Urban complex element evolution prediction method and device

Abstract

The application provides a kind of urban complex element evolution prediction method and device, with such characteristics, including step S1, according to existing urban planning data, construct building distance function;Step S2, whether each existing facility point of specified area meets facility distance function is judged in turn, if not, then execute step S3;Step S3, according to facility distance function and all point of interest POI data, the position data and type of each predicted facility point corresponding to the existing facility point not meeting facility distance function are calculated;Step S4, for each predicted facility point, whether the predicted facility point is feasible is judged according to the position data of the predicted facility point and the city building data of specified area, if yes, then the predicted data point is taken as new facility point;Step S5, the position data and type of all new facility points are taken as evolution prediction result.In short, the present method can generate accurate urban evolution prediction result.

Description

Technical Field

[0001] This invention belongs to the field of urban construction planning, and specifically relates to a method and apparatus for predicting the evolution of complex urban elements. Background Technology

[0002] Urban renewal is gradually becoming an important way to promote urban development. Urban renewal is a broad concept that involves many factors, including the transformation of urban physical space, environmental improvement, functional replacement, population flow, and changes in social production and lifestyle. Among them, the renewal of urban service facilities is an important component, emphasizing the improvement of the quality of life in urban blocks or communities by supplementing missing functions and introducing new functions in existing spaces.

[0003] With the development of technology, a series of studies have emerged both domestically and internationally that utilize intelligent urban planning methods to solve complex urban problems. The effective application of computer-aided tools in various fields of urban development has improved the scientific rigor of planning and design. Examples include research on new planning methods, simulation of future urban development scenarios, machine generation of design schemes, and urban performance evaluation and optimization.

[0004] These intelligent planning methods provide supporting technologies for the allocation of urban resources, and some data- and model-driven technical tools have emerged, mainly optimizing resource layout through the diagnosis, visualization, and simulation of urban functions. However, these tools are primarily used in strategic and routine research, and rarely directly assist in the spatial layout research of urban resources. The key bottleneck lies in the insufficient understanding of the evolution of relevant urban resources and their spatial benefits, and the lack of corresponding technical means, making it difficult to accurately optimize the layout in planning and design. Summary of the Invention

[0005] This invention is made to solve the above-mentioned problems, and aims to provide a method and apparatus for predicting the evolution of complex urban elements.

[0006] This invention provides a method for predicting the evolution of complex urban elements, used to generate evolution prediction results for a specified area. It includes the following steps: Step S1, constructing a facility distance function based on existing urban planning data, including Points of Interest (POI) data and urban building data; Step S2, sequentially determining whether each existing facility point in the specified area satisfies the facility distance function; if not, proceeding to Step S3; Step S3, calculating the location data and type of the predicted facility point corresponding to each existing facility point that does not satisfy the facility distance function based on the facility distance function and all POI data; Step S4, for each predicted facility point, determining whether the predicted facility point is feasible based on the urban building data of the specified area and the location data of the predicted facility point; if so, treating the predicted data point as a new facility point; Step S5, using the location data and type of all newly added facility points as the evolution prediction result.

[0007] The urban complex element evolution prediction method provided by this invention may also have the following features: cluster analysis is performed on all points of interest (POI) data of urban planning data to obtain multiple types. In step S1, the POI data is calculated using machine learning and probability distribution to obtain a facility distance function. The facility distance function obtains the constraint conditions between two existing facility points based on the relationship between the types corresponding to the two existing facility points.

[0008] The urban complex element evolution prediction method provided by this invention may also have the following features: the relationships include integration, dependence, stalemate, avoidance, and separation. When the relationship is integration, the constraint is that facility point A and facility point B are distributed in the same space and the distance does not exceed k. When the relationship is dependence, the constraint is that facility point A and facility point B are distributed in two adjacent spaces and the distance does not exceed k. When the relationship is stalemate, the constraint is that facility point A and facility point B coexist within a range of k, and the distance between facility point B and facility point A is positively correlated with the density of facility point A. When the relationship is avoidance, the constraint is that facility point A and facility point B coexist within a range of k, and when facility point B is within a range of k of facility point A, the function of facility point A fails. When the relationship is separation, the constraint is that facility point A and facility point B cannot coexist within a range of k. Each sub-region after the area corresponding to the urban planning data is divided according to preset rules is taken as a space.

[0009] The urban complex element evolution prediction method provided by the present invention may also have the following feature: in step S2, if the existing facility point satisfies the constraint conditions with other existing facility points, then the existing facility point satisfies the facility distance function.

[0010] The urban complex element evolution prediction method provided by the present invention may also have the following feature: in step S3, when the predicted facility point and each existing facility point meet the constraint conditions, the location data of the preset facility point is obtained.

[0011] The urban complex element evolution prediction method provided by the present invention may also have the following feature: in step S4, when the predicted facility point is calculated to be within a certain building based on the location data of the predicted facility point and the urban building data, the predicted facility point is considered feasible.

[0012] This invention also provides an urban complex element evolution prediction device for generating evolution prediction results for a specified area. It comprises: a function construction module, an existing facility point judgment module, a location and type calculation module, a new facility point generation module, and a result generation module. The function construction module constructs a facility distance function based on existing urban planning data, including Points of Interest (POI) data and urban building data. The existing facility point judgment module sequentially determines whether each existing facility point in the specified area satisfies the facility distance function. If not, the location and type calculation module is executed. This module calculates the location data and type of the predicted facility point corresponding to each existing facility point that does not satisfy the facility distance function, based on the facility distance function and all POI data. The new facility point generation module determines the feasibility of each predicted facility point based on the urban building data of the specified area and the location data of the predicted facility point. If feasible, the predicted facility point is used as a new facility point. The result generation module uses the location data and type of all new facility points as the evolution prediction result.

[0013] The role and effect of invention

[0014] According to the method and apparatus for predicting the evolution of complex urban elements of the present invention, on the one hand, facility distance functions that determine the distance relationships between various types of facility points are extracted from existing urban planning data; on the other hand, corresponding new facility points are generated based on the facility distance functions, thereby optimizing urban planning configuration. Therefore, the method and apparatus for predicting the evolution of complex urban elements of the present invention can generate accurate urban evolution prediction results. Attached Figure Description

[0015] Figure 1 This is a block diagram of the urban complex element evolution prediction device in an embodiment of the present invention;

[0016] Figure 2 This is a flowchart illustrating the method for predicting the evolution of complex urban elements in an embodiment of the present invention. Detailed Implementation

[0017] To make the technical means, creative features, objectives and effects of the present invention easy to understand, the following embodiments, in conjunction with the accompanying drawings, provide a detailed description of the urban complex element evolution prediction method and apparatus of the present invention.

[0018] This embodiment provides a device for predicting the evolution of complex urban elements, used to generate evolution prediction results for a specified area.

[0019] Figure 1 This is a block diagram of the urban complex element evolution prediction device in an embodiment of the present invention.

[0020] like Figure 1 As shown, the urban complex element evolution prediction device 100 includes a function construction module 11, an existing facility point judgment module 12, a location and type calculation module 13, a new facility point generation module 14, a result generation module 15, and a control module 16 that controls the operation of the above modules.

[0021] The function construction module 11 is used to construct facility distance functions based on existing urban planning data, which includes Points of Interest (POI) data and urban building data. In this embodiment, each POI in the urban planning data corresponds to an existing facility point, and the POI data includes the location coordinates, density, and time of the existing facility point. The density is calculated based on the number of existing facility points in the calculation unit. In this embodiment, the density of existing facility point A is the number of existing facility points of the same type as existing facility point A in the calculation unit, used to reflect the number of facility points of the same type in the calculation unit. In other embodiments, the density of existing facility point A is the ratio of the number of existing facility points of the same type as existing facility point A in the calculation unit to all existing facility points in the calculation unit, used to reflect the proportion of the type corresponding to the existing facility point in the calculation unit. The location coordinates are three-dimensional coordinates, including planar coordinates x and y, and height coordinates z.

[0022] The function construction module 11 performs cluster analysis on all Points of Interest (POI) data in the urban planning data to obtain multiple types. Furthermore, the function construction module 11 also calculates facility distance functions from the POI data using machine learning and probability distribution calculations. These facility distance functions derive constraints between two existing facility points based on the relationship between their corresponding types. In this embodiment, the types include ten categories: natural, governance, residential, transportation, commercial, medical, educational, industrial, infrastructure, and innovation.

[0023] Relationships include integration, interdependence, mutual support, mutual avoidance, and separation. Different constraints corresponding to different relationships in the facility distance function include:

[0024] When the relationship is compatible, the constraint is that facility point A and facility point B are distributed in the same space and the distance between them does not exceed k.

[0025] When the relationship is dependent, the constraint is that facility point A and facility point B are located in two adjacent spaces, and the distance between them is no more than k.

[0026] In this context, the area corresponding to the urban planning data is divided into sub-areas according to preset rules, and each sub-area is considered as a space.

[0027] When the relationship is stalemate, the constraint is that facility point A and facility point B coexist within the range of k, and the distance between facility point B and facility point A is positively correlated with the density of facility point A.

[0028] When the relationship is mutually avoidance, the constraint is that facility point A and facility point B coexist within the range of k, and when facility point B is within the range of k of facility point A, the function of facility point A fails.

[0029] When the relationship is disjoint, the constraint is that facility point A and facility point B cannot coexist within the range of k.

[0030] In this embodiment, the value of k is extracted from the data of each existing facility point in the Point of Interest (POI) data. Through probability distribution, the condition that meets the requirements of most existing facility points is selected as the constraint condition. In this embodiment, when the relationship between two existing facility points that is 80% or more in a certain way meets a certain condition, then that condition is the constraint condition.

[0031] In this embodiment, each facility point corresponds to a different store, that is, the fine granularity of the facility point is the store. In other embodiments, other fine granular facility points can be set as needed, such as floors.

[0032] The existing facility point judgment module 12 is used to sequentially judge whether each existing facility point in the specified area satisfies the facility distance function. If not, the location and type calculation module 13 is executed.

[0033] In the existing facility point judgment module 12, if an existing facility point satisfies the constraint conditions with other existing facility points, then the existing facility point satisfies the facility distance function. That is, if it is calculated based on the facility distance function that a certain type of facility point needs to be set up near an existing facility point C, then the existing facility point C does not satisfy the facility distance function, and a corresponding predicted facility point needs to be generated.

[0034] The location and type calculation module 13 is used to calculate the location data and type of the predicted facility point corresponding to each existing facility point that does not satisfy the facility distance function, based on the facility distance function and all point of interest (POI) data.

[0035] In the location and type calculation module 13, the location data of the preset facility point is obtained when the predicted facility point and each existing facility point meet the constraint conditions.

[0036] The new facility point generation module 14 is used to determine whether each predicted facility point is feasible based on the urban building data of the specified area and the location data of the predicted facility point. If so, the predicted data point is used as a new facility point.

[0037] In the newly generated facility point module 14, the predicted facility point is considered feasible if it is located within a building, based on the predicted facility point's location data and urban building data. In this embodiment, the urban building data includes the boundaries and heights of each building. The system determines whether the predicted facility point can be set within the corresponding building based on whether its location data falls within the boundary and height data. If so, the predicted facility point is considered feasible.

[0038] The results generation module 15 is used to generate evolution prediction results from the location data and type of all newly added facility points.

[0039] In this embodiment, the newly added facility points can make up for the unreasonable configuration of existing facility points and optimize the configuration of functional facilities in the entire designated area.

[0040] The control module 16 stores the control program that controls the operation of each module.

[0041] The following description, in conjunction with the accompanying drawings, explains the process of using the urban complex element evolution prediction device 100 to predict the evolution of urban complex elements.

[0042] Figure 2 This is a flowchart illustrating the method for predicting the evolution of complex urban elements in an embodiment of the present invention.

[0043] like Figure 2 As shown, the method for predicting the evolution of complex urban elements includes the following steps:

[0044] Step S1: The function construction module 11 is used to construct the facility distance function based on the existing urban planning data, which includes point of interest (POI) data and urban building data.

[0045] Step S2: The existing facility point judgment module 12 is used to sequentially judge whether each existing facility point in the specified area satisfies the facility distance function. If not, step S3 is executed.

[0046] Step S3: The location and type calculation module 13 calculates the location data and type of the predicted facility point corresponding to each existing facility point that does not satisfy the facility distance function based on the facility distance function and all point of interest (POI) data.

[0047] Step S4: The new facility point generation module 14 is used to determine whether the predicted facility point is feasible for each predicted facility point based on the urban building data of the specified area and the location data of the predicted facility point. If so, the predicted data point is used as the new facility point.

[0048] Step S5: Use the result generation module 15 to take the location data and type of all newly added facility points as the evolution prediction result.

[0049] The role and effect of the embodiments

[0050] According to the urban complex element evolution prediction method and apparatus involved in this embodiment, on the one hand, facility distance functions that determine the distance relationships between various types of facility points are extracted from existing urban planning data; on the other hand, corresponding new facility points are generated for existing facility points based on the facility distance functions, thereby optimizing urban planning configuration. In summary, this method can generate accurate urban evolution prediction results.

[0051] Those skilled in the art should understand that this invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to this invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for urban complex element evolution prediction, used for generating an evolution prediction result of a specified area, and characterized in that, The method comprises the following steps: Step S1, constructing a facility distance function according to existing urban planning data, wherein the urban planning data comprises point of interest (POI) data and urban building data; Step S2, judging whether each existing facility point in the specified region satisfies the facility distance function in sequence, and if not, executing step S3; Step S3, calculating the position data and type of a predicted facility point corresponding to each existing facility point that does not satisfy the facility distance function according to the facility distance function and all the point of interest (POI) data; Step S4, judging whether each predicted facility point is feasible according to the urban building data of the specified region and the position data of the predicted facility point, and if so, taking the predicted data point as a new facility point; Step S5, taking the position data and type of all the new facility points as the evolution prediction result, wherein the point of interest (POI) data is subjected to cluster analysis to obtain a plurality of types, in the step S1, the facility distance function is obtained by machine learning and probability distribution calculation on the point of interest (POI) data, the facility distance function obtains a constraint condition between two existing facility points according to the relationship between the types of the two existing facility points, wherein the relationship comprises fusion, dependence, confrontation, avoidance and separation, when the relationship is fusion, the constraint condition is that facility point A and facility point B are distributed in the same space and the distance is not more than k; when the relationship is dependence, the constraint condition is that facility point A and facility point B are respectively distributed in two adjacent spaces and the distance is not more than k; when the relationship is confrontation, the constraint condition is that facility point A and facility point B coexist within k, and the distance between the facility point B and the facility point A is positively correlated with the density of the facility point A; when the relationship is avoidance, the constraint condition is that facility point A and facility point B coexist within k, and the function of the facility point A is invalid when the facility point B is within the k range of the facility point A; when the relationship is separation, the constraint condition is that facility point A and facility point B cannot coexist within k, each sub-region obtained by dividing the region corresponding to the urban planning data according to a preset rule is taken as the space.

2. The urban complex element evolution prediction method according to claim 1, wherein: wherein in the step S2, the existing facility point satisfies the constraint condition with other existing facility points, and the existing facility point satisfies the facility distance function.

3. The urban complex element evolution prediction method according to claim 2, wherein: wherein in the step S3, the position data of the predicted facility point is obtained when the predicted facility point satisfies the constraint condition with each existing facility point.

4. The urban complex element evolution prediction method according to claim 1, wherein: wherein, In the step S4, according to the position data of the predicted facility point and the urban building data, it is calculated that the predicted facility point is feasible when the predicted facility point is in a certain building.

5. A device for predicting the evolution of complex urban elements, used to generate evolution prediction results for a specified area, characterized in that, Comprise: Function construction module, existing facility point judgment module, position and type calculation module, new facility point generation module and result generation module, Wherein, the function construction module is used to construct the facility distance function according to the existing urban planning data, and the urban planning data includes point of interest POI data and urban building data, The existing facility point judgment module is used to judge whether each existing facility point of the specified area satisfies the facility distance function in turn, if not, the position and type calculation module is executed, The position and type calculation module is used to calculate the position data and type of the predicted facility point corresponding to each existing facility point not satisfying the facility distance function according to the facility distance function and all the point of interest POI data, The new facility point generation module is used to judge whether the predicted facility point is feasible according to the urban building data of the specified area and the position data of the predicted facility point for each predicted facility point, if yes, the predicted data point is taken as a new facility point, The result generation module is used to take the position data and the type of all the new facility points as the evolution prediction result, Wherein, all the point of interest POI data of the urban planning data is subjected to cluster analysis to obtain a plurality of types, In the function construction module, the facility distance function is obtained by machine learning and probability distribution calculation on the point of interest POI data, The facility distance function obtains the constraint condition between the two existing facility points according to the relationship between the types corresponding to the two existing facility points, Wherein, the relationship includes fusion, dependence, confrontation, avoidance and separation, When the relationship is fusion, the constraint condition is that facility point A and facility point B are distributed in the same space and the distance is not more than k; When the relationship is dependence, the constraint condition is that facility point A and facility point B are respectively distributed in two adjacent spaces, and the distance is not more than k; When the relationship is confrontation, the constraint condition is that facility point A and facility point B coexist within k, and the distance between the facility point B and the facility point A is positively correlated with the density of facility point A; When the relationship is avoidance, the constraint condition is that facility point A and facility point B coexist within k, and the function of facility point A is invalid when facility point B is within the k range of facility point A; When the relationship is separation, the constraint condition is that facility point A and facility point B cannot coexist within k, Each subregion obtained by dividing the region corresponding to the urban planning data according to the preset rule is taken as the space.

Images