Land space planning data acquisition and analysis system

Abstract

The invention relates to the technical field of territorial space planning, in particular to a territorial space planning data acquisition and analysis system. Comprising a data acquisition module, a data preprocessing module, a data analysis module, a data storage module and a result display module. Various data sources are integrated, data timeliness is improved by combining various data acquisition modes, territorial space planning is ensured to be performed based on newest information, and planning errors are avoided; a plurality of analysis methods are introduced, including spatial overlay analysis, buffer analysis, statistical analysis and model prediction analysis based on machine learning and deep learning, so that the prediction accuracy is improved, and the planning has perspectiveness and adaptability; the mode of combining the relational database and the non-relational database is adopted, the respective advantages are exerted, the non-relational database adopts a distributed storage architecture, the data storage reliability and expansibility are improved, the system stability is ensured, and the increased data storage requirement is met.

Description

Technical Field

[0001] This invention relates to the field of land and space planning technology, and in particular to a land and space planning data acquisition and analysis system. Background Technology

[0002] With the acceleration of urbanization and the increasing demands for the rational use of land resources, land spatial planning has become crucial. Traditional data collection methods are often inefficient, lack accuracy, and employ limited analytical approaches, failing to meet the complex needs of land spatial planning. Existing systems are inadequate in data integration, analytical depth, and decision support, making it difficult to handle the fusion of multi-source data and the analysis of complex spatial relationships. Therefore, we propose a land spatial planning data collection and analysis system. Summary of the Invention

[0003] The purpose of this invention is to address the shortcomings of some existing systems in the background art in terms of data integration, analysis depth and decision support, and their inability to cope with the problems of multi-source data fusion and complex spatial relationship analysis, and to propose a land spatial planning data acquisition and analysis system.

[0004] The technical solution of this invention: A land spatial planning data acquisition and analysis system, comprising:

[0005] The system includes a data acquisition module, a data preprocessing module, a data analysis module, a data storage module, and a results display module.

[0006] The data acquisition module is used to obtain land and space planning related data from multiple data sources, including geographic information system (GIS) data, remote sensing image data, statistical yearbook data, departmental business data, real-time sensor data, and Internet web page crawling data.

[0007] The data preprocessing module cleans, integrates, transforms, and coordinates the collected data.

[0008] The data analysis module uses spatial analysis, statistical analysis, and model prediction analysis methods to conduct in-depth analysis of the preprocessed data;

[0009] The data storage module uses a combination of relational and non-relational databases to store various types of data;

[0010] The results display module presents the analysis results in a visual manner, including map display, chart display, and report generation.

[0011] Optionally, the data acquisition module includes a sensor data acquisition submodule, a web crawler submodule, and a data interface submodule;

[0012] The sensor data acquisition submodule collects environmental data in real time through various sensors deployed in the monitoring area and sends the data to the system via wireless transmission technology;

[0013] The web crawler submodule crawls web page data related to land and space planning from the Internet, and parses and extracts useful data;

[0014] The data interface submodule interfaces with the information systems of other relevant departments to obtain their business data and achieve automatic data synchronization and updates.

[0015] Optionally, the environmental data collected by the sensor data acquisition submodule includes air quality, water quality, and soil moisture. The air quality data is collected using the following formula to calculate the Air Quality Index (AQI):

[0016]

[0017] Among them, C i I represents the concentration value of the pollutant. Hi This is the upper limit of the pollutant concentration limit, I Li This represents the lower end of the pollutant concentration limit.

[0018] Optionally, the data crawled by the web crawler submodule includes policies and regulations, planning cases, and socio-economic dynamics. During the data parsing process, a regular expression matching algorithm is used to extract key information from the webpage, and its formula is expressed as:

[0019] match=re.findall(pattern, text);

[0020] Here, pattern is the regular expression pattern, text is the text content of the webpage, and match is the list of matched results.

[0021] Optionally, the departmental business data interfaced by the data interface submodule includes land use approval data and construction project planning data. During data synchronization, a timestamp comparison algorithm is used to ensure data consistency. The specific formula is as follows:

[0022] ΔT=T new -T old ;

[0023] Where ΔT is the time difference, T new T represents the latest timestamp of the data in the data source. old This is the timestamp of the corresponding data in the local database. When ΔT > 0, data synchronization and updates are performed.

[0024] Optionally, the spatial analysis function of the data analysis module includes spatial overlay analysis and buffer analysis;

[0025] The spatial overlay analysis is used to overlay spatial data from different layers to analyze their spatial relationships and attribute changes;

[0026] The buffer analysis generates a buffer based on specified elements and buffer distances, and analyzes relevant data within the buffer range.

[0027] Optionally, the statistical analysis functions of the data analysis module include descriptive statistical analysis, correlation analysis, and cluster analysis.

[0028] Optionally, the model prediction analysis function of the data analysis module uses a machine learning and deep learning-based model to predict indicators related to land spatial planning. The input layer receives data from multiple relevant factors, which are processed by the hidden layer, and the prediction result is obtained at the output layer. The training of the neural network model uses the backpropagation algorithm, and its error calculation formula is as follows:

[0029]

[0030] Where E is the error, n is the sample size, and y k This is the actual value. These are predicted values.

[0031] Optionally, the machine learning and deep learning models are neural network models. The input layer receives relevant factor data including historical land use data, population migration data, and economic development data. In model prediction, a linear weighted fusion algorithm is used to fuse the prediction results of multiple models. The formula is as follows:

[0032]

[0033] in, The final fused prediction result, where m is the number of models and w i For the model weights, The prediction result of model i, with weights ω i satisfy

[0034] Optionally, structured data is stored in a relational database, and unstructured data is stored in a non-relational database. The non-relational database uses a distributed storage architecture. In distributed data storage, a consistent hashing algorithm is used to distribute data across different storage nodes. The calculation formula is as follows:

[0035] hash(key)=(h(key)+offset)mod n

[0036] Where hash(key) is the node location where the data is stored, h(key) is the hash value of the data key, offset is the node offset, and n is the total number of nodes.

[0037] In summary, this application includes at least one of the following beneficial technical effects:

[0038] This invention integrates multiple data sources, including real-time sensor data, data obtained from web crawlers, and business data from data interface interfaces. The system can acquire comprehensive and rich information related to land and space planning. The combination of multiple data acquisition methods greatly improves the timeliness of the data. Compared with traditional data sources that rely on periodic updates, this system can acquire data in real time or near real time, ensuring that land and space planning is based on the latest information and avoiding planning errors caused by data lag.

[0039] This invention introduces a variety of analytical methods, including spatial overlay analysis and buffer analysis, which can deeply reveal the complex relationships between spatial data. It also includes descriptive statistics, correlation analysis and cluster analysis in statistical analysis functions, which can uncover the inherent laws and characteristics of data. In addition, model predictive analysis based on machine learning and deep learning, especially the application of neural network models, significantly improves the accuracy of predictions, can provide planners with reliable predictions of future development trends, make planning forward-looking and adaptable, and avoid resource waste and unreasonable planning.

[0040] This invention combines relational and non-relational databases, fully leveraging the advantages of both. Relational databases are suitable for storing structured business data, ensuring data consistency and integrity, and facilitating complex queries and transaction processing. Non-relational databases, on the other hand, are better suited to handle the storage and rapid read / write needs of large-scale data such as unstructured remote sensing image data. Furthermore, the non-relational database employs a distributed storage architecture, further improving the reliability and scalability of data storage. Even if some nodes fail, data can still be accessed through other nodes, ensuring system stability. Simultaneously, as the data volume increases, storage nodes can be easily expanded to meet the ever-growing data storage demands.

[0041] This invention integrates multiple data sources and combines various data collection methods to improve data timeliness, ensuring that land spatial planning is based on the latest information and avoiding planning errors. It also introduces various analysis methods, including spatial overlay analysis, buffer analysis, statistical analysis, and model predictive analysis based on machine learning and deep learning, to improve prediction accuracy and make planning forward-looking and adaptable. This invention adopts a combination of relational and non-relational databases to leverage their respective advantages. The non-relational database uses a distributed storage architecture to improve data storage reliability and scalability, ensuring system stability and meeting growing data storage needs. Detailed Implementation

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Example

[0044] The present invention proposes a land spatial planning data acquisition and analysis system, which includes a data acquisition module, a data preprocessing module, a data analysis module, a data storage module, and a result display module;

[0045] The data acquisition module is used to obtain land and space planning related data from various data sources, including geographic information system (GIS) data, remote sensing image data, statistical yearbook data, departmental business data, real-time sensor data, and Internet web crawling data. The data acquisition module includes a sensor data acquisition submodule, a web crawler submodule, and a data interface submodule.

[0046] During the sensor data acquisition process, air quality sensors, water quality monitoring sensors, and soil moisture sensors are deployed in different areas of the city. In particular, multiple air quality sensors are set up in the industrial park to monitor the concentration of pollutants such as sulfur dioxide, nitrogen oxides, and particulate matter in real time. The sensors collect data every 15 minutes and send the data to the system's data acquisition module via wireless transmission technology (4G network).

[0047] After the system receives the sensor data, it calculates the Air Quality Index (AQI) using the formula...

[0048]

[0049] The monitored sulfur dioxide concentration C1 was 0.05 mg / m³. 3 The high value of its concentration limit I H1 =0.15mg / m 3Low-order value I L1 =0.02mg / m 3 Nitrogen oxide concentration C2 = 0.08 mg / m³ 3 The high value of its concentration limit I H2 =0.12mg / m 3 Low-order value I L2 =0.04mg / m 3 The AQI sub-index of each pollutant is calculated separately, and then the overall air quality index of the region is obtained, providing data support for subsequent environmental assessment and planning.

[0050] Data collection is performed using a web crawler module, targeting relevant websites, including government websites, professional planning websites, and news media websites. When retrieving the latest land planning policies and regulations for a specific region, the crawler module first accesses the target website page, obtains the HTML code of the webpage, and then uses a regular expression matching algorithm. The regular expression pattern is set to `pattern="Land Planning Policies and Regulations: (.*?)\n"` to match and extract the text content of the webpage. If the webpage text contains "Land Planning Policies and Regulations: 'Notice on Strengthening the Management of Urban Land Use Planning'", the system will successfully extract "Notice on Strengthening the Management of Urban Land Use Planning" and subsequent details through regular expression matching, organizing and storing it in the system database for planners to review and analyze.

[0051] In the data acquisition process, the system's data interface sub-module connects with the business system of the urban planning department to obtain land use approval data and construction project planning data, and runs the data synchronization program on a daily schedule.

[0052] During the synchronization process, the latest timestamp T of the data in the data source is first obtained. new The timestamp T of the corresponding data in the local database old If the latest timestamp of a land use approval record in the data source is "2024-10-30 12:00:00", and the timestamp of the same record in the local database is "2024-10-29 18:00:00", then the time difference ΔT = T is calculated. new -T old =18h (time unit is hours). Since ΔT>0, the system will initiate data synchronization and update, synchronizing this and other timestamp-updated data from the data source to the local database to ensure data consistency and timeliness.

[0053] After data acquisition is completed, the data preprocessing module cleans, integrates, transforms, and performs coordinate system unification preprocessing on the acquired data.

[0054] The data analysis module employs spatial analysis, statistical analysis, and model predictive analysis methods to conduct in-depth analysis of the preprocessed data;

[0055] The spatial analysis function of the data analysis module includes spatial overlay analysis and buffer analysis, and the statistical analysis function includes descriptive statistical analysis, correlation analysis and cluster analysis. The model prediction analysis function of the data analysis module uses machine learning and deep learning-based models to predict relevant indicators of land spatial planning.

[0056] Spatial overlay analysis: Taking urban land use planning as an example, the system already has two layers of data: a current land use map and an urban master plan map. The current land use map includes different land use types, such as residential land, commercial land, and industrial land, and each plot has corresponding attribute information. The urban master plan map plans the layout of different functional areas in the future.

[0057] By using the spatial overlay analysis function, two layers are overlaid. During the overlay process, the system matches the plots based on their spatial location. For overlapping plots, it analyzes the differences between their current land use type and the planned land use type, providing planners with specific areas and information for land use adjustments. This allows for further evaluation and decision-making on whether and how to make adjustments, ensuring the rationality and feasibility of the plan.

[0058] Buffer analysis: Taking the planning of a new urban expressway as an example, the impact on the surrounding environment is analyzed. The system uses the buffer analysis function to generate a buffer zone based on the center line of the expressway and a certain buffer distance (such as 500 meters).

[0059] Analysis of relevant data within the buffer zone, including land use type (whether there are residential areas, schools, or other sensitive areas) and population distribution, revealed that the buffer zone contains a primary school and multiple residential areas. This suggests that planners need to consider noise reduction and isolation measures during road design and construction to minimize the impact on surrounding residents and schools, and achieve coordinated development of transportation construction, environmental protection, and residents' lives.

[0060] Model Predictive Analysis: Taking population growth prediction as an example, the input layer of the system's neural network model receives historical land use data (including urban construction land area and agricultural land area in different years), population migration data (including the number of immigrants, the number of immigrants, the origin and destination of migration), economic development data (including regional GDP, industrial structure ratio, etc.) and other relevant factor data (including policy factors and natural environmental factors).

[0061] After data preprocessing and model training, the model's hidden layer contains multiple neurons. These neurons perform complex processing and feature extraction on the input data. When predicting the population growth of a region over the next 5 years, the model obtains the prediction results in the output layer. The predicted population will increase year by year, with growth rates of x1%, x2%, x3%, x4%, and x5%, respectively. Based on the prediction results, planners can plan infrastructure construction and public service facilities in advance to meet the needs of future population growth and avoid urban development pressure and resource shortages caused by population growth.

[0062] After analyzing the data, a data storage module is used to store the data. The data storage module uses a combination of relational databases and non-relational databases to store various types of data.

[0063] Structured data storage: Land use approval form data includes fields such as approval number, project name, land area, land use, approval time, and approval result. This data has a clear structure and relationships, making it suitable for storage in a relational database.

[0064] The system uses a relational database (MySQL) to create the corresponding table structure. A table named "land_use_approval" is created, defining the aforementioned fields and their data types. During data storage, data consistency and integrity are ensured. A primary key (approval number) ensures the uniqueness of each record, and foreign keys are used to link related tables (linked to the land use classification table to ensure the standardization of the land use field). When querying the approval status of a specific project, an efficient SQL query is performed: "SELECT * FROM land_use_approval WHERE project_name = 'Project Name'", quickly retrieving the required data and providing accurate data support for planning decisions and management.

[0065] Unstructured data storage: Remote sensing image data is large in volume and irregular in structure, making it suitable for storage in a non-relational database. The system uses a distributed non-relational database (MongoDB) for storage, employing a distributed storage architecture to distribute the data across multiple nodes.

[0066] For a high-resolution remote sensing image covering a certain urban area, the system first divides it into several blocks. Then, according to the consistent hashing algorithm hash(key) = (h(key) + offset) mod n, where key is the identifier or related attribute of the image block, h(key) is its hash value, offset is the node offset, and n is the total number of nodes, different image blocks are stored on different storage nodes. When the remote sensing image needs to be called for analysis, the system quickly reads the data from the corresponding node, performs stitching and processing, improves the data read and write performance and storage capacity, and meets the storage and application needs of large-scale remote sensing image data in land spatial planning.

[0067] After data storage, the analysis results are presented in a visual manner through the results display module, which includes map display, chart display and report generation. The map display includes two-dimensional map display and three-dimensional scene display.

[0068] Two-dimensional map display: In the system's results display interface, users can select the two-dimensional map display function. The system loads map layers containing various land and space planning data. Users can use the layer control buttons to show or hide specific layers, and can also perform map zooming and panning operations. When planners are concerned about the land use of a specific area, they can zoom the map to view the distribution and attribute information of the land parcels in detail, and pan the map to browse the situation of different areas. At the same time, the system also supports operations such as marking and measuring on the map, which facilitates spatial analysis and recording by planners.

[0069] 3D Scene Display: The system utilizes 3D modeling technology and geographic information data to construct a 3D scene of the city. In the 3D scene, the terrain is simulated using real elevation data, and buildings are presented in the form of 3D models, including their appearance and height. Infrastructure, including roads and bridges, is also 3D modeled. When displaying the planning effect of a new urban area, users can intuitively see the layout of planned buildings, the distribution of parks and green spaces, and the direction of traffic routes in the 3D scene. Users can observe the planning effect from different angles by rotating, zooming, and panning the view. The 3D scene display method can help planners more intuitively evaluate the rationality and aesthetics of the planning scheme, discover potential problems, and thus optimize and adjust them.

[0070] Chart Display: The system generates various charts based on the statistical analysis results. To show the population density distribution in different areas of the city, the system generates a bar chart with the horizontal axis representing the different area names and the vertical axis representing the population density value. The chart shows the differences in population density in different areas, which planners can use to analyze the characteristics and trends of population distribution and provide a basis for the layout and planning of public service facilities.

[0071] Report Generation: The system automatically generates reports based on user needs. The land use status summary report includes the total land area, the area and percentage of each land use type, and the land use situation in different areas. The report supports exporting to PDF and Excel formats for easy processing and sharing. Planning departments can submit the land use status summary report to superiors or relevant departments as a basis for decision-making and work reporting. It can also be distributed to relevant staff to help them understand the land use situation and carry out subsequent planning and management work. In addition, users can customize the content and format of the report according to their actual needs to meet personalized data analysis and display requirements.

[0072] This invention integrates multiple data sources and combines various data collection methods to improve data timeliness, ensuring that land spatial planning is based on the latest information and avoiding planning errors. It also introduces various analysis methods, including spatial overlay analysis, buffer analysis, statistical analysis, and model predictive analysis based on machine learning and deep learning, to improve prediction accuracy and make planning forward-looking and adaptable. This invention adopts a combination of relational and non-relational databases to leverage their respective advantages. The non-relational database uses a distributed storage architecture to improve data storage reliability and scalability, ensuring system stability and meeting growing data storage needs.

[0073] The above specific embodiments are merely several optional embodiments of the present invention. Based on the technical solutions of the present invention and the relevant teachings of the above embodiments, those skilled in the art can make various alternative improvements and combinations to the above specific embodiments.

Claims

1. A land spatial planning data acquisition and analysis system, characterized in that, It includes a data acquisition module, a data preprocessing module, a data analysis module, a data storage module, and a results display module; The data acquisition module is used to obtain land and space planning related data from multiple data sources, including geographic information system data, remote sensing image data, statistical yearbook data, departmental business data, real-time sensor data, and Internet web page crawling data. The data preprocessing module cleans, integrates, transforms, and coordinates the collected data. The data analysis module uses spatial analysis, statistical analysis, and model prediction analysis methods to conduct in-depth analysis of the preprocessed data; The data storage module uses a combination of relational and non-relational databases to store various types of data; The results display module visualizes the analysis results, including map display, chart display, and report generation.

2. The land spatial planning data acquisition and analysis system according to claim 1, characterized in that, The data acquisition module includes a sensor data acquisition submodule, a web crawler submodule, and a data interface submodule; The sensor data acquisition submodule collects environmental data in real time through various sensors deployed in the monitoring area and sends the data to the system via wireless transmission technology; The web crawler submodule crawls web page data related to land and space planning from the Internet, and parses and extracts useful data; The data interface submodule interfaces with the information systems of other relevant departments to obtain their business data and achieve automatic data synchronization and updates.

3. The land spatial planning data acquisition and analysis system according to claim 2, characterized in that, The environmental data collected by the sensor data acquisition submodule includes air quality, water quality, and soil moisture. The air quality data is collected using the following formula to calculate the air quality index: Among them, C i I represents the concentration value of the pollutant. Hi This is the upper limit of the pollutant concentration limit, I Li This represents the lower end of the pollutant concentration limit.

4. The land spatial planning data acquisition and analysis system according to claim 2, characterized in that, The web crawler submodule captures data including policies and regulations, planning cases, and socio-economic dynamics. During data parsing, a regular expression matching algorithm is used to extract key information from the webpages. The formula is as follows: match=re.findall(pattern, text); Here, pattern is the regular expression pattern, text is the text content of the webpage, and match is the list of matched results.

5. A land spatial planning data acquisition and analysis system according to claim 2, characterized in that, The data interface submodule interfaces with departmental business data including land use approval data and construction project planning data. During data synchronization, a timestamp comparison algorithm is used to ensure data consistency. The specific formula is as follows: ΔT=L new -T old ; Where ΔT is the time difference, T new T represents the latest timestamp of the data in the data source. old This is the timestamp of the corresponding data in the local database. When ΔT > 0, the data is synchronized and updated.

6. The land spatial planning data acquisition and analysis system according to claim 1, characterized in that, The spatial analysis function of the data analysis module includes spatial overlay analysis and buffer analysis; The spatial overlay analysis is used to overlay spatial data from different layers to analyze their spatial relationships and attribute changes; The buffer analysis generates a buffer based on specified elements and buffer distances, and analyzes relevant data within the buffer range.

7. The land spatial planning data acquisition and analysis system according to claim 1, characterized in that, The statistical analysis functions of the data analysis module include descriptive statistical analysis, correlation analysis, and cluster analysis.

8. The land spatial planning data acquisition and analysis system according to claim 1, characterized in that, The data analysis module's model prediction and analysis function uses machine learning and deep learning-based models to predict indicators related to land spatial planning. The input layer receives data from multiple relevant factors, which are then processed by the hidden layer, and the prediction results are obtained at the output layer. The neural network model is trained using the backpropagation algorithm, and its error calculation formula is as follows: Where E is the error, n is the sample size, and y k This is the actual value. These are predicted values.

9. A land spatial planning data acquisition and analysis system according to claim 8, characterized in that, The machine learning and deep learning models are neural network models. Their input layer receives relevant factor data including historical land use data, population migration data, and economic development data. In model prediction, a linear weighted fusion algorithm is used to fuse the prediction results from multiple models. The formula is as follows: in, The final fused prediction result, where m is the number of models and w i For the model weights, The prediction result of model i, with weights ω i satisfy 10. A land spatial planning data acquisition and analysis system according to claim 1, characterized in that, Structured data is stored in relational databases, while unstructured data is stored in non-relational databases. Non-relational databases employ a distributed storage architecture, using a consistent hashing algorithm to distribute data across different storage nodes. The calculation formula is as follows: hash(key)=(h(key)+offset)mod n; Where hash(key) is the node location where the data is stored, h(key) is the hash value of the data key, offset is the node offset, and n is the total number of nodes.

Images