Space utilization layout optimization method and system based on artificial intelligence

Abstract

The invention relates to the technical field of park management, and discloses a space utilization layout optimization method and system based on artificial intelligence, and the method comprises the steps: dividing a target industrial park into W park sub-regions based on the geographic position information of Q to-be-processed assets, calculating a living nuclear density value according to the living space information, and calculating the living nuclear density value according to the living nuclear density value; determining an industrial fusion degree value according to the industrial distribution information, classifying the Q to-be-processed assets based on the dwelling nuclear density value and the industrial fusion degree value, finally determining P park planning layouts according to an asset classification result, and calculating an imbalance index corresponding to each park planning layout, and the P park planning layouts are optimized according to the imbalance index and a preset natural heuristic algorithm, so that the problem that asset classification and regional function collaboration and dwelling and industry fusion cannot be balanced in the prior art is solved, the imbalance of resource distribution of each sub-region in the park is effectively adjusted, and the planning layout of the P parks is optimized. And balanced development of a living function and an industrial function is realized.

Description

Technical Field

[0001] The present invention relates to the field of park management technology, and more specifically, to a space utilization layout optimization method and system based on artificial intelligence. Background Art

[0002] Exploring the optimization methods of the spatial layout of industrial parks has become a key path to promote the sustainable development of industrial parks. Although the existing technology has already involved the relevant content of park layout optimization, there are still some shortcomings in practical application, especially in terms of asset classification and regional functional coordination, residential and industrial integration and other dimensions, the imbalance between various regions in the industrial park has not been fully considered, which makes it impossible to effectively improve the efficiency and overall balance of park resource allocation. It involves the relevant content of park layout optimization, but there are still some shortcomings in practical application, especially in terms of asset classification and regional functional coordination, residential and industrial integration and other dimensions, the imbalance between various regions in the industrial park has not been fully considered, which makes it impossible to effectively improve the efficiency and overall balance of park resource allocation.

[0003] In view of this, the present invention proposes an artificial intelligence-based space utilization layout optimization method and system to solve the above-mentioned problems. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a space utilization layout optimization method and system based on artificial intelligence.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] First, a space utilization layout optimization method based on artificial intelligence is provided, including:

[0007] Obtaining geographic location information of Q assets to be processed in the target industrial park, and dividing the target industrial park into W park sub-areas based on the geographic location information of the Q assets to be processed;

[0008] Obtain the residential space information and industrial distribution information corresponding to each park sub-area, calculate the residential kernel density value based on the residential space information, determine the industrial integration value based on the industrial distribution information, and classify the Q assets to be processed based on the residential kernel density value and the industrial integration value to obtain the asset classification results, which include rental assets, intermediate assets and commercial assets;

[0009] The planning layouts of P parks are determined according to the asset classification results, the imbalance index corresponding to the planning layout of each park is calculated, and the planning layouts of P parks are optimized according to the imbalance index and the preset nature-inspired algorithm to obtain the optimal planning layout.

[0010] Furthermore, the method of dividing the target industrial park into W park sub-areas based on the geographic location information of the Q assets to be processed includes:

[0011] The Q assets to be processed are clustered according to the geographic location information to obtain W target asset sets. The target industrial park is divided into W initial sub-areas according to the W target asset sets. The boundaries of the W initial sub-areas are optimized according to the Voronoi diagram algorithm to obtain W park sub-areas, and the park sub-areas correspond to the target asset sets one by one.

[0012] Furthermore, the residential space information includes the coordinates of each residential point in the park sub-area and the coordinates of the target point. The method for calculating the residential kernel density value according to the residential space information includes:

[0013] The kernel function is accumulated and calculated for the coordinates of each residential point in the sub-area of ​​the park and the coordinates of the target point to obtain the residential kernel density value.

[0014] Furthermore, the industry distribution information includes the industry category ratio, the industry staff ratio and the industry facility density. The method for determining the industry integration value according to the industry distribution information includes:

[0015] The industrial integration value is determined by weighted calculation based on the proportion of industrial categories, the proportion of industrial personnel and the density of industrial facilities.

[0016] Furthermore, the Q assets to be processed are classified based on the residential core density value and the industrial integration value, and the method for obtaining the asset classification result includes:

[0017] Input each asset to be processed and the corresponding residential core density value and industrial integration value into the pre-built asset classification model to obtain the asset classification result.

[0018] Furthermore, the method for determining the planning layout of P parks according to the asset classification results includes:

[0019] According to the asset classification results, the rental assets and commercial assets in the target industrial park are determined. Based on the asset classification results, the asset quantity corresponding to the intermediate assets is obtained. The planning layout of P parks is constructed through the enumeration combination method and the number of assets.

[0020] Furthermore, the method for calculating the imbalance index corresponding to each park planning layout includes:

[0021] The total number of park sub-areas, the number of rental assets in the park sub-areas, the number of commercial assets in the park sub-areas, and the number of assets to be processed in the park sub-areas corresponding to each park planning layout are obtained, and the corresponding imbalance index is obtained based on the total number of park sub-areas, the number of rental assets in the park sub-areas, the number of commercial assets in the park sub-areas, and the number of assets to be processed in the park sub-areas.

[0022] Furthermore, the nature-inspired algorithm is a whale optimization algorithm. The method for optimizing the planning layout of P parks according to the imbalance index and the preset nature-inspired algorithm to obtain the optimal planning layout includes:

[0023] S301: Define the initial number of whales as P and the maximum number of iterations , each initial whale individual is represented as a park planning layout, and the random value rand is a random number sampled from a uniform distribution of [0,1];

[0024] S302: Obtain an imbalance index corresponding to the park planning layout, and use the imbalance index as the target fitness value of the initial whale individual;

[0025] S303: When the random value rand is less than 0.5, a shrinking and encircling strategy is performed; when the random value rand is greater than or equal to 0.5, a spiral hunting strategy is performed;

[0026] S304: Repeat the above S303 to continuously update the park planning layout until the maximum number of iterations is reached When the optimal park planning layout is output, the optimal park planning layout is used as the optimal planning layout.

[0027] Furthermore, the method of performing the shrinking and surrounding strategy includes:

[0028] ;

[0029] in, For the next generation of whale positions, is the current whale position, To pursue the target location, is the shrinkage coefficient of the shrinkage and encirclement strategy, is the control factor of the shrinking and encircling strategy, is the current iteration number.

[0030] In a second aspect, a space utilization layout optimization system based on artificial intelligence is provided, which is used to implement the above-mentioned space utilization layout optimization method based on artificial intelligence, including:

[0031] Area division module: used to obtain the geographical location information of Q assets to be processed in the target industrial park, and divide the target industrial park into W park sub-areas based on the geographical location information of the Q assets to be processed;

[0032] Data processing module: used to obtain the residential space information and industrial distribution information corresponding to each park sub-area, calculate the residential kernel density value according to the residential space information, determine the industrial integration value according to the industrial distribution information, classify the Q assets to be processed based on the residential kernel density value and the industrial integration value, and obtain the asset classification results, which include rental assets, intermediate assets and commercial assets;

[0033] Layout optimization module: used to determine the planning layout of P parks according to the asset classification results, calculate the imbalance index corresponding to the planning layout of each park, optimize the planning layout of P parks according to the imbalance index and the preset natural inspiration algorithm to obtain the optimal planning layout.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention first divides the target industrial park into W park sub-areas based on the geographic location information of Q assets to be processed, then obtains the residential space information and industrial distribution information corresponding to each park sub-area, calculates the residential kernel density value according to the residential space information, determines the industrial integration value according to the industrial distribution information, classifies the Q assets to be processed based on the residential kernel density value and the industrial integration value, obtains the asset classification result, and finally determines P park planning layouts according to the asset classification result, calculates the imbalance index corresponding to each park planning layout, optimizes the P park planning layouts according to the imbalance index and the preset natural inspiration algorithm, and obtains the optimal planning layout. In this way, the present invention divides and analyzes the geographic location information of the assets to be processed, comprehensively considers the residential kernel density value and the industrial integration value, classifies the assets to be processed and constructs a variety of park planning layouts, thereby solving the problem of failing to balance asset classification and regional function coordination, and residential and industrial integration in the prior art; by calculating the imbalance index and using the natural inspiration algorithm to optimize the planning layout, the imbalance of resource distribution in each sub-area in the park is effectively adjusted, and the balanced development of residential function and industrial function is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flow chart of the space utilization layout optimization method based on artificial intelligence in the present invention;

[0037] Figure 2 It is a structural schematic diagram of the space utilization layout optimization system based on artificial intelligence in the present invention;

[0038] Figure 3Schematic diagram of a flow chart of a method for dividing a target industrial park into W park sub-areas based on geographic location information of Q assets to be processed in the present invention;

[0039] Figure 4 It is a flow chart of the method for determining the planning layout of P parks according to the asset classification results in the present invention. DETAILED DESCRIPTION

[0040] 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.

[0041] Example 1

[0042] See also Figure 1 As shown, this embodiment discloses a space utilization layout optimization method based on artificial intelligence, including:

[0043] S10: Obtaining geographic location information of Q assets to be processed in the target industrial park, and dividing the target industrial park into W park sub-areas based on the geographic location information of the Q assets to be processed;

[0044] In this embodiment, the assets to be processed can be office buildings or office buildings, etc. There are mainly two uses for the assets to be processed. One use is to rent the assets to be processed (such as office buildings or office buildings) as commercial office space for use by enterprises, companies, etc., so as to ensure that enterprises in the park have office space and promote commercial activities and economic development in the park. Another use is to rent the assets to be processed to individuals, freelancers or other types of tenants, so as to meet the needs of tenants of different sizes and improve the utilization rate of assets.

[0045] like Figure 3 As shown, the method for dividing the target industrial park into W park sub-areas based on the geographic location information of Q assets to be processed includes:

[0046] The Q assets to be processed are clustered according to the geographic location information to obtain W target asset sets. The target industrial park is divided into W initial sub-areas according to the W target asset sets. The boundaries of the W initial sub-areas are optimized according to the Voronoi diagram algorithm to obtain W park sub-areas, and the park sub-areas correspond to the target asset sets one by one.

[0047] It should be noted that the target asset set refers to a group of assets divided from the assets to be processed, and these assets have spatial similarities. In this embodiment, the method for clustering Q assets to be processed can be to adopt K-means clustering or DBSCAN clustering, and the assets to be processed with similar spatial distances are divided into a target asset set. After obtaining W target asset sets, the target industrial park can be divided into W initial sub-areas in an equal area manner, and there is only one target asset set in each initial sub-area.

[0048] In this embodiment, the Voronoi diagram algorithm refers to a method based on geometric space division, which divides the space into multiple areas through a given set of points (usually called seed points or generating points), so that each point in the space belongs to the area of ​​the seed point closest to it. Then, in this embodiment, the central coordinates of the target asset set can be used as the seed point in the Voronoi diagram algorithm, and then by smoothing or adjusting the boundary lines of each initial sub-area to avoid overly complex or irregular shapes, W park sub-areas are obtained. Boundary optimization through the Voronoi diagram algorithm is a prior art, and this embodiment will not go into details. In the above, the central coordinates of the target asset set refer to the geometric center coordinates of the geographical locations of all assets to be processed in the target asset set.

[0049] S20: Acquire the residential space information and industrial distribution information corresponding to each park sub-area, calculate the residential kernel density value according to the residential space information, determine the industrial integration value according to the industrial distribution information, classify the Q assets to be processed based on the residential kernel density value and the industrial integration value, and obtain the asset classification result, which includes rental assets, intermediate assets and commercial assets;

[0050] In some embodiments, the residential space information includes at least the coordinates of each residential point within the park sub-area and the target point coordinates. The residential point refers to the geographical location of the space or facilities used for living in the park sub-area, including residential buildings, apartments and other buildings for people to live in. The target point coordinates can be the geometric center coordinates of the geographical locations of all assets to be processed in the target asset set. Then, each park sub-area corresponds to a target point coordinate.

[0051] Methods for calculating residential kernel density values ​​based on residential space information include:

[0052] The kernel function is accumulated and calculated for the coordinates of each residential point in the sub-area of ​​the park and the coordinates of the target point to obtain the residential kernel density value.

[0053] The specific methods for calculating the residential kernel density value include:

[0054] RKD= ;

[0055] Where RKD is the residential kernel density value, is the total number of residential areas in the park sub-area, is the Gaussian kernel function, is the target point coordinate, For the The coordinates of the residence point, is the preset search radius.

[0056] In this embodiment, the search radius is a preset fixed value, which is used to limit which residential points around the target point will affect the residential kernel density value. The residential kernel density value represents the distribution density of residential points around the target point, that is, the density of residential space in the sub-area of ​​the park where the target point is located. Through the kernel density analysis method, the residential kernel density value can quantify the distribution characteristics of residential points around the target point. The larger the residential kernel density value, the denser the distribution of residential points in the sub-area of ​​the park where the target point is located, the higher the utilization rate of the residential space, and the larger the residential kernel density value, the assets to be processed should be given priority to be rented out as commercial office space. This is to achieve a balanced development of residence and industry and avoid excessive singleness of functions in the region. Using the assets to be processed as commercial office space can introduce more employment opportunities and economic activities, enhance the industrial function of the region, and balance the needs of residence and industry.

[0057] In some embodiments, the industrial distribution information includes at least the industrial category ratio, the industrial population ratio and the industrial facility density. The industrial category ratio refers to the ratio of the number of people engaged in the secondary industry to the number of people engaged in the tertiary industry. The industrial population ratio refers to the ratio of the number of people engaged in the secondary industry to the number of people engaged in the tertiary industry. The industrial facility density refers to the number of tertiary industry facilities per unit area in the park sub-area.

[0058] Methods for determining the industrial integration value based on industrial distribution information include:

[0059] The industrial integration value is determined by weighted calculation based on the proportion of industrial categories, the proportion of industrial personnel and the density of industrial facilities.

[0060] The specific methods for determining the industrial integration value include:

[0061] IND= ;

[0062] Where IND is the industry integration value, is the hyperbolic cosine function, is a logarithmic function with base e, is the inverse cotangent function, is the density of industrial facilities, is the industry category ratio, is the industry headcount ratio, , are all weight factors, and e is a natural constant.

[0063] In this embodiment, the industrial facility density and the industrial category ratio are used as examples. When the industrial facility density is greater, it indicates that the tertiary industry activities in the park sub-area are more concentrated. When the industrial category ratio is greater, it indicates that the number of secondary industry facilities is significantly greater than that of the tertiary industry, indicating that the park sub-area is dominated by productive activities such as manufacturing and industry. Therefore, from the above content, it can be seen that when the industrial integration value is smaller, it indicates that the industrial structure in the park sub-area is relatively single, the secondary industry occupies a dominant position, and the degree of coordination and integration between industries is low. Therefore, it is necessary to use the assets to be processed as commercial office space to increase the proportion of regional service industries and balance the industrial structure.

[0064] The Q assets to be processed are classified based on the residential kernel density value and the industrial integration value. The method for obtaining the asset classification result includes:

[0065] Each asset to be processed and the corresponding residential core density value and industrial integration value are input into the pre-built asset classification model to obtain the asset classification results, which include rental assets, intermediate assets and commercial assets.

[0066] The construction method of asset classification model includes:

[0067] Obtain Z groups of training data, where Z is a positive integer greater than 1, and the training data include historical pending assets, historical residential kernel density values, historical industrial integration values, and historical asset classification results. Take the historical pending assets, historical residential kernel density values, historical industrial integration values, and historical asset classification results as a sample set, divide the sample set into a training set and a test set, build a classifier, take the historical pending assets, historical residential kernel density values, and historical industrial integration values ​​in the training set as input data, take the historical asset classification results in the training set as output data, train the classifier to obtain an initial classifier, test the initial classifier using the test set, and output a classifier that meets the preset accuracy as an asset classification model. The classifier is preferably a naive Bayes model or a support vector machine model.

[0068] In this embodiment, the asset classification results include rental assets, intermediate assets and commercial assets. It can be understood that when the asset classification result is a rental asset, it means that the asset to be processed needs to be rented to individuals, freelancers or other types of tenants. When the asset classification result is a commercial asset, it means that the asset to be processed needs to be used for commercial office space rental for use by enterprises, companies, etc., and when the asset classification result is an intermediate asset, it means that the asset to be processed can be used for both renting to individuals and commercial office space rental. Therefore, it can be seen from the above content that the larger the residential kernel density value or the higher the residential density value in the sub-area of ​​the park, the higher the residential density value. The smaller the industrial integration value is, the greater the probability that the asset classification result is a commercial asset. Correspondingly, the smaller the residential core density value is or the larger the industrial integration value is in the sub-area of ​​the park, the greater the probability that the asset classification result is a rental asset. Taking the residential core density value as an example, the residential core density value reflects the density of residential distribution in the target area. When the residential core density value is large, it indicates that the residential points in the area are highly concentrated and the residential demand has been fully met or in excess. In areas with large residential core density values, classifying the assets to be processed as commercial assets will help optimize regional functions and promote the coordinated development of the secondary and tertiary industries.

[0069] In this embodiment, the target industrial park is first divided into multiple sub-areas by clustering and dividing the geographic location information of the assets to be processed in the target industrial park, ensuring that the assets to be processed in each sub-area have spatial similarity, laying the foundation for subsequent data analysis, and further obtaining residential space information and industrial distribution information on the basis of the divided park sub-areas, calculating the residential kernel density value and the industrial integration value, which are used to accurately classify the assets to be processed. In this way, balanced development of residential functions and industrial functions can be achieved in different regions, avoiding excessive singleness of regional functions.

[0070] S30: Determine the planning layout of P parks according to the asset classification result, calculate the imbalance index corresponding to each park planning layout, and optimize the planning layout of the P parks according to the imbalance index and a preset natural inspiration algorithm to obtain the optimal planning layout;

[0071] like Figure 4 As shown, the method for determining the planning layout of P parks according to the asset classification results includes:

[0072] According to the asset classification results, the rental assets and commercial assets in the target industrial park are determined. Based on the asset classification results, the asset quantity corresponding to the intermediate assets is obtained. The planning layout of P parks is constructed through the enumeration combination method and the number of assets.

[0073] It should be noted that the park planning layout represents the distribution results of the assets to be processed after classification in the target industrial park, including the specific distribution of rental assets, commercial assets and intermediate assets in the park. Since intermediate assets can be used as rental assets and then rented to individuals, freelancers or other types of tenants, and can also be used as commercial assets for commercial office space rental, there are multiple park planning layouts. In this embodiment, the rental assets and commercial assets are first determined, and then the different allocation methods of the intermediate assets are enumerated by the enumeration combination method, so as to construct multiple park planning layouts. In this way, each park planning layout completely represents the spatial distribution of rental assets, commercial assets and intermediate assets in the target industrial park, and provides a comprehensive initial solution set for the subsequent optimization of the optimal planning layout.

[0074] The methods for calculating the imbalance index corresponding to each park planning layout include:

[0075] The total number of park sub-areas, the number of rental assets in the park sub-areas, the number of commercial assets in the park sub-areas, and the number of assets to be processed in the park sub-areas corresponding to each park planning layout are obtained, and the corresponding imbalance index is obtained based on the total number of park sub-areas, the number of rental assets in the park sub-areas, the number of commercial assets in the park sub-areas, and the number of assets to be processed in the park sub-areas.

[0076] The specific methods for calculating the imbalance index include:

[0077] IMX = ;

[0078] Where IMX is the imbalance index, is the total number of sub-areas in the park, For the The number of rental properties in each park sub-area, No. The number of commercial assets within each park sub-area, For the The number of assets to be processed in each park sub-area, is the inverse cotangent function.

[0079] It can be understood that, from the above content, since the intermediate assets can be used as both rental assets and commercial assets, this embodiment enumerates the different distribution methods of the intermediate assets through the enumeration combination method, thereby constructing multiple park planning layouts. Therefore, there are only rental assets and commercial assets in each park planning layout. Then, in order to avoid too many rental assets or commercial assets in the same park sub-area, this embodiment calculates the imbalance index. The imbalance index represents the degree of balance between the distribution of rental assets and commercial assets in each park sub-area. The imbalance index reflects the distribution balance of rental assets and commercial assets among each sub-area in the park planning layout. The smaller the value, the more balanced the distribution, and the larger the value, the more unbalanced the distribution. It is an important indicator for measuring the rationality of the planning layout.

[0080] The natural heuristic algorithm is a whale optimization algorithm. The method for optimizing the planning layout of P parks according to the imbalance index and the preset natural heuristic algorithm to obtain the optimal planning layout includes:

[0081] S301: Define the initial number of whales as P and the maximum number of iterations , each initial whale individual is represented as a park planning layout, and the random value rand is a random number sampled from a uniform distribution of [0,1];

[0082] S302: Obtain an imbalance index corresponding to the park planning layout, and use the imbalance index as the target fitness value of the initial whale individual;

[0083] It can be understood that the imbalance index corresponds to the "fitness value" in the whale optimization algorithm, which represents the "survival ability" of an individual in the entire group. In the whale optimization algorithm, each individual (whale) has a fitness value to measure the quality of the individual. The smaller the fitness value, the closer the individual is to the optimal solution.

[0084] S303: When the random value rand is less than 0.5, a shrinking and encircling strategy is performed; when the random value rand is greater than or equal to 0.5, a spiral hunting strategy is performed;

[0085] Among them, the shrinking and encircling strategy is implemented, and the whale will shrink and encircle around the optimal solution. The spiral hunting strategy is implemented to simulate the whale moving around the target in a spiral path.

[0086] S304: Repeat S303 to continuously update the park planning layout until the maximum number of iterations is reached When the optimal park planning layout is output, the optimal park planning layout is used as the optimal planning layout.

[0087] In this embodiment, in each iteration, the whale group is continuously updated until the maximum number of iterations is reached. After each iteration, the algorithm will update the weight factor combination of individual whales and calculate the new fitness value. Through repeated iterations, the weight factor combination of individual whales is gradually improved each time, so that the whale group gradually approaches the optimal solution.

[0088] Methods for implementing the shrinking and encircling strategy include:

[0089] ;

[0090] in, For the next generation of whale positions, is the current whale position, To pursue the target location, is the shrinkage coefficient of the shrinkage and encirclement strategy, is the control factor of the shrinking and encircling strategy, is the current iteration number.

[0091] This embodiment allows individual whales to gradually shrink when approaching the optimal solution, accurately adjust the weight factor, and perform local optimization. Through this strategy, individual whales gradually approach the current optimal solution, ensuring a detailed search in the solution space.

[0092] Methods for conducting a spiral hunting strategy include:

[0093] = ;

[0094] in, is the spiral contraction coefficient of the spiral hunting strategy, A random value in the range [-1,1].

[0095] In this embodiment, the target industrial park is first divided into W park sub-areas based on the geographic location information of Q assets to be processed, and then the residential space information and industrial distribution information corresponding to each park sub-area are obtained, the residential kernel density value is calculated according to the residential space information, the industrial integration value is determined according to the industrial distribution information, and the Q assets to be processed are classified based on the residential kernel density value and the industrial integration value to obtain the asset classification result, and finally P park planning layouts are determined according to the asset classification result, and the imbalance index corresponding to each park planning layout is calculated. The P park planning layouts are optimized according to the imbalance index and the preset natural inspiration algorithm to obtain the optimal planning layout. In this way, this embodiment divides and analyzes the geographic location information of the assets to be processed, comprehensively considers the residential kernel density value and the industrial integration value, classifies the assets to be processed and constructs a variety of park planning layouts, thereby solving the problem of failing to balance asset classification and regional function coordination, and residential and industrial integration in the prior art; by calculating the imbalance index and using the natural inspiration algorithm to optimize the planning layout, the imbalance of resource distribution in each sub-area in the park is effectively adjusted, and the balanced development of residential function and industrial function is achieved.

[0096] Example 2

[0097] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a space utilization layout optimization system based on artificial intelligence. For details not provided in this embodiment, please refer to the description of the relevant parts in Embodiment 1. The system includes:

[0098] Area division module: used to obtain the geographical location information of Q assets to be processed in the target industrial park, and divide the target industrial park into W park sub-areas based on the geographical location information of the Q assets to be processed;

[0099] In this embodiment, the assets to be processed can be office buildings or office buildings, etc. There are mainly two uses for the assets to be processed. One use is to rent the assets to be processed (such as office buildings or office buildings) as commercial office space for use by enterprises, companies, etc., so as to ensure that enterprises in the park have office space and promote commercial activities and economic development in the park. Another use is to rent the assets to be processed to individuals, freelancers or other types of tenants, so as to meet the needs of tenants of different sizes and improve the utilization rate of assets.

[0100] The method for dividing the target industrial park into W park sub-areas based on the geographic location information of Q assets to be processed includes:

[0101] The Q assets to be processed are clustered according to the geographic location information to obtain W target asset sets. The target industrial park is divided into W initial sub-areas according to the W target asset sets. The boundaries of the W initial sub-areas are optimized according to the Voronoi diagram algorithm to obtain W park sub-areas, and the park sub-areas correspond to the target asset sets one by one.

[0102] Data processing module: used to obtain the residential space information and industrial distribution information corresponding to each park sub-area, calculate the residential kernel density value according to the residential space information, determine the industrial integration value according to the industrial distribution information, classify the Q assets to be processed based on the residential kernel density value and the industrial integration value, and obtain the asset classification results, which include rental assets, intermediate assets and commercial assets;

[0103] In some embodiments, the residential space information includes at least the coordinates of each residential point within the park sub-area and the target point coordinates. The residential point refers to the geographical location of the space or facilities used for living in the park sub-area, including residential buildings, apartments and other buildings for people to live in. The target point coordinates can be the geometric center coordinates of the geographical locations of all assets to be processed in the target asset set. Then, each park sub-area corresponds to a target point coordinate.

[0104] Methods for calculating residential kernel density values ​​based on residential space information include:

[0105] The kernel function is accumulated and calculated for the coordinates of each residential point in the sub-area of ​​the park and the coordinates of the target point to obtain the residential kernel density value.

[0106] The specific methods for calculating the residential kernel density value include:

[0107] RKD= ;

[0108] Where RKD is the residential kernel density value, is the total number of residential areas in the park sub-area, is the Gaussian kernel function, is the target point coordinate, For the The coordinates of the residence, is the preset search radius.

[0109] Methods for determining the industrial integration value based on industrial distribution information include:

[0110] The industrial integration value is determined by weighted calculation based on the proportion of industrial categories, the proportion of industrial personnel and the density of industrial facilities.

[0111] The specific methods for determining the industrial integration value include:

[0112] IND= ;

[0113] Where IND is the industry integration value, is the hyperbolic cosine function, is a logarithmic function with base e, is the inverse cotangent function, is the density of industrial facilities, is the industry category ratio, is the industry headcount ratio, , are all weight factors, and e is a natural constant.

[0114] The Q assets to be processed are classified based on the residential kernel density value and the industrial integration value. The method for obtaining the asset classification result includes:

[0115] Each asset to be processed and the corresponding residential core density value and industrial integration value are input into the pre-built asset classification model to obtain the asset classification results, which include rental assets, intermediate assets and commercial assets.

[0116] The construction method of asset classification model includes:

[0117] Obtain Z groups of training data, where Z is a positive integer greater than 1, and the training data include historical pending assets, historical residential kernel density values, historical industrial integration values, and historical asset classification results. Take the historical pending assets, historical residential kernel density values, historical industrial integration values, and historical asset classification results as a sample set, divide the sample set into a training set and a test set, build a classifier, take the historical pending assets, historical residential kernel density values, and historical industrial integration values ​​in the training set as input data, take the historical asset classification results in the training set as output data, train the classifier to obtain an initial classifier, test the initial classifier using the test set, and output a classifier that meets the preset accuracy as an asset classification model. The classifier is preferably a naive Bayes model or a support vector machine model.

[0118] Layout optimization module: used to determine the planning layout of P parks according to the asset classification results, calculate the imbalance index corresponding to the planning layout of each park, optimize the planning layout of P parks according to the imbalance index and the preset natural inspiration algorithm, and obtain the optimal planning layout;

[0119] Methods for determining the planning layout of P parks based on the asset classification results include:

[0120] According to the asset classification results, the rental assets and commercial assets in the target industrial park are determined. Based on the asset classification results, the asset quantity corresponding to the intermediate assets is obtained. The planning layout of P parks is constructed through the enumeration combination method and the number of assets.

[0121] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0122] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may 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 invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may 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 may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may 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 may be a solid-state hard disk.

[0123] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention 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 the present invention.

[0124] 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.

[0125] In the several embodiments provided by the present invention, 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 one, and 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.

[0126] 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.

[0127] In addition, each functional unit in each embodiment of the present invention 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.

[0128] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

[0129] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A space utilization layout optimization method based on artificial intelligence, characterized in that: include: Obtaining geographic location information of Q assets to be processed in the target industrial park, and dividing the target industrial park into W park sub-areas based on the geographic location information of the Q assets to be processed; Obtain the residential space information and industrial distribution information corresponding to each park sub-area, calculate the residential kernel density value based on the residential space information, determine the industrial integration value based on the industrial distribution information, and classify the Q assets to be processed based on the residential kernel density value and the industrial integration value to obtain the asset classification results, which include rental assets, intermediate assets and commercial assets; The planning layouts of P parks are determined according to the asset classification results, the imbalance index corresponding to the planning layout of each park is calculated, and the planning layouts of P parks are optimized according to the imbalance index and the preset nature-inspired algorithm to obtain the optimal planning layout.

2. The method for optimizing space utilization layout based on artificial intelligence according to claim 1, characterized in that: The method for dividing the target industrial park into W park sub-areas based on the geographic location information of Q assets to be processed includes: The Q assets to be processed are clustered according to the geographic location information to obtain W target asset sets. The target industrial park is divided into W initial sub-areas according to the W target asset sets. The boundaries of the W initial sub-areas are optimized according to the Voronoi diagram algorithm to obtain W park sub-areas, and the park sub-areas correspond to the target asset sets one by one.

3. The method for optimizing space utilization layout based on artificial intelligence according to claim 1, characterized in that: The residential space information includes the coordinates of each residential point in the park sub-area and the coordinates of the target point. The method for calculating the residential kernel density value according to the residential space information includes: The kernel function is accumulated and calculated for the coordinates of each residential point in the sub-area of ​​the park and the coordinates of the target point to obtain the residential kernel density value.

4. The method for optimizing space utilization layout based on artificial intelligence according to claim 3 is characterized in that: The industrial distribution information includes industrial category ratio, industrial staff ratio and industrial facility density. The method for determining the industrial integration value according to the industrial distribution information includes: The industrial integration value is determined by weighted calculation based on the proportion of industrial categories, the proportion of industrial personnel and the density of industrial facilities.

5. The method for optimizing space utilization layout based on artificial intelligence according to claim 4 is characterized in that: The method of classifying Q assets to be processed based on the residential kernel density value and the industrial integration value to obtain the asset classification result includes: Input each asset to be processed and the corresponding residential core density value and industrial integration value into the pre-built asset classification model to obtain the asset classification result.

6. The method for optimizing space utilization layout based on artificial intelligence according to claim 5, characterized in that: The method for determining the planning layout of P parks according to the asset classification results includes: According to the asset classification results, the rental assets and commercial assets in the target industrial park are determined. Based on the asset classification results, the asset quantity corresponding to the intermediate assets is obtained. The planning layout of P parks is constructed through the enumeration combination method and the number of assets.

7. The method for optimizing space utilization layout based on artificial intelligence according to claim 6, characterized in that: The method for calculating the imbalance index corresponding to each park planning layout includes: The total number of park sub-areas, the number of rental assets in the park sub-areas, the number of commercial assets in the park sub-areas, and the number of assets to be processed in the park sub-areas corresponding to each park planning layout are obtained, and the corresponding imbalance index is obtained based on the total number of park sub-areas, the number of rental assets in the park sub-areas, the number of commercial assets in the park sub-areas, and the number of assets to be processed in the park sub-areas.

8. The method for optimizing space utilization layout based on artificial intelligence according to claim 7, characterized in that: The natural heuristic algorithm is a whale optimization algorithm. The method for optimizing the planning layout of P parks according to the imbalance index and the preset natural heuristic algorithm to obtain the optimal planning layout includes: S301: Define the initial number of whales as P and the maximum number of iterations , each initial whale individual is represented as a park planning layout, and the random value rand is a random number sampled from a uniform distribution of [0,1]; S302: Obtain an imbalance index corresponding to the park planning layout, and use the imbalance index as the target fitness value of the initial whale individual; S303: When the random value rand is less than 0.5, a shrinking and encircling strategy is performed; when the random value rand is greater than or equal to 0.5, a spiral hunting strategy is performed; S304: Repeat S303 to continuously update the park planning layout until the maximum number of iterations is reached When the optimal park planning layout is output, the optimal park planning layout is used as the optimal planning layout.

9. The method for optimizing space utilization layout based on artificial intelligence according to claim 8, characterized in that: The method for performing the shrinking and surrounding strategy comprises: ； in, For the next generation of whale positions, is the current whale position, To pursue the target location, is the shrinkage coefficient of the shrinkage and encirclement strategy, is the control factor of the shrinking and encircling strategy, is the current iteration number.

10. A space utilization layout optimization system based on artificial intelligence, which is used to implement the space utilization layout optimization method based on artificial intelligence according to any one of claims 1 to 9, characterized in that: include: Area division module: used to obtain the geographical location information of Q assets to be processed in the target industrial park, and divide the target industrial park into W park sub-areas based on the geographical location information of the Q assets to be processed; Data processing module: used to obtain the residential space information and industrial distribution information corresponding to each park sub-area, calculate the residential kernel density value according to the residential space information, determine the industrial integration value according to the industrial distribution information, classify the Q assets to be processed based on the residential kernel density value and the industrial integration value, and obtain the asset classification results, which include rental assets, intermediate assets and commercial assets; Layout optimization module: used to determine the planning layout of P parks according to the asset classification results, calculate the imbalance index corresponding to the planning layout of each park, optimize the planning layout of P parks according to the imbalance index and the preset natural inspiration algorithm to obtain the optimal planning layout.

Images