A public facility layout optimization method based on artificial intelligence

Abstract

The application relates to the technical field of artificial intelligence, in particular to a public facility layout optimization method based on artificial intelligence, which comprises the following steps: collecting basic data of a public facility layout, sequentially performing cleaning, denoising, weight reduction formatting and feature extraction on the basic data to obtain layout basic features, and mapping the public facility layout into a layout state vector according to the layout basic features; determining the utilization rate of the public facility per unit time based on the actual service amount of the public facility and the design capacity of the public facility to determine whether the space-demand adaptation degree of the public facility layout meets the requirements; determining whether the increment step of the public facility site selection coordinate needs to be reduced according to the spatial Gini coefficient of the public facility layout; and determining the error feedback gain of layout optimization based on the service demand coverage rate of the public facility. The application improves the space-demand adaptation degree of the public facility layout.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a method for optimizing the layout of public facilities based on artificial intelligence. Background Technology

[0002] Against the backdrop of new urbanization and smart city construction, AI-based public facility layout optimization methods have become a key technology for improving urban operational efficiency, promoting equitable resource allocation, and enhancing the quality of public services. Since public facility layout involves the coordination of complex factors across multiple dimensions, including population distribution, transportation networks, land use, environmental carrying capacity, and social equity, its planning directly impacts residents' convenience and urban sustainability. While existing digital planning tools support basic geographic information system analysis and simple optimization models, they often focus on single objectives or limited constraints. Furthermore, they lack the ability to integrate multi-source spatiotemporal data, perform dynamic optimization under complex constraints, and integrate real-time public participation feedback. This makes it difficult to achieve efficient, equitable, and feasible automated layout recommendations in practical urban planning. Therefore, there is an urgent need for an AI-based public facility layout optimization method that can integrate multi-objective reinforcement learning to achieve accurate prediction of multi-scale demands, autonomous optimization under diverse constraints, and a holistic balance between social benefits and operating costs.

[0003] Chinese Patent Publication No. CN114821816A discloses an AI-based method for optimizing the layout of fitness venues, comprising: tracking each user entering the fitness venue to obtain their activity trajectory; determining the user's dwell position and dwell time based on the activity trajectory to obtain the user's fitness intention; statistically analyzing the fitness intentions of all users within a fixed time period, and obtaining a reference usage time for each fitness facility based on the fitness intentions of all users and the theoretical fitness time of different types of fitness facilities; obtaining the usage time of each fitness facility within the fixed time period, and obtaining a first popularity of each fitness facility by the difference between the usage time and the corresponding reference usage time; obtaining the region of interest for each trajectory point in each user's activity trajectory, and selecting fitness facilities of the same type as the fitness facility ultimately selected by the user within each region of interest, and generating a description vector based on its usage information, the number of nearby waiting users, the distance to the nearest fitness facility of a different type, and environmental layout information; obtaining a popularity optimization parameter for each fitness facility through the description vector; and using the product of the popularity optimization parameter and the corresponding first popularity as the actual popularity of the fitness facility. Therefore, it can be seen that the AI-based fitness venue layout optimization method has the problem of insufficient spatial-demand adaptability of public facility layout due to its reliance on local historical behavior data and a single heat balance target, which fails to fully integrate multi-dimensional spatiotemporal constraints and dynamic demand changes. Summary of the Invention

[0004] To address this, the present invention provides an artificial intelligence-based method for optimizing the layout of public facilities, thereby overcoming the problem in existing technologies where the reliance on local historical behavioral data and a single heat balance objective fails to fully integrate multi-dimensional spatiotemporal constraints and dynamic demand changes, resulting in insufficient spatial-demand adaptability of public facility layout.

[0005] To achieve the above objectives, the present invention provides a public facility layout optimization method based on artificial intelligence, comprising:

[0006] Collect basic data on the layout of public facilities, and then perform cleaning, noise reduction, deduplication and formatting, and feature extraction on the basic data to obtain basic layout features. Based on the basic layout features, the layout of public facilities is mapped into a layout state vector.

[0007] The initial model is trained by combining user needs and the layout state vector to obtain an intelligent layout optimization model. The basic data of the public facility layout is analyzed based on the intelligent layout optimization model to output a layout optimization scheme.

[0008] Obtain the actual service volume and design capacity of public facilities, and determine the utilization rate of public facilities per unit time based on the actual service volume and design capacity of public facilities to determine whether the space-demand adaptability of the public facility layout meets the requirements;

[0009] If the spatial-demand fit of the public facility layout does not meet the requirements, the spatial Gini coefficient of the public facility layout is obtained to determine whether the spatial connectivity of the public facility layout meets the requirements.

[0010] If the spatial connectivity of the public facility layout does not meet the requirements, the spatial Gini coefficient of the public facility layout shall be used to determine whether it is necessary to reduce the incremental step size of the public facility site selection coordinates.

[0011] If it is not necessary to reduce the incremental step size of the location coordinates of public facilities, the error feedback gain for layout optimization is determined based on the service demand coverage of public facilities.

[0012] Furthermore, based on the actual service volume and design capacity of the public facilities, the utilization rate of the public facilities per unit time is determined to determine whether the space-demand fit of the public facility layout meets the requirements, including:

[0013] The utilization rate of the public facility per unit time is obtained by using the ratio of the actual service volume of the public facility to the designed capacity of the public facility.

[0014] The utilization rate of public facilities per unit time is compared with the preset utilization rate;

[0015] If the utilization rate of public facilities per unit time is greater than the preset utilization rate, then the space-demand fit of the public facility layout is determined to meet the requirements.

[0016] If the utilization rate of public facilities per unit time is less than or equal to the preset utilization rate, then the space-demand fit of the public facility layout is determined to be unsatisfactory.

[0017] Furthermore, given that the spatial-demand fit of the public facility layout does not meet the requirements, the spatial connectivity of the public facility layout is determined based on the spatial Gini coefficient of the public facility layout.

[0018] Furthermore, the spatial connectivity of public facility layouts is determined based on the spatial Gini coefficient, including:

[0019] The spatial Gini coefficient of the public facility layout is compared with the preset first spatial Gini coefficient;

[0020] If the spatial Gini coefficient of the public facility layout is less than or equal to the preset first spatial Gini coefficient, then the spatial connectivity of the public facility layout is determined to meet the requirements.

[0021] If the spatial Gini coefficient of the public facility layout is greater than the preset first spatial Gini coefficient, then the spatial connectivity of the public facility layout is determined to be non-compliant.

[0022] Further, determine whether it is necessary to reduce the incremental step size of the public facility site selection coordinates, including:

[0023] The spatial Gini coefficient of the public facility layout is compared with the preset first spatial Gini coefficient and the preset second spatial Gini coefficient, respectively;

[0024] If the spatial Gini coefficient of the public facility layout is greater than the preset first spatial Gini coefficient and less than or equal to the preset second spatial Gini coefficient, the incremental step size of the public facility site selection coordinates is reduced.

[0025] If the spatial Gini coefficient of the public facility layout is greater than the preset second spatial Gini coefficient, there is no need to reduce the incremental step size of the public facility site selection coordinates.

[0026] Furthermore, the reduction in the incremental step size of the public facility site selection coordinates is determined by the difference between the spatial Gini coefficient of the public facility layout and the preset first spatial Gini coefficient.

[0027] Furthermore, based on the condition that the spatial Gini coefficient of the public facility layout is greater than the preset second spatial Gini coefficient, it is initially determined that the accuracy of the estimated service demand content does not meet the requirements, and the accuracy of the estimated service demand content is determined based on the service demand coverage rate of the public facilities.

[0028] Furthermore, the accuracy of the estimated service demand content based on the service demand coverage rate of the public facilities is determined to meet the requirements, including:

[0029] Compare the service demand coverage rate of public facilities with the preset coverage rate;

[0030] If the service demand coverage rate of the public facility is greater than the preset coverage rate, then it is determined that the accuracy of the estimated service demand content meets the requirements, and it is determined whether the incremental step size of the public facility site selection coordinates meets the requirements.

[0031] If the service demand coverage rate of the public facility is less than or equal to the preset coverage rate, it is determined that the accuracy of the estimated service demand content does not meet the requirements, and the error feedback gain of the layout optimization is increased.

[0032] Furthermore, the service demand coverage rate of the public facilities is the ratio of the number of services actually provided by the public facilities in a unit area to the total number of user demands.

[0033] Furthermore, the increase in the error feedback gain of the layout optimization is determined by the difference between the preset coverage rate and the service demand coverage rate of the public facility.

[0034] Compared with existing technologies, the beneficial effects of this invention are that the method of this invention determines whether the spatial-demand fit of the public facility layout meets the requirements by determining the utilization rate of the public facility per unit time based on the actual service volume and the designed capacity of the public facility. Since the designed capacity of public facilities is usually set based on historical data and population density, it does not fully consider the actual growth demand of the current area, leading to a gap between the service volume and the designed capacity, resulting in insufficient regional services or wasted facility resources. By determining the fit between the service volume and the designed capacity, it is possible to systematically evaluate whether the public facility layout can reasonably match the current demand, promptly identify areas where facilities cannot effectively serve, and provide a theoretical basis for optimizing the layout. The incremental coordinates of the public facility site selection are based on the spatial Gini coefficient of the public facility layout. The step size is adjusted because the spatial distribution of public facilities in the layout is too concentrated or uneven, resulting in insufficient or excessive service capacity of public facilities in some areas. By reducing the incremental step size of adjusting the site selection coordinates, the layout of facilities can be optimized, the service differences caused by spatial unevenness can be reduced, and spatial connectivity can be improved. The error feedback gain of the layout optimization is adjusted according to the service demand coverage of public facilities. Since the prediction results of service demand do not take into account regional differences, the prediction of demand in some areas is not accurate enough, and the accuracy of the prediction of service demand content is biased. By increasing the error feedback gain, the optimization process can be made more sensitive to demand prediction errors, making the layout optimization more accurate, ensuring that public facilities can be reasonably configured according to the actual service demand, improving the overall service efficiency, and improving the spatial-demand adaptability of the public facility layout.

[0035] Furthermore, the method described in this invention determines whether the spatial-demand fit of the public facility layout meets the requirements by setting a preset utilization rate. Since the design capacity of public facilities is usually set based on historical data and population density, it does not fully consider the actual growth demand of the current area, resulting in a gap between the service volume and the design capacity, leading to insufficient regional services or waste of facility resources. By determining the fit between the service volume and the design capacity, it is possible to systematically evaluate whether the public facility layout can reasonably match the current demand, promptly identify areas where facilities cannot effectively serve, and provide a theoretical basis for optimizing the layout, thereby further improving the spatial-demand fit of the public facility layout.

[0036] Furthermore, the method of the present invention adjusts the incremental step size of the location coordinates of public facilities by setting a preset first spatial Gini coefficient and a preset second spatial Gini coefficient. Since the spatial distribution of public facilities in the layout is too concentrated or uneven, the service capacity of public facilities in some areas is insufficient or excessive. By reducing the incremental step size of the location coordinates, the layout of facilities can be optimized, the service differences caused by spatial unevenness can be reduced, spatial connectivity can be improved, and the spatial-demand adaptability of the layout of public facilities can be further improved.

[0037] Furthermore, the method described in this invention adjusts the error feedback gain of layout optimization by setting a preset coverage rate. Since the prediction results of service demand do not take into account regional differences, the prediction of demand in some areas is not accurate enough, and the accuracy of the prediction of service demand content deviates. By increasing the error feedback gain, the optimization process can be made more sensitive to demand prediction errors, making the layout optimization more accurate, ensuring that public facilities can be reasonably configured according to the actual service demand, improving the overall service efficiency, and further improving the spatial-demand adaptability of public facility layout. Attached Figure Description

[0038] Figure 1 This is an overall flowchart of the public facility layout optimization method based on artificial intelligence according to an embodiment of the present invention;

[0039] Figure 2 This is a flowchart illustrating the process of determining whether the spatial connectivity of a public facility layout meets the requirements using an artificial intelligence-based public facility layout optimization method according to an embodiment of the present invention.

[0040] Figure 3 This is a flowchart illustrating the process of determining the incremental step size of public facility site selection coordinates using the artificial intelligence-based public facility layout optimization method according to an embodiment of the present invention.

[0041] Figure 4 This is a flowchart illustrating the process of determining the error feedback gain for layout optimization using an artificial intelligence-based public facility layout optimization method according to an embodiment of the present invention. Detailed Implementation

[0042] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0043] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0044] Please see Figure 1As shown, it is an overall flowchart of the public facility layout optimization method based on artificial intelligence according to an embodiment of the present invention.

[0045] This invention provides a method for optimizing the layout of public facilities based on artificial intelligence, comprising:

[0046] Step S1: Collect basic data on the layout of public facilities, and perform cleaning, noise reduction, redundancy reduction and formatting, and feature extraction on the basic data in sequence to obtain basic layout features. Map the layout of public facilities into a layout state vector based on the basic layout features.

[0047] Step S2: Train the initial model by combining user needs and the layout state vector to obtain an intelligent layout optimization model; Analyze the basic data of the public facility layout based on the intelligent layout optimization model to output a layout optimization scheme.

[0048] Step S3: Obtain the actual service volume and design capacity of the public facilities, and determine the utilization rate of the public facilities per unit time based on the actual service volume and design capacity of the public facilities to determine whether the space-demand adaptability of the public facility layout meets the requirements.

[0049] Step S4: If the spatial-demand fit of the public facility layout does not meet the requirements, then obtain the spatial Gini coefficient of the public facility layout to determine whether the spatial connectivity of the public facility layout meets the requirements.

[0050] Step S5: If the spatial connectivity of the public facility layout does not meet the requirements, determine whether it is necessary to reduce the incremental step size of the public facility site selection coordinates based on the spatial Gini coefficient of the public facility layout.

[0051] Step S6: If it is not necessary to reduce the incremental step size of the location coordinates of public facilities, then determine the error feedback gain of layout optimization based on the service demand coverage of public facilities.

[0052] Specifically, the basic data for the layout of public facilities includes urban building boundary data, urban population density data, and land use attribute data.

[0053] Specifically, the basic characteristics of the layout include space occupancy rate, regional population density, and the proportion of buildable area.

[0054] Specifically, the layout state vector is a vectorized representation of the state information of public facilities in each spatial unit, and each state vector corresponds to a basic layout feature index.

[0055] Specifically, the process of mapping the layout of public facilities into a layout state vector based on the basic layout features is as follows: the layout area of ​​public facilities is divided into regular spatial units with equal side lengths and equal spacing. The basic layout features of public facilities in each spatial unit are combined into a layout state vector. Among them, numerical features are represented by normalized numerical values, classification features are represented by identifier values, and derived indicators are calculated through the basic features.

[0056] Specifically, user needs include requirements for facility type, facility opening hours, and capacity.

[0057] Specifically, the process of training the initial model by combining user needs and layout state vectors to obtain the intelligent layout optimization model involves taking the layout state vector of each spatial unit and the corresponding service requirements as model inputs, adjusting the model parameters by minimizing the loss function of service coverage error and demand satisfaction gap, so that the model can predict the service satisfaction level, spatial connectivity and resource utilization under different layout schemes, iteratively updating the model parameters until the service indicators of the layout scheme convergence conditions are output, thus obtaining the intelligent layout optimization model.

[0058] Specifically, the initial model is a model framework with the ability to predict service demand and make optimization decisions.

[0059] Specifically, the intelligent layout optimization model can be a convolutional neural network, a temporal model, or a deep Q-network, with a preferred embodiment being a convolutional neural network.

[0060] Specifically, the process of analyzing the basic data of public facility layout based on the intelligent layout optimization model to output layout optimization schemes involves inputting the layout state vector and service demand content into the model, predicting the performance of the existing layout in terms of service coverage, spatial connectivity, facility utilization and balance, generating candidate layout schemes based on preset optimization goals, and finally quantitatively evaluating the candidate schemes and outputting the optimal or optional layout scheme.

[0061] Specifically, the actual service volume of public facilities refers to the number of users who actually receive and complete the services provided by the public facilities.

[0062] Specifically, the design capacity of public facilities is the maximum number of users that can be served under standard operating conditions, determined based on the facility's scale and technical specifications.

[0063] Specifically, the layout optimization plan includes facility location coordinates, facility design capacity, and facility type allocation plan.

[0064] Specifically, the spatial connectivity of public facility layout refers to the existence of the shortest effective path that satisfies the passage rules between public facility services and users within a spatial unit.

[0065] Specifically, the incremental step size of the public facility site selection coordinates is used to limit the maximum allowable spatial adjustment of the site selection coordinates of the facility candidates in a single iteration during the optimization process of public facility site selection.

[0066] Specifically, the error feedback gain of layout optimization is a key parameter used to adjust the correction strength of facility coordinate errors or position deviations by adjusting the update magnitude of each optimization iteration of the public facility layout.

[0067] In practice, the method of this invention determines the utilization rate of public facilities per unit time based on the actual service volume and design capacity of the facilities, thereby assessing whether the spatial-demand fit of the public facility layout meets requirements. Since the design capacity of public facilities is typically set based on historical data and population density, it often fails to fully consider the actual growth demand of the current area, leading to a gap between service volume and design capacity. This results in insufficient regional services or wasted facility resources. By determining the fit between service volume and design capacity, the method can systematically evaluate whether the public facility layout can reasonably match current demand, promptly identify areas where facilities cannot effectively serve, and provide a theoretical basis for layout optimization. The incremental step size of the public facility site selection coordinates is adjusted based on the spatial Gini coefficient of the public facility layout. Because the spatial distribution of public facilities in the layout is too concentrated or uneven, the service capacity of public facilities in some areas is insufficient or excessive. By reducing the incremental step size of adjusting the site selection coordinates, the layout of facilities can be optimized, the service differences caused by spatial unevenness can be reduced, and spatial connectivity can be improved. The error feedback gain of the layout optimization is adjusted according to the service demand coverage of public facilities. Since the prediction results of service demand do not take into account regional differences, the prediction of demand in some areas is not accurate enough, and the accuracy of the prediction of service demand content is biased. By increasing the error feedback gain, the optimization process can be made more sensitive to the demand prediction error, making the layout optimization more accurate, ensuring that public facilities can be reasonably allocated according to the actual service demand, improving the overall service efficiency, and improving the spatial-demand adaptability of the public facility layout.

[0068] Please continue reading. Figure 2 The diagram shown is a logical flowchart illustrating the process by which the public facility layout optimization method based on artificial intelligence, according to an embodiment of the present invention, determines whether the spatial connectivity of the public facility layout meets the requirements.

[0069] Specifically, the utilization rate of the public facilities per unit time is determined based on the actual service volume and design capacity of the public facilities to determine whether the space-demand fit of the public facility layout meets the requirements, including:

[0070] The utilization rate of the public facility per unit time is obtained by using the ratio of the actual service volume of the public facility to the designed capacity of the public facility.

[0071] The utilization rate of public facilities per unit time is compared with the preset utilization rate;

[0072] If the utilization rate of public facilities per unit time is greater than the preset utilization rate, then the space-demand fit of the public facility layout is determined to meet the requirements.

[0073] If the utilization rate of public facilities per unit time is less than or equal to the preset utilization rate, then the space-demand fit of the public facility layout is determined to be unsatisfactory.

[0074] Understandably, in AI-based public facility layout optimization methods, the use of preset utilization rates to characterize the spatial-demand adaptability of public facility layouts involves transforming the qualitative assessment of public facility layout adaptability into a quantifiable utilization rate indicator. By using preset thresholds, it's possible to determine whether the service capacity of facilities in different areas meets actual needs, thus providing a clear basis for layout optimization. Preset utilization rates can be set according to actual operating conditions. The setting of preset utilization rates aims to ensure the spatial-demand adaptability and practicality of public facility layouts. Optionally, the preset utilization rate is determined through a limited number of trials by evaluating the optimization effect of public facility utilization rates within different unit times. The determined preset utilization rate should be neither too low nor excessively disruptive to the public facility layout optimization process. For example, the preset utilization rate is typically selected within the range of [75%, 85%].

[0075] Preferably, the preset utilization rate is 80% in the preferred embodiment.

[0076] Specifically, the utilization rate of public facilities per unit time is the ratio of the actual capacity of public facilities used per unit time to their maximum designed available capacity.

[0077] Specifically, the method described in this invention determines whether the spatial-demand fit of the public facility layout meets the requirements by setting a preset utilization rate. Since the design capacity of public facilities is usually set based on historical data and population density, it does not fully consider the actual growth demand of the current area, resulting in a gap between the service volume and the design capacity, leading to insufficient regional services or waste of facility resources. By determining the fit between the service volume and the design capacity, it is possible to systematically evaluate whether the public facility layout can reasonably match the current demand, promptly identify areas where facilities cannot effectively serve, and provide a theoretical basis for optimizing the layout, thereby further improving the spatial-demand fit of the public facility layout.

[0078] Please continue reading. Figure 3The diagram shown is a logical flowchart illustrating the process of determining the incremental step size of public facility site selection coordinates using the artificial intelligence-based public facility layout optimization method according to an embodiment of the present invention.

[0079] Specifically, under the condition that the spatial-demand fit of the public facility layout does not meet the requirements, the spatial connectivity of the public facility layout is determined based on the spatial Gini coefficient of the public facility layout.

[0080] Specifically, determining whether the spatial connectivity of public facility layouts meets requirements based on the spatial Gini coefficient includes:

[0081] The spatial Gini coefficient of the public facility layout is compared with the preset first spatial Gini coefficient;

[0082] If the spatial Gini coefficient of the public facility layout is less than or equal to the preset first spatial Gini coefficient, then the spatial connectivity of the public facility layout is determined to meet the requirements.

[0083] If the spatial Gini coefficient of the public facility layout is greater than the preset first spatial Gini coefficient, then the spatial connectivity of the public facility layout is determined to be non-compliant.

[0084] Specifically, determining whether it is necessary to reduce the incremental step size of the coordinates for public facility site selection includes:

[0085] The spatial Gini coefficient of the public facility layout is compared with the preset first spatial Gini coefficient and the preset second spatial Gini coefficient, respectively;

[0086] If the spatial Gini coefficient of the public facility layout is greater than the preset first spatial Gini coefficient and less than or equal to the preset second spatial Gini coefficient, the incremental step size of the public facility site selection coordinates is reduced.

[0087] If the spatial Gini coefficient of the public facility layout is greater than the preset second spatial Gini coefficient, there is no need to reduce the incremental step size of the public facility site selection coordinates.

[0088] It is understandable that the preset first spatial Gini coefficient is less than the preset second spatial Gini coefficient. The three intervals divided by the preset first spatial Gini coefficient and the preset second spatial Gini coefficient correspond to three different situations:

[0089] The first interval is where the spatial Gini coefficient of the public facility layout is less than or equal to the preset first spatial Gini coefficient. The corresponding situation is: the spatial connectivity of the public facility layout meets the requirements, and no adjustment is needed.

[0090] The second interval is when the spatial Gini coefficient of the public facility layout is greater than the preset first spatial Gini coefficient and less than or equal to the preset second spatial Gini coefficient. The corresponding situation is: due to the excessively concentrated or uneven spatial distribution of public facilities in the layout, the service capacity of public facilities in some areas is insufficient or excessive. In this case, it is necessary to reduce the incremental step size of the public facility site selection coordinates.

[0091] The third interval is where the spatial Gini coefficient of public facility layout is greater than the preset second spatial Gini coefficient. The corresponding situation is that the prediction results of service demand do not take into account regional differences, resulting in inaccurate prediction of demand in some areas and deviation in the accuracy of the prediction of service demand content. At this time, it is necessary to further judge whether the accuracy of the prediction of service demand content meets the requirements.

[0092] Understandably, in AI-based public facility layout optimization methods, the use of preset first and second spatial Gini coefficients to characterize the spatial connectivity of the public facility layout is based on the core logic of transforming the abstract judgment of spatial connectivity into a quantifiable spatial Gini coefficient range judgment through the correlation between the spatial Gini coefficient and the spatial connectivity of the public facility layout. The preset first spatial Gini coefficient serves as the dividing line for distinguishing whether the spatial connectivity of the public facility layout meets the requirements, and the preset second spatial Gini coefficient serves as the dividing line for the causes of the spatial connectivity of the public facility layout not meeting the requirements, thus providing clear triggering conditions for subsequent optimization. The preset utilization rate can be set according to actual working conditions. The setting of the preset first and second spatial Gini coefficients aims to ensure the spatial-demand adaptability and practicality of the public facility layout. Optionally, the preset first and second spatial Gini coefficients are determined through a limited number of experiments by evaluating the optimization effect of different spatial Gini coefficients on the public facility layout. The determined preset first and second spatial Gini coefficients should satisfy the condition that they are neither too small nor cause excessive interference to the optimization process of the public facility layout. For example, the preset first spatial Gini coefficient is generally selected in the range of [0.24, 0.26], and the preset second spatial Gini coefficient is generally selected in the range of [0.39, 0.41].

[0093] Preferably, the first spatial Gini coefficient is preset to 0.25 in a preferred embodiment, and the second spatial Gini coefficient is preset to 0.4 in a preferred embodiment.

[0094] Specifically, the spatial Gini coefficient of public facility layout is an indicator used to measure the degree of uneven distribution of public facilities among spatial units in the layout. That is, the larger the spatial Gini coefficient, the higher the degree of uneven distribution of public facilities among spatial units in the layout.

[0095] Specifically, the reduction in the incremental step size of the public facility site selection coordinates is determined by the difference between the spatial Gini coefficient of the public facility layout and the preset first spatial Gini coefficient.

[0096] Specifically, when the difference between the spatial Gini coefficient of the public facility layout and the preset first spatial Gini coefficient is within 0.04, the incremental step size of the public facility location coordinates is reduced to 0.9 times the original value. When the difference between the spatial Gini coefficient of the public facility layout and the preset first spatial Gini coefficient exceeds 0.04, in addition to reducing it to 0.9 times the original value, for every 0.02 difference, the incremental step size of the public facility location coordinates is reduced by 0.2 grid lengths. For example, when the difference between the spatial Gini coefficient of the public facility layout and the preset first spatial Gini coefficient is 0.06, the current incremental step size of the public facility location coordinates is 3 grid lengths. The reduced incremental step size of the public facility location coordinates is 3 × 0.9 - 0.2 × 1 = 2.5 grid lengths.

[0097] Specifically, the grid length is the side length of each grid unit, which is the length of the area where public facilities are located, divided into regular spatial grids with equal side lengths and equal spacing.

[0098] In practice, the method of the present invention adjusts the incremental step size of the location coordinates of public facilities by setting a preset first spatial Gini coefficient and a preset second spatial Gini coefficient. Since the spatial distribution of public facilities in the layout is too concentrated or uneven, the service capacity of public facilities in some areas is insufficient or excessive. By reducing the incremental step size of the location coordinates, the layout of facilities can be optimized, the service differences caused by spatial unevenness can be reduced, spatial connectivity can be improved, and the spatial-demand adaptability of the layout of public facilities can be further improved.

[0099] Please continue reading. Figure 4 As shown, it is a logical flowchart of the process of determining the error feedback gain of the layout optimization of the public facilities layout optimization method based on artificial intelligence in an embodiment of the present invention.

[0100] Specifically, if the spatial Gini coefficient of the public facility layout is greater than the preset second spatial Gini coefficient, it is initially determined that the accuracy of the estimated service demand content does not meet the requirements, and the accuracy of the estimated service demand content is determined based on the service demand coverage rate of the public facilities.

[0101] Specifically, the accuracy of the estimated service demand content based on the service demand coverage of the public facilities is determined, including:

[0102] Compare the service demand coverage rate of public facilities with the preset coverage rate;

[0103] If the service demand coverage rate of the public facility is greater than the preset coverage rate, then it is determined that the accuracy of the estimated service demand content meets the requirements, and it is determined whether the incremental step size of the public facility site selection coordinates meets the requirements.

[0104] If the service demand coverage rate of the public facility is less than or equal to the preset coverage rate, it is determined that the accuracy of the estimated service demand content does not meet the requirements, and the error feedback gain of the layout optimization is increased.

[0105] Understandably, in AI-based public facility layout optimization methods, the use of preset coverage rates to characterize the accuracy of service demand predictions involves transforming the abstract accuracy of service demand predictions into quantifiable coverage rate ranges. By comparing the proportion of actual service demand effectively covered by public facilities with a preset threshold, the impact of demand prediction deviations on layout optimization results can be identified. Preset coverage rates can be set according to actual operating conditions. The setting of preset coverage rates aims to ensure the spatial-demand adaptability and practicality of public facility layouts. Optionally, the preset coverage rate is determined through a limited number of trials by evaluating the optimization effect of public facility utilization rates at different unit times. The determined preset coverage rate should be neither too small nor excessively disruptive to the public facility layout optimization process. For example, the preset coverage rate is typically selected within the range of [80%, 90%].

[0106] Preferably, the preset coverage rate is 85% in the preferred embodiment.

[0107] Specifically, the service demand coverage rate of the public facilities is the ratio of the number of services actually provided by the public facilities in a unit area to the total number of user demands.

[0108] Specifically, the increase in the error feedback gain of the layout optimization is determined by the difference between the preset coverage rate and the service demand coverage rate of the public facilities.

[0109] Specifically, when the difference between the preset coverage rate and the service demand coverage rate of public facilities is within 3%, the error feedback gain of layout optimization increases to 1.1 times the original value. When the difference between the preset coverage rate and the service demand coverage rate of public facilities exceeds 3%, in addition to increasing to 1.1 times the original value, the error feedback gain of layout optimization increases by 0.01 for every 1% exceeding the original value. For example, when the difference between the preset coverage rate and the service demand coverage rate of public facilities is 5%, the current error feedback gain of layout optimization is 0.1, and the increased error feedback gain of layout optimization is 0.1×1.1+0.01×2=0.13.

[0110] In practice, the method described in this invention adjusts the error feedback gain of layout optimization by setting a preset coverage rate. Since the prediction results of service demand do not take into account regional differences, the prediction of demand in some areas is not accurate enough, and the accuracy of the prediction of service demand content deviates. By increasing the error feedback gain, the optimization process can be made more sensitive to demand prediction errors, making the layout optimization more accurate, ensuring that public facilities can be reasonably configured according to the actual service demand, improving the overall service efficiency, and further improving the spatial-demand adaptability of public facility layout.

[0111] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for optimizing the layout of public facilities based on artificial intelligence, characterized in that, include: Collect basic data on the layout of public facilities, and then perform cleaning, noise reduction, deduplication and formatting, and feature extraction on the basic data to obtain basic layout features. Based on the basic layout features, the layout of public facilities is mapped into a layout state vector. The initial model is trained by combining user needs and the layout state vector to obtain an intelligent layout optimization model. The basic data of the public facility layout is analyzed based on the intelligent layout optimization model to output a layout optimization scheme. Obtain the actual service volume and design capacity of public facilities, and determine the utilization rate of public facilities per unit time based on the actual service volume and design capacity of public facilities to determine whether the space-demand adaptability of the public facility layout meets the requirements; If the spatial-demand fit of the public facility layout does not meet the requirements, the spatial Gini coefficient of the public facility layout is obtained to determine whether the spatial connectivity of the public facility layout meets the requirements. If the spatial connectivity of the public facility layout does not meet the requirements, the spatial Gini coefficient of the public facility layout shall be used to determine whether it is necessary to reduce the incremental step size of the public facility site selection coordinates. If it is not necessary to reduce the incremental step size of the location coordinates of public facilities, then the error feedback gain of layout optimization is determined based on the service demand coverage of public facilities. The error feedback gain of the layout optimization is a key parameter used to adjust the correction strength of facility coordinate errors or position deviations by adjusting the update magnitude of each optimization iteration of the public facility layout.

2. The public facility layout optimization method based on artificial intelligence according to claim 1, characterized in that, The utilization rate of the public facilities per unit time is determined based on the actual service volume and design capacity of the public facilities to determine whether the space-demand fit of the public facility layout meets the requirements, including: The utilization rate of the public facility per unit time is obtained by using the ratio of the actual service volume of the public facility to the designed capacity of the public facility. The utilization rate of public facilities per unit time is compared with the preset utilization rate; If the utilization rate of public facilities per unit time is greater than the preset utilization rate, then the space-demand fit of the public facility layout is determined to meet the requirements. If the utilization rate of public facilities per unit time is less than or equal to the preset utilization rate, then the space-demand fit of the public facility layout is determined to be unsatisfactory.

3. The method for optimizing the layout of public facilities based on artificial intelligence according to claim 2, characterized in that, If the spatial-demand fit of the public facility layout does not meet the requirements, the spatial connectivity of the public facility layout is determined based on the spatial Gini coefficient of the public facility layout.

4. The method for optimizing the layout of public facilities based on artificial intelligence according to claim 3, characterized in that, Determining whether the spatial connectivity of public facility layouts meets requirements based on the spatial Gini coefficient of public facility layout includes: The spatial Gini coefficient of the public facility layout is compared with the preset first spatial Gini coefficient; If the spatial Gini coefficient of the public facility layout is less than or equal to the preset first spatial Gini coefficient, then the spatial connectivity of the public facility layout is determined to meet the requirements. If the spatial Gini coefficient of the public facility layout is greater than the preset first spatial Gini coefficient, then the spatial connectivity of the public facility layout is determined to be non-compliant.

5. The public facility layout optimization method based on artificial intelligence according to claim 4, characterized in that, Determine whether it is necessary to reduce the incremental step size of the public facility site selection coordinates, including: The spatial Gini coefficient of the public facility layout is compared with the preset first spatial Gini coefficient and the preset second spatial Gini coefficient, respectively; If the spatial Gini coefficient of the public facility layout is greater than the preset first spatial Gini coefficient and less than or equal to the preset second spatial Gini coefficient, the incremental step size of the public facility site selection coordinates is reduced. If the spatial Gini coefficient of the public facility layout is greater than the preset second spatial Gini coefficient, there is no need to reduce the incremental step size of the public facility site selection coordinates.

6. The method for optimizing the layout of public facilities based on artificial intelligence according to claim 5, characterized in that, The reduction in the incremental step size of the public facility site selection coordinates is determined by the difference between the spatial Gini coefficient of the public facility layout and the preset first spatial Gini coefficient.

7. The method for optimizing the layout of public facilities based on artificial intelligence according to claim 6, characterized in that, Given that the spatial Gini coefficient of the public facility layout is greater than the preset second spatial Gini coefficient, it is initially determined that the accuracy of the estimated service demand content does not meet the requirements, and the accuracy of the estimated service demand content is determined based on the service demand coverage rate of the public facilities.

8. The method for optimizing the layout of public facilities based on artificial intelligence according to claim 7, characterized in that, The accuracy of the estimated service demand content based on the service demand coverage rate of the public facilities is determined to meet the requirements, including: Compare the service demand coverage rate of public facilities with the preset coverage rate; If the service demand coverage rate of the public facility is greater than the preset coverage rate, then it is determined that the accuracy of the estimated service demand content meets the requirements, and it is determined whether the incremental step size of the public facility site selection coordinates meets the requirements. If the service demand coverage rate of the public facility is less than or equal to the preset coverage rate, it is determined that the accuracy of the estimated service demand content does not meet the requirements, and the error feedback gain of the layout optimization is increased.

9. The method for optimizing the layout of public facilities based on artificial intelligence according to claim 8, characterized in that, The service demand coverage rate of public facilities is the ratio of the number of services actually provided by public facilities in a unit area to the total number of user demands.

10. The method for optimizing the layout of public facilities based on artificial intelligence according to claim 9, characterized in that, The increase in the error feedback gain of the layout optimization is determined by the difference between the preset coverage rate and the service demand coverage rate of the public facilities.

Images