Data processing method and device for regional sustainable development index knowledge graph

Abstract

The invention provides a data processing method and device for a regional sustainable development index knowledge graph, and relates to the technical field of big data analysis and knowledge graph construction, and the method comprises the specific steps: firstly, continuously collecting economic, environmental and social sustainable development index data of a plurality of historical years in the same region; a multi-element coordination index is calculated after standardization processing so as to evaluate the coordination development degree of the three fields, a knowledge graph is constructed based on the data, time sequence data is extracted, a sustainable development prediction model is constructed by means of a long and short-term memory network, and training is carried out by taking the time sequence data of the previous year as input and taking the data of the next year as output. And then, extracting data from the current knowledge graph, inputting the data into the trained model, obtaining a predicted value of the next year, and constructing a knowledge graph of the next year according to the predicted value. According to the method, multi-field data are integrated, the coordination index is calculated, the model is constructed, the regional development relation is analyzed, and evaluation and prospective prediction are provided 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 to a data processing method and device for a regional sustainable development indicator knowledge graph. Background Art

[0002] Driven by the wave of digitalization, the field of urban and regional development research has undergone profound changes. As a key support for gaining insight into regional development laws and formulating scientific development strategies, data processing methods have become increasingly important. Regional sustainable development is related to the rational allocation of resources, the protection of the ecological environment, and the improvement of social livelihood. It is a core issue for achieving long-term prosperity of human society.

[0003] In this context, the data processing method based on the knowledge graph of big data city indicators provided by the prior art with the publication number CN117708192A includes the following steps: including: obtaining the city macro big data of multiple historical years in the target area to generate an original indicator set; selecting the first city indicator with the highest priority from the original indicator set, and determining each second city indicator with the first city indicator as the pre-indicator, thereby generating an available indicator set; extracting multiple indicator combinations in the available indicator set one by one, respectively learning the data relationship between each indicator combination and the first city indicator in the same year, and determining the best indicator combination and the best data model; returning to the operation of selecting the first city indicator until all the city indicators in the original indicator set are selected; constructing a knowledge graph with each city indicator as a node according to the best indicator combination and the best data model corresponding to each city indicator. This method clarifies the complex data relationship between a large number of city indicators in a quantitative form.

[0004] However, there are still some shortcomings. From the above statements, it can be seen that, on the one hand, the existing methods focus on sorting out the data relationship 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 coordination between multiple goals such as economic growth, environmental protection, and social equity and justice. The existing methods fail to systematically integrate and deeply analyze environmental monitoring data and social development indicators, making it difficult to generate key indicators such as the multivariate coordination index to evaluate regional sustainable development, making it impossible 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 make in-depth predictions on regional development trends with the help of time series data. In the dynamic process of regional development, the evolution trend of various indicators over time is of irreplaceable value for predicting future development directions and planning response strategies in advance. However, the existing methods only focus on the data relationship between indicators in the same year, ignoring the development law of indicators in the time dimension, and cannot provide strong prediction support for regional long-term planning and scientific decision-making.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one 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 regional sustainable development indicator knowledge graph to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: A data processing method for a regional sustainable development indicator knowledge graph, the specific steps comprising: S1. Continuously collect sustainable development indicator data for the same region in multiple historical years. Sustainable development indicator data include economic statistics, environmental monitoring data and social development indicator data, and standardize economic statistics, environmental monitoring data and social development indicator data; S2. Calculate the standardized economic statistics, environmental monitoring data and social development indicator data to generate a multivariate coordination index for evaluating the degree of coordinated development of the economy, environment and society; S3. Based on the sustainable development indicator data and multivariate coordination index data of multiple historical years in the same region, a knowledge graph of sustainable development indicators in each historical year of the same region is constructed, and time series data is extracted from the constructed knowledge graph of sustainable development indicators. The time series data includes the sustainable development indicator data and 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, take the time series data of the previous year among multiple historical years as input, take the sustainable development indicator data and coordination index data of the next year among multiple historical years as label output, and 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 multivariate coordination index data of the region for the next year; S6. Based on the predicted values ​​of the sustainable development indicator data and multivariate coordination index data of the region for the next year, a knowledge graph of sustainable development indicators for the next year is constructed.

[0008] Furthermore, economic statistics include per capita GDP and employment growth rate, environmental monitoring data include air quality index and forest coverage rate, and social development indicator data include average years of education per capita and energy consumption per unit of GDP.

[0009] Furthermore, the standardized economic statistics, environmental monitoring data and social development indicator data are calculated to generate the multivariate coordination index, based on the following formula: ; in, For the same area The multivariate coordination index for each historical year, For the same area GDP per capita for each historical year, For the same area Energy consumption per unit of GDP in each historical year, For the same area The average number of years of education per capita in each historical year, For the same area Air quality index for historical years, For the same area The forest coverage rate in each historical year, For the same area employment growth rate in each historical year; In the formula, is the weight coefficient of the ratio of per capita GDP to energy consumption per unit GDP, is the weight coefficient of the three indicators of per capita GDP, energy consumption per unit GDP and average years of education in the comprehensive assessment of the coordinated development of economy, environment and society. is the weight coefficient of the two indicators of per capita GDP and air quality index in the comprehensive assessment of the coordinated development of economy, environment and society. is the weight coefficient of the ratio of forest coverage rate to energy consumption per unit GDP, is the weight coefficient of the employment growth rate and air quality index in the comprehensive evaluation of the coordinated development of economy, environment and society. On the basis of .

[0010] 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: Data association: Using region and time as indexes, integrate economic statistics, environmental monitoring data, and social development indicator data, and associate the per capita GDP, air quality index, and per capita years of education data for the same region in the same year; Knowledge extraction: extracting entities, entity relationships, entity attributes, and relationship attributes from raw data; Graph construction: select a storage solution based on the data scale. Use Neo4j database for small data volumes and a distributed database for large data volumes. Set the extracted entities as nodes, entity relationships as edges, and add attributes to nodes and edges. Set nodes: Set "economic development representation body" and "ecological environment quality body" as nodes, the former includes per capita GDP data, and the latter includes air quality index; Define edges and relationships: The two establish directed edges based on "the impact of economic activities on the ecological environment", with the direction from the former to the latter; Add node attributes: Add per capita GDP attribute to "economic development representation"; Add edge attributes: Add the "influence degree" attribute to the edge and determine the influence strength through expert evaluation; Graph optimization and verification: perform consistency checking, knowledge reasoning, and visual verification.

[0011] Furthermore, we construct a knowledge graph of regional sustainable development indicators for the next year. The specific process is as follows: Referring to the previous method of constructing the knowledge graph of historical years in the same region, the knowledge graph of regional sustainable development indicators for the next year is constructed based on the predicted values. In the new knowledge graph, the node of the next year is added, and the corresponding edges are added according to the logical relationship and influence mechanism between the indicators, thereby forming a knowledge graph that can reflect the regional sustainable development situation in the next year.

[0012] To achieve the above object, the present invention also provides the following technical solutions: A data processing device for a regional sustainable development indicator knowledge graph, the device being used to execute any of the above-mentioned data processing methods for a regional sustainable development indicator knowledge graph, comprising: The data collection module is used to continuously collect regional sustainable development indicator data for the same region in multiple historical years, including economic statistics data, environmental monitoring data and social development indicator data, and to standardize the economic statistics data, environmental monitoring data and social development indicator data; The data calculation module 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 degree of coordinated development of the economy, environment and society; A graph construction module 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 regional sustainable development indicator knowledge graph, where the time series data includes the sustainable development indicator data and multivariate coordination index data for each year in the same region; A prediction model building module is used to build a sustainable development prediction model based on a long short-term memory network, using the time series data of the previous year among multiple historical years as input and the regional sustainable development indicator data and coordination index data of the next year among multiple historical years as label output to train the regional sustainable development prediction model; The simulation module is used to extract the time series data of the current year from the current knowledge graph, input the trained sustainable development prediction model, and obtain the predicted values ​​of the sustainable development indicator data and multivariate coordination index data of the region in the next year; The graph prediction module is used to construct a 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 region for the next year.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention continuously collects regional economic statistics, environmental monitoring data and social development indicator data, and standardizes and processes them, calculates the multivariate coordination index, and conducts a multi-dimensional comprehensive evaluation of the regional sustainable development level, breaking through the traditional limitation of focusing on a single field, and clearly presents the coordinated state of regional development. With the help of a unique algorithm, the key data of the three major systems of economy, environment and society are integrated, the degree of coordination of the three major systems is accurately measured, and the coordinated development status among the three systems is quantified, so as to help researchers and decision makers fully and intuitively understand the coordination of regional development. With the help of long short-term memory networks, the time series data of regional sustainable development indicators are deeply modeled. The model can automatically learn the complex evolution laws of various indicators in the time dimension, capture the cyclical changes of economic, environmental and social indicators, and discover the long-term dependencies between data. Through this comprehensive and in-depth modeling and analysis, the model forms a thorough understanding of the complex relationship between regional economic, environmental and social systems, provides highly forward-looking predictions for regional sustainable development, and helps regional managers plan development paths in advance. When formulating economic development strategies, they fully consider the impact on the environment and society, rationally allocate resources, coordinate the relationship between economic growth and environmental protection and social development, effectively respond to potential challenges in population, resources, environment and other aspects, and achieve the long-term goal of regional sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the overall method flow of the present invention; Figure 2 This is a block diagram of the module composition of the present invention. DETAILED DESCRIPTION

[0015] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0016] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0017] Embodiment 1: See also Figure 1 , the present invention provides a technical solution: A data processing method for a regional sustainable development indicator knowledge graph, the specific steps comprising: S1. Continuously collect sustainable development indicator data for the same region in multiple historical years. Sustainable development indicator data include economic statistics, environmental monitoring data and social development indicator data, and standardize economic statistics, environmental monitoring data and social development indicator data; Based on the above embodiment, the economic statistics include GDP per capita and employment growth rate; Environmental monitoring data include air quality index and forest cover; Social development indicator data include average years of education per capita and energy consumption per unit of GDP.

[0018] Based on the above embodiment, the method for collecting economic statistical data, environmental monitoring data and social development indicator data is as follows: Per capita GDP is usually calculated by national or local statistical departments based on 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.

[0019] The employment growth rate is obtained through labor force surveys, employment registration and other methods. The statistical department calculates the employment growth rate based on the number of employed people in different periods, using the formula: employment growth rate = (number of employed people in the next period - number of employed people in the previous period) / number of employed people in the previous period × 100%.

[0020] The air quality index is monitored in real time through air quality monitoring stations distributed in different areas. 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, ozone, etc. in the air. The air quality index is calculated based on the concentration values ​​of these pollutants.

[0021] 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. Image processing and analysis techniques are used to identify forest-covered areas and calculate their areas. Vector boundary data of the study area are obtained from professional geographic information databases or natural resources departments. 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 using the formula: Forest coverage rate = forest coverage area / total land area × 100%.

[0022] The average number of years of education per capita is usually calculated by obtaining information on residents' educational level through population censuses, sample surveys, etc., and taking the weighted average of the years of education for people with different educational levels.

[0023] 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 calculated by counting the consumption of various energy sources such as coal, oil, natural gas, and electricity.

[0024] S2. Calculate the standardized economic statistics, environmental monitoring data and social development indicator data to generate a multivariate coordination index for evaluating the degree of coordinated development of the economy, environment and society; On the basis of the above embodiment, the standardized economic statistical data, environmental monitoring data and social development indicator data are calculated to generate a multivariate coordination index according to the following formula: ; in, For the same area The multivariate coordination index of historical years is used to comprehensively evaluate the coordinated development of 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. The larger the multivariate coordination index, the better the coordinated development of economy, environment and society. In the formula, For the same area GDP per capita for each historical year, For the same area Energy consumption per unit of GDP in each historical year, For the same area The average number of years of education per capita in each historical year, For the same area Air quality index for historical years, For the same area The forest coverage rate in each historical year, For the same area employment growth rate in each historical year; On this basis, it should be noted that when the ratio of per capita GDP to energy consumption per unit GDP is When it increases, it means that while reducing energy consumption, product output and quality are improved, and per capita GDP growth is promoted. At the same time, the proportion of clean energy in the energy consumption structure increases, energy utilization efficiency is improved, and energy consumption per unit GDP decreases accordingly. The development of the clean energy industry drives the development of related industrial chains and promotes per capita GDP growth, thereby improving the degree of coordinated development of the economy and the environment, making the multi-coordination index Increase; When the ratio of GDP per capita to energy consumption per unit of GDP When the average number of years of education per capita increases, it means that the quality of the labor force is improved, providing strong intellectual support for technological innovation. In the production process, high-quality labor can introduce advanced technology and management experience, greatly improving production efficiency. Taking the manufacturing industry as an example, highly educated technical talents can not only reduce the energy consumption per unit of GDP by optimizing the production process, but also improve the quality and output of products, promote the growth of per capita GDP, and then promote the coordinated development of economy and environment, so that the multi-coordination index Increase; As GDP per capita increases, air quality index When the consumption structure of residents gradually changes to green and healthy direction, the demand of consumers for environmentally friendly products increases significantly, prompting enterprises to adjust their production strategies and increase investment in the research and development and production of green products. Taking the home appliance industry as an example, consumers’ preference for energy-saving and low-pollution home appliances promotes enterprises to adopt more environmentally friendly materials and production processes, and reduce pollution emissions in the production process. This not only improves air quality, but also promotes the green transformation of the industry, thereby improving the coordinated development of economy and environment, making the multi-coordination index Increase; When the ratio of forest coverage to energy consumption per unit of GDP When the energy consumption increases, it improves the ecological environment and provides a foundation for the development of green industries such as ecotourism and forest economy. These green industries consume relatively less energy while creating economic value, which helps to reduce energy consumption per unit of GDP, thereby improving the coordinated development of economy and environment and making the multi-coordination index Increase; When employment growth increases, air quality index When the number of jobs decreases, the increase in employment growth rate, especially in the field of green industries, shows that green industries are developing rapidly. The expansion of green industries not only creates a large number of jobs, but also plays a positive role in improving air quality. For example, the development of environmental protection equipment manufacturing industry not only absorbs a large number of labor forces, but also produces environmental protection equipment used 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 improves the coordinated development of economy and environment and makes the multi-coordination index Increase.

[0025] Therefore, the multivariate coordination index It is positively correlated with per capita GDP, per capita years of education, forest coverage, and employment growth rate. The multivariate coordination index It is negatively correlated with energy consumption per unit of GDP and air quality index.

[0026] In summary, the above form is used to express the multivariate coordination index The functional relationship between per capita GDP, average years of education per capita, forest coverage rate, employment growth rate, energy consumption per unit of GDP, and air quality index.

[0027] In the formula, is the weight coefficient of the ratio of per capita GDP to energy consumption per unit GDP, is the weight coefficient of the three indicators of per capita GDP, energy consumption per unit GDP and average years of education in the comprehensive assessment of the coordinated development of economy, environment and society. is the weight coefficient of the two indicators of per capita GDP and air quality index in the comprehensive assessment of the coordinated development of economy, environment and society. is the weight coefficient of the ratio of forest coverage rate to energy consumption per unit GDP, It is the weight coefficient of the two indicators, employment growth rate and air quality index, in the comprehensive evaluation of the coordinated development of economy, environment and society; The ratio of GDP per capita to energy consumption per unit of GDP directly reflects the energy efficiency in the process of economic development, which is crucial to measuring the initial coordination between economy and environment. If a region can reduce energy consumption per unit of GDP while increasing GDP per capita, it will undoubtedly lay a good foundation for the coordinated development of economy, environment and society. Compared with other complex indicator combinations, this ratio can more directly reflect the quality of economic development. Therefore, In the weighting system, it usually occupies a relatively large proportion.

[0028] As the global economy transforms to a knowledge-based economy, labor quality and technological innovation capabilities have gradually become the core elements for promoting sustainable economic development. The combination of per capita GDP, energy consumption per unit GDP and average years of education fully reflects the impact of labor quality on economic growth and energy efficiency. High-quality labor can not only promote technological innovation and improve production efficiency, but also promote the optimization and upgrading of industrial structure. In the long run, it has a far-reaching impact on the coordinated development of economy, environment and society. Therefore, The weight is usually second only to .

[0029] 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 air quality index reflects the relationship between economic development and environmental quality. While pursuing economic development, ensuring good air quality is the key to achieving coordinated development of economy, environment and society. In addition, the forest coverage rate and the energy consumption per unit GDP ratio reflect the relationship between ecological environment and economic development, which is of great significance to maintaining ecological balance and sustainable development. Therefore, and The weight of ; 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. The forest coverage rate maintains the stability of the ecosystem by regulating the climate, conserving water resources, maintaining water and soil, and other ecological functions. It is crucial to the survival and reproduction of wild animals and plants. The relationship between per capita GDP and the air quality index focuses on the impact of economic development on residents' health; the relationship between forest coverage and energy consumption per unit of GDP focuses on the effect of economic activities on the ecosystem. One of them is related to human health, and the other is related to ecological balance. They are equally important to the sustainable development of human society, which makes them equally important in the coordinated development evaluation system. Therefore, ; The combination of employment growth rate and air quality index reflects the dual impact of green industry development on employment and environment. Although creating employment opportunities and improving air quality have a positive effect on the coordinated development of economy, environment and society, their impact on overall coordinated development is relatively indirect compared with other indicators. The weight of is usually relatively small.

[0030] In summary, On the basis of .

[0031] As an implementation method, The value range is 0.35-0.6, The value range is 0.25-0.45, The value range is 0.1-0.2. The value range is 0.1-0.2. The value range is 0.05-0.15. The specific value is set by the technicians according to the actual situation and is not limited here.

[0032] S3. Based on the sustainable development indicator data and multivariate coordination index data of multiple historical years in the same region, a knowledge graph of sustainable development indicators in each historical year of the same region is constructed, and time series data is extracted from the constructed knowledge graph of sustainable development indicators. The time series data includes the sustainable development indicator data and multivariate coordination index data of each historical year in the same region; On the basis of the above embodiment, based on the regional sustainable development indicator data of multiple historical years in the same region, a knowledge graph of regional sustainable development indicators in each historical year of the same region is constructed. The specific process is as follows: Data association: Using region and time as indexes, economic statistics, environmental monitoring data, and social development indicator data are integrated. For example, the per capita GDP data, air quality index data, and per capita years of education data for the same region in the current year are associated; Knowledge extraction: Extracting entities, entity relationships, entity attributes, and relationship attributes from raw data to lay the foundation for building a knowledge graph. This means analyzing the objects (entities) in the data, as well as the connections (relationships) between these objects, and determining the characteristics (attributes) of each object and connection. Graph construction: Choose a suitable knowledge graph storage solution based on the scale of data in each historical year. When the amount of data is small, use the Neo4j database. When the amount of data is large, choose a distributed database. Define the extracted entities as graph nodes, define the relationships between entities as edges, and add attributes to the nodes and edges; Setting nodes: When constructing the knowledge graph of regional sustainable development indicators, the "economic development representation body" and "ecological environment quality body" are set as nodes. The former integrates data such as per capita GDP and employment growth rate to directly reflect the level of regional economic development; the latter integrates information such as air quality index, water quality compliance rate, and forest coverage rate to comprehensively reflect the regional ecological environment status; Define the edge and relationship: The two are connected through the "impact of economic activities on the ecological environment", forming a directed edge. This edge indicates that the process of economic development will have an impact on the ecological environment, and the direction is from the "economic development representation body" to the "ecological environment quality body"; Add node attributes: economic development representation, add specific values ​​of per capita GDP, employment growth rate percentage, specific values ​​of air quality index, forest coverage percentage, specific values ​​of per capita years of education, and energy consumption per unit GDP percentage; Add edge attributes: Add the "influence degree" attribute to the edge "influence of economic activities on ecological environment". This attribute determines the intensity of the impact of economic development on the ecological environment through quantitative analysis or expert evaluation; Graph optimization and verification phase: consistency check, knowledge reasoning and visual verification.

[0033] S4. Construct a sustainable development prediction model based on the long short-term memory network, take the time series data of the previous year among multiple historical years as input, take the sustainable development indicator data and coordination index data of the next year among multiple historical years as label output, and train the sustainable development prediction model; On the basis of the above embodiment, when building the LSTM (Long Short-Term Memory Network) model, it is necessary to select a deep learning framework such as Keras (an advanced 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 the time series data and capture the trend of data changes over time. The fully connected layer generates the final prediction results based on the output results of the LSTM layer. In 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 continuous 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 multivariate coordination index data of the previous year; determine the number of features of the output data, that is, the number of sustainable development indicator data and coordination index data of the next year.

[0034] In order for the model to effectively learn the patterns in the data, it is necessary to select appropriate loss functions and optimizers. Common loss functions include MSE (mean square error) and MAE (mean absolute error), which are used to measure the difference between the model prediction results and the true labels. The optimizer is responsible for adjusting the parameters of the model to minimize the loss function. Common optimizers include Adam (adaptive moment estimation), SGD (stochastic gradient descent), etc.

[0035] Use the training set to train the built model, input the prepared input data and label data into the built 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 differences between the input data and the label data to minimize the error between the predicted results and the actual labels. Through multiple iterative training, the model gradually learns the inherent laws of changes in sustainable development indicators and improves the accuracy of predictions.

[0036] 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 multivariate coordination index data of the region for the next year; S6. Based on the predicted values ​​of the sustainable development indicator data and multivariate coordination index data of the region for the next year, a knowledge graph of sustainable development indicators for the next year is constructed.

[0037] On the basis of the above embodiment, referring to the previous method of constructing the knowledge graph of historical years, the 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 (such as economic, environmental, social indicator nodes and multivariate coordination index nodes) are added, and corresponding edges are added according to the logical relationship and influence mechanism between the indicators, thereby forming a knowledge graph that can reflect the sustainable development situation of the next year.

[0038] See also Figure 2 , the present invention also provides a technical solution: A data processing device for a regional sustainable development indicator knowledge graph, the device being used to execute any of the above-mentioned data processing methods for a regional sustainable development indicator knowledge graph, comprising: The data collection module is used to continuously collect regional sustainable development indicator data for the same region in multiple historical years, including economic statistics data, environmental monitoring data and social development indicator data, and to standardize the economic statistics data, environmental monitoring data and social development indicator data; The data calculation module 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 degree of coordinated development of the economy, environment and society; A graph construction module 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 regional sustainable development indicator knowledge graph, where the time series data includes the sustainable development indicator data and multivariate coordination index data for each year in the same region; A prediction model building module is used to build a sustainable development prediction model based on a long short-term memory network, using the time series data of the previous year among multiple historical years as input and the regional sustainable development indicator data and coordination index data of the next year among multiple historical years as label output to train the regional sustainable development prediction model; The simulation module is used to extract the time series data of the current year from the current knowledge graph, input the trained sustainable development prediction model, and obtain the predicted values ​​of the sustainable development indicator data and multivariate coordination index data of the region in the next year; The graph prediction module is used to construct a 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 region for the next year.

[0039] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0040] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0041] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0042] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A data processing method for a regional sustainable development indicator knowledge graph, characterized in that: The specific steps include: S1. Continuously collect sustainable development indicator data for the same region in multiple historical years. Sustainable development indicator data include economic statistics, environmental monitoring data and social development indicator data, and standardize economic statistics, environmental monitoring data and social development indicator data; S2. Calculate the standardized economic statistics, environmental monitoring data and social development indicator data to generate a multivariate coordination index for evaluating the degree of coordinated development of the economy, environment and society; S3. Based on the sustainable development indicator data and multivariate coordination index data of multiple historical years in the same region, a knowledge graph of sustainable development indicators in each historical year of the same region is constructed, and time series data is extracted from the constructed knowledge graph of sustainable development indicators. The time series data includes the sustainable development indicator data and 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, take the time series data of the previous year among multiple historical years as input, take the sustainable development indicator data and coordination index data of the next year among multiple historical years as label output, and 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 multivariate coordination index data of the region for the next year; S6. Based on the predicted values ​​of the sustainable development indicator data and multivariate coordination index data of the region for the next year, a knowledge graph of sustainable development indicators for the next year is constructed.

2. The data processing method of the regional sustainable development indicator knowledge graph according to claim 1 is characterized by: Economic statistics include per capita GDP and employment growth rate, environmental monitoring data include air quality index and forest coverage rate, and social development indicator data include per capita years of education and energy consumption per unit of GDP.

3. The data processing method of the regional sustainable development indicator knowledge graph according to claim 2 is characterized by: The standardized economic statistics, environmental monitoring data and social development indicator data are calculated to generate the multivariate coordination index based on the following formula: ； in, For the same area The multivariate coordination index for each historical year, For the same area GDP per capita for each historical year, For the same area Energy consumption per unit of GDP in each historical year, For the same area The average number of years of education per capita in each historical year, For the same area Air quality index for historical years, For the same area The forest coverage rate in each historical year, For the same area employment growth rate in each historical year; In the formula, is the weight coefficient of the ratio of per capita GDP to energy consumption per unit GDP, is the weight coefficient of the three indicators of per capita GDP, energy consumption per unit GDP and average years of education in the comprehensive assessment of the coordinated development of economy, environment and society. is the weight coefficient of the two indicators of per capita GDP and air quality index in the comprehensive assessment of the coordinated development of economy, environment and society. is the weight coefficient of the ratio of forest coverage rate to energy consumption per unit GDP, is the weight coefficient of the employment growth rate and air quality index in the comprehensive evaluation of the coordinated development of economy, environment and society. On the basis of .

4. The data processing method of the regional sustainable development indicator knowledge graph according to claim 3 is characterized by: 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: Data association: Using region and time as indexes, integrate economic statistics, environmental monitoring data, and social development indicator data, and associate the per capita GDP, air quality index, and per capita years of education data for the same region in the same year; Knowledge extraction: extracting entities, entity relationships, entity attributes, and relationship attributes from raw data; Graph construction: select a storage solution based on the data scale. Use Neo4j database for small data volumes and a distributed database for large data volumes. Set the extracted entities as nodes, entity relationships as edges, and add attributes to nodes and edges. Set nodes: Set "economic development representation body" and "ecological environment quality body" as nodes. The former includes per capita GDP data, and the latter includes air quality index; Define edges and relationships: The two establish directed edges based on "the impact of economic activities on the ecological environment", with the direction from the former to the latter; Add node attributes: Add per capita GDP attribute to "economic development representation"; Add edge attributes: Add the "influence degree" attribute to the edge and determine the influence intensity through expert evaluation; Graph optimization and verification: perform consistency checking, knowledge reasoning, and visual verification.

5. The data processing method of the regional sustainable development indicator knowledge graph according to claim 4 is characterized by: Construct the knowledge graph of regional sustainable development indicators for the next year. The specific process is as follows: Referring to the previous method of constructing the knowledge graph of historical years in the same region, the knowledge graph of regional sustainable development indicators for the next year is constructed based on the predicted values. In the new knowledge graph, the node of the next year is added, and the corresponding edges are added according to the logical relationship and influence mechanism between the indicators, thereby forming a knowledge graph that can reflect the regional sustainable development situation in the next year.

6. A data processing device for a regional sustainable development indicator knowledge graph, the device being used to execute a data processing method for a regional sustainable development indicator knowledge graph according to any one of claims 1 to 5, characterized in that: include: The data collection module is used to continuously collect regional sustainable development indicator data for the same region in multiple historical years, including economic statistics data, environmental monitoring data and social development indicator data, and to standardize the economic statistics data, environmental monitoring data and social development indicator data; The data calculation module 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 degree of coordinated development of the economy, environment and society; A graph construction module 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 regional sustainable development indicator knowledge graph, where the time series data includes the sustainable development indicator data and multivariate coordination index data for each year in the same region; A prediction model building module is used to build a sustainable development prediction model based on a long short-term memory network, using the time series data of the previous year among multiple historical years as input and the regional sustainable development indicator data and coordination index data of the next year among multiple historical years as label output to train the regional sustainable development prediction model; The simulation module is used to extract the time series data of the current year from the current knowledge graph, input the trained sustainable development prediction model, and obtain the predicted values ​​of the sustainable development indicator data and multivariate coordination index data of the region in the next year; The graph prediction module is used to construct a 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 region for the next year.

Images