of the input data, that is, the number of sustainable development indicator data and multi-factor coordination index data in the previous year; and determine the number of features of the output data, that is, the number of sustainable development indicator data and coordination index data in the next year.

[0093] To enable the model to effectively learn the patterns in the data, it is necessary to select appropriate loss functions and optimizers. Commonly used loss functions include MSE (Mean Squared Error) and MAE (Mean Absolute Error), which are used to measure the difference between the model's prediction results and the true labels. The optimizer is responsible for adjusting the model's parameters to minimize the loss function. Common optimizers include Adam (Adaptive Moment Estimation) and SGD (Stochastic Gradient Descent), etc.

[0094] Use the training set to train the built model. Input the prepared input data and label data into the constructed model and start the training process. During the training process, the model will continuously adjust its own parameters (such as weights and biases, etc.) according to the difference between the input data and the label data to minimize the error between the prediction results and the actual labels. Through multiple iterative trainings, the model gradually learns the internal laws of the changes in sustainable development indicators and improves the prediction accuracy.

[0095] S5. Extract the time series data of the current year from the current knowledge graph, input it into the trained sustainable development prediction model, and obtain the predicted values of the sustainable development indicator data and multi-factor coordination index data for the next year in this region;

[0096] S6. Based on the predicted values of the sustainable development indicator data and multi-factor coordination index data for the next year in this region, construct the knowledge graph of the sustainable development indicators for the next year.

[0097] Based on the above embodiments, referring to the method of constructing the knowledge graph of historical years before, a knowledge graph of sustainable development indicators for the next year is constructed based on the predicted values. In the new knowledge graph, relevant nodes for the next year are added (such as economic, environmental, social indicator nodes and multi - dimensional coordination index nodes), and corresponding edges are added according to the logical relationships and influence mechanisms between the indicators, so as to form a knowledge graph that can reflect the sustainable development situation of the next year.

[0098] Please refer to Figure 2 , the present invention also provides a technical solution:

[0099] A data processing device for a knowledge graph of regional sustainable development indicators, the device is used to execute the data processing method of a knowledge graph of regional sustainable development indicators described in any one of the above, including:

[0100] A data collection module, configured to continuously collect regional sustainable development indicator data of multiple historical years in the same region, including economic statistical data, environmental monitoring data, and social development indicator data, and perform standardization processing on the economic statistical data, environmental monitoring data, and social development indicator data;

[0101] A data calculation module, configured to calculate the standardized economic statistical data, environmental monitoring data, and social development indicator data to generate a multi - dimensional coordination index for evaluating the coordinated development degree of the economy, environment, and society;

[0102] A graph construction module, configured to construct a knowledge graph of sustainable development indicators for each historical year in the same region based on the sustainable development indicator data and multi - dimensional coordination index data of multiple historical years in the same region, and extract time - series data from the constructed knowledge graph of regional sustainable development indicators, where the time - series data includes sustainable development indicator data and multi - dimensional coordination index data of each year in the same region;

[0103] A prediction model construction module, configured to construct a sustainable development prediction model based on a long - short - term memory network, use the time - series data of the previous year in multiple historical years as input, and use the regional sustainable development indicator data and coordination index data of the next year in multiple historical years as label output to train the regional sustainable development prediction model;

[0104] A simulation module, configured to extract the time - series data of the current year from the current knowledge graph, input it into the trained sustainable development prediction model, and obtain the predicted values of the sustainable development indicator data and multi - dimensional coordination index data of the next year in this region;

[0105] The atlas prediction module is used to construct a knowledge atlas of sustainable development indicators for the next year based on the predicted values of the sustainable development indicator data and the multivariate coordination index data for the next year in this region.

[0106] All of the above formulas are dimensionless and take their numerical values for calculation. The formula is obtained by collecting a large amount of data for software simulation to get a formula that is closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0107] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0108] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application.

Claims

1. A data processing method for a knowledge graph of regional sustainable development indicators, characterized in that The specific steps include: S1. Continuously collect the sustainable development indicator data of the same region in multiple historical years. The sustainable development indicator data includes economic statistical data, environmental monitoring data, and social development indicator data, and standardize the economic statistical data, environmental monitoring data, and social development indicator data; S2. Calculate the standardized economic statistical data, environmental monitoring data, and social development indicator data to generate a multivariate coordination index for evaluating the coordinated development degree of the economy, environment, and society; S3. Based on the sustainable development indicator data and the multivariate coordination index data of multiple historical years in the same region, construct the sustainable development indicator knowledge graph of each historical year in the same region, and extract time series data from the constructed sustainable development indicator knowledge graph. The time series data includes the sustainable development indicator data and the multivariate coordination index data of each historical year in the same region; S4. Construct a sustainable development prediction model based on the long short-term memory network, use the time series data of the previous year in multiple historical years as input, and use the sustainable development indicator data and the coordination index data of the next year in multiple historical years as the label output to train the sustainable development prediction model; S5. Extract the time series data of the current year from the current knowledge graph, input it into the trained sustainable development prediction model, and obtain the predicted values of the sustainable development indicator data and the multivariate coordination index data of the next year in this region; S6. Based on the predicted values of the sustainable development indicator data and the multivariate coordination index data of the next year in this region, construct the sustainable development indicator knowledge graph of the next year; The economic statistical data includes per capita GDP and employment growth rate, the environmental monitoring data includes air quality index and forest coverage rate, and the social development indicator data includes average years of education per capita and energy consumption per unit of GDP; Calculate the standardized economic statistical data, environmental monitoring data, and social development indicator data to generate a multivariate coordination index. The formula is as follows: Among them, is the multi - coordinated index of the th historical year in the same region, is the per capita GDP of the th historical year in the same region, is the energy consumption per unit GDP of the th historical year in the same region, is the average years of education per capita of the th historical year in the same region, is the air quality index of the th historical year in the same region, is the forest coverage rate of the th historical year in the same region, is the employment growth rate of the th historical year in the same region; wherein, is the weight coefficient of the ratio of per capita GDP to energy consumption per unit of GDP, is the weight coefficient of three indicators, namely, the ratio of per capita GDP to energy consumption per unit of GDP and the average years of education per capita, when comprehensively evaluating the coordinated development degree of economy, environment and society, is the weight coefficient of two indicators, namely, per capita GDP and air quality index, when comprehensively evaluating the coordinated development degree of economy, environment and society, is the weight coefficient of the forest coverage rate and the ratio of energy consumption per unit of GDP, is the weight coefficient of two indicators, namely, the employment growth rate and the air quality index, when comprehensively evaluating the coordinated development degree of economy, environment and society. On the basis of , let .

2. The data processing method of the knowledge graph of regional sustainable development indicators according to claim 1, characterized in that: Based on the regional sustainable development indicator data of multiple historical years in the same region, construct the regional sustainable development indicator knowledge graph of each historical year. The specific process is as follows: Data association: Index by region and time, integrate economic statistical data, environmental monitoring data, and social development indicator data, and associate the per capita GDP, air quality index, and average years of education per capita data of the same region in the same year; Knowledge extraction: Extract entities, entity relationships, entity attributes, and relationship attributes from the original data; Graph construction: Select a storage solution according to the data scale. Use the Neo4j database for less data volume and a distributed database for large data volume. Set the extracted entities as nodes, the entity relationships as edges, and add attributes to the nodes and edges; Set nodes: Set "economic development representation entity" and "ecological environment quality entity" as nodes. The former includes per capita GDP data, and the latter includes air quality index; Define edges and relationships: Establish a directed edge between the two with "the impact of economic activities on the ecological environment", and the direction is from the former to the latter; Add node attributes: Add the per capita GDP attribute to the "economic development representation entity"; Add edge attributes: Add the "influence degree" attribute to the edges, and determine the influence intensity through expert evaluation. Map optimization and verification: Conduct consistency checks, knowledge reasoning, and visualization verification.

3. The data processing method of the regional sustainable development index knowledge graph according to claim 2, wherein: Construct the knowledge graph of regional sustainable development indicators for the next year. The specific process is as follows: Refer to the method of constructing the knowledge graph of historical years in the same region before. Based on the predicted values, construct the knowledge graph of regional sustainable development indicators for the next year. In the new knowledge graph, add nodes for the next year, and according to the logical relationships and influence mechanisms between the indicators, add corresponding edges, so as to form a knowledge graph that can reflect the regional sustainable development situation in the next year.

4. A data processing device for a knowledge graph of regional sustainable development indicators, the device being used to execute the data processing method of a knowledge graph of regional sustainable development indicators according to any one of claims 1-3, characterized in that: Including: Data collection module, which is used to continuously collect the regional sustainable development indicator data of multiple historical years in the same region, including economic statistical data, environmental monitoring data, and social development indicator data, and standardize the economic statistical data, environmental monitoring data, and social development indicator data. Data calculation module, which is used to calculate the standardized economic statistical data, environmental monitoring data, and social development indicator data to generate a multivariate coordination index for evaluating the coordinated development degree of economy, environment, and society. Map construction module, which is used to construct the knowledge graph of sustainable development indicators for each historical year in the same region based on the sustainable development indicator data and multivariate coordination index data of multiple historical years in the same region, and extract time series data from the constructed knowledge graph of regional sustainable development indicators. The time series data includes the sustainable development indicator data and multivariate coordination index data of each year in the same region. Prediction model construction module, which is used to construct a sustainable development prediction model based on the long short-term memory network, use the time series data of the previous year in multiple historical years as input, and use the regional sustainable development indicator data and coordination index data of the next year in multiple historical years as label output to train the regional sustainable development prediction model. Simulation module, which is used to extract the time series data of the current year from the current knowledge graph, input it into the trained sustainable development prediction model, and obtain the predicted values of the sustainable development indicator data and multivariate coordination index data of the next year in this region. Map prediction module, which is used to construct the knowledge graph of sustainable development indicators for the next year based on the predicted values of the sustainable development indicator data and multivariate coordination index data of the next year in this region.

Images