A GIS-based national land space planning optimization system and method

Abstract

The present invention discloses a territorial space planning optimization system and method based on GIS, which relates to the technical field of GIS. The system generates a heat map H of tourist activities by collecting activity data of tourist users, and fuses the heat map H with GIS data to obtain hotspot areas Rhot, and calculates the development potential factor P(r) of each area in the hotspot area, thereby realizing a more detailed and personalized regional development evaluation, overcoming the defect of insufficient consideration of tourist behavior and regional characteristics in traditional methods. In the optimization process, the optimized total cost Copt(r) of each area is analyzed and obtained by combining tourist flow and regional transportation capacity information, solving the problem that the previous planning based on static data and experience cannot flexibly adapt to the dynamically changing tourist flow and regional demand, improving the matching degree between regional facility planning and actual tourist demand, thereby realizing more efficient and accurate regional development and resource allocation.

Description

Technical Field

[0001] The present invention relates to the field of GIS technology, and in particular to a GIS-based national land space planning optimization system and method. Background Art

[0002] In modern society, with the rapid development of information technology, data-driven decision-making in various fields has become a trend. As an important means for national and local governments to rationally allocate resources, protect the environment, develop the economy and manage society, the optimization methods and technical means of national land space planning have been constantly evolving. Specifically, national land space planning involves land use, infrastructure layout, ecological protection and other aspects. Especially in resource-intensive urban and regional planning, how to more accurately evaluate the potential and rational use of land has become an urgent problem to be solved in the planning process.

[0003] Although GIS-based national land space planning methods have been applied in many fields, the existing traditional planning methods still have certain limitations when facing dynamic and diverse social activities and land demands. Traditional national land space planning mostly relies on static spatial data, such as land use status, population distribution, infrastructure conditions, etc., but these data often lack timeliness and flexibility, and it is difficult to reflect the rapidly changing social and economic activities, especially in some special areas, such as tourist cities and popular scenic spots, where the mobility and spatial demand of tourists often change very quickly.

[0004] For example, in tourist cities, traditional GIS planning methods often rely on historical data and traditional survey methods for land use planning, but these methods ignore the changing patterns and activity trends of tourists' behavior. Tourists' points of interest and activity frequency fluctuate dramatically with the seasons, holidays or special events. Traditional GIS analysis is difficult to capture this dynamic nature, resulting in planning results often lagging behind actual needs, affecting the effective layout of tourist facilities and the optimal use of land resources. In particular, the rise of social media has enabled a large amount of data on tourist locations and activities to be presented in real time, which provides us with a new perspective and decision-making basis in national land space planning. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a GIS-based national land space planning optimization system and method, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a GIS-based land space planning optimization method, comprising the following steps:

[0007] S1, by collecting tourist user activity data from social network platforms, generating a heat map H of tourist activities, and integrating it with GIS data to obtain hot spots Rhot;

[0008] S2. Perform cluster analysis based on the obtained hotspot areas Rhot and tourists’ behaviors, and calculate the development potential factor P(r) of each area r in the hotspot area Rhot;

[0009] S3. By analyzing the development potential factor P(r) and the transportation capacity information and tourist flow information of each area r, the optimized planning total cost Copt(r) is obtained, and the planning total cost Copt(r) of each area r is processed by using a genetic algorithm to obtain the optimal layout plan Lopt(r) of each area r;

[0010] S4, by obtaining historical optimization activity data and existing planning facility distribution information, and then using the time series model to predict the predicted tourist flow Tp (r) of area r in a fixed period in the future;

[0011] S5. Based on the obtained predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), a comprehensive analysis is performed to obtain the matching degree between the development potential and facility planning of each area r, which is marked as the comprehensive evaluation coefficient Sopt(r);

[0012] S6. According to the obtained comprehensive evaluation coefficient Sopt (r), the actual tourist flow effect of the tracking area r is evaluated, the execution effect evaluation vector E is obtained, and it is matched with the preset effect execution iterative optimization threshold Ethe to obtain the regional planning iterative optimization evaluation result.

[0013] Preferably, said S1 includes S11 and S12;

[0014] S11, by collecting tourist user activity data from the social networking platform, the tourist user activity data includes geographic tags, tourist stay information, tourist activity frequency information, activity type, tourist flow path and content posted by tourist users, and cleaning and pre-processing the collected tourist user activity data, the pre-processing includes removing duplicate, invalid and missing data, and then performing standardization processing, including unifying the time format, geographic coordinate format and removing tourist user privacy information, to obtain activity data Dc after cleaning and standardization pre-processing;

[0015] S12. Generate a heat map H by using a spatial density estimation method for the activity data Dc, and fuse it with the GIS data. Combine the location information of the hot spot areas in the heat map H with the geographic information in the GIS data through spatial overlap to obtain the hot spot areas Rhot.

[0016] Preferably, the thermal map H is obtained by the following calculation formula:

[0017] ;

[0018] Where H(x, y) represents the tourist activity density at the location (x, y), specifically represents the tourist activity heat at the location (x, y) in the heat map H, M represents the total number of active tourist users, j represents the jth tourist user, x(j) and y(j) represent the location coordinates of tourist user j, K represents the kernel function, and h represents the smoothing parameter;

[0019] The hot spot area Rhot is obtained by the following calculation formula:

[0020] ;

[0021] Where Rr represents the rth region in the heat map H, specifically a grid area, which is obtained by radiating a fixed range with the position (x, y) in the heat map H as the center. Hr represents the activity density value of the rth region in the heat map. Intersect (Rr, GIS) represents the overlap limit between the rth region Rr in the heat map H and the actual geographic area.

[0022] Preferably, said S2 includes S21;

[0023] S21, cluster analysis is performed based on the obtained hot spot area Rhot and the tourist behavior, including extracting the tourist stay information and the tourist activity frequency information from the activity data Dc, marking them as the stay duration L and the activity frequency F, and then using the K-means clustering algorithm to divide the tourist behavior into k clusters, and analyze the current tourist behavior to obtain the cluster cluster C(k) of the tourist user j's behavior in cluster k;

[0024] The cluster C(k) is obtained by the following calculation formula:

[0025] ;

[0026] Wherein, T(j) represents tourist user j at time T, Dc(j) represents the tourist user activity data of the jth tourist user in the activity data Dc, U(v) represents the center point of the vth cluster, specifically represents the average value of all tourist behavior characteristics in the vth cluster in cluster k, ||Dc(j)-U(v)|| represents the distance between the tourist user activity data of the jth tourist user and the center point of the vth cluster, specifically obtained by Euclidean distance calculation, and B represents the cluster analysis threshold, which is specifically used to judge the tightness of the tourist's behavior with the vth cluster.

[0027] Preferably, said S2 includes S22;

[0028] S22, calculating the development potential factor P(r) of each area in the hotspot area Rhot according to the obtained cluster C(k) of the behavior of the tourist user j in the cluster k;

[0029] The development potential factor P (r) is obtained by the following calculation formula:

[0030] ;

[0031] Where L(r, j) represents the length of time user j stays in area r, and H(r, j) represents the activity frequency of user j in area r.

[0032] Preferably, said S3 includes S31 and S32;

[0033] S31. Count the historical tourist data and the number of people passing through area r through GIS and social network data, obtain the tourist flow Fflow(r) of area r and the tourist transportation capacity Dcapacity(r) of area r, and obtain the total planning cost Copt(r) by fitting the development potential factor P(r), the tourist flow Fflow(r) and the tourist transportation capacity Dcapacity(r);

[0034] The total planning cost Copt (r) is obtained by the following calculation formula:

[0035] ;

[0036] In the formula, c1, c2 and c3 represent the fitting coefficients of the fitting development potential factor P (r), tourist flow Fflow (r) and tourist transport capacity Dcapacity (r), respectively, and c1+c2+c3=1. The specific value is set by the user.

[0037] S32, according to the obtained total planning cost Copt(r), using a genetic algorithm to process the total planning cost Copt(r) of each region r, and obtaining the optimal layout solution Lopt(r) of each region r;

[0038] The optimal layout solution Lopt (r) is obtained by the following calculation formula:

[0039] ;

[0040] Where argmin represents the minimization operation function.

[0041] Preferably, the S4 includes S41;

[0042] S41, by obtaining historical optimization activity data and existing planned facility distribution information, the time series model is used to predict the tourist flow Fflow(r) of area r in a future fixed period, which is marked as predicted tourist flow Tp(r);

[0043] The predicted tourist flow Tp (r) is obtained by the following calculation formula:

[0044] ;

[0045] Where Q represents the window length of historical data, specifically the time dimension of historical optimization activity data, Fflow(r,q) represents the tourist flow Fflow(r) of area r at time q, and t(q) represents the weight factor, specifically the influence of historical data on the predicted tourist flow Tp(r).

[0046] Preferably, the S5 includes S51;

[0047] S51. Based on the obtained predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), a comprehensive analysis is performed to obtain the matching degree between the development potential and the facility planning of each region r, which is marked as the comprehensive evaluation coefficient Sopt(r), reflecting the matching layout of the facility layout and the tourist flow of region r;

[0048] The comprehensive evaluation coefficient Sopt (r) is obtained by Obtain the calculation formula.

[0049] Preferably, said S6 includes S61 and S62;

[0050] S61, evaluating the actual tourist flow and facility usage of the tracking area r according to the obtained comprehensive evaluation coefficient Sopt(r), and obtaining an execution effect evaluation vector E;

[0051] The execution effect evaluation vector E is The calculation formula is obtained, where e1 and e2 represent weight coefficients. Specifically, e1 represents the weight coefficient of the impact of the calculation results of the predicted tourist flow Tp (r) and the tourist flow Fflow (r) on the execution effect evaluation vector E, and e2 represents the weight coefficient of the comprehensive evaluation coefficient Sopt (r) on the execution effect evaluation vector E;

[0052] S62, matching the obtained execution effect evaluation vector E with the preset effect execution iterative optimization threshold Ethe to obtain the regional planning iterative optimization evaluation result;

[0053] The regional planning iterative optimization evaluation results are obtained through the following matching method:

[0054] When the execution effect evaluation vector E≤the effect execution iterative optimization threshold Ethe, the regional planning iterative optimization evaluation result is obtained as a non-optimized result;

[0055] When the execution effect evaluation vector E>the effect execution iterative optimization threshold Ethe, the regional planning iterative optimization evaluation result is obtained as the optimization result, and the spatial planning within the region r needs to be adjusted, including adjusting the frequency of tourist transportation facilities and the layout route of the facilities.

[0056] A GIS-based national land space planning optimization system, including a data collection module, a data analysis module, a program optimization module, a prediction module, a comprehensive analysis module and a decision-making module;

[0057] The data collection module generates a heat map H of tourist activities by collecting tourist user activity data from the social network platform, and fuses it with GIS data to obtain hotspot areas Rhot;

[0058] The data analysis module performs cluster analysis based on the acquired hotspot areas Rhot and the tourists' behaviors, and calculates the development potential factor P(r) of each area r in the hotspot area Rhot;

[0059] The scheme optimization module obtains the optimized planning total cost Copt(r) by analyzing the development potential factor P(r) and the transportation capacity information and tourist flow information of each area r, and uses a genetic algorithm to process the planning total cost Copt(r) of each area r to obtain the optimal layout scheme Lopt(r) of each area r;

[0060] The prediction module obtains historical optimization activity data and existing planning facility distribution information, and then uses the time series model to predict the predicted tourist flow Tp(r) of area r within a fixed period in the future;

[0061] The comprehensive analysis module performs a comprehensive analysis based on the obtained predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), and obtains the matching degree between the development potential and the facility planning of each area r, which is marked as the comprehensive evaluation coefficient Sopt(r);

[0062] The decision module evaluates the actual tourist flow effect of the tracking area r according to the obtained comprehensive evaluation coefficient Sopt(r), obtains the execution effect evaluation vector E, and matches it with the preset effect execution iterative optimization threshold Ethe to obtain the regional planning iterative optimization evaluation result.

[0063] The present invention provides a GIS-based national land space planning optimization system and method, which has the following beneficial effects:

[0064] (1) By collecting the activity data of tourist users to generate a heat map H of tourist activities, and integrating it with GIS data, the hot spot area Rhot is obtained. This solves the problem that traditional planning methods cannot accurately reflect the real-time distribution and behavior characteristics of tourists. The development potential factor P(r) of each area is calculated within the hot spot area, thereby achieving a more detailed and personalized regional development evaluation and overcoming the defect of insufficient consideration of tourist behavior and regional characteristics in traditional methods. In the optimization process, the tourist flow and regional transportation capacity information are combined to analyze and obtain the optimized total cost Copt(r) of each area, solving the problem that the previous planning based on static data and experience cannot flexibly adapt to the dynamically changing tourist flow and regional demand. It improves the matching degree between regional facility planning and actual tourist demand, thereby achieving more efficient and accurate regional development and resource allocation.

[0065] (2) Comprehensive analysis of the development potential factor P(r) with the tourist flow Fflow(r) and tourist transport capacity Dcapacity(r) of the region further optimizes the planning cost and layout plan of the region. By statistically analyzing historical tourist data and the number of passers-by, the tourist flow and tourist transport capacity data of region r are obtained. Combining these data with the development potential factor P(r), the total planning cost Copt(r) of each region is calculated using the fitting method, thereby improving the resource utilization efficiency and tourist experience of the region. By using the time series model to predict the predicted tourist flow Tp(r) within a fixed period in the future, accurate flow forecasts are provided for subsequent facility planning and resource allocation, making the prediction of tourist flow more accurate, thereby avoiding excessive or insufficient prediction of future demand, and further improving the scientific nature and feasibility of planning.

[0066] (3) By comprehensively analyzing the predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), the matching degree between the development potential and facility planning of each region r was obtained, namely the comprehensive evaluation coefficient Sopt(r). This coefficient reflects the matching between the regional facility layout and the tourist flow, thus providing a quantitative basis for the subsequent spatial planning optimization. Further, by tracking the actual tourist flow and facility usage in the region, the regional planning effect was evaluated, and the execution effect evaluation vector E was calculated, which provided accurate data support for judging the effectiveness of the planning scheme. This feedback mechanism ensures that the regional planning can be continuously adjusted according to the actual situation, accurately responding to changes in tourist flow and facility usage, and optimizing resource allocation and facility layout. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 A schematic diagram of the steps of a GIS-based land space planning optimization method of the present invention;

[0068] Figure 2The present invention is a schematic diagram of a block diagram of a GIS-based national land space planning optimization system. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0070] Example 1

[0071] The present invention provides a GIS-based land space planning optimization method, please refer to Figure 1 , including the following steps:

[0072] S1, by collecting tourist user activity data from social network platforms, generating a heat map H of tourist activities, and integrating it with GIS data to obtain hot spots Rhot;

[0073] S2. Perform cluster analysis based on the obtained hotspot areas Rhot and tourists’ behaviors, and calculate the development potential factor P(r) of each area r in the hotspot area Rhot;

[0074] S3. By analyzing the development potential factor P(r) and the transportation capacity information and tourist flow information of each area r, the optimized planning total cost Copt(r) is obtained, and the planning total cost Copt(r) of each area r is processed by using a genetic algorithm to obtain the optimal layout plan Lopt(r) of each area r;

[0075] S4, by obtaining historical optimization activity data and existing planning facility distribution information, and then using the time series model to predict the predicted tourist flow Tp (r) of area r in a fixed period in the future;

[0076] S5. Based on the obtained predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), a comprehensive analysis is performed to obtain the matching degree between the development potential and facility planning of each area r, which is marked as the comprehensive evaluation coefficient Sopt(r);

[0077] S6. According to the obtained comprehensive evaluation coefficient Sopt (r), the actual tourist flow effect of the tracking area r is evaluated, the execution effect evaluation vector E is obtained, and it is matched with the preset effect execution iterative optimization threshold Ethe to obtain the regional planning iterative optimization evaluation result.

[0078] In this embodiment, the activity data of tourist users is collected to generate a heat map H of tourist activities, and the heat map is integrated with GIS data to obtain the hot spot area Rhot, which solves the problem that the traditional planning method cannot accurately reflect the real-time distribution and behavior characteristics of tourists. Through cluster analysis, the development potential factor P(r) of each area is calculated in the hot spot area, thereby achieving a more detailed and personalized regional development evaluation, overcoming the defects of insufficient consideration of tourist behavior and regional characteristics in traditional methods. In the optimization process, the optimized total cost Copt(r) of each area is analyzed and obtained by combining the information of tourist flow and regional transportation capacity, and the total cost is further optimized by genetic algorithm to obtain the optimal layout plan Lopt(r) for each area. This process makes full use of historical data and prediction models, optimizes resource allocation and facility layout, and solves the problem that the previous planning based on static data and experience cannot flexibly adapt to the dynamically changing tourist flow and regional needs. In particular, by using the time series model to predict the predicted tourist flow Tp(r) within a fixed period in the future, planning adjustments can be made in advance to reduce future planning deviations. Finally, the planning effect of the region is evaluated through the comprehensive evaluation coefficient Sopt(r), which provides a basis for further optimization and improves the matching degree between regional facility planning and actual tourist demand, thereby achieving more efficient and accurate regional development and resource allocation.

[0079] Example 2

[0080] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the S1 includes S11 and S12;

[0081] S11, by collecting tourist user activity data from the social networking platform, the tourist user activity data includes geographic tags, tourist stay information, tourist activity frequency information, activity type, tourist flow path and content posted by tourist users, and cleaning and pre-processing the collected tourist user activity data, the pre-processing includes removing duplicate, invalid and missing data, and then performing standardization processing, including unifying the time format, geographic coordinate format and removing tourist user privacy information, to obtain activity data Dc after cleaning and standardization pre-processing;

[0082] S12. Generate a heat map H by using a spatial density estimation method for the activity data Dc, and fuse it with the GIS data. Combine the location information of the hot spot areas in the heat map H with the geographic information in the GIS data through spatial overlap to obtain the hot spot areas Rhot.

[0083] The thermal map H is obtained by the following calculation formula:

[0084] ;

[0085] Wherein, H(x, y) represents the tourist activity density at the position (x, y), specifically represents the tourist activity heat at the position (x, y) in the heat map H, M represents the total number of active tourist users, specifically represents the number of non-repeated tourist users collected in the activity data Dc, j represents the jth tourist user, x(j) and y(j) represent the location coordinates of tourist user j, specifically obtained through the geographic tags in the activity data Dc, K represents the kernel function, including using the Gaussian kernel function to weight the location of each tourist user. The closer the tourist user is to the position (x, y) in the heat map H, the greater the weight of the activity, and h represents the smoothing parameter, specifically used to control the smoothness of the heat map;

[0086] The hot spot area Rhot is obtained by the following calculation formula:

[0087] ;

[0088] Where Rr represents the rth region in the heat map H, specifically a grid area, which is obtained by radiating a fixed range with the position (x, y) in the heat map H as the center. Hr represents the activity density value of the rth region in the heat map. Intersect (Rr, GIS) represents the overlap limit between the rth region Rr in the heat map H and the actual geographical area, which is used to ensure that the hot spot area is consistent with the actual geographical layout.

[0089] In this embodiment, the quality and consistency of the activity data are ensured by collecting the activity data of tourist users from the social networking platform and performing cleaning preprocessing and standardization. By eliminating duplicate data, invalid data and missing data, standardizing the time format, geographic coordinate format and removing privacy information, the activity data Dc after cleaning preprocessing is obtained, providing a reliable data basis for subsequent analysis. This process effectively solves the problem of low data quality and noise data affecting the analysis results in traditional methods, thereby improving the accuracy and reliability of subsequent analysis, using the spatial density estimation method to generate the heat map H of tourist activities, and combining GIS data to ensure the accurate docking of hot spots with actual geographical areas. By calculating the density value H(x, y) of tourist activities and using the Gaussian kernel function to weight the tourist user location, a heat map that accurately reflects the flow of tourists and the concentration of activities is obtained. Further, by spatial overlap, the hot spots in the heat map are combined with the geographic information in the GIS data to ensure the accuracy of the hot spots Rhot obtained. This method not only improves the accuracy of hot spot area identification, but also makes up for the deficiency of traditional methods in dynamically capturing tourist flow patterns, making it possible to conduct a more detailed analysis of the spatial distribution of tourist activities, thereby providing more scientific and effective support for regional planning and facility layout, and ensuring that spatial planning optimization can be based on real and dynamically changing tourist behavior data, greatly improving the scientific nature and pertinence of planning.

[0090] Example 3

[0091] This embodiment is explained in Example 2. Please refer to Figure 1 , specifically: the S2 includes S21;

[0092] S21, cluster analysis is performed based on the obtained hot spot area Rhot and the tourist behavior, including extracting the tourist stay information and the tourist activity frequency information from the activity data Dc, marking them as the stay duration L and the activity frequency F, and then using the K-means clustering algorithm to divide the tourist behavior into k clusters, and analyze the current tourist behavior to obtain the cluster cluster C(k) of the tourist user j's behavior in cluster k;

[0093] The cluster C(k) is obtained by the following calculation formula:

[0094] ;

[0095] Wherein, T(j) represents tourist user j at time T, Dc(j) represents the tourist user activity data of the jth tourist user in the activity data Dc, U(v) represents the center point of the vth cluster, specifically represents the average value of all tourist behavior characteristics in the vth cluster in cluster k, ||Dc(j)-U(v)|| represents the distance between the tourist user activity data of the jth tourist user and the center point of the vth cluster, specifically obtained by Euclidean distance calculation, B represents the cluster analysis threshold, specifically used to judge the tightness of the tourist behavior and the vth cluster. When the cluster analysis threshold B is set too small, it may lead to overly fine clustering, otherwise it may be too loose. The specific value is set by the user.

[0096] The S2 includes S22;

[0097] S22, calculating the development potential factor P(r) of each area in the hotspot area Rhot according to the obtained cluster C(k) of the behavior of the tourist user j in the cluster k;

[0098] The development potential factor P (r) is obtained by the following calculation formula:

[0099] ;

[0100] Where L(r, j) represents the length of time user j stays in area r, and H(r, j) represents the activity frequency of user j in area r.

[0101] In this embodiment, through cluster analysis of the obtained hot spot area Rhot and tourist behavior data, an in-depth understanding and refinement of the tourist behavior pattern is achieved, and it is marked as the length of stay L and the activity frequency F, and then the K-means clustering algorithm is used to divide the tourist behavior into different clusters. This process can effectively identify the activity characteristics of different tourist groups, and classify tourists with similar behavior patterns into the same category, ensuring that the analysis of tourist behavior is more accurate and targeted. By using the Euclidean distance to calculate the distance between each tourist and the center point of the cluster, and combining the set cluster analysis threshold B, the cluster C(k) to which the tourist belongs can be determined according to the tourist's behavioral characteristics, ensuring the scientificity and rationality of the tourist behavior grouping. This clustering method not only breaks through the traditional method's assumption of the singularity of tourist behavior, but also can classify and analyze the dynamic behavior of tourists more flexibly. The tourist behavior grouping C(k) obtained by cluster analysis can then calculate the development potential factor P(r) of each area r, realizing the quantitative evaluation of regional development potential. By calculating the length of stay L(r, j) and activity frequency H(r, j) of tourists in each area and comprehensively analyzing these behavioral data, the development potential of each hot spot area can be accurately evaluated, providing data support for subsequent regional planning and facility layout. Compared with traditional regional development evaluation methods, this analysis method based on tourists' actual behavior is more accurate and can fully consider tourists' dynamic needs and behavioral changes, thereby optimizing regional development strategies and improving the matching degree of facility resources.

[0102] Example 4

[0103] This embodiment is explained in Example 3, please refer to Figure 1 , specifically: S3 includes S31 and S32;

[0104] S31. Count the historical tourist data and the number of people passing through area r through GIS and social network data, obtain the tourist flow Fflow(r) of area r and the tourist transportation capacity Dcapacity(r) of area r, and obtain the total planning cost Copt(r) by fitting the development potential factor P(r), the tourist flow Fflow(r) and the tourist transportation capacity Dcapacity(r);

[0105] The total planning cost Copt (r) is obtained by the following calculation formula:

[0106] ;

[0107] In the formula, c1, c2 and c3 represent the fitting coefficients of the fitting development potential factor P (r), tourist flow Fflow (r) and tourist transport capacity Dcapacity (r), respectively, and c1+c2+c3=1. The specific value is set by the user.

[0108] S32, according to the obtained total planning cost Copt(r), using a genetic algorithm to process the total planning cost Copt(r) of each region r, and obtaining the optimal layout solution Lopt(r) of each region r;

[0109] The optimal layout solution Lopt (r) is obtained by the following calculation formula:

[0110] ;

[0111] Where argmin represents the minimization operation function.

[0112] The S4 includes S41;

[0113] S41, by obtaining historical optimization activity data and existing planned facility distribution information, the time series model is used to predict the tourist flow Fflow(r) of area r in a future fixed period, which is marked as predicted tourist flow Tp(r);

[0114] The predicted tourist flow Tp (r) is obtained by the following calculation formula:

[0115] ;

[0116] Where Q represents the window length of historical data, specifically the time dimension of historical optimization activity data, Fflow(r,q) represents the tourist flow Fflow(r) of area r at time q, and t(q) represents the weight factor, specifically the influence of historical data on the predicted tourist flow Tp(r).

[0117] In this embodiment, the planning cost and layout plan of the region are further optimized by comprehensively analyzing the development potential factor P(r) with the tourist flow Fflow(r) and the tourist transportation capacity Dcapacity(r) of the region. The tourist flow and tourist transportation capacity data of region r are obtained by statistically analyzing the historical tourist data and the number of people passing through. Combining these data with the development potential factor P(r), the total planning cost Copt(r) of each region is calculated by the fitting method, and the genetic algorithm is used for optimization to further obtain the optimal layout plan Lopt(r) of each region r. This process enables the spatial planning of the region to achieve the best balance between cost and benefit. The introduction of the genetic algorithm enables the optimization process to have a stronger global search capability, which can avoid the local optimal solution and ensure that the most potential layout plan is found, thereby improving the resource utilization efficiency and tourist experience of the region. By using the time series model to predict the predicted tourist flow Tp(r) in a fixed period in the future, accurate flow prediction is provided for subsequent facility planning and resource allocation. This process combines historical data with future demand, making the prediction of tourist flow more accurate, thereby avoiding excessive or insufficient prediction of future demand, and further improving the scientificity and executability of planning.

[0118] Example 5

[0119] This embodiment is explained in Example 4. Please refer to Figure 1 Specifically: the S5 includes S51;

[0120] S51. Based on the obtained predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), a comprehensive analysis is performed to obtain the matching degree between the development potential and the facility planning of each region r, which is marked as the comprehensive evaluation coefficient Sopt(r), reflecting the matching layout of the facility layout and the tourist flow of region r;

[0121] The comprehensive evaluation coefficient Sopt (r) is obtained by Obtain the calculation formula.

[0122] The S6 includes S61 and S62;

[0123] S61, evaluating the actual tourist flow and facility usage of the tracking area r according to the obtained comprehensive evaluation coefficient Sopt(r), and obtaining an execution effect evaluation vector E;

[0124] The execution effect evaluation vector E is The calculation formula is obtained, where e1 and e2 represent weight coefficients. Specifically, e1 represents the weight coefficient of the impact of the calculation results of the predicted tourist flow Tp (r) and the tourist flow Fflow (r) on the execution effect evaluation vector E, and e2 represents the weight coefficient of the comprehensive evaluation coefficient Sopt (r) on the execution effect evaluation vector E;

[0125] S62, matching the obtained execution effect evaluation vector E with the preset effect execution iterative optimization threshold Ethe to obtain the regional planning iterative optimization evaluation result;

[0126] The regional planning iterative optimization evaluation results are obtained through the following matching method:

[0127] When the execution effect evaluation vector E≤the effect execution iterative optimization threshold Ethe, the regional planning iterative optimization evaluation result is obtained as a non-optimized result;

[0128] When the execution effect evaluation vector E>the effect execution iterative optimization threshold Ethe, the regional planning iterative optimization evaluation result is obtained as the optimization result, and the spatial planning within the region r needs to be adjusted, including adjusting the frequency of tourist transportation facilities and the layout route of the facilities.

[0129] In this embodiment, by comprehensively analyzing the predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), the matching degree between the development potential of each region r and the facility planning is obtained, that is, the comprehensive evaluation coefficient Sopt(r). This coefficient reflects the matching between the regional facility layout and the tourist flow, thereby providing a quantitative basis for the subsequent spatial planning optimization. Further, by tracking the actual tourist flow and facility usage in the region, the regional planning effect is evaluated, and the execution effect evaluation vector E is calculated, which provides accurate data support for judging the effectiveness of the planning scheme. This feedback mechanism ensures that the regional planning can be continuously adjusted according to the actual situation, accurately responds to changes in tourist flow and facility usage, and optimizes resource allocation and facility layout.

[0130] Example 6

[0131] A GIS-based national land space planning optimization system, please refer to Figure 2 ,Specifically: including data acquisition module, data analysis module, solution optimization module, prediction module, comprehensive analysis module and decision-making module;

[0132] The data collection module generates a heat map H of tourist activities by collecting tourist user activity data from the social network platform, and fuses it with GIS data to obtain hotspot areas Rhot;

[0133] The data analysis module performs cluster analysis based on the acquired hotspot areas Rhot and the tourists' behaviors, and calculates the development potential factor P(r) of each area r in the hotspot area Rhot;

[0134] The scheme optimization module obtains the optimized planning total cost Copt(r) by analyzing the development potential factor P(r) and the transportation capacity information and tourist flow information of each area r, and uses a genetic algorithm to process the planning total cost Copt(r) of each area r to obtain the optimal layout scheme Lopt(r) of each area r;

[0135] The prediction module obtains historical optimization activity data and existing planning facility distribution information, and then uses the time series model to predict the predicted tourist flow Tp(r) of area r within a fixed period in the future;

[0136] The comprehensive analysis module performs a comprehensive analysis based on the obtained predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), and obtains the matching degree between the development potential and the facility planning of each area r, which is marked as the comprehensive evaluation coefficient Sopt(r);

[0137] The decision module evaluates the actual tourist flow effect of the tracking area r according to the obtained comprehensive evaluation coefficient Sopt(r), obtains the execution effect evaluation vector E, and matches it with the preset effect execution iterative optimization threshold Ethe to obtain the regional planning iterative optimization evaluation result.

[0138] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A GIS-based land space planning optimization method, characterized by: The following steps are involved: S1, by collecting tourist user activity data from social network platforms, generating a heat map H of tourist activities, and integrating it with GIS data to obtain hot spots Rhot; S2. Perform cluster analysis based on the obtained hotspot areas Rhot and tourists’ behaviors, and calculate the development potential factor P(r) of each area r in the hotspot area Rhot; S3. By analyzing the development potential factor P(r) and the transportation capacity information and tourist flow information of each area r, the optimized planning total cost Copt(r) is obtained, and the planning total cost Copt(r) of each area r is processed by using a genetic algorithm to obtain the optimal layout plan Lopt(r) of each area r; S4, by obtaining historical optimization activity data and existing planning facility distribution information, and then using the time series model to predict the predicted tourist flow Tp (r) of area r in a fixed period in the future; S5. Based on the obtained predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), a comprehensive analysis is performed to obtain the matching degree between the development potential and facility planning of each area r, which is marked as the comprehensive evaluation coefficient Sopt(r); S6. According to the obtained comprehensive evaluation coefficient Sopt(r), the actual tourist flow effect of the tracking area r is evaluated, and the execution effect evaluation vector E is obtained, and it is matched with the preset effect execution iterative optimization threshold Ethe to obtain the regional planning iterative optimization evaluation result; The S6 includes S61 and S62; S61, evaluating the actual tourist flow and facility usage of the tracking area r according to the obtained comprehensive evaluation coefficient Sopt(r), and obtaining an execution effect evaluation vector E; The execution effect evaluation vector E is The calculation formula is obtained, where e1 and e2 represent weight coefficients. Specifically, e1 represents the weight coefficient of the impact of the calculation results of the predicted tourist flow Tp (r) and the tourist flow Fflow (r) on the execution effect evaluation vector E, and e2 represents the weight coefficient of the comprehensive evaluation coefficient Sopt (r) on the execution effect evaluation vector E; S62, matching the obtained execution effect evaluation vector E with the preset effect execution iterative optimization threshold Ethe to obtain the regional planning iterative optimization evaluation result; The regional planning iterative optimization evaluation results are obtained through the following matching method: When the execution effect evaluation vector E≤the effect execution iterative optimization threshold Ethe, the regional planning iterative optimization evaluation result is obtained as a non-optimized result; When the execution effect evaluation vector E>the effect execution iterative optimization threshold Ethe, the regional planning iterative optimization evaluation result is obtained as the optimization result, and the spatial planning within the region r needs to be adjusted, including adjusting the frequency of tourist transportation facilities and the layout route of the facilities.

2. The GIS-based land space planning optimization method according to claim 1, characterized in that: Said S1 includes S11 and S12; S11, by collecting tourist user activity data from the social networking platform, the tourist user activity data includes geographic tags, tourist stay information, tourist activity frequency information, activity type, tourist flow path and content posted by tourist users, and cleaning and pre-processing the collected tourist user activity data, the pre-processing includes removing duplicate, invalid and missing data, and then performing standardization processing, including unifying the time format, geographic coordinate format and removing tourist user privacy information, to obtain activity data Dc after cleaning and standardization pre-processing; S12. Generate a heat map H by using a spatial density estimation method for the activity data Dc, and fuse it with the GIS data. Combine the location information of the hot spot areas in the heat map H with the geographic information in the GIS data through spatial overlap to obtain the hot spot areas Rhot.

3. The GIS-based land space planning optimization method according to claim 2 is characterized by: The thermal map H is obtained by the following calculation formula: ； Where H(x, y) represents the tourist activity density at the location (x, y), specifically represents the tourist activity heat at the location (x, y) in the heat map H, M represents the total number of active tourist users, j represents the jth tourist user, x(j) and y(j) represent the location coordinates of tourist user j, K represents the kernel function, and h represents the smoothing parameter; The hot spot area Rhot is obtained by the following calculation formula: ； Where Rr represents the rth region in the heat map H, specifically a grid area, which is obtained by radiating a fixed range with the position (x, y) in the heat map H as the center. Hr represents the activity density value of the rth region in the heat map. Intersect (Rr, GIS) represents the overlap limit between the rth region Rr in the heat map H and the actual geographic area.

4. The GIS-based land space planning optimization method according to claim 3 is characterized by: Said S2 includes S21; S21, cluster analysis is performed based on the obtained hot spot area Rhot and the tourist behavior, including extracting the tourist stay information and the tourist activity frequency information from the activity data Dc, marking them as the stay duration L and the activity frequency F, and then using the K-means clustering algorithm to divide the tourist behavior into k clusters, and analyze the current tourist behavior to obtain the cluster cluster C(k) of the tourist user j's behavior in cluster k; The cluster C(k) is obtained by the following calculation formula: ； Wherein, T(j) represents tourist user j at time T, Dc(j) represents the tourist user activity data of the jth tourist user in the activity data Dc, U(v) represents the center point of the vth cluster, specifically represents the average value of all tourist behavior characteristics in the vth cluster in cluster k, ||Dc(j)-U(v)|| represents the distance between the tourist user activity data of the jth tourist user and the center point of the vth cluster, specifically obtained by Euclidean distance calculation, and B represents the cluster analysis threshold, which is specifically used to judge the tightness of the tourist's behavior with the vth cluster.

5. The GIS-based land space planning optimization method according to claim 4 is characterized by: The S2 includes S22; S22, according to the obtained cluster C(k) of the behavior of tourist user j in cluster k, calculate the development potential factor P(r) of each area in the hot spot area Rhot; The development potential factor P (r) is obtained by the following calculation formula: ； Where L(r, j) represents the length of time user j stays in area r, and H(r, j) represents the activity frequency of user j in area r.

6. The GIS-based land space planning optimization method according to claim 5 is characterized by: The S3 includes S31 and S32; S31. Count the historical tourist data and the number of people passing through area r through GIS and social network data, obtain the tourist flow Fflow(r) of area r and the tourist transportation capacity Dcapacity(r) of area r, and obtain the total planning cost Copt(r) by fitting the development potential factor P(r), the tourist flow Fflow(r) and the tourist transportation capacity Dcapacity(r); The total planning cost Copt (r) is obtained by the following calculation formula: ； In the formula, c1, c2 and c3 represent the fitting coefficients of the fitting development potential factor P (r), tourist flow Fflow (r) and tourist transport capacity Dcapacity (r), respectively, and c1+c2+c3=1. The specific value is set by the user. S32, according to the obtained total planning cost Copt(r), using a genetic algorithm to process the total planning cost Copt(r) of each region r, and obtaining the optimal layout solution Lopt(r) of each region r; The optimal layout solution Lopt (r) is obtained by the following calculation formula: ； Where argmin represents the minimization operation function.

7. The GIS-based land space planning optimization method according to claim 6 is characterized by: The S4 includes S41; S41, by obtaining historical optimization activity data and existing planned facility distribution information, the time series model is used to predict the tourist flow Fflow(r) of area r in a future fixed period, which is marked as predicted tourist flow Tp(r); The predicted tourist flow Tp (r) is obtained by the following calculation formula: ； Where Q represents the window length of historical data, specifically the time dimension of historical optimization activity data, Fflow(r,q) represents the tourist flow Fflow(r) of area r at time q, and t(q) represents the weight factor, specifically the influence of historical data on the predicted tourist flow Tp(r).

8. The GIS-based land space planning optimization method according to claim 1 is characterized by: The S5 includes S51; S51. Based on the obtained predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), a comprehensive analysis is performed to obtain the matching degree between the development potential and the facility planning of each region r, which is marked as the comprehensive evaluation coefficient Sopt(r), reflecting the matching layout of the facility layout and the tourist flow of region r; The comprehensive evaluation coefficient Sopt (r) is obtained by Obtain the calculation formula.

9. A GIS-based national land space planning optimization system, applied to a GIS-based national land space planning optimization method according to any one of claims 1 to 8, characterized in that: It includes data collection module, data analysis module, solution optimization module, prediction module, comprehensive analysis module and decision-making module; The data collection module generates a heat map H of tourist activities by collecting tourist user activity data from the social network platform, and fuses it with GIS data to obtain hotspot areas Rhot; The data analysis module performs cluster analysis based on the acquired hotspot areas Rhot and the tourists' behaviors, and calculates the development potential factor P(r) of each area r in the hotspot area Rhot; The scheme optimization module obtains the optimized planning total cost Copt(r) by analyzing the development potential factor P(r) and the transportation capacity information and tourist flow information of each area r, and uses a genetic algorithm to process the planning total cost Copt(r) of each area r to obtain the optimal layout scheme Lopt(r) of each area r; The prediction module obtains historical optimization activity data and existing planning facility distribution information, and then uses the time series model to predict the predicted tourist flow Tp(r) of area r in a fixed period in the future; The comprehensive analysis module performs a comprehensive analysis based on the obtained predicted tourist flow Tp(r) and the optimal layout plan Lopt(r), and obtains the matching degree between the development potential and the facility planning of each area r, which is marked as the comprehensive evaluation coefficient Sopt(r); The decision module evaluates the actual tourist flow effect of the tracking area r according to the obtained comprehensive evaluation coefficient Sopt(r), obtains the execution effect evaluation vector E, and matches it with the preset effect execution iterative optimization threshold Ethe to obtain the regional planning iterative optimization evaluation result.

Images