Land use planning method and system based on big data analysis

Abstract

The present invention discloses a land use planning method and system based on big data analysis, which relates to the technical field of land use planning. The area to be planned is divided into several sub-areas, and the sub-areas are divided into undeveloped areas and developed areas according to thermal values, and the corresponding land use status data are predicted and obtained respectively. The protection coefficient is constructed from the land use prediction data in the undeveloped area, and the target area is screened out in several undeveloped areas according to the protection coefficient. After the area to be transferred is screened out in the developed area according to the load coefficient, a transfer plan is formulated to transfer the target facilities from the area to be transferred to the target area; the improvement coefficient is constructed from the plan test data, and the transfer plan is selected as the target plan. According to the target plan, the facilities in the area to be transferred are transferred to the target area in sequence. When carrying out land planning, the load of some areas is reduced, so that the development in each sub-area is more balanced.

Description

Technical Field

[0001] The present invention relates to the technical field of land use planning, and in particular to a land use planning method and system based on big data analysis. Background Art

[0002] Land use planning, also known as land planning, is the overall strategic layout and overall arrangement of land development, utilization, governance and protection in space and time within a certain area according to the requirements of national social and economic sustainable development and local natural, economic and social conditions. Land use planning is to reasonably adjust the land use structure and layout based on the overall and long-term interests, taking all the land in the region as the object; taking utilization as the center, making overall arrangements and long-term planning for land development, utilization, governance and protection.

[0003] The purpose is to strengthen the macro-control and planning management of land use, make rational use of land resources, and promote the coordinated development of the national economy. At the same time, it is also the basis for implementing land use control. In summary, land use planning is a comprehensive strategic deployment and overall arrangement work, which aims to promote the sustainable development of the economy and society through rational land use.

[0004] In the Chinese invention patent with application publication number CN118094196A, a land use planning method and planning system based on data analysis are disclosed, which include the following steps: obtaining land resource field survey data; preprocessing the land resource field survey data to generate standard land resource field survey data; obtaining multi-source geographic information data; extracting terrain data from the multi-source geographic information data to generate a multi-source geographic terrain feature data set; performing elevation conversion on the multi-source geographic terrain feature data set to generate multi-source geographic elevation data; performing terrain feature analysis on the multi-source geographic elevation data to generate terrain feature analysis data; performing land cover classification on the standard land resource field survey data to generate land cover classification areas. The present invention improves the accuracy and operability of planning results by analyzing terrain features and land cover classification, and predicting the overlap marks of plots and the potential for plot utilization.

[0005] Combining the above applications and the prior art:

[0006] When development is uneven among various areas of a city, the city should be replanned, and various resources that are conducive to the development of the city's economy should be dispatched and allocated, including water resources, energy and land resources. For example, office areas in high-density population areas can be transferred to low-density areas, and new roads can be planned in high-density population areas to reduce traffic pressure.

[0007] In order to ensure the planning of land use, big data technology is usually introduced in land use planning. Through a large amount of data analysis, reference opinions are provided for land use planning to ensure the effectiveness of land planning and utilization. In the existing land planning and utilization methods, it is usually based on the overall perspective to provide an overall planning scheme for the area that needs to be planned. This planning method has high integrity and its effectiveness is easy to verify. However, in different regions, the proportion of farmland occupied and the amount of water resources consumed vary greatly. When the environment in different regions varies greatly, when the land is planned according to the existing planning method, the land use planning for each region is less targeted and it is difficult to achieve reasonable use of land in each region.

[0008] To this end, the present invention provides a land use planning method and system based on big data analysis. Summary of the invention

[0009] 1. Technical issues to be solved

[0010] In view of the deficiencies of the prior art, the present invention provides a land use planning method and system based on big data analysis, which divides the sub-areas into undeveloped areas and developed areas according to thermal values, and predicts and obtains the corresponding land use status data respectively, constructs a protection coefficient from the land use prediction data in the undeveloped areas, screens out the target areas in several undeveloped areas according to the protection coefficient, and screens out the areas to be transferred in the developed areas according to the load coefficient, and then formulates a transfer plan for transferring the target facilities from the areas to be transferred to the target areas; constructs an improvement coefficient from the plan test data, selects the transfer plan as the target plan, and transfers the facilities in the areas to be transferred to the target areas in turn according to the target plan. In land planning, the load of some areas is reduced, and the development of each sub-area is more balanced, thereby solving the technical problems raised in the background technology.

[0011] (II) Technical solution

[0012] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0013] The land use planning method based on big data analysis includes: collecting data in the area to be planned and generating a regional environmental data set, generating an environmental anomaly Yot from the regional environmental data set, and issuing a data collection instruction to the outside if the obtained environmental anomaly Yot exceeds expectations;

[0014] Preprocess the sample data collected in the planning area, train the neural convolution network with the sample data, and then build a regional planning digital twin model;

[0015] The planned area is divided into several sub-areas, and the thermal value Rtz is calculated based on the development status data in the sub-areas. The sub-areas are divided into undeveloped areas and developed areas based on the thermal value Rtz, and the corresponding land use status data are predicted and obtained respectively to generate a land use prediction data set; after obtaining the centrality Vt of the target area, combined with the thermal value Rtz of the target area, the transfer priority Zyt of land development in each target area is calculated, where:

[0016]

[0017] Among them, 0≤α≤1, 0≤β≤1, C x is the constant correction factor;

[0018] The protection coefficient Bot is constructed from the land use prediction data in the undeveloped area. The target area is screened out from several undeveloped areas based on the protection coefficient Bot. After the area to be transferred is screened out from the developed area based on the load coefficient Fst, a transfer plan is formulated to transfer the target facilities from the area to be transferred to the target area.

[0019] The optimized transfer plan is tested using the land planning digital twin model. The improvement coefficient Pts is constructed based on the acquired plan test data. The transfer plan is selected as the target plan based on the improvement coefficient Pts. The facilities in the area to be transferred are transferred to the target area in sequence according to the target plan and transfer priority.

[0020] Furthermore, several collection points are set in the planned area, data are collected at the collection points, and a regional environmental data set is generated. The environmental anomaly Yot is generated from the regional environmental data set, where the farmland encroachment ratio Qv and water resource consumption Hv are linearly normalized, and the corresponding data values ​​are mapped to the interval [0,1] in the following manner:

[0021]

[0022] Where i = 1, 2, ..., n, n is the number of acquisition points, weight coefficient: 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1, and F1 + F2 = 1; Hv i is the water resource consumption of the ith collection point, Hv a is the mean value of water resource consumption, Hv b is the acceptable value of water consumption; Qv i is the farmland encroachment ratio of the i-th collection point, Qv a is the mean value of farmland encroachment ratio, Qv b is the acceptable value of farmland encroachment ratio.

[0023] Further, after receiving the data collection instruction, data collection is performed in the area to be planned, and the collected data are summarized to generate a regional planning data set; data preprocessing is performed on the data in the regional planning data set, and part of the data in the preprocessed data set is extracted as sample data;

[0024] Taking the preprocessed regional planning data as input, the trained spatial analysis model is used to identify the spatial distribution characteristics of different locations in the area to be planned; based on the acquired spatial distribution characteristics, the trained classification model is used to divide the area to be planned into several sub-areas and mark them on the electronic map.

[0025] Furthermore, after collecting the development status data of each sub-area, the thermal value Ttz is calculated. If the thermal value Ttz is lower than the thermal threshold, it will be regarded as an undeveloped area, and the remaining sub-areas will be regarded as developed areas. The regional planning digital twin model predicts the land use status of the developed area and the undeveloped area respectively, obtains the corresponding prediction data, and after summarizing the obtained prediction data, a land use prediction data set is generated.

[0026] Furthermore, the protection coefficient Bot is constructed from the predicted data. If the protection coefficient Bot exceeds the protection threshold, the corresponding undeveloped area is used as the protection area, and the remaining undeveloped area is used as the target area. The target area is marked on the electronic map, and after obtaining the location information of the target area, the centrality Vt of each target area is calculated as follows:

[0027]

[0028] Weight coefficient, 0≤α≤1, 0≤β≤1; n is the number of target areas, G ij is the distance from the i-th target area to the j-th target area, G a is the average value of the distance.

[0029] Furthermore, the traffic load degree and power load density in the developed area are obtained, and the load factor Fst of the developed area is obtained in association. If the load factor Fst exceeds the preset load threshold, the corresponding developed area will be used as the area to be transferred. After formulating the facility transfer plan, the transfer plan is optimized using a multi-objective optimization algorithm with the optimization goal of reducing the environmental anomaly Yot in the area to be planned, and the optimized transfer plan is obtained.

[0030] Furthermore, the land planning digital twin model tests the optimized transfer scheme and obtains the corresponding test data, and the obtained scheme test data is summarized to generate a scheme test data set; after the environmental anomaly degree Yot on each test node is obtained, several environmental anomaly degrees Yot are arranged along the time axis to construct the improvement coefficient Pst;

[0031] If the improvement coefficient Pts does not exceed expectations, the transfer plan is optimized and the optimized transfer plan is used as the target plan; according to the target plan and the transfer priority, the facilities in the area to be transferred are transferred to the target area in turn.

[0032] Furthermore, after the transfer plan is executed, after collecting various data after land planning within the preset monitoring period, the load factor Fst in each sub-area is generated again. If the load factor Fst still exceeds the corresponding load threshold, an alarm instruction is issued to the outside; the alert degree Mop is generated based on the time node and location data of the received alarm instruction. If the alert degree Mop is higher than the warning threshold, an abnormal reminder instruction is issued to the outside.

[0033] Furthermore, the alertness Mop method is generated from the time node and location data of the alarm instruction as follows:

[0034]

[0035] Weight coefficient: 0≤F1≤1, 0≤F2≤1, and F1+F2=1; n is the number of sub-regions, T ij and U ij are the time interval and distance interval between the ith alarm instruction and the jth alarm instruction, T a is the average value of the time interval, T b is the acceptable value of the time interval; U a is the average value of the distance interval, U b are acceptable values ​​for the distance interval.

[0036] Furthermore, the population density Mp and economic output value Xp are linearly normalized, and the corresponding data values ​​are mapped to the interval [0,1], and the thermal value Rtz is obtained as follows:

[0037]

[0038] Weight coefficient, 0≤α≤1, 0≤β≤1;

[0039] Furthermore, the species richness Fd and biomass Sv are linearly normalized, the corresponding data values ​​are mapped to the interval [0,1], and then the protection coefficient Bot is constructed as follows:

[0040]

[0041] Among them, Fd i Species richness in region i, Fd a is the mean species richness, Sv i Biomass in region i, Sv ais the mean value of biomass, i=1, 2, …, n, n is the number of regions, k2 and k1 are weight coefficients, 0≤k1≤1, 0≤k2≤1, and k1+k2=1;

[0042] Furthermore, the traffic load Cu and power load density Cs are linearly normalized, the corresponding data values ​​are mapped to the interval [0,1], and then the load factor Fst is generated according to the following formula:

[0043]

[0044] Weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1; i=1, 2, …p, where p is the number of developed areas; Cu i is the traffic load of the ith developed area, Cu a is the mean value of traffic load, Cs i is the power load density of the ith developed region, Cs a is the mean value of power load density;

[0045] Furthermore, the improvement coefficient Pts is constructed as follows:

[0046]

[0047] Among them, Yot i is the environmental abnormality degree on the i-th test node, Yot a is the corresponding mean, Yot b is its qualified standard value;

[0048] Ut i is the i-th improved intermediate value, Ut a is its mean, i=1, 2, …, k, k is the number of sub-periods, weight coefficient: 0≤S1≤1, 0≤S2≤1 and S2+S1=1;

[0049] The land use planning system based on big data analysis includes an environmental difference analysis unit, which collects data in the area to be planned and generates a regional environmental data set, generates an environmental anomaly Yot from the regional environmental data set, and issues a data collection instruction to the outside if the obtained environmental anomaly Yot exceeds expectations;

[0050] The model building unit pre-processes the sample data collected in the planning area, trains the neural convolution network with the sample data, and then builds the regional planning digital twin model;

[0051] Regional division unit: the planned area is divided into several sub-areas, and the thermal value Rtz is calculated based on the development status data in the sub-areas. The sub-areas are divided into undeveloped areas and developed areas based on the thermal value Rtz, and the corresponding land use status data are predicted and obtained respectively to generate a land use prediction data set;

[0052] The load analysis unit constructs a protection coefficient Bot from the land use prediction data in the undeveloped area, selects the target area from several undeveloped areas based on the protection coefficient Bot, selects the area to be transferred from the developed area based on the load coefficient Fst, and then formulates a transfer plan to transfer the target facilities from the area to be transferred to the target area;

[0053] The transfer optimization unit uses the land planning digital twin model to test the optimized transfer plan, constructs the improvement coefficient Pts based on the acquired plan test data, selects the transfer plan as the target plan based on the improvement coefficient Pts, and transfers the facilities in the area to be transferred to the target area in sequence according to the target plan and transfer priority.

[0054] (III) Beneficial effects

[0055] The present invention provides a land use planning method and system based on big data analysis, which has the following beneficial effects:

[0056] 1. Make a preliminary assessment of the ecological environment in the region based on the environmental anomaly degree Yot, determine whether the current land use planning status is qualified, and judge whether there is a need for re-planning. When the current land planning is no longer reasonable, it can be adjusted continuously.

[0057] 2. Based on the regional planning digital twin model, the output land planning plan can be tested to verify the effect of land planning and ensure the effect of land planning.

[0058] 3. Use the thermal value Rtz to divide the area into undeveloped areas and developed areas, and set up targeted planning plans to achieve targeted processing and realize the rational use of land in each area.

[0059] 4. Through the constructed protection coefficient Bot, the protection area can be screened out in the undeveloped area, and the external interference in the protection area can be reduced to protect the environment; through the transfer priority Zyt, the target facilities in other areas can be transferred to the target area in turn, so that each target area can be adjusted in an orderly manner.

[0060] 5. Evaluate the land planning status in the corresponding developed area based on the load factor Fst. If the developed area is already in a high-load state, the land planning and development in each area can be more reasonable by transferring the facilities in the high-load area to the low-load area. The transfer efficiency can also be improved by formulating and optimizing the transfer plan.

[0061] 6. Based on the obtained improvement coefficient Pts, the feasibility of the current transfer plan can be judged. By selecting and optimizing the transfer plan, the reliability of the transfer plan can be ensured. During land planning, the load of some areas can be reduced, the development of each sub-area can be more balanced, and the damage to environmental conditions can be reduced.

[0062] 7. Generate the alert level Mop based on the change status of the load data in each sub-area, judge and evaluate the degree of development balance in the region, and evaluate the current land planning effect again. When the land planning effect cannot meet the expectations, timely adjustments are made to ensure the land planning effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a flow chart of a land use planning method based on big data analysis of the present invention;

[0064] Figure 2 This is a schematic diagram of the structure of the land use planning system based on big data analysis in the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] See also Figure 1 The present invention provides a land use planning method based on big data analysis, including:

[0067] Step 1: Collect data in the planned area and generate a regional environmental data set, and generate an environmental anomaly Yot from the regional environmental data set. If the obtained environmental anomaly Yot exceeds expectations, send a data collection instruction to the outside;

[0068] The step 1 includes the following contents:

[0069] Step 101: When land use planning is required, several collection points are set in the planned area, and data is collected at the collection points. For example, the proportion of farmland occupation is obtained by monitoring the changes in agricultural land, and water resource consumption data is collected, etc., to generate a regional environmental data set;

[0070] Step 102: Generate the environmental anomaly Yot from the regional environmental data set, wherein the farmland encroachment ratio Qv and the water resource consumption Hv are linearly normalized, and the corresponding data values ​​are mapped to the interval [0,1] in the following manner:

[0071]

[0072] Where i = 1, 2, ..., n, n is the number of acquisition points, weight coefficient: 0 ≤ F1 ≤ 1, 0 ≤ F2 ≤ 1, and F1 + F2 = 1; weight coefficient is determined by reference to the hierarchical analysis method; Hv i is the water resource consumption of the ith collection point, Hv a is the mean value of water resource consumption, Hv b is the acceptable value of water consumption; Qv i is the farmland encroachment ratio of the i-th collection point, Qv a is the mean value of farmland encroachment ratio, Qv b is the acceptable value of farmland encroachment ratio;

[0073] Based on historical data and the management expectations for the ecological environment, an abnormal threshold is set in advance; if the obtained environmental abnormality Yot exceeds the abnormal threshold, it means that the ecological environment in the planned area is gradually deteriorating, and there are large differences between different areas, which requires timely management. At this time, a data collection instruction is issued to the outside;

[0074] When using, combine the contents in steps 101 and 102:

[0075] When it is necessary to plan land use, the encroachment of farmland and waste of water resources in the planning area are detected, and the environmental anomaly degree Yot is constructed based on this. Based on the environmental anomaly degree Yot, a preliminary evaluation of the ecological environment in the area can be made to determine whether the current land use planning status is qualified and whether there is a need for re-planning. In this way, adjustments can be made when the current land planning is no longer reasonable.

[0076] In order to ensure the planning of land use, big data technology is usually introduced in land use planning. Through a large amount of data analysis, reference opinions are provided for land use planning to ensure the effectiveness of land planning and utilization. In the existing land planning and utilization methods, it is usually based on the overall perspective to provide an overall planning scheme for the area that needs to be planned. This planning method has high integrity and its effectiveness is easy to verify. However, in different regions, the proportion of farmland occupied and the amount of water resources consumed vary greatly. When the environment in different regions varies greatly, when the land is planned according to the existing planning method, the land use planning for each region is less targeted and it is difficult to achieve reasonable use of land in each region.

[0077] Step 2: Preprocess the sample data collected in the planning area, train the neural convolution network with the sample data, and then build a regional planning digital twin model;

[0078] The step 2 includes the following contents:

[0079] Step 201: after receiving the data collection instruction, data collection is performed in the area to be planned, including remote sensing data, topography, landform, soil type and climate information, etc.; policy and regulatory data; demographic data, such as population density and age structure, etc., economic activity data, such as industrial, commercial and service distribution data, etc.; the collected data are aggregated to generate a regional planning data set;

[0080] Step 202: preprocess the data in the regional planning data set, including data cleaning, data conversion, and data integration. Extract some data from the preprocessed data set as sample data, train a neural convolutional network with the sample data, and then build a regional planning digital twin model.

[0081] When using, combine the contents in steps 201 and 202:

[0082] By collecting various data within the planning area and training the regional planning digital twin model with the collected data, the output land planning plan can be tested based on the regional planning digital twin model to verify the effect of land planning and ensure the effect of land planning.

[0083] Step 3: The planned area is divided into several sub-areas, and the thermal value Rtz is calculated based on the development status data in the sub-areas. The sub-areas are divided into undeveloped areas and developed areas based on the thermal value Rtz, and the corresponding land use status data are predicted and obtained respectively to generate a land use prediction data set;

[0084] The step three includes the following contents:

[0085] Step 301: train a recurrent neural network with sample data to obtain a trained spatial analysis model, use the preprocessed regional planning data as input, and use the trained spatial analysis model to identify spatial distribution features at different locations in the area to be planned; based on the obtained spatial distribution features, use the trained classification model to divide the area to be planned into several sub-areas, and mark them on the electronic map;

[0086] When in use, the area to be planned is divided into several sub-areas by identifying and classifying the spatial distribution characteristics. By adjusting the several sub-areas, the planning and adjustment of the current area to be planned can be completed;

[0087] Step 302: After collecting the development status data such as population density and economic output value in each sub-region, the thermal value Rtz is calculated in the following manner, wherein the population density Mp and the economic output value Xp are linearly normalized and the corresponding data values ​​are mapped to the interval [0,1] in the following manner:

[0088]

[0089] Weight coefficient, 0≤α≤1, 0≤β≤1; the weight coefficient can be obtained by referring to the hierarchical analysis method;

[0090] Based on historical data and expectations for regional development, a thermal threshold is pre-set; if the thermal value Rtz is lower than the thermal threshold, it means that the population density and economic development in the current sub-region are poor, so it can be regarded as an undeveloped area, and the remaining sub-regions as developed areas;

[0091] When in use, the thermal value Rtz is used to divide the area into undeveloped areas and developed areas, which can be targeted in further regional planning. By setting up targeted planning plans, the rational use of land in each area can be achieved.

[0092] Step 303: In the scenario where the current population growth rate is maintained in the area to be planned, the regional planning digital twin model predicts the land use status in the developed area and the undeveloped area respectively, and obtains corresponding prediction data, such as land utilization rate, population density and economic output value, and also includes biodiversity index: such as species richness, biomass, uniformity index, etc. After summarizing the obtained prediction data, a land use prediction data set is generated;

[0093] When using, combine the contents in steps 301 to 303:

[0094] After determining the current economic development scenario, the current land use status is predicted. When the land needs to be re-planned, this can be used as a reference, allowing for better foresight when planning.

[0095] Step 4: Construct a protection coefficient Bot from the land use prediction data in the undeveloped area, select the target area from several undeveloped areas based on the protection coefficient Bot, select the area to be transferred from the developed area based on the load factor Fst, and then formulate a transfer plan to transfer the target facilities from the area to be transferred to the target area;

[0096] The step 4 includes the following contents:

[0097] Step 401: After obtaining the prediction data in the undeveloped area, the protection coefficient Bot is constructed based on the prediction data, where:

[0098] Linear normalization was performed on species richness Fd and biomass Sv, and the corresponding data values ​​were mapped to the interval [0,1], and then the following method was used:

[0099]

[0100] Among them, Fd i Species richness in region i, Fd a is the mean species richness, Sv i Biomass in region i, Sv a is the mean value of biomass, i=1, 2, …, n, n is the number of regions, k2 and k1 are weight coefficients, 0≤k1≤1, 0≤k2≤1, and k1+k2=1. The specific value is set by the user or obtained by referring to the hierarchical analysis method;

[0101] Based on historical data and the need for ecological management, the protection threshold is pre-set; if the protection coefficient Bot exceeds the protection threshold, the corresponding undeveloped area can be used as a protected area, the development of the protected area can be suspended, the ecological environment in the protected area can be maintained, and the remaining undeveloped area can be used as the target area;

[0102] When in use, the protection coefficient Bot constructed can screen out the protection area in the undeveloped area, and protect the environment by reducing external interference in the protection area.

[0103] Step 402: Mark the target area on the electronic map, obtain the location information of the target area, and calculate the center degree Vt of each target area in the following manner:

[0104]

[0105] Weight coefficient, 0≤α≤1, 0≤β≤1; n is the number of target areas, G ij is the distance from the i-th target area to the j-th target area, G a is the average value of the distance;

[0106] After obtaining the centrality Vt of the target area, combined with the thermal value Rtz of the target area, the transfer priority Zyt of land development in each target area is calculated under dimensionless conditions, and the target area is marked with the transfer priority Zyt in the following manner:

[0107]

[0108] Among them, 0≤α≤1, 0≤β≤1, the weight coefficient is consistent with the previous value, C x is a constant correction coefficient, and its value falls within [0.01, 0.2];

[0109] When in use, after screening out several target areas, the transfer priority is obtained according to the location and thermal value Rtz of the target area. Through the transfer priority Zyt, the target facilities in other areas can be transferred to the target area in turn, so that each target area can be adjusted in an orderly manner;

[0110] Step 403: Obtain the traffic load degree and power load density in the developed area; wherein the traffic load degree refers to the ratio of the actual traffic flow of the road section to the traffic capacity of the road section, which is used to reflect the traffic operation status of the road section; the power load density refers to the power load per unit area, which is an important indicator for measuring the concentration of power load in the urban area, and is helpful for evaluating the carrying capacity of the power grid and planning the layout of the power grid;

[0111] The load factor Fst of the developed area is obtained by correlating the traffic load degree and the power load density. The traffic load degree Cu and the power load density Cs are linearly normalized, and the corresponding data values ​​are mapped to the interval [0,1], and then according to the following formula:

[0112]

[0113] Weight coefficient: 0≤S1≤1, 0≤S2≤1, and S1+S2=1, the weight coefficient is obtained by referring to the hierarchical analysis method; i=1, 2, …p, p is the number of developed areas; Cu i is the traffic load of the ith developed area, Cu a is the mean value of traffic load, Cs i is the power load density of the ith developed region, Cs a is the mean value of power load density;

[0114] If the load factor Fst exceeds the preset load threshold, the corresponding developed area will be used as the area to be transferred; after formulating the facility transfer plan, the multi-objective optimization algorithm is used to optimize the transfer plan with the optimization goal of reducing the environmental anomaly Yot in the area to be planned, and the optimized transfer plan is obtained;

[0115] When using, combine the contents in steps 401 to 403:

[0116] After obtaining relevant data from several developed areas, the load factor Fst is analyzed and obtained. The land planning status of the corresponding developed areas is evaluated based on the load factor Fst. If the developed area is already in a high-load state, the facilities in the high-load area can be transferred to the low-load area to make the land planning and development in each area more reasonable. At the same time, the transfer efficiency can also be improved by formulating and optimizing the transfer plan.

[0117] Step 5: Use the land planning digital twin model to test the optimized transfer plan, construct the improvement coefficient Pts based on the obtained plan test data, select the transfer plan as the target plan based on the improvement coefficient Pts, and transfer the facilities in the area to be transferred to the target area in turn according to the target plan and transfer priority;

[0118] The step five includes the following contents:

[0119] Step 501: After obtaining the optimized transfer scheme, the land planning digital twin model tests the optimized transfer scheme and obtains corresponding test data, including farmland occupation data and water resource waste data, and aggregates the obtained scheme test data to generate a scheme test data set;

[0120] Step 502: After the environmental anomaly degree Yot on each test node in the solution test data set, several environmental anomaly degrees Yot are arranged along the time axis to construct an improvement coefficient Pts, and the improvement coefficient Pts is used to determine whether the current water resource waste and land occupation have been improved, in the following manner:

[0121]

[0122] Among them, Yot i is the environmental abnormality degree on the i-th test node, Yot a is the corresponding mean, Yot b is its qualified standard value; Ut i is the i-th improved intermediate value, Ut a is its mean, i=1, 2, …, k, k is the number of sub-periods, weight coefficient: 0≤S1≤1, 0≤S2≤1 and S2+S1=1; the weight coefficient is consistent with the previous value;

[0123] If the improvement coefficient Pts does not exceed expectations, it means that the current land planning effect is poor and fails to achieve the expected effect. At this time, the transfer plan is optimized again and the optimized transfer plan is used as the target plan. According to the target plan and transfer priority, the facilities in the area to be transferred are transferred to the target area in sequence.

[0124] When in use, after obtaining the transfer plan, the land planning digital twin model is used to test the optimized transfer plan, and then the environmental anomaly degree Yot and the improvement coefficient Pts are obtained. According to the obtained improvement coefficient Pts, the feasibility of the current transfer plan can be judged. By selecting and optimizing the transfer plan, the reliability of the transfer plan is ensured, and the load of some areas is reduced during land planning, so that the development in each sub-area is more balanced and the damage to environmental conditions is reduced;

[0125] Step 503: After executing the transfer plan, after collecting various data after land planning within the preset monitoring period, the load factor Fst in each sub-area is generated again. If the load factor Fst still exceeds the corresponding load threshold, an alarm instruction is issued to the outside; under dimensionless conditions, the alert degree Mop is generated according to the time node and location data of the received alarm instruction, in the following manner:

[0126]

[0127] Weight coefficient: 0≤F1≤1, 0≤F2≤1, and F1+F2=1; the value of the weight coefficient is consistent with the previous value; n is the number of sub-regions, T ij and U ij are the time interval and distance interval between the ith alarm instruction and the jth alarm instruction, T a is the average value of the time interval, T b is the acceptable value of the time interval; U a is the average value of the distance interval, U b is the acceptable value of the distance interval;

[0128] If the alert level Mop is higher than the alert threshold, it means that the current land planning may not achieve the expected effect and needs to be adjusted again. At this time, an abnormal reminder instruction is issued to the outside;

[0129] When using, combine the contents in steps 501 to 503:

[0130] After completing the land planning process, the alert level Mop is generated based on the change status of the load data in each sub-area. This can be used to judge and evaluate the degree of development balance in the region, and to evaluate the current land planning effect again. The effect of land planning can be determined, so that timely adjustments can be made when the land planning effect fails to meet expectations, thereby ensuring the land planning effect.

[0131] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0132] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0133] See also Figure 2 The present invention provides a land use planning system based on big data analysis, including:

[0134] The environmental difference analysis unit collects data in the area to be planned and generates a regional environmental data set, and generates an environmental anomaly Yot from the regional environmental data set. If the obtained environmental anomaly Yot exceeds expectations, a data collection instruction is issued to the outside;

[0135] The model building unit pre-processes the sample data collected in the planning area, trains the neural convolution network with the sample data, and then builds the regional planning digital twin model;

[0136] Regional division unit: the planned area is divided into several sub-areas, and the thermal value Rtz is calculated based on the development status data in the sub-areas. The sub-areas are divided into undeveloped areas and developed areas based on the thermal value Rtz, and the corresponding land use status data are predicted and obtained respectively to generate a land use prediction data set;

[0137] The load analysis unit constructs a protection coefficient Bot from the land use prediction data in the undeveloped area, selects the target area from several undeveloped areas based on the protection coefficient Bot, selects the area to be transferred from the developed area based on the load coefficient Fst, and then formulates a transfer plan to transfer the target facilities from the area to be transferred to the target area;

[0138] The transfer optimization unit uses the land planning digital twin model to test the optimized transfer plan, constructs the improvement coefficient Pts based on the acquired plan test data, selects the transfer plan as the target plan based on the improvement coefficient Pts, and transfers the facilities in the area to be transferred to the target area in sequence according to the target plan and transfer priority.

[0139] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0140] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0143] 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, that is, they 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.

[0144] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0145] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0146] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present 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. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A land use planning method based on big data analysis, characterized by: include, Collect data in the planned area and generate a regional environmental data set, and generate an environmental anomaly degree from the regional environmental data set , if the obtained environment abnormality If the data exceeds expectations, a data collection instruction is issued to the outside. In the planned area, several collection points are set up, data is collected at the collection points, and a regional environmental data set is generated. The environmental anomaly degree is generated from the regional environmental data set. , of which the proportion of farmland encroachment and water consumption Perform linear normalization and map the corresponding data values ​​to the interval In the following way: in, , is the number of collection points, weight coefficient: , ,and ; is the water resource consumption of the ith collection point, is the average water consumption, is the acceptable value of water consumption; is the farmland encroachment ratio of the i-th collection point, is the average value of farmland encroachment ratio, is the acceptable value of farmland encroachment ratio; Data preprocessing is performed on each data in the regional planning data set. The preprocessing methods include data cleaning, data conversion and data integration. Some data is extracted from the preprocessed data set as sample data. After the neural convolution network is trained with the sample data, a regional planning digital twin model is constructed. The planned area is divided into several sub-areas, and the thermal value is calculated based on the development status data in the sub-areas. , where population density and economic output Perform linear normalization and map the corresponding data values ​​to the interval The thermal value is obtained as follows : Weight coefficient, , ; Based on thermal value The sub-region is divided into undeveloped areas and developed areas, and the corresponding land use status data are predicted and obtained respectively to generate a land use prediction data set; after obtaining the centrality of the target area Finally, combined with the thermal value of the target area , calculate the transfer priority of land development in each target area ,in, in, , , is the constant correction factor; Among them, the protection factor is constructed by the predicted data , if the protection factor When the protection threshold is exceeded, the corresponding undeveloped area is used as the protection area, and the remaining undeveloped area is used as the target area; the target area is marked on the electronic map, and after obtaining the location information of the target area, the center of each target area is calculated. , as follows: Weight coefficient, , ; n is the number of target areas, is the distance from the i-th target area to the j-th target area, is the average value of the distance; Constructing protection factors from predicted land use data within undeveloped areas , among which, species richness and biomass Perform linear normalization and map the corresponding data values ​​to the interval Then the protection factor is constructed as follows : in, The species richness in region i, is the mean species richness, The biomass in region i, is the mean value of biomass, , is the number of regions, is the weight coefficient, , ,and ; Based on protection factor Select target areas from several undeveloped areas and calculate the load factor After selecting the area to be transferred from the developed area, formulate a transfer plan to transfer the target facilities from the area to be transferred to the target area; Among them, the traffic load and power load density Perform linear normalization and map the corresponding data values ​​to the interval Then generate the load factor according to the following formula : Weight coefficient: , ,and ; , is the number of developed areas; is the traffic load of the ith developed area, is the mean value of traffic load, is the power load density of the ith developed region, is the mean value of power load density; The optimized transfer scheme is tested using the land planning digital twin model, and the improvement coefficient is constructed based on the obtained scheme test data. , where the improvement coefficient is constructed as follows : in, is the environmental abnormality degree on the i-th test node, is the corresponding mean, is its qualified standard value; is the i-th improved intermediate value, is its mean value, , is the number of sub-periods, and the weight coefficient is: , and ; Based on the improvement factor The transfer plan is selected as the target plan, and the facilities in the area to be transferred are transferred to the target area in sequence according to the target plan and the transfer priority.

2. The land use planning method based on big data analysis according to claim 1 is characterized in that: After receiving the data collection instruction, data collection is performed in the area to be planned, and the collected data are summarized to generate a regional planning data set; Perform data preprocessing on each data in the regional planning data set, and extract part of the data in the preprocessed data set as sample data; Taking the preprocessed regional planning data as input, the trained spatial analysis model identifies the spatial distribution characteristics of different locations in the planned area; Based on the acquired spatial distribution characteristics, the trained classification model is used to divide the area to be planned into several sub-areas and mark them on the electronic map.

3. The land use planning method based on big data analysis according to claim 2 is characterized in that: Collect the development status data of each sub-area and calculate the thermal value If the thermal value If it is below the thermal threshold, it is regarded as an undeveloped area, and the remaining sub-areas are regarded as developed areas; The regional planning digital twin model predicts the land use status in developed areas and undeveloped areas respectively, obtains corresponding prediction data, and aggregates the obtained prediction data to generate a land use prediction data set.

4. The land use planning method based on big data analysis according to claim 3 is characterized in that: Obtain the traffic load and power load density in the developed area, and obtain the load factor of the developed area in association , if the load factor If the load threshold is exceeded, the corresponding developed area will be used as the area to be transferred; After formulating the facility transfer plan, the environmental abnormality in the planned area will be reduced. In order to optimize the target, a multi-objective optimization algorithm is used to optimize the transfer plan and obtain the optimized transfer plan.

5. The land use planning method based on big data analysis according to claim 4 is characterized in that: The land planning digital twin model tests the optimized transfer scheme and obtains the corresponding test data, and aggregates the obtained scheme test data to generate a scheme test data set; The degree of environmental anomaly on each test node After that, several environmental abnormalities Arrange along the time axis to construct the improvement coefficient ; If the improvement factor If the transfer plan does not exceed expectations, the transfer plan is optimized and the optimized transfer plan is used as the target plan; According to the target plan and transfer priority, the facilities in the area to be transferred will be transferred to the target area in sequence.

6. The land use planning method based on big data analysis according to claim 5 is characterized by: After the transfer plan is implemented, the load factors in each sub-area are generated again after collecting all the data after the land planning is completed within the preset monitoring period. , if the load factor If it still exceeds the corresponding load threshold, an alarm command will be issued to the outside; Generate alert level based on the time and location data of the alarm command received If the alertness If the value is higher than the warning threshold, an abnormal warning instruction will be issued to the outside.

7. The land use planning method based on big data analysis according to claim 6 is characterized by: Generate alert level based on time node and location data of alarm command Here is how: Weight coefficient: , ,and ; n is the number of sub-regions, and are the time interval and distance interval between the ith alarm instruction and the jth alarm instruction, respectively. is the average value of the time interval, is the acceptable value for the time interval; is the average value of the distance interval, are acceptable values ​​for the distance interval.

8. A land use planning system based on big data analysis, applying the planning method according to any one of claims 1 to 7, characterized in that: include, The environmental difference analysis unit collects data in the planned area and generates a regional environmental data set, which generates an environmental anomaly degree , if the obtained environment abnormality Exceeding expectations, issuing data collection instructions to external parties; The model building unit pre-processes the sample data collected in the planning area, trains the neural convolution network with the sample data, and then builds the regional planning digital twin model; Regional division unit: the planned area is divided into several sub-areas, and the thermal value is calculated based on the development status data in the sub-areas. , according to the thermal value Divide the sub-region into undeveloped areas and developed areas, and predict and obtain the corresponding land use status data respectively to generate a land use prediction data set; Load analysis unit, which constructs protection factors from land use prediction data in undeveloped areas , according to the protection factor Select target areas from several undeveloped areas and calculate the load factor After selecting the area to be transferred from the developed area, formulate a transfer plan to transfer the target facilities from the area to be transferred to the target area; The transfer optimization unit uses the land planning digital twin model to test the optimized transfer plan and constructs the improvement coefficient based on the obtained plan test data , according to the improvement factor The transfer plan is selected as the target plan, and the facilities in the area to be transferred are transferred to the target area in sequence according to the target plan and the transfer priority.

Images