Intelligent land utilization optimization method, system and equipment based on geographic big data

Abstract

The invention discloses an intelligent land utilization optimization method based on geographic big data. The method comprises the following steps: S1, generating all land allocation schemes according to the geographic big data and generating a land allocation scheme set; s2, a multi-objective function fi (x) is generated according to the geographic big data, and x is a land allocation scheme in the land allocation scheme set; s3, the multi-objective function fi (x) is converted into a single-objective function # imgabs0 # imgabs1 #, omega i is the index weight of the corresponding multi-objective function fi (x), omega i meets # imgabs2 #, and omega i is larger than or equal to 0; s4, calculating a solution corresponding to the land allocation scheme corresponding to each x according to the single objective function # imgabs3 #, and generating a solution set; and S5, finding an optimal solution in the solution set, and carrying out reverse calculation to obtain an optimal land allocation scheme in the land allocation scheme set. Therefore, on one hand, scientificity and accuracy of land utilization planning can be improved, and on the other hand, benefits of all parties can be balanced.

Description

Technical Field

[0001] The present invention relates to the field of land planning, and in particular to an intelligent land utilization optimization method, system and equipment based on geographic big data. Background Art

[0002] With the acceleration of urbanization and the increasing tension of land resources, how to use land resources efficiently and reasonably has become an important issue facing the current society. Traditional land use planning methods often rely on experience and qualitative analysis, which is difficult to fully and accurately reflect the actual situation of land resources and the complex and changeable utilization needs. Therefore, exploring an intelligent land use optimization method based on big data is of great significance to improving land use efficiency and promoting sustainable development.

[0003] At present, geographic big data has been widely used in many fields. Its rich data resources and powerful analytical capabilities provide new possibilities for land use optimization. Geographic big data covers information on topography, soil type, climate conditions, transportation network, population distribution and other aspects. This information is crucial for formulating scientific land use plans. However, how to effectively integrate these geographic big data and apply them to land use optimization is still a problem that needs to be solved urgently.

[0004] In addition, land use optimization often involves multiple goals and stakeholders' needs, such as economic benefits, environmental protection, social stability, etc. These goals often conflict and constrain each other, making land use optimization a complex multi-objective optimization problem. Traditional optimization methods often find it difficult to consider multiple goals at the same time, resulting in the optimization results often being biased towards the interests of one aspect while ignoring the needs of other aspects. Summary of the invention

[0005] The present invention aims to solve the technical problems in the above-mentioned technology at least to some extent.

[0006] To this end, the present invention discloses in a first aspect an intelligent land use optimization method based on geographic big data, comprising the following steps: S1: generating all land allocation plans and generating a land allocation plan set according to the geographic big data; S2: generating a multi-objective function f according to the geographic big data i (x), where x is a land allocation scheme in the land allocation scheme set; S3: convert the multi-objective function f i (x) is converted into a single objective function Among them, ω i is the corresponding multi-objective function f i (x) indicator weight, ω i satisfy And ω i≥0; S4: According to the single objective function Calculate the solution corresponding to each land allocation scheme corresponding to x and generate a solution set; S5: find the optimal solution in the solution set and reversely obtain the optimal land allocation scheme in the land allocation scheme set.

[0007] The intelligent land use optimization method based on geographic big data disclosed in the present invention has the following beneficial effects:

[0008] (1) Improve the scientificity and accuracy of land use planning. By integrating geographic big data, it can comprehensively and accurately reflect the actual situation of land resources and the complex and changing utilization needs, thereby avoiding the unscientific and inaccurate planning caused by traditional methods that rely too much on experience and qualitative analysis, making land use planning more in line with reality and better meeting the needs of social and economic development;

[0009] (2) Balancing the interests of all parties. Land use optimization often involves multiple goals and the needs of stakeholders, such as economic benefits, environmental protection, and social stability. These goals often conflict with and constrain each other, making land use optimization a complex multi-objective optimization problem. The present invention constructs a multi-objective function and sets corresponding indicator weights to transform the multi-objective problem into a single-objective problem for solution. This ensures economic benefits while taking into account multiple needs such as environmental protection and social stability, thereby achieving a balance of interests among all parties.

[0010] In addition, the intelligent land use optimization method based on geographic big data disclosed in the present invention may also have the following additional technical features:

[0011] In one embodiment of the present invention, the step of generating all land allocation plans and generating a land allocation plan set based on geographic big data further includes the following steps: S1.1: generating constraint conditions C based on the geographic big data j ; S1.2: Eliminate all the land allocation schemes that do not meet the constraint condition C j of the land allocation scheme.

[0012] In one embodiment of the present invention, the single objective function Calculating the solution corresponding to each land allocation scheme corresponding to x and generating a solution set also includes the following steps: S4.1: selecting any one of the land allocation schemes in the land allocation scheme set as the initial land allocation scheme; S4.2: substituting the initial land allocation scheme into the single objective function Calculate and obtain an initial solution; S4.3: Change a plot parameter of the initial land allocation scheme to obtain a new land allocation scheme and substitute it into the single objective function Calculate and obtain a new solution; S4.4: If the new solution is better than the previous solution, change a plot parameter of the new land allocation scheme to obtain another new land allocation scheme and substitute it into the single objective function Calculate and obtain another new solution, repeat steps S4.3 and S4.4 until the solution obtained is no longer better than the previous solution, and stop steps S4.3 and S4.4.

[0013] In one embodiment of the present invention, in steps S4.3 and S4.4, the upper bound of the current solution If it is smaller than the currently known optimal solution in the solution set or the lower bound F(x) is larger than the currently known optimal solution in the solution set, stop steps S4.3 and S4.4.

[0014] In one embodiment of the present invention, the method of finding the optimal solution in the solution set and inversely obtaining the optimal land allocation plan in the land allocation plan set also includes the following steps: S5.1: dividing the solution set into multiple sub-solution sets; S5.2: traversing each of the sub-solution sets and finding the sub-optimal solution in each of the sub-solution sets; S5.3: traversing each of the sub-optimal solutions and obtaining the optimal solution.

[0015] In one embodiment of the present invention, the multi-objective function Among them, p k is the unit area of ​​the kth piece of land, q k is the impact factor per unit area of ​​the kth piece of land.

[0016] In a second aspect, the present invention discloses an intelligent land use optimization system based on geographic big data, comprising: a first generation module, used to generate all land allocation plans according to geographic big data and form a land allocation plan set; a second generation module, used to generate a multi-objective function based on the geographic big data; a conversion module, used to convert the multi-objective function into a single objective function, and set corresponding indicator weights; a calculation module, used to calculate the solution corresponding to each land allocation plan according to the single objective function, and generate a solution set; an optimal solution determination module, used to find the optimal solution in the solution set, and inversely obtain the optimal land allocation plan in the land allocation plan set.

[0017] The present invention discloses a device in a third aspect, comprising: a processor and a memory, wherein the memory stores executable instructions, and when the executable instructions are executed by the processor, the device is capable of executing the intelligent land use optimization method based on geographic big data as described in any one of claims 1 to 6.

[0018] Additional contents and advantages of the present invention will be given in the following description or may be understood through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The technical solutions and beneficial effects of the present invention will become apparent and easily understood from the following contents in conjunction with the accompanying drawings, wherein:

[0020] Figure 1 A schematic diagram of a flow chart of an intelligent land use optimization method based on geographic big data in one embodiment of the present invention;

[0021] Figure 2 It is a flow chart of an intelligent land use optimization method based on geographic big data in another embodiment of the present invention;

[0022] Figure 3 It is a flow chart of an intelligent land use optimization method based on geographic big data in another embodiment of the present invention;

[0023] Figure 4 It is a flow chart of an intelligent land use optimization method based on geographic big data in another embodiment of the present invention;

[0024] Figure 5 This is a system block diagram of an intelligent land use optimization system based on geographic big data in another embodiment of the present invention. DETAILED DESCRIPTION

[0025] Embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. In addition, the embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0026] The following will describe the intelligent land use optimization method, system and equipment based on geographic big data disclosed in the present invention with reference to the accompanying drawings.

[0027] like Figure 1 As shown, an intelligent land use optimization method based on geographic big data includes the following steps:

[0028] S1: Generate all land allocation plans based on geographic big data and generate a land allocation plan set;

[0029] Specifically, in this step, we first clarify the various indicators of geographic big data, such as the area and location of residential, industrial, agricultural and ecological protection lands; then, based on these indicators, we generate all possible land allocation plans to form a land allocation plan set;

[0030] S2: Generate multi-objective function f based on geographic big data i (x), where x is a land allocation scheme in the land allocation scheme set;

[0031] Specifically, in this step, a multi-objective function is constructed based on various indicators of geographic big data; each objective function is related to the purpose of the land parcel and reflects the needs and goals of different stakeholders. For example, the goals that can be set for residential land include improving the quality of life of residents and ensuring housing supply, while the goals for industrial land are to promote economic growth and increase employment opportunities. Each goal corresponds to a mathematical expression, namely the objective function; all objective functions are combined to form a multi-objective optimization problem.

[0032] x3: multi-objective function f i (x) is converted into a single objective function Among them, ω i is the corresponding multi-objective function f i (x) indicator weight, ω i satisfy And ω i ≥0;

[0033] Specifically, in this step, the multi-objective function is converted into a single-objective function by setting corresponding indicator weights for each multi-objective function; these weights can be flexibly adjusted according to actual conditions to reflect the priorities and importance of different stakeholders;

[0034] S4: Based on the single objective function Calculate the solution corresponding to each land allocation scheme corresponding to x and generate a solution set;

[0035] Specifically, in this step, each plan in the land allocation plan set is substituted into the single objective function for calculation to obtain the corresponding solution and form a solution set;

[0036] S5: Find the optimal solution in the solution set and reversely obtain the optimal land allocation solution in the land allocation solution set;

[0037] Specifically, in this step, the optimal solution is found by comparing the solutions in the solution set, and the corresponding land allocation scheme is inferred as the optimal land allocation scheme.

[0038] In the embodiment of the present invention, it is assumed that there are S plots in total, denoted as S1, S2, ..., Su , each plot can have T uses, denoted as T1, T2, …, T v , multi-objective function f i (x) are all related to the purpose of the plot and are multi-objective functions f i (x) Establish the corresponding indicator weight ω i ;

[0039] Specifically, suppose there are 5 plots in total, and each plot is numbered S1, S2, S3, S4, S5. Each plot can have 5 uses, namely T1, T2, T3, T4, T5, corresponding to residential, industrial, agricultural, commercial and ecological protection respectively. 5 = 3125 allocation options, for example:

[0040] Plan 1: (residence, residence, residence, residence, residence), Plan 2: (residence, residence, residence, residence, industry), …, Plan 3125: (ecological protection, ecological protection, ecological protection, ecological protection, ecological protection);

[0041] Because all the land distribution options are quite large, only a few examples are listed here as representatives, and other options are omitted;

[0042] Assuming there are two main goals, namely: maximizing economic benefits f1(x) and minimizing environmental impact f2(x), the economic benefits and environmental impacts of each plot under different uses are shown in the following table:

[0043] <![CDATA[T1]]> <![CDATA[T2]]> <![CDATA[T3]]> <![CDATA[T4]]> <![CDATA[T5]]> <![CDATA[S1]]> 0.8 / 0.4 1.2 / 0.4 0.6 / 0.1 1.0 / 0.7 0.1 / 0.1 <![CDATA[S2]]> 0.7 / 0.2 1.1 / 0.5 0.5 / 0.2 0.9 / 0.2 0.2 / 0.1 <![CDATA[S3]]> 0.9 / 0.2 1.3 / 0.5 0.7 / 0.3 1.1 / 0.3 0.3 / 0.2 <![CDATA[S4]]> 0.8 / 0.3 1.2 / 0.7 0.6 / 02 1.0 / 0.4 0.2 / 0.2 <![CDATA[S5]]> 0.7 / 0.1 1.1 / 0.4 0.5 / 0.3 0.9 / 0.5 0.4 / 0.1

[0044] Table 1

[0045] The corresponding multi-objective function is as follows:

[0046] Economic Benefits Environmental impact

[0047] Set the indicator weight ω=(ω1,ω2), satisfying ω1+ω2=1,ω1>0,ω2>0. For example, if more emphasis is placed on economic benefits, then ω1=0.7,ω2=0.3. At this time, the single objective function F(x)=ω1f1(x)+ω2f2(x) can be obtained. Based on this, the solution corresponding to each land allocation scheme is calculated and a solution set is generated. Taking scheme 1: (residence, residence, residence, residence, residence) as an example, economic benefits are maximized f1(x)=0.8, and environmental impact is minimized f2(x)=0.1. Then the single objective function F(x)=0.7*0.8+0.3*0.1=0.59. Then, each land allocation scheme is calculated until all solutions are obtained and a solution set is generated at the same time.

[0048] After calculation, assuming that the optimal solution is found, the corresponding land allocation plan may be (industry, commerce, agriculture, residence, environmental protection), which depends on the actual calculation results. It is known that the land allocation plan is the optimal solution based on the current geographic big data environment;

[0049] According to the intelligent land use optimization method based on geographic big data disclosed in the present invention, on the one hand, the scientificity and accuracy of land use planning can be improved. By integrating geographic big data, the actual situation of land resources and complex and changeable utilization needs can be fully and accurately reflected, thereby avoiding the problem of unscientific and inaccurate planning caused by traditional methods relying too much on experience and qualitative analysis, making land use planning more in line with reality and better meeting the needs of social and economic development; on the other hand, it can balance the interests of all parties. Land use optimization often involves multiple goals and the needs of stakeholders, such as economic benefits, environmental protection, social stability, etc. There are often conflicts and constraints between these goals, making land use optimization a complex multi-objective optimization problem. The present invention constructs a multi-objective function and sets corresponding indicator weights to convert the multi-objective problem into a single-objective problem for solution, thereby being able to ensure economic benefits while taking into account multiple needs such as environmental protection and social stability, thereby achieving a balance of interests of all parties.

[0050] In order to better explain the present invention, in one embodiment of the present invention, as Figure 2 As shown, all land allocation plans are generated according to geographic big data and a land allocation plan set is generated, and the following steps are also included:

[0051] S1.1: Generate constraint conditions C based on geographic big data j ;

[0052] Specifically, in this step, corresponding constraints are generated based on various indicators of geographic big data, such as the existence of an upper limit on the total land area or the prohibition of development in nature reserves;

[0053] S1.2: Eliminate all land allocation solutions that do not meet the constraint condition C j land distribution scheme;

[0054] Specifically, in this step, the land allocation scheme set is screened according to the generated constraints, and all land allocation schemes that do not meet the constraints are excluded.

[0055] In the embodiment of the present invention, the constraint condition C is used j To exclude incompatible land allocation schemes, the amount of calculation of the subsequent single objective function F(x) can be effectively reduced. For example, assuming the following constraint condition C j, respectively: at least 2 pieces of land are needed for residence C1 and at least 1 piece of land is needed for ecological protection C2;

[0056] For example, the above constraints can exclude land allocation plans such as (industry, industry, agriculture, residence, environmental protection), (industry, commerce, agriculture, agriculture, environmental protection) or (industry, commerce, agriculture, residence, residence).

[0057] In order to better explain the present invention, in one embodiment of the present invention, as Figure 3 As shown, according to the single objective function Calculating the solution corresponding to each land allocation scheme corresponding to x and generating a solution set also includes the following steps:

[0058] S4.1: Select any one of the land allocation schemes in the land allocation scheme set as the initial land allocation scheme;

[0059] S4.2: Substitute the initial land allocation plan into the single objective function Calculate and obtain the initial solution;

[0060] S4.3: Change one of the parameters of the initial land allocation scheme to obtain a new land allocation scheme and substitute it into the single objective function Calculate and obtain a new solution;

[0061] S4.4: If the new solution is better than the previous one, change one of the land parcel parameters of the new land allocation scheme to obtain another new land allocation scheme and substitute it into the single objective function Calculate and obtain another new solution, repeat steps S4.3 and S4.4 until the solution obtained is no longer better than the previous solution, and stop steps S4.3 and S4.4.

[0062] In the embodiment of the present invention, it is assumed that after the two constraints of requiring at least two pieces of land for residence C1 and requiring at least one piece of land for ecological protection C2 are screened out, the following land allocation scheme is obtained:

[0063] Scheme 1: (residential, residential, agriculture, commerce, ecological protection), Scheme 2: (residential, residential, agriculture, commerce, commerce), Scheme 3: (residential, residential, agriculture, commerce, industry), Scheme 4: (residential, residential, agriculture, commerce, residential), We choose Scheme 1: (residential, residential, agriculture, commerce, ecological protection) as the initial land allocation scheme;

[0064] The specific calculation process will not be repeated here. The single objective function F(x) of the initial land allocation plan is obtained as 2.09. The use of plot S1 in the initial land allocation plan is changed in turn, and the single objective function of the new land allocation plan is F(x)=2.34. The use of plot S2 in the initial land allocation plan is changed, and the single objective function of the new land allocation plan is F(x)=2.37. The use of plot S3 in the initial land allocation plan is changed, and the single objective function of the new land allocation plan is F(x)=2.61. The use of plot S4 in the initial land allocation plan is changed, and the single objective function of the new land allocation plan is F(x)=2.33. From these solutions, the land allocation plan (residential, residential, industrial, commercial, ecological protection) corresponding to the single objective function F(x)=2.61 is the current optimal solution.

[0065] To better explain the present invention, in one embodiment of the present invention, in steps S4.3 and S4.4, the upper bound of the current solution If it is smaller than the currently known optimal solution in the solution set or the lower bound F(x) is larger than the currently known optimal solution in the solution set, stop steps S4.3 and S4.4.

[0066] In an embodiment of the present invention, if the value of the single objective function F(x) of the current land allocation plan is less than the currently known optimal solution in the solution set, it means that the current land allocation plan will not be better than the known optimal solution no matter how it is adjusted; if the value of the single objective function F(x) of the current land allocation plan is greater than the currently known optimal solution in the solution set, it means that the current land allocation plan will not be better than the known optimal solution no matter how it is adjusted; through this judgment, those land allocation plans that cannot become the optimal solution can be eliminated as early as possible, thereby reducing unnecessary calculations and improving the efficiency of the entire method.

[0067] In order to better explain the present invention, in one embodiment of the present invention, as Figure 4 As shown, finding the optimal solution in the solution set and inversely obtaining the optimal land allocation solution in the land allocation solution set also includes the following steps:

[0068] S5.1: Split the solution set into multiple sub-solution sets;

[0069] Specifically, in this step, by performing parallel operations on multiple sub-solution sets, the efficiency can be further improved;

[0070] S5.2: traverse each sub-solution set and find the sub-optimal solution in each sub-solution set;

[0071] S5.3: Traverse each sub-optimal solution and obtain the optimal solution. Once the optimal solution is obtained, it can be reversed to the specific land allocation plan.

[0072] In addition, relevant staff can appropriately simplify the multi-objective function Among them, p k is the unit area of ​​the kth piece of land, q k is the impact factor per unit area of ​​the kth piece of land, which can further reduce the amount of calculation.

[0073] Moreover, Figure 5 As shown, the intelligent land use optimization system 100 based on geographic big data disclosed in the present invention includes:

[0074] The first generation module 101 is used to generate all land allocation plans according to geographic big data and form a land allocation plan set;

[0075] The second generating module 102 is used to generate a multi-objective function based on geographic big data;

[0076] The conversion module 103 is used to convert the multi-objective function into a single-objective function and set the corresponding indicator weights;

[0077] A calculation module 104, used to calculate the solution corresponding to each land allocation scheme according to the single objective function and generate a solution set;

[0078] The optimal solution determination module 105 is used to find the optimal solution in the solution set and reversely deduce the optimal land allocation solution in the land allocation solution set.

[0079] Finally, the device disclosed in the present invention comprises: a processor and a memory, wherein the memory stores executable instructions, and when the executable instructions are executed by the processor, the device is capable of executing the intelligent land utilization optimization method based on geographic big data as claimed in any one of claims 1 to 6;

[0080] In summary, the intelligent land use optimization method based on geographic big data disclosed in the present invention can, on the one hand, improve the scientificity and accuracy of land use planning. By integrating geographic big data, it can comprehensively and accurately reflect the actual situation of land resources and complex and changeable utilization needs, thereby avoiding the unscientific and inaccurate planning caused by the traditional method's over-reliance on experience and qualitative analysis, making land use planning more in line with reality and better able to meet the needs of social and economic development; on the other hand, it can balance the interests of all parties. Land use optimization often involves multiple goals and the needs of stakeholders, such as economic benefits, environmental protection, social stability, etc. These goals often conflict with and restrict each other, making land use optimization a complex multi-objective optimization problem. The present invention constructs a multi-objective function and sets corresponding indicator weights to convert the multi-objective problem into a single-objective problem for solution, thereby being able to ensure economic benefits while taking into account environmental protection, social stability and other needs, and achieving a balance of interests of all parties.

[0081] In the description of this specification, those skilled in the art may combine and combine the different embodiments or examples and the features of the different embodiments or examples described in this specification to the extent that there is no contradiction. Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. Those skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. An intelligent land use optimization method based on geographic big data, characterized in that: The following steps are involved: S1: Generate all land allocation plans based on geographic big data and generate a land allocation plan set; S2: Generate a multi-objective function f based on the geographic big data i (x), where x is a land allocation scheme in the land allocation scheme set; S3: The multi-objective function f i (x) is converted into a single objective function Among them, ω i is the corresponding multi-objective function f i (x) indicator weight, ω i satisfy And ω i ≥0; S4: According to the single objective function Calculate the solution corresponding to the land allocation scheme for each x and generate a solution set; S5: Find the optimal solution in the solution set and reversely obtain the optimal land allocation plan in the land allocation plan set.

2. The intelligent land use optimization method based on geographic big data according to claim 1, characterized in that: The method of generating all land allocation plans and generating a land allocation plan set according to geographic big data also includes the following steps: S1.1: Generate constraint conditions C based on the geographic big data j ; S1.2: Eliminate all the land allocation schemes that do not satisfy the constraint condition C j of the land allocation scheme.

3. The intelligent land use optimization method based on geographic big data as claimed in claim 2, characterized in that: According to the single objective function Calculating the solution corresponding to the land allocation scheme for each x and generating a solution set also includes the following steps: S4.1: Select any one of the land allocation schemes in the land allocation scheme set as an initial land allocation scheme; S4.2: Substituting the initial land allocation plan into the single objective function Calculate and obtain the initial solution; S4.3: Change a plot parameter of the initial land allocation scheme to obtain a new land allocation scheme and substitute it into the single objective function Calculate and obtain a new solution; S4.4: If the new solution is better than the previous solution, then change a plot parameter of the new land allocation scheme to obtain another new land allocation scheme and substitute it into the single objective function Calculate and obtain another new solution, repeat steps S4.3 and S4.4 until the solution obtained is no longer better than the previous solution, and stop steps S4.3 and S4.

4.

4. The intelligent land use optimization method based on geographic big data according to claim 3, characterized in that: In steps S4.3 and S4.4, the upper bound of the current solution is If it is smaller than the currently known optimal solution in the solution set or the lower bound F(x) is larger than the currently known optimal solution in the solution set, stop steps S4.3 and S4.

4.

5. The intelligent land use optimization method based on geographic big data according to claim 1, characterized in that: The step of finding the optimal solution in the solution set and inversely obtaining the optimal land allocation solution in the land allocation solution set also includes the following steps: S5.1: Split the solution set into multiple sub-solution sets; S5.2: traverse each of the sub-solution sets and find the sub-optimal solution in each of the sub-solution sets; S5.3: Traverse each of the sub-optimal solutions and obtain the optimal solution.

6. The intelligent land use optimization method based on geographic big data according to claim 1, characterized in that: The multi-objective function Among them, p k is the unit area of ​​the kth piece of land, q k is the impact factor per unit area of ​​the kth piece of land.

7. An intelligent land use optimization system based on geographic big data, characterized in that: include: The first generation module is used to generate all land allocation plans based on geographic big data and form a land allocation plan set; A second generating module is used to generate a multi-objective function based on the geographic big data; A conversion module, used to convert the multi-objective function into a single objective function and set corresponding indicator weights; A calculation module, used to calculate the solution corresponding to each land allocation scheme according to the single objective function and generate a solution set; The optimal solution determination module is used to find the optimal solution in the solution set and reversely deduce the optimal land allocation solution in the land allocation solution set.

8. A device, characterized in that include: A processor and a memory, wherein the memory stores executable instructions, and when the executable instructions are executed by the processor, the device is able to execute the intelligent land use optimization method based on geographic big data as described in any one of claims 1 to 6.

Images